gcc/libcpp/charset.cc

2511 lines
77 KiB
C++
Raw Normal View History

/* CPP Library - charsets
2022-01-03 10:42:10 +01:00
Copyright (C) 1998-2022 Free Software Foundation, Inc.
Change references of .c files to .cc files ChangeLog: * MAINTAINERS: Rename .c names to .cc. contrib/ChangeLog: * filter-clang-warnings.py: Rename .c names to .cc. * gcc_update: Likewise. * paranoia.cc: Likewise. contrib/header-tools/ChangeLog: * README: Rename .c names to .cc. gcc/ChangeLog: * Makefile.in: Rename .c names to .cc. * alias.h: Likewise. * asan.cc: Likewise. * auto-profile.h: Likewise. * basic-block.h (struct basic_block_d): Likewise. * btfout.cc: Likewise. * builtins.cc (expand_builtin_longjmp): Likewise. (validate_arg): Likewise. (access_ref::offset_bounded): Likewise. * caller-save.cc (reg_restore_code): Likewise. (setup_save_areas): Likewise. * calls.cc (initialize_argument_information): Likewise. (expand_call): Likewise. (emit_library_call_value_1): Likewise. * cfg-flags.def (RTL): Likewise. (SIBCALL): Likewise. (CAN_FALLTHRU): Likewise. * cfganal.cc (post_order_compute): Likewise. * cfgcleanup.cc (try_simplify_condjump): Likewise. (merge_blocks_move_predecessor_nojumps): Likewise. (merge_blocks_move_successor_nojumps): Likewise. (merge_blocks_move): Likewise. (old_insns_match_p): Likewise. (try_crossjump_bb): Likewise. * cfgexpand.cc (expand_gimple_stmt): Likewise. * cfghooks.cc (split_block_before_cond_jump): Likewise. (profile_record_check_consistency): Likewise. * cfghooks.h: Likewise. * cfgrtl.cc (pass_free_cfg::execute): Likewise. (rtl_can_merge_blocks): Likewise. (try_redirect_by_replacing_jump): Likewise. (make_pass_outof_cfg_layout_mode): Likewise. (cfg_layout_can_merge_blocks_p): Likewise. * cgraph.cc (release_function_body): Likewise. (cgraph_node::get_fun): Likewise. * cgraph.h (struct cgraph_node): Likewise. (asmname_hasher::equal): Likewise. (cgraph_inline_failed_type): Likewise. (thunk_adjust): Likewise. (dump_callgraph_transformation): Likewise. (record_references_in_initializer): Likewise. (ipa_discover_variable_flags): Likewise. * cgraphclones.cc (GTY): Likewise. * cgraphunit.cc (symbol_table::finalize_compilation_unit): Likewise. * collect-utils.h (GCC_COLLECT_UTILS_H): Likewise. * collect2-aix.h (GCC_COLLECT2_AIX_H): Likewise. * collect2.cc (maybe_run_lto_and_relink): Likewise. * combine-stack-adj.cc: Likewise. * combine.cc (setup_incoming_promotions): Likewise. (combine_simplify_rtx): Likewise. (count_rtxs): Likewise. * common.opt: Likewise. * common/config/aarch64/aarch64-common.cc: Likewise. * common/config/arm/arm-common.cc (arm_asm_auto_mfpu): Likewise. * common/config/avr/avr-common.cc: Likewise. * common/config/i386/i386-isas.h (struct _isa_names_table): Likewise. * conditions.h: Likewise. * config.gcc: Likewise. * config/aarch64/aarch64-builtins.cc (aarch64_resolve_overloaded_memtag): Likewise. * config/aarch64/aarch64-protos.h (aarch64_classify_address): Likewise. (aarch64_get_extension_string_for_isa_flags): Likewise. * config/aarch64/aarch64-sve-builtins.cc (function_builder::add_function): Likewise. * config/aarch64/aarch64.cc (aarch64_regmode_natural_size): Likewise. (aarch64_sched_first_cycle_multipass_dfa_lookahead): Likewise. (aarch64_option_valid_attribute_p): Likewise. (aarch64_short_vector_p): Likewise. (aarch64_float_const_representable_p): Likewise. * config/aarch64/aarch64.h (DBX_REGISTER_NUMBER): Likewise. (ASM_OUTPUT_POOL_EPILOGUE): Likewise. (GTY): Likewise. * config/aarch64/cortex-a57-fma-steering.cc: Likewise. * config/aarch64/driver-aarch64.cc (contains_core_p): Likewise. * config/aarch64/t-aarch64: Likewise. * config/aarch64/x-aarch64: Likewise. * config/aarch64/x-darwin: Likewise. * config/alpha/alpha-protos.h: Likewise. * config/alpha/alpha.cc (alpha_scalar_mode_supported_p): Likewise. * config/alpha/alpha.h (LONG_DOUBLE_TYPE_SIZE): Likewise. (enum reg_class): Likewise. * config/alpha/alpha.md: Likewise. * config/alpha/driver-alpha.cc (AMASK_LOCKPFTCHOK): Likewise. * config/alpha/x-alpha: Likewise. * config/arc/arc-protos.h (arc_eh_uses): Likewise. * config/arc/arc.cc (ARC_OPT): Likewise. (arc_ccfsm_advance): Likewise. (arc_arg_partial_bytes): Likewise. (conditionalize_nonjump): Likewise. * config/arc/arc.md: Likewise. * config/arc/builtins.def: Likewise. * config/arc/t-arc: Likewise. * config/arm/arm-c.cc (arm_resolve_overloaded_builtin): Likewise. (arm_pragma_target_parse): Likewise. * config/arm/arm-protos.h (save_restore_target_globals): Likewise. (arm_cpu_cpp_builtins): Likewise. * config/arm/arm.cc (vfp3_const_double_index): Likewise. (shift_op): Likewise. (thumb2_final_prescan_insn): Likewise. (arm_final_prescan_insn): Likewise. (arm_asm_output_labelref): Likewise. (arm_small_register_classes_for_mode_p): Likewise. * config/arm/arm.h: Likewise. * config/arm/arm.md: Likewise. * config/arm/driver-arm.cc: Likewise. * config/arm/symbian.h: Likewise. * config/arm/t-arm: Likewise. * config/arm/thumb1.md: Likewise. * config/arm/x-arm: Likewise. * config/avr/avr-c.cc (avr_register_target_pragmas): Likewise. * config/avr/avr-fixed.md: Likewise. * config/avr/avr-log.cc (avr_log_vadump): Likewise. * config/avr/avr-mcus.def: Likewise. * config/avr/avr-modes.def (FRACTIONAL_INT_MODE): Likewise. * config/avr/avr-passes.def (INSERT_PASS_BEFORE): Likewise. * config/avr/avr-protos.h (make_avr_pass_casesi): Likewise. * config/avr/avr.cc (avr_option_override): Likewise. (avr_build_builtin_va_list): Likewise. (avr_mode_dependent_address_p): Likewise. (avr_function_arg_advance): Likewise. (avr_asm_output_aligned_decl_common): Likewise. * config/avr/avr.h (RETURN_ADDR_RTX): Likewise. (SUPPORTS_INIT_PRIORITY): Likewise. * config/avr/avr.md: Likewise. * config/avr/builtins.def: Likewise. * config/avr/gen-avr-mmcu-specs.cc (IN_GEN_AVR_MMCU_TEXI): Likewise. * config/avr/gen-avr-mmcu-texi.cc (IN_GEN_AVR_MMCU_TEXI): Likewise. (main): Likewise. * config/avr/t-avr: Likewise. * config/bfin/bfin.cc (frame_related_constant_load): Likewise. * config/bpf/bpf-protos.h (GCC_BPF_PROTOS_H): Likewise. * config/bpf/bpf.h (enum reg_class): Likewise. * config/bpf/t-bpf: Likewise. * config/c6x/c6x-protos.h (GCC_C6X_PROTOS_H): Likewise. * config/cr16/cr16-protos.h: Likewise. * config/cris/cris.cc (cris_address_cost): Likewise. (cris_side_effect_mode_ok): Likewise. (cris_init_machine_status): Likewise. (cris_emit_movem_store): Likewise. * config/cris/cris.h (INDEX_REG_CLASS): Likewise. (enum reg_class): Likewise. (struct cum_args): Likewise. * config/cris/cris.opt: Likewise. * config/cris/sync.md: Likewise. * config/csky/csky.cc (csky_expand_prologue): Likewise. * config/darwin-c.cc: Likewise. * config/darwin-f.cc: Likewise. * config/darwin-sections.def (zobj_const_section): Likewise. * config/darwin.cc (output_objc_section_asm_op): Likewise. (fprintf): Likewise. * config/darwin.h (GTY): Likewise. * config/elfos.h: Likewise. * config/epiphany/epiphany-sched.md: Likewise. * config/epiphany/epiphany.cc (epiphany_function_value): Likewise. * config/epiphany/epiphany.h (GTY): Likewise. (NO_FUNCTION_CSE): Likewise. * config/epiphany/mode-switch-use.cc: Likewise. * config/epiphany/predicates.md: Likewise. * config/epiphany/t-epiphany: Likewise. * config/fr30/fr30-protos.h: Likewise. * config/frv/frv-protos.h: Likewise. * config/frv/frv.cc (TLS_BIAS): Likewise. * config/frv/frv.h (ASM_OUTPUT_ALIGNED_LOCAL): Likewise. * config/ft32/ft32-protos.h: Likewise. * config/gcn/gcn-hsa.h (ASM_APP_OFF): Likewise. * config/gcn/gcn.cc (gcn_init_libfuncs): Likewise. * config/gcn/mkoffload.cc (copy_early_debug_info): Likewise. * config/gcn/t-gcn-hsa: Likewise. * config/gcn/t-omp-device: Likewise. * config/h8300/h8300-protos.h (GCC_H8300_PROTOS_H): Likewise. (same_cmp_following_p): Likewise. * config/h8300/h8300.cc (F): Likewise. * config/h8300/h8300.h (struct cum_arg): Likewise. (BRANCH_COST): Likewise. * config/i386/cygming.h (DEFAULT_PCC_STRUCT_RETURN): Likewise. * config/i386/djgpp.h (TARGET_ASM_LTO_END): Likewise. * config/i386/dragonfly.h (NO_PROFILE_COUNTERS): Likewise. * config/i386/driver-i386.cc (detect_caches_intel): Likewise. * config/i386/freebsd.h (NO_PROFILE_COUNTERS): Likewise. * config/i386/i386-c.cc (ix86_target_macros): Likewise. * config/i386/i386-expand.cc (get_mode_wider_vector): Likewise. * config/i386/i386-options.cc (ix86_set_func_type): Likewise. * config/i386/i386-protos.h (ix86_extract_perm_from_pool_constant): Likewise. (ix86_register_pragmas): Likewise. (ix86_d_has_stdcall_convention): Likewise. (i386_pe_seh_init_sections): Likewise. * config/i386/i386.cc (ix86_function_arg_regno_p): Likewise. (ix86_function_value_regno_p): Likewise. (ix86_compute_frame_layout): Likewise. (legitimize_pe_coff_symbol): Likewise. (output_pic_addr_const): Likewise. * config/i386/i386.h (defined): Likewise. (host_detect_local_cpu): Likewise. (CONSTANT_ADDRESS_P): Likewise. (DEFAULT_LARGE_SECTION_THRESHOLD): Likewise. (struct machine_frame_state): Likewise. * config/i386/i386.md: Likewise. * config/i386/lynx.h (ASM_OUTPUT_ALIGN): Likewise. * config/i386/mmx.md: Likewise. * config/i386/sse.md: Likewise. * config/i386/t-cygming: Likewise. * config/i386/t-djgpp: Likewise. * config/i386/t-gnu-property: Likewise. * config/i386/t-i386: Likewise. * config/i386/t-intelmic: Likewise. * config/i386/t-omp-device: Likewise. * config/i386/winnt-cxx.cc (i386_pe_type_dllimport_p): Likewise. (i386_pe_adjust_class_at_definition): Likewise. * config/i386/winnt.cc (gen_stdcall_or_fastcall_suffix): Likewise. (i386_pe_mangle_decl_assembler_name): Likewise. (i386_pe_encode_section_info): Likewise. * config/i386/x-cygwin: Likewise. * config/i386/x-darwin: Likewise. * config/i386/x-i386: Likewise. * config/i386/x-mingw32: Likewise. * config/i386/x86-tune-sched-core.cc: Likewise. * config/i386/x86-tune.def: Likewise. * config/i386/xm-djgpp.h (STANDARD_STARTFILE_PREFIX_1): Likewise. * config/ia64/freebsd.h: Likewise. * config/ia64/hpux.h (REGISTER_TARGET_PRAGMAS): Likewise. * config/ia64/ia64-protos.h (ia64_except_unwind_info): Likewise. * config/ia64/ia64.cc (ia64_function_value_regno_p): Likewise. (ia64_secondary_reload_class): Likewise. (bundling): Likewise. * config/ia64/ia64.h: Likewise. * config/ia64/ia64.md: Likewise. * config/ia64/predicates.md: Likewise. * config/ia64/sysv4.h: Likewise. * config/ia64/t-ia64: Likewise. * config/iq2000/iq2000.h (FUNCTION_MODE): Likewise. * config/iq2000/iq2000.md: Likewise. * config/linux.h (TARGET_HAS_BIONIC): Likewise. (if): Likewise. * config/m32c/m32c.cc (m32c_function_needs_enter): Likewise. * config/m32c/m32c.h (MAX_REGS_PER_ADDRESS): Likewise. * config/m32c/t-m32c: Likewise. * config/m32r/m32r-protos.h: Likewise. * config/m32r/m32r.cc (m32r_print_operand): Likewise. * config/m32r/m32r.h: Likewise. * config/m32r/m32r.md: Likewise. * config/m68k/m68k-isas.def: Likewise. * config/m68k/m68k-microarchs.def: Likewise. * config/m68k/m68k-protos.h (strict_low_part_peephole_ok): Likewise. (m68k_epilogue_uses): Likewise. * config/m68k/m68k.cc (m68k_call_tls_get_addr): Likewise. (m68k_sched_adjust_cost): Likewise. (m68k_sched_md_init): Likewise. * config/m68k/m68k.h (__transfer_from_trampoline): Likewise. (enum m68k_function_kind): Likewise. * config/m68k/m68k.md: Likewise. * config/m68k/m68kemb.h: Likewise. * config/m68k/uclinux.h (ENDFILE_SPEC): Likewise. * config/mcore/mcore-protos.h: Likewise. * config/mcore/mcore.cc (mcore_expand_insv): Likewise. (mcore_expand_prolog): Likewise. * config/mcore/mcore.h (TARGET_MCORE): Likewise. * config/mcore/mcore.md: Likewise. * config/microblaze/microblaze-protos.h: Likewise. * config/microblaze/microblaze.cc (microblaze_legitimate_pic_operand): Likewise. (microblaze_function_prologue): Likewise. (microblaze_function_epilogue): Likewise. (microblaze_select_section): Likewise. (microblaze_asm_output_mi_thunk): Likewise. (microblaze_eh_return): Likewise. * config/microblaze/microblaze.h: Likewise. * config/microblaze/microblaze.md: Likewise. * config/microblaze/t-microblaze: Likewise. * config/mips/driver-native.cc: Likewise. * config/mips/loongson2ef.md: Likewise. * config/mips/mips-protos.h (mips_expand_vec_cmp_expr): Likewise. * config/mips/mips.cc (mips_rtx_costs): Likewise. (mips_output_filename): Likewise. (mips_output_function_prologue): Likewise. (mips_output_function_epilogue): Likewise. (mips_output_mi_thunk): Likewise. * config/mips/mips.h: Likewise. * config/mips/mips.md: Likewise. * config/mips/t-mips: Likewise. * config/mips/x-native: Likewise. * config/mmix/mmix-protos.h: Likewise. * config/mmix/mmix.cc (mmix_option_override): Likewise. (mmix_dbx_register_number): Likewise. (mmix_expand_prologue): Likewise. * config/mmix/mmix.h: Likewise. * config/mmix/mmix.md: Likewise. * config/mmix/predicates.md: Likewise. * config/mn10300/mn10300.cc (mn10300_symbolic_operand): Likewise. (mn10300_legitimate_pic_operand_p): Likewise. * config/mn10300/mn10300.h (enum reg_class): Likewise. (NO_FUNCTION_CSE): Likewise. * config/moxie/moxie-protos.h: Likewise. * config/moxie/uclinux.h (TARGET_LIBC_HAS_FUNCTION): Likewise. * config/msp430/msp430-devices.cc (extract_devices_dir_from_exec_prefix): Likewise. * config/msp430/msp430.cc (msp430_gimplify_va_arg_expr): Likewise. (msp430_incoming_return_addr_rtx): Likewise. * config/msp430/msp430.h (msp430_get_linker_devices_include_path): Likewise. * config/msp430/t-msp430: Likewise. * config/nds32/nds32-cost.cc (nds32_rtx_costs_speed_prefer): Likewise. (nds32_rtx_costs_size_prefer): Likewise. (nds32_init_rtx_costs): Likewise. * config/nds32/nds32-doubleword.md: Likewise. * config/nds32/nds32.cc (nds32_memory_move_cost): Likewise. (nds32_builtin_decl): Likewise. * config/nds32/nds32.h (enum nds32_16bit_address_type): Likewise. (enum nds32_isr_nested_type): Likewise. (enum reg_class): Likewise. * config/nds32/predicates.md: Likewise. * config/nds32/t-nds32: Likewise. * config/nios2/nios2.cc (nios2_pragma_target_parse): Likewise. * config/nvptx/nvptx-protos.h: Likewise. * config/nvptx/nvptx.cc (nvptx_goacc_expand_var_decl): Likewise. * config/nvptx/nvptx.h (TARGET_CPU_CPP_BUILTINS): Likewise. * config/nvptx/t-nvptx: Likewise. * config/nvptx/t-omp-device: Likewise. * config/pa/elf.h: Likewise. * config/pa/pa-linux.h (GLOBAL_ASM_OP): Likewise. * config/pa/pa-netbsd.h (GLOBAL_ASM_OP): Likewise. * config/pa/pa-openbsd.h (TARGET_ASM_GLOBALIZE_LABEL): Likewise. * config/pa/pa-protos.h (pa_eh_return_handler_rtx): Likewise. (pa_legitimize_reload_address): Likewise. (pa_can_use_return_insn): Likewise. * config/pa/pa.cc (mem_shadd_or_shadd_rtx_p): Likewise. (som_output_text_section_asm_op): Likewise. * config/pa/pa.h (PROFILE_BEFORE_PROLOGUE): Likewise. * config/pa/pa.md: Likewise. * config/pa/som.h: Likewise. * config/pa/t-pa: Likewise. * config/pdp11/pdp11.cc (decode_pdp11_d): Likewise. * config/pdp11/pdp11.h: Likewise. * config/pdp11/pdp11.md: Likewise. * config/pdp11/t-pdp11: Likewise. * config/pru/pru.md: Likewise. * config/pru/t-pru: Likewise. * config/riscv/riscv-protos.h (NUM_SYMBOL_TYPES): Likewise. (riscv_gpr_save_operation_p): Likewise. (riscv_d_register_target_info): Likewise. (riscv_init_builtins): Likewise. * config/riscv/riscv.cc (riscv_output_mi_thunk): Likewise. * config/riscv/riscv.h (CSW_MAX_OFFSET): Likewise. * config/riscv/t-riscv: Likewise. * config/rl78/rl78.cc (rl78_asm_ctor_dtor): Likewise. * config/rl78/t-rl78: Likewise. * config/rs6000/aix.h: Likewise. * config/rs6000/aix71.h (ASM_SPEC_COMMON): Likewise. * config/rs6000/aix72.h (ASM_SPEC_COMMON): Likewise. * config/rs6000/aix73.h (ASM_SPEC_COMMON): Likewise. * config/rs6000/darwin.h (TARGET_ASM_GLOBALIZE_LABEL): Likewise. * config/rs6000/driver-rs6000.cc: Likewise. * config/rs6000/freebsd.h: Likewise. * config/rs6000/freebsd64.h: Likewise. * config/rs6000/lynx.h (ASM_OUTPUT_ALIGN): Likewise. * config/rs6000/rbtree.cc: Likewise. * config/rs6000/rbtree.h: Likewise. * config/rs6000/rs6000-c.cc (rs6000_target_modify_macros): Likewise. * config/rs6000/rs6000-call.cc (rs6000_invalid_builtin): Likewise. (rs6000_expand_builtin): Likewise. (rs6000_init_builtins): Likewise. * config/rs6000/rs6000-cpus.def: Likewise. * config/rs6000/rs6000-gen-builtins.cc (write_init_ovld_table): Likewise. * config/rs6000/rs6000-internal.h (ALTIVEC_REG_BIT): Likewise. (quad_address_offset_p): Likewise. * config/rs6000/rs6000-logue.cc (interesting_frame_related_regno): Likewise. (rs6000_emit_epilogue): Likewise. * config/rs6000/rs6000-overload.def: Likewise. * config/rs6000/rs6000-p8swap.cc: Likewise. * config/rs6000/rs6000-protos.h (GCC_RS6000_PROTOS_H): Likewise. (rs6000_const_f32_to_i32): Likewise. * config/rs6000/rs6000.cc (legitimate_lo_sum_address_p): Likewise. (rs6000_debug_legitimize_address): Likewise. (rs6000_mode_dependent_address): Likewise. (rs6000_adjust_priority): Likewise. (rs6000_c_mode_for_suffix): Likewise. * config/rs6000/rs6000.h (defined): Likewise. (LONG_DOUBLE_TYPE_SIZE): Likewise. * config/rs6000/rs6000.md: Likewise. * config/rs6000/sysv4.h: Likewise. * config/rs6000/t-linux: Likewise. * config/rs6000/t-linux64: Likewise. * config/rs6000/t-rs6000: Likewise. * config/rs6000/x-darwin: Likewise. * config/rs6000/x-darwin64: Likewise. * config/rs6000/x-rs6000: Likewise. * config/rs6000/xcoff.h (ASM_OUTPUT_LABELREF): Likewise. * config/rx/rx.cc (rx_expand_builtin): Likewise. * config/s390/constraints.md: Likewise. * config/s390/driver-native.cc: Likewise. * config/s390/htmxlintrin.h: Likewise. * config/s390/s390-builtins.def (B_DEF): Likewise. (OB_DEF_VAR): Likewise. * config/s390/s390-builtins.h: Likewise. * config/s390/s390-c.cc: Likewise. * config/s390/s390-opts.h: Likewise. * config/s390/s390-protos.h (s390_check_symref_alignment): Likewise. (s390_register_target_pragmas): Likewise. * config/s390/s390.cc (s390_init_builtins): Likewise. (s390_expand_plus_operand): Likewise. (s390_expand_atomic): Likewise. (s390_valid_target_attribute_inner_p): Likewise. * config/s390/s390.h (LONG_DOUBLE_TYPE_SIZE): Likewise. * config/s390/s390.md: Likewise. * config/s390/t-s390: Likewise. * config/s390/vx-builtins.md: Likewise. * config/s390/x-native: Likewise. * config/sh/divtab-sh4-300.cc (main): Likewise. * config/sh/divtab-sh4.cc (main): Likewise. * config/sh/divtab.cc (main): Likewise. * config/sh/elf.h: Likewise. * config/sh/sh-protos.h (sh_fsca_int2sf): Likewise. * config/sh/sh.cc (SYMBOL_FLAG_FUNCVEC_FUNCTION): Likewise. (sh_struct_value_rtx): Likewise. (sh_remove_reg_dead_or_unused_notes): Likewise. * config/sh/sh.h (MIN_UNITS_PER_WORD): Likewise. * config/sh/t-sh: Likewise. * config/sol2-protos.h (solaris_override_options): Likewise. * config/sol2.h: Likewise. * config/sparc/driver-sparc.cc: Likewise. * config/sparc/freebsd.h: Likewise. * config/sparc/sparc-protos.h (make_pass_work_around_errata): Likewise. * config/sparc/sparc.cc (sparc_output_mi_thunk): Likewise. (sparc_asan_shadow_offset): Likewise. * config/sparc/sparc.h: Likewise. * config/sparc/sparc.md: Likewise. * config/sparc/t-sparc: Likewise. * config/sparc/x-sparc: Likewise. * config/stormy16/stormy16.cc (xstormy16_mode_dependent_address_p): Likewise. * config/t-darwin: Likewise. * config/t-dragonfly: Likewise. * config/t-freebsd: Likewise. * config/t-glibc: Likewise. * config/t-linux: Likewise. * config/t-netbsd: Likewise. * config/t-openbsd: Likewise. * config/t-pnt16-warn: Likewise. * config/t-sol2: Likewise. * config/t-vxworks: Likewise. * config/t-winnt: Likewise. * config/tilegx/t-tilegx: Likewise. * config/tilegx/tilegx-c.cc: Likewise. * config/tilegx/tilegx-protos.h (tilegx_function_profiler): Likewise. * config/tilegx/tilegx.md: Likewise. * config/tilepro/t-tilepro: Likewise. * config/tilepro/tilepro-c.cc: Likewise. * config/v850/t-v850: Likewise. * config/v850/v850-protos.h: Likewise. * config/v850/v850.cc (F): Likewise. * config/v850/v850.h (enum reg_class): Likewise. (SLOW_BYTE_ACCESS): Likewise. * config/vax/vax.cc (vax_mode_dependent_address_p): Likewise. * config/vax/vax.h (enum reg_class): Likewise. * config/vax/vax.md: Likewise. * config/visium/visium.cc (visium_legitimate_address_p): Likewise. * config/visium/visium.h: Likewise. * config/vms/t-vms: Likewise. * config/vms/vms-crtlmap.map: Likewise. * config/vms/vms-protos.h (vms_c_get_vms_ver): Likewise. * config/vx-common.h: Likewise. * config/x-darwin: Likewise. * config/x-hpux: Likewise. * config/x-linux: Likewise. * config/x-netbsd: Likewise. * config/x-openbsd: Likewise. * config/x-solaris: Likewise. * config/xtensa/xtensa-protos.h (xtensa_mem_offset): Likewise. * config/xtensa/xtensa.cc (xtensa_option_override): Likewise. * config/xtensa/xtensa.h: Likewise. * configure.ac: Likewise. * context.cc: Likewise. * convert.h: Likewise. * coretypes.h: Likewise. * coverage.cc: Likewise. * coverage.h: Likewise. * cppdefault.h (struct default_include): Likewise. * cprop.cc (local_cprop_pass): Likewise. (one_cprop_pass): Likewise. * cse.cc (hash_rtx_cb): Likewise. (fold_rtx): Likewise. * ctfc.h (ctfc_get_num_vlen_bytes): Likewise. * data-streamer.h (bp_unpack_var_len_int): Likewise. (streamer_write_widest_int): Likewise. * dbgcnt.def: Likewise. * dbxout.cc (dbxout_early_global_decl): Likewise. (dbxout_common_check): Likewise. * dbxout.h: Likewise. * debug.h (struct gcc_debug_hooks): Likewise. (dump_go_spec_init): Likewise. * df-core.cc: Likewise. * df-scan.cc (df_insn_info_delete): Likewise. (df_insn_delete): Likewise. * df.h (debug_df_chain): Likewise. (can_move_insns_across): Likewise. * dfp.cc (decimal_from_binary): Likewise. * diagnostic-color.cc: Likewise. * diagnostic-event-id.h: Likewise. * diagnostic-show-locus.cc (test_one_liner_labels): Likewise. * diagnostic.cc (bt_callback): Likewise. (num_digits): Likewise. * doc/avr-mmcu.texi: Likewise. * doc/cfg.texi: Likewise. * doc/contrib.texi: Likewise. * doc/cppinternals.texi: Likewise. * doc/extend.texi: Likewise. * doc/generic.texi: Likewise. * doc/gimple.texi: Likewise. * doc/gty.texi: Likewise. * doc/invoke.texi: Likewise. * doc/loop.texi: Likewise. * doc/lto.texi: Likewise. * doc/match-and-simplify.texi: Likewise. * doc/md.texi: Likewise. * doc/optinfo.texi: Likewise. * doc/options.texi: Likewise. * doc/passes.texi: Likewise. * doc/plugins.texi: Likewise. * doc/rtl.texi: Likewise. * doc/sourcebuild.texi: Likewise. * doc/tm.texi: Likewise. * doc/tm.texi.in: Likewise. * doc/tree-ssa.texi: Likewise. * dojump.cc (do_jump): Likewise. * dojump.h: Likewise. * dumpfile.cc (test_impl_location): Likewise. (test_capture_of_dump_calls): Likewise. * dumpfile.h (enum dump_kind): Likewise. (class dump_location_t): Likewise. (dump_enabled_p): Likewise. (enable_rtl_dump_file): Likewise. (dump_combine_total_stats): Likewise. * dwarf2asm.cc (dw2_asm_output_delta_uleb128): Likewise. * dwarf2ctf.h (ctf_debug_finish): Likewise. * dwarf2out.cc (dwarf2out_begin_prologue): Likewise. (struct loc_descr_context): Likewise. (rtl_for_decl_location): Likewise. (gen_subprogram_die): Likewise. (gen_label_die): Likewise. (is_trivial_indirect_ref): Likewise. (dwarf2out_late_global_decl): Likewise. (dwarf_file_hasher::hash): Likewise. (dwarf2out_end_source_file): Likewise. (dwarf2out_define): Likewise. (dwarf2out_early_finish): Likewise. * dwarf2out.h (struct dw_fde_node): Likewise. (struct dw_discr_list_node): Likewise. (output_loc_sequence_raw): Likewise. * emit-rtl.cc (gen_raw_REG): Likewise. (maybe_set_max_label_num): Likewise. * emit-rtl.h (struct rtl_data): Likewise. * errors.cc (internal_error): Likewise. (trim_filename): Likewise. * et-forest.cc: Likewise. * except.cc (init_eh_for_function): Likewise. * explow.cc (promote_ssa_mode): Likewise. (get_dynamic_stack_size): Likewise. * explow.h: Likewise. * expmed.h: Likewise. * expr.cc (safe_from_p): Likewise. (expand_expr_real_2): Likewise. (expand_expr_real_1): Likewise. * file-prefix-map.cc (remap_filename): Likewise. * final.cc (app_enable): Likewise. (make_pass_compute_alignments): Likewise. (final_scan_insn_1): Likewise. (final_scan_insn): Likewise. * fixed-value.h (fixed_from_string): Likewise. * flag-types.h (NO_DEBUG): Likewise. (DWARF2_DEBUG): Likewise. (VMS_DEBUG): Likewise. (BTF_DEBUG): Likewise. (enum ctf_debug_info_levels): Likewise. * fold-const.cc (const_binop): Likewise. (fold_binary_loc): Likewise. (fold_checksum_tree): Likewise. * fp-test.cc: Likewise. * function.cc (expand_function_end): Likewise. * function.h (struct function): Likewise. * fwprop.cc (should_replace_address): Likewise. * gcc-main.cc: Likewise. * gcc-rich-location.h (class gcc_rich_location): Likewise. * gcc-symtab.h: Likewise. * gcc.cc (MIN_FATAL_STATUS): Likewise. (driver_handle_option): Likewise. (quote_spec_arg): Likewise. (driver::finalize): Likewise. * gcc.h (set_input): Likewise. * gcov-dump.cc: Likewise. * gcov.cc (solve_flow_graph): Likewise. * gcse-common.cc: Likewise. * gcse.cc (make_pass_rtl_hoist): Likewise. * genattr-common.cc: Likewise. * genattrtab.cc (min_fn): Likewise. (write_const_num_delay_slots): Likewise. * genautomata.cc: Likewise. * genconditions.cc (write_one_condition): Likewise. * genconstants.cc: Likewise. * genemit.cc (gen_exp): Likewise. * generic-match-head.cc: Likewise. * genextract.cc: Likewise. * gengenrtl.cc (always_void_p): Likewise. * gengtype-parse.cc (gtymarker_opt): Likewise. * gengtype-state.cc (state_writer::state_writer): Likewise. (write_state_trailer): Likewise. (equals_type_number): Likewise. (read_state): Likewise. * gengtype.cc (open_base_files): Likewise. (struct file_rule_st): Likewise. (header_dot_h_frul): Likewise. * gengtype.h: Likewise. * genmatch.cc (main): Likewise. * genmddeps.cc: Likewise. * genmodes.cc (emit_mode_inner): Likewise. (emit_mode_unit_size): Likewise. * genpeep.cc (gen_peephole): Likewise. * genpreds.cc (write_tm_preds_h): Likewise. * genrecog.cc (validate_pattern): Likewise. (write_header): Likewise. (main): Likewise. * gensupport.cc (change_subst_attribute): Likewise. (traverse_c_tests): Likewise. (add_predicate): Likewise. (init_predicate_table): Likewise. * gensupport.h (struct optab_pattern): Likewise. (get_num_insn_codes): Likewise. (maybe_eval_c_test): Likewise. (struct pred_data): Likewise. * ggc-internal.h: Likewise. * gimple-fold.cc (maybe_fold_reference): Likewise. (get_range_strlen_tree): Likewise. * gimple-fold.h (gimple_stmt_integer_valued_real_p): Likewise. * gimple-low.cc: Likewise. * gimple-match-head.cc (directly_supported_p): Likewise. * gimple-pretty-print.h: Likewise. * gimple-ssa-sprintf.cc (format_percent): Likewise. (adjust_range_for_overflow): Likewise. * gimple-streamer.h: Likewise. * gimple.h (struct GTY): Likewise. (is_gimple_resx): Likewise. * gimplify.cc (gimplify_expr): Likewise. (gimplify_init_constructor): Likewise. (omp_construct_selector_matches): Likewise. (gimplify_omp_target_update): Likewise. (gimplify_omp_ordered): Likewise. (gimplify_va_arg_expr): Likewise. * graphite-isl-ast-to-gimple.cc (should_copy_to_new_region): Likewise. * haifa-sched.cc (increase_insn_priority): Likewise. (try_ready): Likewise. (sched_create_recovery_edges): Likewise. * ifcvt.cc (find_if_case_1): Likewise. (find_if_case_2): Likewise. * inchash.h: Likewise. * incpath.cc (add_env_var_paths): Likewise. * input.cc (dump_location_info): Likewise. (assert_loceq): Likewise. (test_lexer_string_locations_concatenation_1): Likewise. (test_lexer_string_locations_concatenation_2): Likewise. (test_lexer_string_locations_concatenation_3): Likewise. * input.h (BUILTINS_LOCATION): Likewise. (class string_concat_db): Likewise. * internal-fn.cc (expand_MUL_OVERFLOW): Likewise. (expand_LOOP_VECTORIZED): Likewise. * ipa-cp.cc (make_pass_ipa_cp): Likewise. * ipa-fnsummary.cc (remap_freqcounting_preds_after_dup): Likewise. (ipa_fn_summary_t::duplicate): Likewise. (make_pass_ipa_fn_summary): Likewise. * ipa-fnsummary.h (enum ipa_hints_vals): Likewise. * ipa-free-lang-data.cc (fld_simplified_type): Likewise. (free_lang_data_in_decl): Likewise. * ipa-inline.cc (compute_inlined_call_time): Likewise. (inline_always_inline_functions): Likewise. * ipa-inline.h (free_growth_caches): Likewise. (inline_account_function_p): Likewise. * ipa-modref.cc (modref_access_analysis::analyze_stmt): Likewise. (modref_eaf_analysis::analyze_ssa_name): Likewise. * ipa-param-manipulation.cc (ipa_param_body_adjustments::mark_dead_statements): Likewise. (ipa_param_body_adjustments::remap_with_debug_expressions): Likewise. * ipa-prop.cc (ipa_set_node_agg_value_chain): Likewise. * ipa-prop.h (IPA_UNDESCRIBED_USE): Likewise. (unadjusted_ptr_and_unit_offset): Likewise. * ipa-reference.cc (make_pass_ipa_reference): Likewise. * ipa-reference.h (GCC_IPA_REFERENCE_H): Likewise. * ipa-split.cc (consider_split): Likewise. * ipa-sra.cc (isra_read_node_info): Likewise. * ipa-utils.h (struct ipa_dfs_info): Likewise. (recursive_call_p): Likewise. (ipa_make_function_pure): Likewise. * ira-build.cc (ira_create_allocno): Likewise. (ira_flattening): Likewise. * ira-color.cc (do_coloring): Likewise. (update_curr_costs): Likewise. * ira-conflicts.cc (process_regs_for_copy): Likewise. * ira-int.h (struct ira_emit_data): Likewise. (ira_prohibited_mode_move_regs): Likewise. (ira_get_dup_out_num): Likewise. (ira_destroy): Likewise. (ira_tune_allocno_costs): Likewise. (ira_implicitly_set_insn_hard_regs): Likewise. (ira_build_conflicts): Likewise. (ira_color): Likewise. * ira-lives.cc (process_bb_node_lives): Likewise. * ira.cc (class ira_spilled_reg_stack_slot): Likewise. (setup_uniform_class_p): Likewise. (def_dominates_uses): Likewise. * ira.h (ira_nullify_asm_goto): Likewise. * langhooks.cc (lhd_post_options): Likewise. * langhooks.h (class substring_loc): Likewise. (struct lang_hooks_for_tree_inlining): Likewise. (struct lang_hooks_for_types): Likewise. (struct lang_hooks): Likewise. * libfuncs.h (synchronize_libfunc): Likewise. * loop-doloop.cc (doloop_condition_get): Likewise. * loop-init.cc (fix_loop_structure): Likewise. * loop-invariant.cc: Likewise. * lower-subreg.h: Likewise. * lra-constraints.cc (curr_insn_transform): Likewise. * lra-int.h (struct lra_insn_reg): Likewise. (lra_undo_inheritance): Likewise. (lra_setup_reload_pseudo_preferenced_hard_reg): Likewise. (lra_split_hard_reg_for): Likewise. (lra_coalesce): Likewise. (lra_final_code_change): Likewise. * lra-spills.cc (lra_final_code_change): Likewise. * lra.cc (lra_process_new_insns): Likewise. * lto-compress.h (struct lto_compression_stream): Likewise. * lto-streamer-out.cc (DFS::DFS_write_tree_body): Likewise. (write_symbol): Likewise. * lto-streamer.h (enum LTO_tags): Likewise. (lto_value_range_error): Likewise. (lto_append_block): Likewise. (lto_streamer_hooks_init): Likewise. (stream_read_tree_ref): Likewise. (lto_prepare_function_for_streaming): Likewise. (select_what_to_stream): Likewise. (omp_lto_input_declare_variant_alt): Likewise. (cl_optimization_stream_in): Likewise. * lto-wrapper.cc (append_compiler_options): Likewise. * machmode.def: Likewise. * machmode.h (struct int_n_data_t): Likewise. * main.cc (main): Likewise. * match.pd: Likewise. * omp-builtins.def (BUILT_IN_GOMP_CRITICAL_NAME_END): Likewise. (BUILT_IN_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT): Likewise. * omp-expand.cc (expand_omp_atomic_fetch_op): Likewise. (make_pass_expand_omp_ssa): Likewise. * omp-low.cc (struct omp_context): Likewise. (struct omp_taskcopy_context): Likewise. (lower_omp): Likewise. * omp-oacc-neuter-broadcast.cc (omp_sese_active_worker_call): Likewise. (mask_name): Likewise. (omp_sese_dump_pars): Likewise. (worker_single_simple): Likewise. * omp-offload.cc (omp_finish_file): Likewise. (execute_oacc_loop_designation): Likewise. * optabs-query.cc (lshift_cheap_p): Likewise. * optc-gen.awk: Likewise. * optc-save-gen.awk: Likewise. * optinfo-emit-json.cc (optrecord_json_writer::optrecord_json_writer): Likewise. * opts-common.cc: Likewise. * output.h (app_enable): Likewise. (output_operand_lossage): Likewise. (insn_current_reference_address): Likewise. (get_insn_template): Likewise. (output_quoted_string): Likewise. * pass_manager.h (struct register_pass_info): Likewise. * plugin.cc: Likewise. * plugin.def (PLUGIN_ANALYZER_INIT): Likewise. * plugin.h (invoke_plugin_callbacks): Likewise. * pointer-query.cc (handle_mem_ref): Likewise. * postreload-gcse.cc (alloc_mem): Likewise. * predict.h (enum prediction): Likewise. (add_reg_br_prob_note): Likewise. * prefix.h: Likewise. * profile.h (get_working_sets): Likewise. * read-md.cc: Likewise. * read-md.h (struct mapping): Likewise. (class md_reader): Likewise. (class noop_reader): Likewise. * read-rtl-function.cc (function_reader::create_function): Likewise. (function_reader::extra_parsing_for_operand_code_0): Likewise. * read-rtl.cc (initialize_iterators): Likewise. * real.cc: Likewise. * real.h (struct real_value): Likewise. (format_helper::format_helper): Likewise. (real_hash): Likewise. (real_can_shorten_arithmetic): Likewise. * recog.cc (struct target_recog): Likewise. (offsettable_nonstrict_memref_p): Likewise. (constrain_operands): Likewise. * recog.h (MAX_RECOG_ALTERNATIVES): Likewise. (which_op_alt): Likewise. (struct insn_gen_fn): Likewise. * reg-notes.def (REG_NOTE): Likewise. * reg-stack.cc: Likewise. * regs.h (reg_is_parm_p): Likewise. * regset.h: Likewise. * reload.cc (push_reload): Likewise. (find_reloads): Likewise. (find_reloads_address_1): Likewise. (find_replacement): Likewise. (refers_to_regno_for_reload_p): Likewise. (refers_to_mem_for_reload_p): Likewise. * reload.h (push_reload): Likewise. (deallocate_reload_reg): Likewise. * reload1.cc (emit_input_reload_insns): Likewise. * reorg.cc (relax_delay_slots): Likewise. * rtl.def (UNKNOWN): Likewise. (SEQUENCE): Likewise. (BARRIER): Likewise. (ASM_OPERANDS): Likewise. (EQ_ATTR_ALT): Likewise. * rtl.h (struct GTY): Likewise. (LABEL_NAME): Likewise. (LABEL_ALT_ENTRY_P): Likewise. (SUBREG_BYTE): Likewise. (get_stack_check_protect): Likewise. (dump_rtx_statistics): Likewise. (unwrap_const_vec_duplicate): Likewise. (subreg_promoted_mode): Likewise. (gen_lowpart_common): Likewise. (operand_subword): Likewise. (immed_wide_int_const): Likewise. (decide_function_section): Likewise. (active_insn_p): Likewise. (delete_related_insns): Likewise. (try_split): Likewise. (val_signbit_known_clear_p): Likewise. (simplifiable_subregs): Likewise. (set_insn_deleted): Likewise. (subreg_get_info): Likewise. (remove_free_EXPR_LIST_node): Likewise. (finish_subregs_of_mode): Likewise. (get_mem_attrs): Likewise. (lookup_constant_def): Likewise. (rtx_to_tree_code): Likewise. (hash_rtx): Likewise. (condjump_in_parallel_p): Likewise. (validate_subreg): Likewise. (make_compound_operation): Likewise. (schedule_ebbs): Likewise. (print_inline_rtx): Likewise. (fixup_args_size_notes): Likewise. (expand_dec): Likewise. (prepare_copy_insn): Likewise. (mark_elimination): Likewise. (valid_mode_changes_for_regno): Likewise. (make_debug_expr_from_rtl): Likewise. (delete_vta_debug_insns): Likewise. (simplify_using_condition): Likewise. (set_insn_locations): Likewise. (fatal_insn_not_found): Likewise. (word_register_operation_p): Likewise. * rtlanal.cc (get_call_fndecl): Likewise. (side_effects_p): Likewise. (subreg_nregs): Likewise. (rtx_cost): Likewise. (canonicalize_condition): Likewise. * rtlanal.h (rtx_properties::try_to_add_note): Likewise. * run-rtl-passes.cc (run_rtl_passes): Likewise. * sanitizer.def (BUILT_IN_ASAN_VERSION_MISMATCH_CHECK): Likewise. * sched-deps.cc (add_dependence_1): Likewise. * sched-ebb.cc (begin_move_insn): Likewise. (add_deps_for_risky_insns): Likewise. (advance_target_bb): Likewise. * sched-int.h (reemit_notes): Likewise. (struct _haifa_insn_data): Likewise. (HID): Likewise. (DEP_CANCELLED): Likewise. (debug_ds): Likewise. (number_in_ready): Likewise. (schedule_ebbs_finish): Likewise. (find_modifiable_mems): Likewise. * sched-rgn.cc (debug_rgn_dependencies): Likewise. * sel-sched-dump.cc (dump_lv_set): Likewise. * sel-sched-dump.h: Likewise. * sel-sched-ir.cc (sel_insn_rtx_cost): Likewise. (setup_id_reg_sets): Likewise. (has_dependence_p): Likewise. (sel_num_cfg_preds_gt_1): Likewise. (bb_ends_ebb_p): Likewise. * sel-sched-ir.h (struct _list_node): Likewise. (struct idata_def): Likewise. (bb_next_bb): Likewise. * sel-sched.cc (vinsn_writes_one_of_regs_p): Likewise. (choose_best_pseudo_reg): Likewise. (verify_target_availability): Likewise. (can_speculate_dep_p): Likewise. (sel_rank_for_schedule): Likewise. * selftest-run-tests.cc (selftest::run_tests): Likewise. * selftest.h (class auto_fix_quotes): Likewise. * shrink-wrap.cc (handle_simple_exit): Likewise. * shrink-wrap.h: Likewise. * simplify-rtx.cc (simplify_context::simplify_associative_operation): Likewise. (simplify_context::simplify_gen_vec_select): Likewise. * spellcheck-tree.h: Likewise. * spellcheck.h: Likewise. * statistics.h (struct function): Likewise. * stmt.cc (conditional_probability): Likewise. * stmt.h: Likewise. * stor-layout.h: Likewise. * streamer-hooks.h: Likewise. * stringpool.h: Likewise. * symtab.cc (symbol_table::change_decl_assembler_name): Likewise. * target.def (HOOK_VECTOR_END): Likewise. (type.): Likewise. * target.h (union cumulative_args_t): Likewise. (by_pieces_ninsns): Likewise. (class predefined_function_abi): Likewise. * targhooks.cc (default_translate_mode_attribute): Likewise. * timevar.def: Likewise. * timevar.h (class timer): Likewise. * toplev.h (enable_rtl_dump_file): Likewise. * trans-mem.cc (collect_bb2reg): Likewise. * tree-call-cdce.cc (gen_conditions_for_pow): Likewise. * tree-cfg.cc (remove_bb): Likewise. (verify_gimple_debug): Likewise. (remove_edge_and_dominated_blocks): Likewise. (push_fndecl): Likewise. * tree-cfgcleanup.h (GCC_TREE_CFGCLEANUP_H): Likewise. * tree-complex.cc (expand_complex_multiplication): Likewise. (expand_complex_div_straight): Likewise. * tree-core.h (enum tree_index): Likewise. (enum operand_equal_flag): Likewise. * tree-eh.cc (honor_protect_cleanup_actions): Likewise. * tree-if-conv.cc (if_convertible_gimple_assign_stmt_p): Likewise. * tree-inline.cc (initialize_inlined_parameters): Likewise. * tree-inline.h (force_value_to_type): Likewise. * tree-nested.cc (get_chain_decl): Likewise. (walk_all_functions): Likewise. * tree-object-size.h: Likewise. * tree-outof-ssa.cc: Likewise. * tree-parloops.cc (create_parallel_loop): Likewise. * tree-pretty-print.cc (print_generic_expr_to_str): Likewise. (dump_generic_node): Likewise. * tree-profile.cc (tree_profiling): Likewise. * tree-sra.cc (maybe_add_sra_candidate): Likewise. * tree-ssa-address.cc: Likewise. * tree-ssa-alias.cc: Likewise. * tree-ssa-alias.h (ao_ref::max_size_known_p): Likewise. (dump_alias_stats): Likewise. * tree-ssa-ccp.cc: Likewise. * tree-ssa-coalesce.h: Likewise. * tree-ssa-live.cc (remove_unused_scope_block_p): Likewise. * tree-ssa-loop-manip.cc (copy_phi_node_args): Likewise. * tree-ssa-loop-unswitch.cc: Likewise. * tree-ssa-math-opts.cc: Likewise. * tree-ssa-operands.cc (class operands_scanner): Likewise. * tree-ssa-pre.cc: Likewise. * tree-ssa-reassoc.cc (optimize_ops_list): Likewise. (debug_range_entry): Likewise. * tree-ssa-sccvn.cc (eliminate_dom_walker::eliminate_stmt): Likewise. * tree-ssa-sccvn.h (TREE_SSA_SCCVN_H): Likewise. * tree-ssa-scopedtables.cc (add_expr_commutative): Likewise. (equal_mem_array_ref_p): Likewise. * tree-ssa-strlen.cc (is_strlen_related_p): Likewise. * tree-ssa-strlen.h (get_range_strlen_dynamic): Likewise. * tree-ssa-tail-merge.cc (stmt_local_def): Likewise. * tree-ssa-ter.h: Likewise. * tree-ssa-threadupdate.h (enum bb_dom_status): Likewise. * tree-streamer-in.cc (lto_input_ts_block_tree_pointers): Likewise. * tree-streamer-out.cc (pack_ts_block_value_fields): Likewise. (write_ts_block_tree_pointers): Likewise. * tree-streamer.h (struct streamer_tree_cache_d): Likewise. (streamer_read_tree_bitfields): Likewise. (streamer_write_integer_cst): Likewise. * tree-vect-patterns.cc (apply_binop_and_append_stmt): Likewise. (vect_synth_mult_by_constant): Likewise. * tree-vect-stmts.cc (vectorizable_operation): Likewise. * tree-vectorizer.cc: Likewise. * tree-vectorizer.h (class auto_purge_vect_location): Likewise. (vect_update_inits_of_drs): Likewise. (vect_get_mask_type_for_stmt): Likewise. (vect_rgroup_iv_might_wrap_p): Likewise. (cse_and_gimplify_to_preheader): Likewise. (vect_free_slp_tree): Likewise. (vect_pattern_recog): Likewise. (vect_stmt_dominates_stmt_p): Likewise. * tree.cc (initialize_tree_contains_struct): Likewise. (need_assembler_name_p): Likewise. (type_with_interoperable_signedness): Likewise. * tree.def (SWITCH_EXPR): Likewise. * tree.h (TYPE_SYMTAB_ADDRESS): Likewise. (poly_int_tree_p): Likewise. (inlined_function_outer_scope_p): Likewise. (tree_code_for_canonical_type_merging): Likewise. * value-prof.cc: Likewise. * value-prof.h (get_nth_most_common_value): Likewise. (find_func_by_profile_id): Likewise. * value-range.cc (vrp_operand_equal_p): Likewise. * value-range.h: Likewise. * var-tracking.cc: Likewise. * varasm.cc (default_function_section): Likewise. (function_section_1): Likewise. (assemble_variable): Likewise. (handle_vtv_comdat_section): Likewise. * vec.h (struct vec_prefix): Likewise. * vmsdbgout.cc (full_name): Likewise. * vtable-verify.cc: Likewise. * vtable-verify.h (struct vtv_graph_node): Likewise. * xcoffout.cc: Likewise. * xcoffout.h (DEBUG_SYMS_TEXT): Likewise. gcc/ada/ChangeLog: * Make-generated.in: Rename .c names to .cc. * adaint.c: Likewise. * ctrl_c.c (dummy_handler): Likewise. * gcc-interface/Makefile.in: Likewise. * gcc-interface/config-lang.in: Likewise. * gcc-interface/decl.cc (concat_name): Likewise. (init_gnat_decl): Likewise. * gcc-interface/gigi.h (concat_name): Likewise. (init_gnat_utils): Likewise. (build_call_raise_range): Likewise. (gnat_mark_addressable): Likewise. (gnat_protect_expr): Likewise. (gnat_rewrite_reference): Likewise. * gcc-interface/lang-specs.h (ADA_DUMPS_OPTIONS): Likewise. * gcc-interface/utils.cc (GTY): Likewise. (add_deferred_type_context): Likewise. (init_gnat_utils): Likewise. * gcc-interface/utils2.cc (gnat_stable_expr_p): Likewise. (gnat_protect_expr): Likewise. (gnat_stabilize_reference_1): Likewise. (gnat_rewrite_reference): Likewise. * gsocket.h: Likewise. * init.cc (__gnat_error_handler): Likewise. * libgnarl/s-intman.ads: Likewise. * libgnarl/s-osinte__android.ads: Likewise. * libgnarl/s-osinte__darwin.ads: Likewise. * libgnarl/s-osinte__hpux.ads: Likewise. * libgnarl/s-osinte__linux.ads: Likewise. * libgnarl/s-osinte__qnx.ads: Likewise. * libgnarl/s-taskin.ads: Likewise. * rtfinal.cc: Likewise. * s-oscons-tmplt.c (CND): Likewise. * set_targ.ads: Likewise. gcc/analyzer/ChangeLog: * analyzer.cc (is_special_named_call_p): Rename .c names to .cc. (is_named_call_p): Likewise. * region-model-asm.cc (deterministic_p): Likewise. * region.cc (field_region::get_relative_concrete_offset): Likewise. * sm-malloc.cc (method_p): Likewise. * supergraph.cc (superedge::dump_dot): Likewise. gcc/c-family/ChangeLog: * c-ada-spec.cc: Rename .c names to .cc. * c-ada-spec.h: Likewise. * c-common.cc (c_build_vec_convert): Likewise. (warning_candidate_p): Likewise. * c-common.h (enum rid): Likewise. (build_real_imag_expr): Likewise. (finish_label_address_expr): Likewise. (c_get_substring_location): Likewise. (c_build_bind_expr): Likewise. (conflict_marker_get_final_tok_kind): Likewise. (c_parse_error): Likewise. (check_missing_format_attribute): Likewise. (invalid_array_size_error): Likewise. (warn_for_multistatement_macros): Likewise. (build_attr_access_from_parms): Likewise. * c-cppbuiltin.cc (c_cpp_builtins): Likewise. * c-format.cc: Likewise. * c-gimplify.cc (c_gimplify_expr): Likewise. * c-indentation.h: Likewise. * c-objc.h (objc_prop_attr_kind_for_rid): Likewise. * c-omp.cc (c_omp_predetermined_mapping): Likewise. * c-opts.cc (c_common_post_options): Likewise. (set_std_cxx23): Likewise. * c-pragma.cc (handle_pragma_redefine_extname): Likewise. * c-pretty-print.h: Likewise. gcc/c/ChangeLog: * Make-lang.in: Rename .c names to .cc. * c-convert.cc: Likewise. * c-decl.cc (struct lang_identifier): Likewise. (pop_scope): Likewise. (finish_decl): Likewise. * c-objc-common.h (GCC_C_OBJC_COMMON): Likewise. * c-parser.cc (c_parser_skip_to_end_of_block_or_statement): Likewise. * c-parser.h (GCC_C_PARSER_H): Likewise. * c-tree.h (c_keyword_starts_typename): Likewise. (finish_declspecs): Likewise. (c_get_alias_set): Likewise. (enum c_oracle_request): Likewise. (tag_exists_p): Likewise. (set_c_expr_source_range): Likewise. * c-typeck.cc (c_common_type): Likewise. (c_finish_omp_clauses): Likewise. * config-lang.in: Likewise. gcc/cp/ChangeLog: * Make-lang.in: Rename .c names to .cc. * config-lang.in: Likewise. * constexpr.cc (cxx_eval_constant_expression): Likewise. * coroutines.cc (morph_fn_to_coro): Likewise. * cp-gimplify.cc (cp_gimplify_expr): Likewise. * cp-lang.cc (struct lang_hooks): Likewise. (get_template_argument_pack_elems_folded): Likewise. * cp-objcp-common.cc (cp_tree_size): Likewise. (cp_unit_size_without_reusable_padding): Likewise. (pop_file_scope): Likewise. (cp_pushdecl): Likewise. * cp-objcp-common.h (GCC_CP_OBJCP_COMMON): Likewise. (cxx_simulate_record_decl): Likewise. * cp-tree.h (struct named_label_entry): Likewise. (current_function_return_value): Likewise. (more_aggr_init_expr_args_p): Likewise. (get_function_version_dispatcher): Likewise. (common_enclosing_class): Likewise. (strip_fnptr_conv): Likewise. (current_decl_namespace): Likewise. (do_aggregate_paren_init): Likewise. (cp_check_const_attributes): Likewise. (qualified_name_lookup_error): Likewise. (generic_targs_for): Likewise. (mark_exp_read): Likewise. (is_global_friend): Likewise. (maybe_reject_flexarray_init): Likewise. (module_token_lang): Likewise. (handle_module_option): Likewise. (literal_integer_zerop): Likewise. (build_extra_args): Likewise. (build_if_nonnull): Likewise. (maybe_check_overriding_exception_spec): Likewise. (finish_omp_target_clauses): Likewise. (maybe_warn_zero_as_null_pointer_constant): Likewise. (cxx_print_error_function): Likewise. (decl_in_std_namespace_p): Likewise. (merge_exception_specifiers): Likewise. (mangle_module_global_init): Likewise. (cxx_block_may_fallthru): Likewise. (fold_builtin_source_location): Likewise. (enum cp_oracle_request): Likewise. (subsumes): Likewise. (cp_finish_injected_record_type): Likewise. (vtv_build_vtable_verify_fndecl): Likewise. (cp_tree_c_finish_parsing): Likewise. * cvt.cc (diagnose_ref_binding): Likewise. (convert_to_void): Likewise. (convert_force): Likewise. (type_promotes_to): Likewise. * decl.cc (make_unbound_class_template_raw): Likewise. (cxx_init_decl_processing): Likewise. (check_class_member_definition_namespace): Likewise. (cxx_maybe_build_cleanup): Likewise. * decl2.cc (maybe_emit_vtables): Likewise. * error.cc (dump_function_name): Likewise. * init.cc (is_class_type): Likewise. (build_new_1): Likewise. * lang-specs.h: Likewise. * method.cc (make_alias_for_thunk): Likewise. * module.cc (specialization_add): Likewise. (module_state::read_cluster): Likewise. * name-lookup.cc (check_extern_c_conflict): Likewise. * name-lookup.h (struct cxx_binding): Likewise. * parser.cc (cp_parser_identifier): Likewise. * parser.h (struct cp_parser): Likewise. * pt.cc (has_value_dependent_address): Likewise. (push_tinst_level_loc): Likewise. * semantics.cc (finish_omp_clauses): Likewise. (finish_omp_atomic): Likewise. * tree.cc (cp_save_expr): Likewise. (cp_free_lang_data): Likewise. * typeck.cc (cp_common_type): Likewise. (strip_array_domain): Likewise. (rationalize_conditional_expr): Likewise. (check_return_expr): Likewise. * vtable-class-hierarchy.cc: Likewise. gcc/d/ChangeLog: * d-gimplify.cc: Rename .c names to .cc. * d-incpath.cc: Likewise. * lang-specs.h: Likewise. gcc/fortran/ChangeLog: * check.cc (gfc_check_all_any): Rename .c names to .cc. * class.cc (find_intrinsic_vtab): Likewise. * config-lang.in: Likewise. * cpp.cc (cpp_define_builtins): Likewise. * data.cc (get_array_index): Likewise. * decl.cc (match_clist_expr): Likewise. (get_proc_name): Likewise. (gfc_verify_c_interop_param): Likewise. (gfc_get_pdt_instance): Likewise. (gfc_match_formal_arglist): Likewise. (gfc_get_type_attr_spec): Likewise. * dependency.cc: Likewise. * error.cc (gfc_format_decoder): Likewise. * expr.cc (check_restricted): Likewise. (gfc_build_default_init_expr): Likewise. * f95-lang.cc: Likewise. * gfc-internals.texi: Likewise. * gfortran.h (enum match): Likewise. (enum procedure_type): Likewise. (enum oacc_routine_lop): Likewise. (gfc_get_pdt_instance): Likewise. (gfc_end_source_files): Likewise. (gfc_mpz_set_hwi): Likewise. (gfc_get_option_string): Likewise. (gfc_find_sym_in_expr): Likewise. (gfc_errors_to_warnings): Likewise. (gfc_real_4_kind): Likewise. (gfc_free_finalizer): Likewise. (gfc_sym_get_dummy_args): Likewise. (gfc_check_intrinsic_standard): Likewise. (gfc_free_case_list): Likewise. (gfc_resolve_oacc_routines): Likewise. (gfc_check_vardef_context): Likewise. (gfc_free_association_list): Likewise. (gfc_implicit_pure_function): Likewise. (gfc_ref_dimen_size): Likewise. (gfc_compare_actual_formal): Likewise. (gfc_resolve_wait): Likewise. (gfc_dt_upper_string): Likewise. (gfc_generate_module_code): Likewise. (gfc_delete_bbt): Likewise. (debug): Likewise. (gfc_build_block_ns): Likewise. (gfc_dep_difference): Likewise. (gfc_invalid_null_arg): Likewise. (gfc_is_finalizable): Likewise. (gfc_fix_implicit_pure): Likewise. (gfc_is_size_zero_array): Likewise. (gfc_is_reallocatable_lhs): Likewise. * gfortranspec.cc: Likewise. * interface.cc (compare_actual_expr): Likewise. * intrinsic.cc (add_functions): Likewise. * iresolve.cc (gfc_resolve_matmul): Likewise. (gfc_resolve_alarm_sub): Likewise. * iso-c-binding.def: Likewise. * lang-specs.h: Likewise. * libgfortran.h (GFC_STDERR_UNIT_NUMBER): Likewise. * match.cc (gfc_match_label): Likewise. (gfc_match_symbol): Likewise. (match_derived_type_spec): Likewise. (copy_ts_from_selector_to_associate): Likewise. * match.h (gfc_match_call): Likewise. (gfc_get_common): Likewise. (gfc_match_omp_end_single): Likewise. (gfc_match_volatile): Likewise. (gfc_match_bind_c): Likewise. (gfc_match_literal_constant): Likewise. (gfc_match_init_expr): Likewise. (gfc_match_array_constructor): Likewise. (gfc_match_end_interface): Likewise. (gfc_match_print): Likewise. (gfc_match_expr): Likewise. * matchexp.cc (next_operator): Likewise. * mathbuiltins.def: Likewise. * module.cc (free_true_name): Likewise. * openmp.cc (gfc_resolve_omp_parallel_blocks): Likewise. (gfc_omp_save_and_clear_state): Likewise. * parse.cc (parse_union): Likewise. (set_syms_host_assoc): Likewise. * resolve.cc (resolve_actual_arglist): Likewise. (resolve_elemental_actual): Likewise. (check_host_association): Likewise. (resolve_typebound_function): Likewise. (resolve_typebound_subroutine): Likewise. (gfc_resolve_expr): Likewise. (resolve_assoc_var): Likewise. (resolve_typebound_procedures): Likewise. (resolve_equivalence_derived): Likewise. * simplify.cc (simplify_bound): Likewise. * symbol.cc (gfc_set_default_type): Likewise. (gfc_add_ext_attribute): Likewise. * target-memory.cc (gfc_target_interpret_expr): Likewise. * target-memory.h (gfc_target_interpret_expr): Likewise. * trans-array.cc (gfc_get_cfi_dim_sm): Likewise. (gfc_conv_shift_descriptor_lbound): Likewise. (gfc_could_be_alias): Likewise. (gfc_get_dataptr_offset): Likewise. * trans-const.cc: Likewise. * trans-decl.cc (trans_function_start): Likewise. (gfc_trans_deferred_vars): Likewise. (generate_local_decl): Likewise. (gfc_generate_function_code): Likewise. * trans-expr.cc (gfc_vptr_size_get): Likewise. (gfc_trans_class_array_init_assign): Likewise. (POWI_TABLE_SIZE): Likewise. (gfc_conv_procedure_call): Likewise. (gfc_trans_arrayfunc_assign): Likewise. * trans-intrinsic.cc (gfc_conv_intrinsic_len): Likewise. (gfc_conv_intrinsic_loc): Likewise. (conv_intrinsic_event_query): Likewise. * trans-io.cc (gfc_build_st_parameter): Likewise. * trans-openmp.cc (gfc_omp_check_optional_argument): Likewise. (gfc_omp_unshare_expr_r): Likewise. (gfc_trans_omp_array_section): Likewise. (gfc_trans_omp_clauses): Likewise. * trans-stmt.cc (trans_associate_var): Likewise. (gfc_trans_deallocate): Likewise. * trans-stmt.h (gfc_trans_class_init_assign): Likewise. (gfc_trans_deallocate): Likewise. (gfc_trans_oacc_declare): Likewise. * trans-types.cc: Likewise. * trans-types.h (enum gfc_packed): Likewise. * trans.cc (N_): Likewise. (trans_code): Likewise. * trans.h (gfc_build_compare_string): Likewise. (gfc_conv_expr_type): Likewise. (gfc_trans_deferred_vars): Likewise. (getdecls): Likewise. (gfc_get_array_descr_info): Likewise. (gfc_omp_firstprivatize_type_sizes): Likewise. (GTY): Likewise. gcc/go/ChangeLog: * config-lang.in: Rename .c names to .cc. * go-backend.cc: Likewise. * go-lang.cc: Likewise. * gospec.cc: Likewise. * lang-specs.h: Likewise. gcc/jit/ChangeLog: * config-lang.in: Rename .c names to .cc. * docs/_build/texinfo/libgccjit.texi: Likewise. * docs/internals/index.rst: Likewise. * jit-builtins.cc (builtins_manager::make_builtin_function): Likewise. * jit-playback.cc (fold_const_var): Likewise. (playback::context::~context): Likewise. (new_field): Likewise. (new_bitfield): Likewise. (new_compound_type): Likewise. (playback::compound_type::set_fields): Likewise. (global_set_init_rvalue): Likewise. (load_blob_in_ctor): Likewise. (new_global_initialized): Likewise. (double>): Likewise. (new_string_literal): Likewise. (as_truth_value): Likewise. (build_call): Likewise. (playback::context::build_cast): Likewise. (new_array_access): Likewise. (new_field_access): Likewise. (dereference): Likewise. (postprocess): Likewise. (add_jump): Likewise. (add_switch): Likewise. (build_goto_operands): Likewise. (playback::context::read_dump_file): Likewise. (init_types): Likewise. * jit-recording.cc (recording::context::get_int_type): Likewise. * jit-recording.h: Likewise. * libgccjit.cc (compatible_types): Likewise. (gcc_jit_context_acquire): Likewise. (gcc_jit_context_release): Likewise. (gcc_jit_context_new_child_context): Likewise. (gcc_jit_type_as_object): Likewise. (gcc_jit_context_get_type): Likewise. (gcc_jit_context_get_int_type): Likewise. (gcc_jit_type_get_pointer): Likewise. (gcc_jit_type_get_const): Likewise. (gcc_jit_type_get_volatile): Likewise. (gcc_jit_type_dyncast_array): Likewise. (gcc_jit_type_is_bool): Likewise. (gcc_jit_type_is_pointer): Likewise. (gcc_jit_type_is_integral): Likewise. (gcc_jit_type_dyncast_vector): Likewise. (gcc_jit_type_is_struct): Likewise. (gcc_jit_vector_type_get_num_units): Likewise. (gcc_jit_vector_type_get_element_type): Likewise. (gcc_jit_type_unqualified): Likewise. (gcc_jit_type_dyncast_function_ptr_type): Likewise. (gcc_jit_function_type_get_return_type): Likewise. (gcc_jit_function_type_get_param_count): Likewise. (gcc_jit_function_type_get_param_type): Likewise. (gcc_jit_context_new_array_type): Likewise. (gcc_jit_context_new_field): Likewise. (gcc_jit_field_as_object): Likewise. (gcc_jit_context_new_struct_type): Likewise. (gcc_jit_struct_as_type): Likewise. (gcc_jit_struct_set_fields): Likewise. (gcc_jit_struct_get_field_count): Likewise. (gcc_jit_context_new_union_type): Likewise. (gcc_jit_context_new_function_ptr_type): Likewise. (gcc_jit_param_as_rvalue): Likewise. (gcc_jit_context_new_function): Likewise. (gcc_jit_function_get_return_type): Likewise. (gcc_jit_function_dump_to_dot): Likewise. (gcc_jit_block_get_function): Likewise. (gcc_jit_global_set_initializer_rvalue): Likewise. (gcc_jit_rvalue_get_type): Likewise. (gcc_jit_context_new_rvalue_from_int): Likewise. (gcc_jit_context_one): Likewise. (gcc_jit_context_new_rvalue_from_double): Likewise. (gcc_jit_context_null): Likewise. (gcc_jit_context_new_string_literal): Likewise. (valid_binary_op_p): Likewise. (gcc_jit_context_new_binary_op): Likewise. (gcc_jit_context_new_comparison): Likewise. (gcc_jit_context_new_call): Likewise. (is_valid_cast): Likewise. (gcc_jit_context_new_cast): Likewise. (gcc_jit_object_get_context): Likewise. (gcc_jit_object_get_debug_string): Likewise. (gcc_jit_lvalue_access_field): Likewise. (gcc_jit_rvalue_access_field): Likewise. (gcc_jit_rvalue_dereference_field): Likewise. (gcc_jit_rvalue_dereference): Likewise. (gcc_jit_lvalue_get_address): Likewise. (gcc_jit_lvalue_set_tls_model): Likewise. (gcc_jit_lvalue_set_link_section): Likewise. (gcc_jit_function_new_local): Likewise. (gcc_jit_block_add_eval): Likewise. (gcc_jit_block_add_assignment): Likewise. (is_bool): Likewise. (gcc_jit_block_end_with_conditional): Likewise. (gcc_jit_block_add_comment): Likewise. (gcc_jit_block_end_with_jump): Likewise. (gcc_jit_block_end_with_return): Likewise. (gcc_jit_block_end_with_void_return): Likewise. (case_range_validator::case_range_validator): Likewise. (case_range_validator::validate): Likewise. (case_range_validator::get_wide_int): Likewise. (gcc_jit_block_end_with_switch): Likewise. (gcc_jit_context_set_str_option): Likewise. (gcc_jit_context_set_int_option): Likewise. (gcc_jit_context_set_bool_option): Likewise. (gcc_jit_context_set_bool_allow_unreachable_blocks): Likewise. (gcc_jit_context_set_bool_use_external_driver): Likewise. (gcc_jit_context_add_command_line_option): Likewise. (gcc_jit_context_add_driver_option): Likewise. (gcc_jit_context_enable_dump): Likewise. (gcc_jit_context_compile): Likewise. (gcc_jit_context_compile_to_file): Likewise. (gcc_jit_context_set_logfile): Likewise. (gcc_jit_context_dump_reproducer_to_file): Likewise. (gcc_jit_context_get_first_error): Likewise. (gcc_jit_context_get_last_error): Likewise. (gcc_jit_result_get_code): Likewise. (gcc_jit_result_get_global): Likewise. (gcc_jit_rvalue_set_bool_require_tail_call): Likewise. (gcc_jit_type_get_aligned): Likewise. (gcc_jit_type_get_vector): Likewise. (gcc_jit_function_get_address): Likewise. (gcc_jit_version_patchlevel): Likewise. (gcc_jit_block_add_extended_asm): Likewise. (gcc_jit_extended_asm_as_object): Likewise. (gcc_jit_extended_asm_set_volatile_flag): Likewise. (gcc_jit_extended_asm_set_inline_flag): Likewise. (gcc_jit_extended_asm_add_output_operand): Likewise. (gcc_jit_extended_asm_add_input_operand): Likewise. (gcc_jit_extended_asm_add_clobber): Likewise. * notes.txt: Likewise. gcc/lto/ChangeLog: * config-lang.in: Rename .c names to .cc. * lang-specs.h: Likewise. * lto-common.cc (gimple_register_canonical_type_1): Likewise. * lto-common.h: Likewise. * lto-dump.cc (lto_main): Likewise. * lto-lang.cc (handle_fnspec_attribute): Likewise. (lto_getdecls): Likewise. (lto_init): Likewise. * lto.cc (lto_main): Likewise. * lto.h: Likewise. gcc/objc/ChangeLog: * Make-lang.in: Rename .c names to .cc. * config-lang.in: Likewise. * lang-specs.h: Likewise. * objc-act.cc (objc_build_component_ref): Likewise. (objc_copy_binfo): Likewise. (lookup_method_in_hash_lists): Likewise. (objc_finish_foreach_loop): Likewise. * objc-act.h (objc_common_init_ts): Likewise. * objc-gnu-runtime-abi-01.cc: Likewise. * objc-lang.cc (struct lang_hooks): Likewise. * objc-map.cc: Likewise. * objc-next-runtime-abi-01.cc (generate_objc_symtab_decl): Likewise. * objc-runtime-shared-support.cc: Likewise. * objc-runtime-shared-support.h (build_protocol_initializer): Likewise. gcc/objcp/ChangeLog: * Make-lang.in: Rename .c names to .cc. * config-lang.in: Likewise. * lang-specs.h: Likewise. * objcp-decl.cc (objcp_end_compound_stmt): Likewise. * objcp-lang.cc (struct lang_hooks): Likewise. gcc/po/ChangeLog: * EXCLUDES: Rename .c names to .cc. libcpp/ChangeLog: * Makefile.in: Rename .c names to .cc. * charset.cc (convert_escape): Likewise. * directives.cc (directive_diagnostics): Likewise. (_cpp_handle_directive): Likewise. (lex_macro_node): Likewise. * include/cpplib.h (struct _cpp_file): Likewise. (PURE_ZERO): Likewise. (cpp_defined): Likewise. (cpp_error_at): Likewise. (cpp_forall_identifiers): Likewise. (cpp_compare_macros): Likewise. (cpp_get_converted_source): Likewise. (cpp_read_state): Likewise. (cpp_directive_only_process): Likewise. (struct cpp_decoded_char): Likewise. * include/line-map.h (enum lc_reason): Likewise. (enum location_aspect): Likewise. * include/mkdeps.h: Likewise. * init.cc (cpp_destroy): Likewise. (cpp_finish): Likewise. * internal.h (struct cpp_reader): Likewise. (_cpp_defined_macro_p): Likewise. (_cpp_backup_tokens_direct): Likewise. (_cpp_destroy_hashtable): Likewise. (_cpp_has_header): Likewise. (_cpp_expand_op_stack): Likewise. (_cpp_commit_buff): Likewise. (_cpp_restore_special_builtin): Likewise. (_cpp_bracket_include): Likewise. (_cpp_replacement_text_len): Likewise. (ufputs): Likewise. * line-map.cc (linemap_macro_loc_to_exp_point): Likewise. (linemap_check_files_exited): Likewise. (line_map_new_raw): Likewise. * traditional.cc (enum ls): Likewise.
2022-01-14 16:57:02 +01:00
Broken out of c-lex.cc Apr 2003, adding valid C99 UCN ranges.
This program is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 3, or (at your option) any
later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program; see the file COPYING3. If not see
<http://www.gnu.org/licenses/>. */
#include "config.h"
#include "system.h"
#include "cpplib.h"
Makefile.def (host_modules): add libcpp. ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Makefile.def (host_modules): add libcpp. * Makefile.tpl: Add dependencies on and for libcpp. * Makefile.in: Regenerate. * configure.in: Add libcpp host module. * configure: Regenerate. config/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * acx.m4 (ACX_HEADER_STDBOOL, ACX_HEADER_STRING): From gcc. gcc/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Move libcpp to the toplevel. * Makefile.in: Remove references to libcpp files, use CPPLIBS instead of libcpp.a. Define SYMTAB_H and change hashtable.h to that. * aclocal.m4 (gcc_AC_HEADER_STDBOOL, gcc_AC_HEADER_STRING, gcc_AC_C__BOOL): Remove. * configure.ac (gcc_AC_C__BOOL, HAVE_UCHAR): Remove tests. * configure: Regenerate. * config.in: Regenerate. * c-ppoutput.c: Include ../libcpp/internal.h instead of cpphash.h. * cppcharset.c: Removed. * cpperror.c: Removed. * cppexp.c: Removed. * cppfiles.c: Removed. * cpphash.c: Removed. * cpphash.h: Removed. * cppinit.c: Removed. * cpplex.c: Removed. * cpplib.c: Removed. * cpplib.h: Removed. * cppmacro.c: Removed. * cpppch.c: Removed. * cpptrad.c: Removed. * cppucnid.h: Removed. * cppucnid.pl: Removed. * cppucnid.tab: Removed. * hashtable.c: Removed. * hashtable.h: Removed. * line-map.c: Removed. * line-map.h: Removed. * mkdeps.c: Removed. * mkdeps.h: Removed. * stringpool.h: Include symtab.h instead of hashtable.h. * tree.h: Include symtab.h instead of hashtable.h. * system.h (O_NONBLOCK, O_NOCTTY): Do not define. gcc/cp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: No need to specify $(LIBCPP). gcc/java/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: Link in $(LIBCPP) instead of mkdeps.o. libcpp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Moved libcpp from the gcc subdirectory to the toplevel. * Makefile.am: New file. * Makefile.in: Regenerate. * configure.ac: New file. * configure: Regenerate. * config.in: Regenerate. * charset.c: Moved from gcc/cppcharset.c. Add note about brokenness of input charset detection. Adjust for change in name of cppucnid.h. * errors.c: Moved from gcc/cpperror.c. Do not include intl.h. * expr.c: Moved from gcc/cppexp.c. * files.c: Moved from gcc/cppfiles.c. Do not include intl.h. Remove #define of O_BINARY, it is in system.h. * identifiers.c: Moved from gcc/cpphash.c. * internal.h: Moved from gcc/cpphash.h. Change header guard name. All other files adjusted to match name change. * init.c: Moved from gcc/cppinit.c. (init_library) [ENABLE_NLS]: Call bindtextdomain. * lex.c: Moved from gcc/cpplex.c. * directives.c: Moved from gcc/cpplib.c. * macro.c: Moved from gcc/cppmacro.c. * pch.c: Moved from gcc/cpppch.c. Do not include intl.h. * traditional.c: Moved from gcc/cpptrad.c. * ucnid.h: Moved from gcc/cppucnid.h. Change header guard name. * ucnid.pl: Moved from gcc/cppucnid.pl. * ucnid.tab: Moved from gcc/cppucnid.tab. Change header guard name. * symtab.c: Moved from gcc/hashtable.c. * line-map.c: Moved from gcc. Do not include intl.h. * mkdeps.c: Moved from gcc. * system.h: New file. libcpp/include/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * cpplib.h: Moved from gcc. Change header guard name. * line-map.h: Moved from gcc. Change header guard name. * mkdeps.h: Moved from gcc. Change header guard name. * symtab.h: Moved from gcc/hashtable.h. Change header guard name. libcpp/po/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * be.po: Extracted from gcc/po/be.po. * ca.po: Extracted from gcc/po/ca.po. * da.po: Extracted from gcc/po/da.po. * de.po: Extracted from gcc/po/de.po. * el.po: Extracted from gcc/po/el.po. * es.po: Extracted from gcc/po/es.po. * fr.po: Extracted from gcc/po/fr.po. * ja.po: Extracted from gcc/po/ja.po. * nl.po: Extracted from gcc/po/nl.po. * sv.po: Extracted from gcc/po/sv.po. * tr.po: Extracted from gcc/po/tr.po. From-SVN: r82199
2004-05-24 12:50:45 +02:00
#include "internal.h"
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Character set handling for C-family languages.
Terminological note: In what follows, "charset" or "character set"
will be taken to mean both an abstract set of characters and an
encoding for that set.
The C99 standard discusses two character sets: source and execution.
The source character set is used for internal processing in translation
phases 1 through 4; the execution character set is used thereafter.
Both are required by 5.2.1.2p1 to be multibyte encodings, not wide
character encodings (see 3.7.2, 3.7.3 for the standardese meanings
of these terms). Furthermore, the "basic character set" (listed in
5.2.1p3) is to be encoded in each with values one byte wide, and is
to appear in the initial shift state.
It is not explicitly mentioned, but there is also a "wide execution
character set" used to encode wide character constants and wide
string literals; this is supposed to be the result of applying the
standard library function mbstowcs() to an equivalent narrow string
(6.4.5p5). However, the behavior of hexadecimal and octal
\-escapes is at odds with this; they are supposed to be translated
directly to wchar_t values (6.4.4.4p5,6).
The source character set is not necessarily the character set used
to encode physical source files on disk; translation phase 1 converts
from whatever that encoding is to the source character set.
The presence of universal character names in C99 (6.4.3 et seq.)
forces the source character set to be isomorphic to ISO 10646,
that is, Unicode. There is no such constraint on the execution
character set; note also that the conversion from source to
execution character set does not occur for identifiers (5.1.1.2p1#5).
For convenience of implementation, the source character set's
encoding of the basic character set should be identical to the
execution character set OF THE HOST SYSTEM's encoding of the basic
character set, and it should not be a state-dependent encoding.
cpplib uses UTF-8 or UTF-EBCDIC for the source character set,
depending on whether the host is based on ASCII or EBCDIC (see
respectively Unicode section 2.3/ISO10646 Amendment 2, and Unicode
Technical Report #16). With limited exceptions, it relies on the
system library's iconv() primitive to do charset conversion
(specified in SUSv2). */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
#if !HAVE_ICONV
/* Make certain that the uses of iconv(), iconv_open(), iconv_close()
below, which are guarded only by if statements with compile-time
constant conditions, do not cause link errors. */
#define iconv_open(x, y) (errno = EINVAL, (iconv_t)-1)
#define iconv(a,b,c,d,e) (errno = EINVAL, (size_t)-1)
#define iconv_close(x) (void)0
#define ICONV_CONST
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
#endif
#if HOST_CHARSET == HOST_CHARSET_ASCII
#define SOURCE_CHARSET "UTF-8"
#define LAST_POSSIBLY_BASIC_SOURCE_CHAR 0x7e
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
#elif HOST_CHARSET == HOST_CHARSET_EBCDIC
#define SOURCE_CHARSET "UTF-EBCDIC"
#define LAST_POSSIBLY_BASIC_SOURCE_CHAR 0xFF
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
#else
#error "Unrecognized basic host character set"
#endif
#ifndef EILSEQ
#define EILSEQ EINVAL
#endif
/* This structure is used for a resizable string buffer throughout. */
/* Don't call it strbuf, as that conflicts with unistd.h on systems
such as DYNIX/ptx where unistd.h includes stropts.h. */
struct _cpp_strbuf
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
uchar *text;
size_t asize;
size_t len;
};
/* This is enough to hold any string that fits on a single 80-column
line, even if iconv quadruples its size (e.g. conversion from
ASCII to UTF-32) rounded up to a power of two. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
#define OUTBUF_BLOCK_SIZE 256
/* Conversions between UTF-8 and UTF-16/32 are implemented by custom
logic. This is because a depressing number of systems lack iconv,
or have have iconv libraries that do not do these conversions, so
we need a fallback implementation for them. To ensure the fallback
doesn't break due to neglect, it is used on all systems.
UTF-32 encoding is nice and simple: a four-byte binary number,
constrained to the range 00000000-7FFFFFFF to avoid questions of
signedness. We do have to cope with big- and little-endian
variants.
UTF-16 encoding uses two-byte binary numbers, again in big- and
little-endian variants, for all values in the 00000000-0000FFFF
range. Values in the 00010000-0010FFFF range are encoded as pairs
of two-byte numbers, called "surrogate pairs": given a number S in
this range, it is mapped to a pair (H, L) as follows:
H = (S - 0x10000) / 0x400 + 0xD800
L = (S - 0x10000) % 0x400 + 0xDC00
Two-byte values in the D800...DFFF range are ill-formed except as a
component of a surrogate pair. Even if the encoding within a
two-byte value is little-endian, the H member of the surrogate pair
comes first.
There is no way to encode values in the 00110000-7FFFFFFF range,
which is not currently a problem as there are no assigned code
points in that range; however, the author expects that it will
eventually become necessary to abandon UTF-16 due to this
limitation. Note also that, because of these pairs, UTF-16 does
not meet the requirements of the C standard for a wide character
encoding (see 3.7.3 and 6.4.4.4p11).
UTF-8 encoding looks like this:
value range encoded as
00000000-0000007F 0xxxxxxx
00000080-000007FF 110xxxxx 10xxxxxx
00000800-0000FFFF 1110xxxx 10xxxxxx 10xxxxxx
00010000-001FFFFF 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx
00200000-03FFFFFF 111110xx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
04000000-7FFFFFFF 1111110x 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx 10xxxxxx
Values in the 0000D800 ... 0000DFFF range (surrogates) are invalid,
which means that three-byte sequences ED xx yy, with A0 <= xx <= BF,
never occur. Note also that any value that can be encoded by a
given row of the table can also be encoded by all successive rows,
but this is not done; only the shortest possible encoding for any
given value is valid. For instance, the character 07C0 could be
encoded as any of DF 80, E0 9F 80, F0 80 9F 80, F8 80 80 9F 80, or
FC 80 80 80 9F 80. Only the first is valid.
An implementation note: the transformation from UTF-16 to UTF-8, or
vice versa, is easiest done by using UTF-32 as an intermediary. */
/* Internal primitives which go from an UTF-8 byte stream to native-endian
UTF-32 in a cppchar_t, or vice versa; this avoids an extra marshal/unmarshal
operation in several places below. */
static inline int
one_utf8_to_cppchar (const uchar **inbufp, size_t *inbytesleftp,
cppchar_t *cp)
{
static const uchar masks[6] = { 0x7F, 0x1F, 0x0F, 0x07, 0x03, 0x01 };
static const uchar patns[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
cppchar_t c;
const uchar *inbuf = *inbufp;
size_t nbytes, i;
if (*inbytesleftp < 1)
return EINVAL;
c = *inbuf;
if (c < 0x80)
{
*cp = c;
*inbytesleftp -= 1;
*inbufp += 1;
return 0;
}
/* The number of leading 1-bits in the first byte indicates how many
bytes follow. */
for (nbytes = 2; nbytes < 7; nbytes++)
if ((c & ~masks[nbytes-1]) == patns[nbytes-1])
goto found;
return EILSEQ;
found:
if (*inbytesleftp < nbytes)
return EINVAL;
c = (c & masks[nbytes-1]);
inbuf++;
for (i = 1; i < nbytes; i++)
{
cppchar_t n = *inbuf++;
if ((n & 0xC0) != 0x80)
return EILSEQ;
c = ((c << 6) + (n & 0x3F));
}
/* Make sure the shortest possible encoding was used. */
if (c <= 0x7F && nbytes > 1) return EILSEQ;
if (c <= 0x7FF && nbytes > 2) return EILSEQ;
if (c <= 0xFFFF && nbytes > 3) return EILSEQ;
if (c <= 0x1FFFFF && nbytes > 4) return EILSEQ;
if (c <= 0x3FFFFFF && nbytes > 5) return EILSEQ;
/* Make sure the character is valid. */
if (c > 0x7FFFFFFF || (c >= 0xD800 && c <= 0xDFFF)) return EILSEQ;
*cp = c;
*inbufp = inbuf;
*inbytesleftp -= nbytes;
return 0;
}
static inline int
one_cppchar_to_utf8 (cppchar_t c, uchar **outbufp, size_t *outbytesleftp)
{
static const uchar masks[6] = { 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
static const uchar limits[6] = { 0x80, 0xE0, 0xF0, 0xF8, 0xFC, 0xFE };
size_t nbytes;
uchar buf[6], *p = &buf[6];
uchar *outbuf = *outbufp;
nbytes = 1;
if (c < 0x80)
*--p = c;
else
{
do
{
*--p = ((c & 0x3F) | 0x80);
c >>= 6;
nbytes++;
}
while (c >= 0x3F || (c & limits[nbytes-1]));
*--p = (c | masks[nbytes-1]);
}
if (*outbytesleftp < nbytes)
return E2BIG;
while (p < &buf[6])
*outbuf++ = *p++;
*outbytesleftp -= nbytes;
*outbufp = outbuf;
return 0;
}
/* The following four functions transform one character between the two
encodings named in the function name. All have the signature
int (*)(iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
uchar **outbufp, size_t *outbytesleftp)
BIGEND must have the value 0 or 1, coerced to (iconv_t); it is
interpreted as a boolean indicating whether big-endian or
little-endian encoding is to be used for the member of the pair
that is not UTF-8.
INBUFP, INBYTESLEFTP, OUTBUFP, OUTBYTESLEFTP work exactly as they
do for iconv.
The return value is either 0 for success, or an errno value for
failure, which may be E2BIG (need more space), EILSEQ (ill-formed
input sequence), ir EINVAL (incomplete input sequence). */
static inline int
one_utf8_to_utf32 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
uchar **outbufp, size_t *outbytesleftp)
{
uchar *outbuf;
cppchar_t s = 0;
int rval;
/* Check for space first, since we know exactly how much we need. */
if (*outbytesleftp < 4)
return E2BIG;
rval = one_utf8_to_cppchar (inbufp, inbytesleftp, &s);
if (rval)
return rval;
outbuf = *outbufp;
outbuf[bigend ? 3 : 0] = (s & 0x000000FF);
outbuf[bigend ? 2 : 1] = (s & 0x0000FF00) >> 8;
outbuf[bigend ? 1 : 2] = (s & 0x00FF0000) >> 16;
outbuf[bigend ? 0 : 3] = (s & 0xFF000000) >> 24;
*outbufp += 4;
*outbytesleftp -= 4;
return 0;
}
static inline int
one_utf32_to_utf8 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
uchar **outbufp, size_t *outbytesleftp)
{
cppchar_t s;
int rval;
const uchar *inbuf;
if (*inbytesleftp < 4)
return EINVAL;
inbuf = *inbufp;
s = inbuf[bigend ? 0 : 3] << 24;
s += inbuf[bigend ? 1 : 2] << 16;
s += inbuf[bigend ? 2 : 1] << 8;
s += inbuf[bigend ? 3 : 0];
if (s >= 0x7FFFFFFF || (s >= 0xD800 && s <= 0xDFFF))
return EILSEQ;
rval = one_cppchar_to_utf8 (s, outbufp, outbytesleftp);
if (rval)
return rval;
*inbufp += 4;
*inbytesleftp -= 4;
return 0;
}
static inline int
one_utf8_to_utf16 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
uchar **outbufp, size_t *outbytesleftp)
{
int rval;
cppchar_t s = 0;
const uchar *save_inbuf = *inbufp;
size_t save_inbytesleft = *inbytesleftp;
uchar *outbuf = *outbufp;
rval = one_utf8_to_cppchar (inbufp, inbytesleftp, &s);
if (rval)
return rval;
if (s > 0x0010FFFF)
{
*inbufp = save_inbuf;
*inbytesleftp = save_inbytesleft;
return EILSEQ;
}
if (s <= 0xFFFF)
{
if (*outbytesleftp < 2)
{
*inbufp = save_inbuf;
*inbytesleftp = save_inbytesleft;
return E2BIG;
}
outbuf[bigend ? 1 : 0] = (s & 0x00FF);
outbuf[bigend ? 0 : 1] = (s & 0xFF00) >> 8;
*outbufp += 2;
*outbytesleftp -= 2;
return 0;
}
else
{
cppchar_t hi, lo;
if (*outbytesleftp < 4)
{
*inbufp = save_inbuf;
*inbytesleftp = save_inbytesleft;
return E2BIG;
}
hi = (s - 0x10000) / 0x400 + 0xD800;
lo = (s - 0x10000) % 0x400 + 0xDC00;
/* Even if we are little-endian, put the high surrogate first.
??? Matches practice? */
outbuf[bigend ? 1 : 0] = (hi & 0x00FF);
outbuf[bigend ? 0 : 1] = (hi & 0xFF00) >> 8;
outbuf[bigend ? 3 : 2] = (lo & 0x00FF);
outbuf[bigend ? 2 : 3] = (lo & 0xFF00) >> 8;
*outbufp += 4;
*outbytesleftp -= 4;
return 0;
}
}
static inline int
one_utf16_to_utf8 (iconv_t bigend, const uchar **inbufp, size_t *inbytesleftp,
uchar **outbufp, size_t *outbytesleftp)
{
cppchar_t s;
const uchar *inbuf = *inbufp;
int rval;
if (*inbytesleftp < 2)
return EINVAL;
s = inbuf[bigend ? 0 : 1] << 8;
s += inbuf[bigend ? 1 : 0];
/* Low surrogate without immediately preceding high surrogate is invalid. */
if (s >= 0xDC00 && s <= 0xDFFF)
return EILSEQ;
/* High surrogate must have a following low surrogate. */
else if (s >= 0xD800 && s <= 0xDBFF)
{
cppchar_t hi = s, lo;
if (*inbytesleftp < 4)
return EINVAL;
lo = inbuf[bigend ? 2 : 3] << 8;
lo += inbuf[bigend ? 3 : 2];
if (lo < 0xDC00 || lo > 0xDFFF)
return EILSEQ;
s = (hi - 0xD800) * 0x400 + (lo - 0xDC00) + 0x10000;
}
rval = one_cppchar_to_utf8 (s, outbufp, outbytesleftp);
if (rval)
return rval;
/* Success - update the input pointers (one_cppchar_to_utf8 has done
the output pointers for us). */
if (s <= 0xFFFF)
{
*inbufp += 2;
*inbytesleftp -= 2;
}
else
{
*inbufp += 4;
*inbytesleftp -= 4;
}
return 0;
}
/* Helper routine for the next few functions. The 'const' on
one_conversion means that we promise not to modify what function is
pointed to, which lets the inliner see through it. */
static inline bool
conversion_loop (int (*const one_conversion)(iconv_t, const uchar **, size_t *,
uchar **, size_t *),
iconv_t cd, const uchar *from, size_t flen, struct _cpp_strbuf *to)
{
const uchar *inbuf;
uchar *outbuf;
size_t inbytesleft, outbytesleft;
int rval;
inbuf = from;
inbytesleft = flen;
outbuf = to->text + to->len;
outbytesleft = to->asize - to->len;
for (;;)
{
do
rval = one_conversion (cd, &inbuf, &inbytesleft,
&outbuf, &outbytesleft);
while (inbytesleft && !rval);
if (__builtin_expect (inbytesleft == 0, 1))
{
to->len = to->asize - outbytesleft;
return true;
}
if (rval != E2BIG)
{
errno = rval;
return false;
}
outbytesleft += OUTBUF_BLOCK_SIZE;
to->asize += OUTBUF_BLOCK_SIZE;
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
to->text = XRESIZEVEC (uchar, to->text, to->asize);
outbuf = to->text + to->asize - outbytesleft;
}
}
/* These functions convert entire strings between character sets.
They all have the signature
bool (*)(iconv_t cd, const uchar *from, size_t flen, struct _cpp_strbuf *to);
The input string FROM is converted as specified by the function
name plus the iconv descriptor CD (which may be fake), and the
result appended to TO. On any error, false is returned, otherwise true. */
/* These four use the custom conversion code above. */
static bool
convert_utf8_utf16 (iconv_t cd, const uchar *from, size_t flen,
struct _cpp_strbuf *to)
{
return conversion_loop (one_utf8_to_utf16, cd, from, flen, to);
}
static bool
convert_utf8_utf32 (iconv_t cd, const uchar *from, size_t flen,
struct _cpp_strbuf *to)
{
return conversion_loop (one_utf8_to_utf32, cd, from, flen, to);
}
static bool
convert_utf16_utf8 (iconv_t cd, const uchar *from, size_t flen,
struct _cpp_strbuf *to)
{
return conversion_loop (one_utf16_to_utf8, cd, from, flen, to);
}
static bool
convert_utf32_utf8 (iconv_t cd, const uchar *from, size_t flen,
struct _cpp_strbuf *to)
{
return conversion_loop (one_utf32_to_utf8, cd, from, flen, to);
}
/* Identity conversion, used when we have no alternative. */
static bool
convert_no_conversion (iconv_t cd ATTRIBUTE_UNUSED,
const uchar *from, size_t flen, struct _cpp_strbuf *to)
{
if (to->len + flen > to->asize)
{
to->asize = to->len + flen;
to->asize += to->asize / 4;
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
to->text = XRESIZEVEC (uchar, to->text, to->asize);
}
memcpy (to->text + to->len, from, flen);
to->len += flen;
return true;
}
/* And this one uses the system iconv primitive. It's a little
different, since iconv's interface is a little different. */
#if HAVE_ICONV
#define CONVERT_ICONV_GROW_BUFFER \
do { \
outbytesleft += OUTBUF_BLOCK_SIZE; \
to->asize += OUTBUF_BLOCK_SIZE; \
to->text = XRESIZEVEC (uchar, to->text, to->asize); \
outbuf = (char *)to->text + to->asize - outbytesleft; \
} while (0)
static bool
convert_using_iconv (iconv_t cd, const uchar *from, size_t flen,
struct _cpp_strbuf *to)
{
ICONV_CONST char *inbuf;
char *outbuf;
size_t inbytesleft, outbytesleft;
/* Reset conversion descriptor and check that it is valid. */
if (iconv (cd, 0, 0, 0, 0) == (size_t)-1)
return false;
inbuf = (ICONV_CONST char *)from;
inbytesleft = flen;
outbuf = (char *)to->text + to->len;
outbytesleft = to->asize - to->len;
for (;;)
{
iconv (cd, &inbuf, &inbytesleft, &outbuf, &outbytesleft);
if (__builtin_expect (inbytesleft == 0, 1))
{
/* Close out any shift states, returning to the initial state. */
if (iconv (cd, 0, 0, &outbuf, &outbytesleft) == (size_t)-1)
{
if (errno != E2BIG)
return false;
CONVERT_ICONV_GROW_BUFFER;
if (iconv (cd, 0, 0, &outbuf, &outbytesleft) == (size_t)-1)
return false;
}
to->len = to->asize - outbytesleft;
return true;
}
if (errno != E2BIG)
return false;
CONVERT_ICONV_GROW_BUFFER;
}
}
#else
#define convert_using_iconv 0 /* prevent undefined symbol error below */
#endif
/* Arrange for the above custom conversion logic to be used automatically
when conversion between a suitable pair of character sets is requested. */
#define APPLY_CONVERSION(CONVERTER, FROM, FLEN, TO) \
CONVERTER.func (CONVERTER.cd, FROM, FLEN, TO)
struct cpp_conversion
{
const char *pair;
convert_f func;
iconv_t fake_cd;
};
static const struct cpp_conversion conversion_tab[] = {
{ "UTF-8/UTF-32LE", convert_utf8_utf32, (iconv_t)0 },
{ "UTF-8/UTF-32BE", convert_utf8_utf32, (iconv_t)1 },
{ "UTF-8/UTF-16LE", convert_utf8_utf16, (iconv_t)0 },
{ "UTF-8/UTF-16BE", convert_utf8_utf16, (iconv_t)1 },
{ "UTF-32LE/UTF-8", convert_utf32_utf8, (iconv_t)0 },
{ "UTF-32BE/UTF-8", convert_utf32_utf8, (iconv_t)1 },
{ "UTF-16LE/UTF-8", convert_utf16_utf8, (iconv_t)0 },
{ "UTF-16BE/UTF-8", convert_utf16_utf8, (iconv_t)1 },
};
/* Subroutine of cpp_init_iconv: initialize and return a
cset_converter structure for conversion from FROM to TO. If
iconv_open() fails, issue an error and return an identity
converter. Silently return an identity converter if FROM and TO
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
are identical.
PFILE is only used for generating diagnostics; setting it to NULL
suppresses diagnostics. */
static struct cset_converter
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
init_iconv_desc (cpp_reader *pfile, const char *to, const char *from)
{
struct cset_converter ret;
char *pair;
size_t i;
ret.to = to;
ret.from = from;
if (!strcasecmp (to, from))
{
ret.func = convert_no_conversion;
ret.cd = (iconv_t) -1;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
ret.width = -1;
return ret;
}
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
pair = (char *) alloca(strlen(to) + strlen(from) + 2);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
strcpy(pair, from);
strcat(pair, "/");
strcat(pair, to);
for (i = 0; i < ARRAY_SIZE (conversion_tab); i++)
if (!strcasecmp (pair, conversion_tab[i].pair))
{
ret.func = conversion_tab[i].func;
ret.cd = conversion_tab[i].fake_cd;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
ret.width = -1;
return ret;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* No custom converter - try iconv. */
if (HAVE_ICONV)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
ret.func = convert_using_iconv;
ret.cd = iconv_open (to, from);
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
ret.width = -1;
if (ret.cd == (iconv_t) -1)
{
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
if (pfile)
{
if (errno == EINVAL)
cpp_error (pfile, CPP_DL_ERROR, /* FIXME should be DL_SORRY */
"conversion from %s to %s not supported by iconv",
from, to);
else
cpp_errno (pfile, CPP_DL_ERROR, "iconv_open");
}
ret.func = convert_no_conversion;
}
}
else
{
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
if (pfile)
{
cpp_error (pfile, CPP_DL_ERROR, /* FIXME: should be DL_SORRY */
"no iconv implementation, cannot convert from %s to %s",
from, to);
}
ret.func = convert_no_conversion;
ret.cd = (iconv_t) -1;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
ret.width = -1;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
return ret;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
/* If charset conversion is requested, initialize iconv(3) descriptors
for conversion from the source character set to the execution
character sets. If iconv is not present in the C library, and
conversion is requested, issue an error. */
void
cpp_init_iconv (cpp_reader *pfile)
{
const char *ncset = CPP_OPTION (pfile, narrow_charset);
const char *wcset = CPP_OPTION (pfile, wide_charset);
const char *default_wcset;
bool be = CPP_OPTION (pfile, bytes_big_endian);
if (CPP_OPTION (pfile, wchar_precision) >= 32)
default_wcset = be ? "UTF-32BE" : "UTF-32LE";
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else if (CPP_OPTION (pfile, wchar_precision) >= 16)
default_wcset = be ? "UTF-16BE" : "UTF-16LE";
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else
/* This effectively means that wide strings are not supported,
so don't do any conversion at all. */
default_wcset = SOURCE_CHARSET;
if (!ncset)
ncset = SOURCE_CHARSET;
if (!wcset)
wcset = default_wcset;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
pfile->narrow_cset_desc = init_iconv_desc (pfile, ncset, SOURCE_CHARSET);
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision);
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
pfile->utf8_cset_desc = init_iconv_desc (pfile, "UTF-8", SOURCE_CHARSET);
pfile->utf8_cset_desc.width = CPP_OPTION (pfile, char_precision);
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
pfile->char16_cset_desc = init_iconv_desc (pfile,
be ? "UTF-16BE" : "UTF-16LE",
SOURCE_CHARSET);
pfile->char16_cset_desc.width = 16;
pfile->char32_cset_desc = init_iconv_desc (pfile,
be ? "UTF-32BE" : "UTF-32LE",
SOURCE_CHARSET);
pfile->char32_cset_desc.width = 32;
pfile->wide_cset_desc = init_iconv_desc (pfile, wcset, SOURCE_CHARSET);
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
pfile->wide_cset_desc.width = CPP_OPTION (pfile, wchar_precision);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
/* Destroy iconv(3) descriptors set up by cpp_init_iconv, if necessary. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
void
_cpp_destroy_iconv (cpp_reader *pfile)
{
if (HAVE_ICONV)
{
if (pfile->narrow_cset_desc.func == convert_using_iconv)
iconv_close (pfile->narrow_cset_desc.cd);
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
if (pfile->utf8_cset_desc.func == convert_using_iconv)
iconv_close (pfile->utf8_cset_desc.cd);
if (pfile->char16_cset_desc.func == convert_using_iconv)
iconv_close (pfile->char16_cset_desc.cd);
if (pfile->char32_cset_desc.func == convert_using_iconv)
iconv_close (pfile->char32_cset_desc.cd);
if (pfile->wide_cset_desc.func == convert_using_iconv)
iconv_close (pfile->wide_cset_desc.cd);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
}
/* Utility routine for use by a full compiler. C is a character taken
from the *basic* source character set, encoded in the host's
execution encoding. Convert it to (the target's) execution
encoding, and return that value.
Issues an internal error if C's representation in the narrow
execution character set fails to be a single-byte value (C99
5.2.1p3: "The representation of each member of the source and
execution character sets shall fit in a byte.") May also issue an
internal error if C fails to be a member of the basic source
character set (testing this exactly is too hard, especially when
the host character set is EBCDIC). */
cppchar_t
cpp_host_to_exec_charset (cpp_reader *pfile, cppchar_t c)
{
uchar sbuf[1];
struct _cpp_strbuf tbuf;
/* This test is merely an approximation, but it suffices to catch
the most important thing, which is that we don't get handed a
character outside the unibyte range of the host character set. */
if (c > LAST_POSSIBLY_BASIC_SOURCE_CHAR)
{
cpp_error (pfile, CPP_DL_ICE,
"character 0x%lx is not in the basic source character set\n",
(unsigned long)c);
return 0;
}
/* Being a character in the unibyte range of the host character set,
we can safely splat it into a one-byte buffer and trust that that
is a well-formed string. */
sbuf[0] = c;
/* This should never need to reallocate, but just in case... */
tbuf.asize = 1;
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
tbuf.text = XNEWVEC (uchar, tbuf.asize);
tbuf.len = 0;
if (!APPLY_CONVERSION (pfile->narrow_cset_desc, sbuf, 1, &tbuf))
{
cpp_errno (pfile, CPP_DL_ICE, "converting to execution character set");
return 0;
}
if (tbuf.len != 1)
{
cpp_error (pfile, CPP_DL_ICE,
"character 0x%lx is not unibyte in execution character set",
(unsigned long)c);
return 0;
}
c = tbuf.text[0];
free(tbuf.text);
return c;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* cpp_substring_ranges's constructor. */
cpp_substring_ranges::cpp_substring_ranges () :
m_ranges (NULL),
m_num_ranges (0),
m_alloc_ranges (8)
{
m_ranges = XNEWVEC (source_range, m_alloc_ranges);
}
/* cpp_substring_ranges's destructor. */
cpp_substring_ranges::~cpp_substring_ranges ()
{
free (m_ranges);
}
/* Add RANGE to the vector of source_range information. */
void
cpp_substring_ranges::add_range (source_range range)
{
if (m_num_ranges >= m_alloc_ranges)
{
m_alloc_ranges *= 2;
m_ranges
= (source_range *)xrealloc (m_ranges,
sizeof (source_range) * m_alloc_ranges);
}
m_ranges[m_num_ranges++] = range;
}
/* Read NUM ranges from LOC_READER, adding them to the vector of source_range
information. */
void
cpp_substring_ranges::add_n_ranges (int num,
cpp_string_location_reader &loc_reader)
{
for (int i = 0; i < num; i++)
add_range (loc_reader.get_next ());
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Utility routine that computes a mask of the form 0000...111... with
WIDTH 1-bits. */
static inline size_t
width_to_mask (size_t width)
{
width = MIN (width, BITS_PER_CPPCHAR_T);
if (width >= CHAR_BIT * sizeof (size_t))
return ~(size_t) 0;
else
return ((size_t) 1 << width) - 1;
}
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* A large table of unicode character information. */
enum {
/* Valid in a C99 identifier? */
C99 = 1,
/* Valid in a C99 identifier, but not as the first character? */
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
N99 = 2,
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Valid in a C++ identifier? */
CXX = 4,
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
/* Valid in a C11/C++11 identifier? */
C11 = 8,
/* Valid in a C11/C++11 identifier, but not as the first character? */
N11 = 16,
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
/* Valid in a C++23 identifier? */
CXX23 = 32,
/* Valid in a C++23 identifier, but not as the first character? */
NXX23 = 64,
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* NFC representation is not valid in an identifier? */
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
CID = 128,
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Might be valid NFC form? */
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
NFC = 256,
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Might be valid NFKC form? */
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
NKC = 512,
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Certain preceding characters might make it not valid NFC/NKFC form? */
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
CTX = 1024
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
};
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
struct ucnrange {
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Bitmap of flags above. */
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
unsigned short flags;
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Combining class of the character. */
unsigned char combine;
/* Last character in the range described by this entry. */
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
unsigned int end;
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
};
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
#include "ucnid.h"
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* ISO 10646 defines the UCS codespace as the range 0-0x10FFFF inclusive. */
#define UCS_LIMIT 0x10FFFF
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Returns 1 if C is valid in an identifier, 2 if C is valid except at
the start of an identifier, and 0 if C is not valid in an
identifier. We assume C has already gone through the checks of
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
_cpp_valid_ucn. Also update NST for C if returning nonzero. The
algorithm is a simple binary search on the table defined in
ucnid.h. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static int
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
ucn_valid_in_identifier (cpp_reader *pfile, cppchar_t c,
struct normalize_state *nst)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
int mn, mx, md;
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
unsigned short valid_flags, invalid_start_flags;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
if (c > UCS_LIMIT)
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
return 0;
mn = 0;
mx = ARRAY_SIZE (ucnranges) - 1;
while (mx != mn)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
md = (mn + mx) / 2;
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
if (c <= ucnranges[md].end)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
mx = md;
else
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
mn = md + 1;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* When -pedantic, we require the character to have been listed by
the standard for the current language. Otherwise, we accept the
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
union of the acceptable sets for all supported language versions. */
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
valid_flags = C99 | CXX | C11 | CXX23;
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
if (CPP_PEDANTIC (pfile))
{
if (CPP_OPTION (pfile, cplusplus))
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
valid_flags = CXX23;
else if (CPP_OPTION (pfile, c11_identifiers))
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
valid_flags = C11;
else if (CPP_OPTION (pfile, c99))
valid_flags = C99;
}
if (! (ucnranges[mn].flags & valid_flags))
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
return 0;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
/* Update NST. */
if (ucnranges[mn].combine != 0 && ucnranges[mn].combine < nst->prev_class)
nst->level = normalized_none;
else if (ucnranges[mn].flags & CTX)
{
bool safe;
cppchar_t p = nst->previous;
/* For Hangul, characters in the range AC00-D7A3 are NFC/NFKC,
and are combined algorithmically from a sequence of the form
1100-1112 1161-1175 11A8-11C2
(if the third is not present, it is treated as 11A7, which is not
really a valid character).
Unfortunately, C99 allows (only) the NFC form, but C++ allows
only the combining characters. */
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
if (c >= 0x1161 && c <= 0x1175)
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
safe = p < 0x1100 || p > 0x1112;
else if (c >= 0x11A8 && c <= 0x11C2)
safe = (p < 0xAC00 || p > 0xD7A3 || (p - 0xAC00) % 28 != 0);
else
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
safe = check_nfc (pfile, c, p);
if (!safe)
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
{
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
if ((c >= 0x1161 && c <= 0x1175) || (c >= 0x11A8 && c <= 0x11C2))
nst->level = MAX (nst->level, normalized_identifier_C);
else
nst->level = normalized_none;
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
}
}
else if (ucnranges[mn].flags & NKC)
;
else if (ucnranges[mn].flags & NFC)
nst->level = MAX (nst->level, normalized_C);
else if (ucnranges[mn].flags & CID)
nst->level = MAX (nst->level, normalized_identifier_C);
else
nst->level = normalized_none;
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
if (ucnranges[mn].combine == 0)
nst->previous = c;
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
nst->prev_class = ucnranges[mn].combine;
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
if (!CPP_PEDANTIC (pfile))
{
/* If not -pedantic, accept as character that may
begin an identifier a union of characters allowed
at that position in each of the character sets. */
if ((ucnranges[mn].flags & (C99 | N99)) == C99
|| (ucnranges[mn].flags & CXX) != 0
|| (ucnranges[mn].flags & (C11 | N11)) == C11
|| (ucnranges[mn].flags & (CXX23 | NXX23)) == CXX23)
return 1;
return 2;
}
if (CPP_OPTION (pfile, cplusplus))
libcpp: Implement C++23 P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 The following patch implements the P1949R7 - C++ Identifier Syntax using Unicode Standard Annex 31 paper. We already allow UTF-8 characters in the source, so that part is already implemented, so IMHO all we need to do is pedwarn instead of just warn for the (default) -Wnormalize=nfc (or for -Wnormalize={id,nkfc}) if the character is not in NFC and to use the unicode XID_Start and XID_Continue derived code properties to find out what characters are allowed (the standard actually adds U+005F to XID_Start, but we are handling the ASCII compatible characters differently already and they aren't allowed in UCNs in identifiers). Instead of hardcoding the large tables in ucnid.tab, this patch makes makeucnid.c read them from the Unicode tables (13.0.0 version at this point). For non-pedantic mode, we accept as 2nd+ char in identifiers a union of valid characters in all supported modes, but for the 1st char it was actually pedantically requiring that it is not any of the characters that may not appear in the currently chosen standard as the first character. This patch changes it such that also what is allowed at the start of an identifier is a union of characters valid at the start of an identifier in any of the pedantic modes. 2021-09-01 Jakub Jelinek <jakub@redhat.com> PR c++/100977 libcpp/ * include/cpplib.h (struct cpp_options): Add cxx23_identifiers. * charset.c (CXX23, NXX23): New enumerators. (CID, NFC, NKC, CTX): Renumber. (ucn_valid_in_identifier): Implement P1949R7 - use CXX23 and NXX23 flags for cxx23_identifiers. For start character in non-pedantic mode, allow characters that are allowed as start characters in any of the supported language modes, rather than disallowing characters allowed only as non-start characters in current mode but for characters from other language modes allowing them even if they are never allowed at start. * init.c (struct lang_flags): Add cxx23_identifiers. (lang_defaults): Add cxx23_identifiers column. (cpp_set_lang): Initialize CPP_OPTION (pfile, cxx23_identifiers). * lex.c (warn_about_normalization): If cxx23_identifiers, use cpp_pedwarning_with_line instead of cpp_warning_with_line for "is not in NFC" diagnostics. * makeucnid.c: Adjust usage comment. (CXX23, NXX23): New enumerators. (all_languages): Add CXX23. (not_NFC, not_NFKC, maybe_not_NFC): Renumber. (read_derivedcore): New function. (write_table): Print also CXX23 and NXX23 columns. (main): Require 5 arguments instead of 4, call read_derivedcore. * ucnid.h: Regenerated using Unicode 13.0.0 files. gcc/testsuite/ * g++.dg/cpp23/normalize1.C: New test. * g++.dg/cpp23/normalize2.C: New test. * g++.dg/cpp23/normalize3.C: New test. * g++.dg/cpp23/normalize4.C: New test. * g++.dg/cpp23/normalize5.C: New test. * g++.dg/cpp23/normalize6.C: New test. * g++.dg/cpp23/normalize7.C: New test. * g++.dg/cpp23/ucnid-1-utf8.C: New test. * g++.dg/cpp23/ucnid-2-utf8.C: New test. * gcc.dg/cpp/ucnid-4.c: Don't expect "not valid at the start of an identifier" errors. * gcc.dg/cpp/ucnid-4-utf8.c: Likewise. * gcc.dg/cpp/ucnid-5-utf8.c: New test.
2021-09-01 22:33:06 +02:00
invalid_start_flags = NXX23;
else if (CPP_OPTION (pfile, c11_identifiers))
invalid_start_flags = N11;
else if (CPP_OPTION (pfile, c99))
invalid_start_flags = N99;
else
invalid_start_flags = 0;
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
/* In C99, UCN digits may not begin identifiers. In C11 and C++11,
UCN combining characters may not begin identifiers. */
if (ucnranges[mn].flags & invalid_start_flags)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return 2;
return 1;
}
/* [lex.charset]: The character designated by the universal character
name \UNNNNNNNN is that character whose character short name in
ISO/IEC 10646 is NNNNNNNN; the character designated by the
universal character name \uNNNN is that character whose character
short name in ISO/IEC 10646 is 0000NNNN. If the hexadecimal value
for a universal character name corresponds to a surrogate code point
(in the range 0xD800-0xDFFF, inclusive), the program is ill-formed.
Additionally, if the hexadecimal value for a universal-character-name
outside a character or string literal corresponds to a control character
(in either of the ranges 0x00-0x1F or 0x7F-0x9F, both inclusive) or to a
character in the basic source character set, the program is ill-formed.
C99 6.4.3: A universal character name shall not specify a character
whose short identifier is less than 00A0 other than 0024 ($), 0040 (@),
or 0060 (`), nor one in the range D800 through DFFF inclusive.
If the hexadecimal value is larger than the upper bound of the UCS
codespace specified in ISO/IEC 10646, a pedantic warning is issued
in all versions of C and in the C++20 or later versions of C++.
*PSTR must be preceded by "\u" or "\U"; it is assumed that the
buffer end is delimited by a non-hex digit. Returns false if the
UCN has not been consumed, true otherwise.
The value of the UCN, whether valid or invalid, is returned in *CP.
Diagnostics are emitted for invalid values. PSTR is updated to point
one beyond the UCN, or to the syntactically invalid character.
IDENTIFIER_POS is 0 when not in an identifier, 1 for the start of
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
an identifier, or 2 otherwise.
If LOC_READER is non-NULL, then position information is
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
read from *LOC_READER and CHAR_RANGE->m_finish is updated accordingly. */
bool
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
_cpp_valid_ucn (cpp_reader *pfile, const uchar **pstr,
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
const uchar *limit, int identifier_pos,
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
struct normalize_state *nst, cppchar_t *cp,
source_range *char_range,
cpp_string_location_reader *loc_reader)
{
cppchar_t result, c;
unsigned int length;
const uchar *str = *pstr;
const uchar *base = str - 2;
if (!CPP_OPTION (pfile, cplusplus) && !CPP_OPTION (pfile, c99))
cpp_error (pfile, CPP_DL_WARNING,
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
"universal character names are only valid in C++ and C99");
else if (CPP_OPTION (pfile, cpp_warn_c90_c99_compat) > 0
re PR c/51849 (-Wc99-compat would be considered useful) PR c/51849 gcc/ * gcc/doc/invoke.texi: Document -Wc90-c99-compat. gcc/c-family/ * c-opts.c (sanitize_cpp_opts): Pass warn_c90_c99_compat to libcpp. * c.opt (Wc90-c99-compat): Add option. gcc/c/ * c-decl.c (build_array_declarator): Remove check for !flag_isoc99. Call pedwarn_c90 instead of pedwarn. (check_bitfield_type_and_width): Likewise. (declspecs_add_qual): Likewise. (declspecs_add_type): Likewise. (warn_variable_length_array): Unify function for -pedantic and -Wvla. Adjust to only call pedwarn_c90. (grokdeclarator): Remove pedantic && !flag_isoc99 check. Call pedwarn_c90 instead of pedwarn. * c-errors.c (pedwarn_c90): Handle -Wc90-c99-compat. * c-parser.c (disable_extension_diagnostics): Handle warn_c90_c99_compat. (restore_extension_diagnostics): Likewise. (c_parser_enum_specifier): Remove check for !flag_isoc99. Call pedwarn_c90 instead of pedwarn. (c_parser_initelt): Likewise. (c_parser_postfix_expression): Likewise. (c_parser_postfix_expression_after_paren_type): Likewise. (c_parser_compound_statement_nostart): Remove check for !flag_isoc99. * c-tree.h: Fix formatting. * c-typeck.c (build_array_ref): Remove check for !flag_isoc99. Call pedwarn_c90 instead of pedwarn. gcc/testsuite/ * gcc.dg/Wc90-c99-compat-1.c: New test. * gcc.dg/Wc90-c99-compat-2.c: New test. * gcc.dg/Wc90-c99-compat-3.c: New test. * gcc.dg/Wc90-c99-compat-4.c: New test. * gcc.dg/Wc90-c99-compat-5.c: New test. * gcc.dg/Wc90-c99-compat-6.c: New test. * gcc.dg/wvla-1.c: Adjust dg-warning. * gcc.dg/wvla-2.c: Adjust dg-warning. * gcc.dg/wvla-4.c: Adjust dg-warning. * gcc.dg/wvla-6.c: Adjust dg-warning. libcpp/ * lex.c (_cpp_lex_direct): Warn when -Wc90-c99-compat is in effect. * charset.c (_cpp_valid_ucn): Likewise. * include/cpplib.h (cpp_options): Add cpp_warn_c90_c99_compat. * macro.c (replace_args): Warn when -Wc90-c99-compat is in effect. (parse_params): Likewise. From-SVN: r213786
2014-08-10 08:10:49 +02:00
&& !CPP_OPTION (pfile, cplusplus))
cpp_error (pfile, CPP_DL_WARNING,
"C99's universal character names are incompatible with C90");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else if (CPP_WTRADITIONAL (pfile) && identifier_pos == 0)
diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * c-tree.h (c_cpp_error): Add warning reason argument. * opts.c (_warning_as_error_callback): New. (register_warning_as_error_callback): Store callback for warnings enabled via enable_warning_as_error. (enable_warning_as_error): Call callback, minor code tidy. * opts.h (register_warning_as_error_callback): Declare. * c-opts.c (warning_as_error_callback): New, set cpp_opts flag in response to -Werror=. (c_common_init_options): Register warning_as_error_callback in opts.c. * common.opt: Add -Wno-cpp option. * c-common.c (struct reason_option_codes_t): Map cpp warning reason codes to gcc option indexes. * (c_option_controlling_cpp_error): New function, lookup the gcc option index for a cpp warning reason code. * (c_cpp_error): Add warning reason argument, call c_option_controlling_cpp_error for diagnostic_override_option_index. * doc/invoke.texi: Document -Wno-cpp. * cpp.c (cb_cpp_error): Add warning reason argument, set a value for diagnostic_override_option_index if CPP_W_WARNING_DIRECTIVE. * directives.c (do_diagnostic): Add warning reason argument, call appropriate error reporting function for code. (directive_diagnostics): Call specific warning functions with warning reason where appropriate. (do_error, do_warning, do_pragma_dependency): Add warning reason argument to do_diagnostic calls. * macro.c (_cpp_warn_if_unused_macro, enter_macro_context, _cpp_create_definition): Call specific warning functions with warning reason where appropriate. * Makefile.in: Add new diagnostic functions to gettext translations. * include/cpplib.h (struct cpp_callbacks): Add warning reason code to error callback. (CPP_DL_WARNING, CPP_DL_WARNING_SYSHDR, CPP_DL_PEDWARN, CPP_DL_ERROR, CPP_DL_ICE, CPP_DL_NOTE, CPP_DL_FATAL): Replace macros with enums. (CPP_W_NONE, CPP_W_DEPRECATED, CPP_W_COMMENTS, CPP_W_MISSING_INCLUDE_DIRS, CPP_W_TRIGRAPHS, CPP_W_MULTICHAR, CPP_W_TRADITIONAL, CPP_W_LONG_LONG, CPP_W_ENDIF_LABELS, CPP_W_NUM_SIGN_CHANGE, CPP_W_VARIADIC_MACROS, CPP_W_BUILTIN_MACRO_REDEFINED, CPP_W_DOLLARS, CPP_W_UNDEF, CPP_W_UNUSED_MACROS, CPP_W_CXX_OPERATOR_NAMES, CPP_W_NORMALIZE, CPP_W_INVALID_PCH, CPP_W_WARNING_DIRECTIVE): New enums for cpp warning reason codes. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * pch.c (cpp_valid_state): Call specific warning functions with warning reason where appropriate. * errors.c (cpp_diagnostic, cpp_diagnostic_with_line): New central diagnostic handlers. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * expr.c (cpp_classify_number, eval_token, num_unary_op): Call specific warning functions with warning reason where appropriate. * lex.c (_cpp_process_line_notes, _cpp_skip_block_comment, warn_about_normalization, lex_identifier_intern, lex_identifier, _cpp_lex_direct): Ditto. * charset.c (_cpp_valid_ucn, convert_hex, convert_escape, narrow_str_to_charconst): Ditto. * gcc.dg/cpp/warn-undef-2.c: New. * gcc.dg/cpp/warn-traditional-2.c: New. * gcc.dg/cpp/warn-comments-2.c: New. * gcc.dg/cpp/warning-directive-1.c: New. * gcc.dg/cpp/warn-long-long.c: New. * gcc.dg/cpp/warn-traditional.c: New. * gcc.dg/cpp/warn-variadic-2.c: New. * gcc.dg/cpp/warn-undef.c: New. * gcc.dg/cpp/warn-normalized-1.c: New. * gcc.dg/cpp/warning-directive-2.c: New. * gcc.dg/cpp/warn-long-long-2.c: New. * gcc.dg/cpp/warn-variadic.c: New. * gcc.dg/cpp/warn-normalized-2.c: New. * gcc.dg/cpp/warning-directive-3.c: New. * gcc.dg/cpp/warn-deprecated-2.c: New. * gcc.dg/cpp/warn-trigraphs-1.c: New. * gcc.dg/cpp/warn-multichar-2.c: New. * gcc.dg/cpp/warn-normalized-3.c: New. * gcc.dg/cpp/warning-directive-4.c: New. * gcc.dg/cpp/warn-unused-macros.c: New. * gcc.dg/cpp/warn-trigraphs-2.c: New. * gcc.dg/cpp/warn-cxx-compat-2.c: New. * gcc.dg/cpp/warn-cxx-compat.c: New. * gcc.dg/cpp/warn-redefined.c: New. * gcc.dg/cpp/warn-trigraphs-3.c: New. * gcc.dg/cpp/warn-unused-macros-2.c: New. * gcc.dg/cpp/warn-deprecated.c: New. * gcc.dg/cpp/warn-trigraphs-4.c: New. * gcc.dg/cpp/warn-redefined-2.c: New. * gcc.dg/cpp/warn-comments.c: New. * gcc.dg/cpp/warn-multichar.c: New. * g++.dg/cpp/warning-directive-1.C: New. * g++.dg/cpp/warning-directive-2.C: New. * g++.dg/cpp/warning-directive-3.C: New. * g++.dg/cpp/warning-directive-4.C: New. * gfortran.dg/warning-directive-1.F90: New. * gfortran.dg/warning-directive-3.F90: New. * gfortran.dg/warning-directive-2.F90: New. * gfortran.dg/warning-directive-4.F90: New. From-SVN: r158079
2010-04-07 19:18:10 +02:00
cpp_warning (pfile, CPP_W_TRADITIONAL,
"the meaning of '\\%c' is different in traditional C",
(int) str[-1]);
if (str[-1] == 'u')
length = 4;
else if (str[-1] == 'U')
length = 8;
else
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
{
cpp_error (pfile, CPP_DL_ICE, "In _cpp_valid_ucn but not a UCN");
length = 4;
}
result = 0;
do
{
c = *str;
if (!ISXDIGIT (c))
break;
str++;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (loc_reader)
{
gcc_assert (char_range);
char_range->m_finish = loc_reader->get_next ().m_finish;
}
result = (result << 4) + hex_value (c);
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
while (--length && str < limit);
/* Partial UCNs are not valid in strings, but decompose into
multiple tokens in identifiers, so we can't give a helpful
error message in that case. */
if (length && identifier_pos)
{
*cp = 0;
return false;
}
*pstr = str;
if (length)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
cpp_error (pfile, CPP_DL_ERROR,
"incomplete universal character name %.*s",
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
(int) (str - base), base);
result = 1;
}
/* The C99 standard permits $, @ and ` to be specified as UCNs. We use
hex escapes so that this also works with EBCDIC hosts.
C++0x permits everything below 0xa0 within literals;
ucn_valid_in_identifier will complain about identifiers. */
else if ((result < 0xa0
&& !CPP_OPTION (pfile, cplusplus)
&& (result != 0x24 && result != 0x40 && result != 0x60))
|| (result & 0x80000000)
|| (result >= 0xD800 && result <= 0xDFFF))
{
cpp_error (pfile, CPP_DL_ERROR,
"%.*s is not a valid universal character",
(int) (str - base), base);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
result = 1;
}
else if (identifier_pos && result == 0x24
&& CPP_OPTION (pfile, dollars_in_ident))
{
if (CPP_OPTION (pfile, warn_dollars) && !pfile->state.skipping)
{
CPP_OPTION (pfile, warn_dollars) = 0;
cpp_error (pfile, CPP_DL_PEDWARN, "'$' in identifier or number");
}
ucnid-2011-1.c: New test. gcc/testsuite: * c-c++-common/cpp/ucnid-2011-1.c: New test. libcpp: * ucnid.tab: Add C11 and C11NOSTART data. * makeucnid.c (digit): Rename enum value to N99. (C11, N11, all_languages): New enum values. (NUM_CODE_POINTS, MAX_CODE_POINT): New macros. (flags, decomp, combining_value): Use NUM_CODE_POINTS as array size. (decomp): Use unsigned int as element type. (all_decomp): New array. (read_ucnid): Handle C11 and C11NOSTART. Use MAX_CODE_POINT. (read_table): Use MAX_CODE_POINT. Store all decompositions in all_decomp. (read_derived): Use MAX_CODE_POINT. (write_table): Use NUM_CODE_POINTS. Print N99, C11 and N11 flags. Print whole array variable declaration rather than just array contents. (char_id_valid, write_context_switch): New functions. (main): Call write_context_switch. * ucnid.h: Regenerate. * include/cpplib.h (struct cpp_options): Add c11_identifiers. * init.c (struct lang_flags): Add c11_identifiers. (cpp_set_lang): Set c11_identifiers option from selected language. * internal.h (struct normalize_state): Document "previous" as previous starter character. (NORMALIZE_STATE_UPDATE_IDNUM): Take character as argument. * charset.c (DIG): Rename enum value to N99. (C11, N11): New enum values. (struct ucnrange): Give name to struct. Use short for flags and unsigned int for end of range. Include ucnid.h for whole variable declaration. (ucn_valid_in_identifier): Allow for characters up to 0x10FFFF. Allow for C11 in determining valid characters and valid start characters. Use check_nfc for non-Hangul context-dependent checks. Only store starter characters in nst->previous. (_cpp_valid_ucn): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. * lex.c (lex_identifier): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. Call NORMALIZE_STATE_UPDATE_IDNUM after initial non-UCN part of identifier. (lex_number): Pass new argument to NORMALIZE_STATE_UPDATE_IDNUM. From-SVN: r204886
2013-11-16 01:05:08 +01:00
NORMALIZE_STATE_UPDATE_IDNUM (nst, result);
}
else if (identifier_pos)
{
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
int validity = ucn_valid_in_identifier (pfile, result, nst);
if (validity == 0)
cpp_error (pfile, CPP_DL_ERROR,
"universal character %.*s is not valid in an identifier",
(int) (str - base), base);
else if (validity == 2 && identifier_pos == 1)
cpp_error (pfile, CPP_DL_ERROR,
"universal character %.*s is not valid at the start of an identifier",
(int) (str - base), base);
}
else if (result > UCS_LIMIT
&& (!CPP_OPTION (pfile, cplusplus)
|| CPP_OPTION (pfile, lang) > CLK_CXX17))
cpp_error (pfile, CPP_DL_PEDWARN,
"%.*s is outside the UCS codespace",
(int) (str - base), base);
*cp = result;
return true;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Convert an UCN, pointed to by FROM, to UTF-8 encoding, then translate
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
it to the execution character set and write the result into TBUF,
if TBUF is non-NULL.
An advanced pointer is returned. Issues all relevant diagnostics.
If LOC_READER is non-NULL, then RANGES must be non-NULL and CHAR_RANGE
contains the location of the character so far: location information
is read from *LOC_READER, and *RANGES is updated accordingly. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static const uchar *
convert_ucn (cpp_reader *pfile, const uchar *from, const uchar *limit,
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
struct _cpp_strbuf *tbuf, struct cset_converter cvt,
source_range char_range,
cpp_string_location_reader *loc_reader,
cpp_substring_ranges *ranges)
{
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
cppchar_t ucn;
uchar buf[6];
uchar *bufp = buf;
size_t bytesleft = 6;
int rval;
Index: gcc/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * doc/cppopts.texi (-fexec-charset): Add concept index entry. (-fwide-exec-charset): Likewise. (-finput-charset): Likewise. * doc/invoke.texi (Warning Options): Document -Wnormalized=. * c-opts.c (c_common_handle_option): Handle -Wnormalized=. * c.opt (Wnormalized): New. Index: libcpp/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * init.c (cpp_create_reader): Default warn_normalize to normalized_C. * charset.c: Update for new format of ucnid.h. (ucn_valid_in_identifier): Update for new format of ucnid.h. Add NST parameter, and update it; update callers. (cpp_valid_ucn): Add NST parameter, update callers. Replace abort with cpp_error. (convert_ucn): Pass normalize_state to cpp_valid_ucn. * internal.h (struct normalize_state): New. (INITIAL_NORMALIZE_STATE): New. (NORMALIZE_STATE_RESULT): New. (NORMALIZE_STATE_UPDATE_IDNUM): New. (_cpp_valid_ucn): New. * lex.c (warn_about_normalization): New. (forms_identifier_p): Add normalize_state parameter, update callers. (lex_identifier): Add normalize_state parameter, update callers. Keep the state current. (lex_number): Likewise. (_cpp_lex_direct): Pass normalize_state to subroutines. Check it with warn_about_normalization. * makeucnid.c: New. * ucnid.h: Replace. * ucnid.pl: Remove. * ucnid.tab: Make appropriate for input to makeucnid.c. Remove comments about obsolete version of C++. * include/cpplib.h (enum cpp_normalize_level): New. (struct cpp_options): Add warn_normalize field. Index: gcc/testsuite/ChangeLog 2005-03-14 Geoffrey Keating <geoffk@apple.com> * gcc.dg/cpp/normalize-1.c: New. * gcc.dg/cpp/normalize-2.c: New. * gcc.dg/cpp/normalize-3.c: New. * gcc.dg/cpp/normalize-4.c: New. * gcc.dg/cpp/ucnid-4.c: New. * gcc.dg/cpp/ucnid-5.c: New. * g++.dg/cpp/normalize-1.C: New. * g++.dg/cpp/ucnid-1.C: New. From-SVN: r96459
2005-03-15 01:36:33 +01:00
struct normalize_state nst = INITIAL_NORMALIZE_STATE;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* loc_reader and ranges must either be both NULL, or both be non-NULL. */
gcc_assert ((loc_reader != NULL) == (ranges != NULL));
from++; /* Skip u/U. */
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (loc_reader)
/* The u/U is part of the spelling of this character. */
char_range.m_finish = loc_reader->get_next ().m_finish;
_cpp_valid_ucn (pfile, &from, limit, 0, &nst,
&ucn, &char_range, loc_reader);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
rval = one_cppchar_to_utf8 (ucn, &bufp, &bytesleft);
if (rval)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
errno = rval;
cpp_errno (pfile, CPP_DL_ERROR,
"converting UCN to source character set");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
else
{
if (tbuf)
if (!APPLY_CONVERSION (cvt, buf, 6 - bytesleft, tbuf))
cpp_errno (pfile, CPP_DL_ERROR,
"converting UCN to execution character set");
if (loc_reader)
{
int num_encoded_bytes = 6 - bytesleft;
for (int i = 0; i < num_encoded_bytes; i++)
ranges->add_range (char_range);
}
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return from;
}
Support extended characters in C/C++ identifiers (PR c/67224) libcpp/ChangeLog 2019-09-19 Lewis Hyatt <lhyatt@gmail.com> PR c/67224 * charset.c (_cpp_valid_utf8): New function to help lex UTF-8 tokens. * internal.h (_cpp_valid_utf8): Declare. * lex.c (forms_identifier_p): Use it to recognize UTF-8 identifiers. (_cpp_lex_direct): Handle UTF-8 in identifiers and CPP_OTHER tokens. Do all work in "default" case to avoid slowing down typical code paths. Also handle $ and UCN in the default case for consistency. gcc/Changelog 2019-09-19 Lewis Hyatt <lhyatt@gmail.com> PR c/67224 * doc/cpp.texi: Document support for extended characters in identifiers. * doc/cppopts.texi: Likewise. gcc/testsuite/ChangeLog 2019-09-19 Lewis Hyatt <lhyatt@gmail.com> PR c/67224 * c-c++-common/cpp/ucnid-2011-1-utf8.c: New test. * g++.dg/cpp/ucnid-1-utf8.C: New test. * g++.dg/cpp/ucnid-2-utf8.C: New test. * g++.dg/cpp/ucnid-3-utf8.C: New test. * g++.dg/cpp/ucnid-4-utf8.C: New test. * g++.dg/other/ucnid-1-utf8.C: New test. * gcc.dg/cpp/ucnid-1-utf8.c: New test. * gcc.dg/cpp/ucnid-10-utf8.c: New test. * gcc.dg/cpp/ucnid-11-utf8.c: New test. * gcc.dg/cpp/ucnid-12-utf8.c: New test. * gcc.dg/cpp/ucnid-13-utf8.c: New test. * gcc.dg/cpp/ucnid-14-utf8.c: New test. * gcc.dg/cpp/ucnid-15-utf8.c: New test. * gcc.dg/cpp/ucnid-2-utf8.c: New test. * gcc.dg/cpp/ucnid-3-utf8.c: New test. * gcc.dg/cpp/ucnid-4-utf8.c: New test. * gcc.dg/cpp/ucnid-6-utf8.c: New test. * gcc.dg/cpp/ucnid-7-utf8.c: New test. * gcc.dg/cpp/ucnid-9-utf8.c: New test. * gcc.dg/ucnid-1-utf8.c: New test. * gcc.dg/ucnid-10-utf8.c: New test. * gcc.dg/ucnid-11-utf8.c: New test. * gcc.dg/ucnid-12-utf8.c: New test. * gcc.dg/ucnid-13-utf8.c: New test. * gcc.dg/ucnid-14-utf8.c: New test. * gcc.dg/ucnid-15-utf8.c: New test. * gcc.dg/ucnid-16-utf8.c: New test. * gcc.dg/ucnid-2-utf8.c: New test. * gcc.dg/ucnid-3-utf8.c: New test. * gcc.dg/ucnid-4-utf8.c: New test. * gcc.dg/ucnid-5-utf8.c: New test. * gcc.dg/ucnid-6-utf8.c: New test. * gcc.dg/ucnid-7-utf8.c: New test. * gcc.dg/ucnid-8-utf8.c: New test. * gcc.dg/ucnid-9-utf8.c: New test. From-SVN: r275979
2019-09-19 21:56:11 +02:00
/* Performs a similar task as _cpp_valid_ucn, but parses UTF-8-encoded
extended characters rather than UCNs. If the return value is TRUE, then a
character was successfully decoded and stored in *CP; *PSTR has been
updated to point one past the valid UTF-8 sequence. Diagnostics may have
been emitted if the character parsed is not allowed in the current context.
If the return value is FALSE, then *PSTR has not been modified and *CP may
equal 0, to indicate that *PSTR does not form a valid UTF-8 sequence, or it
may, when processing an identifier in C mode, equal a codepoint that was
validly encoded but is not allowed to appear in an identifier. In either
case, no diagnostic is emitted, and the return value of FALSE should cause
a new token to be formed.
Unlike _cpp_valid_ucn, this will never be called when lexing a string; only
a potential identifier, or a CPP_OTHER token. NST is unused in the latter
case.
As in _cpp_valid_ucn, IDENTIFIER_POS is 0 when not in an identifier, 1 for
the start of an identifier, or 2 otherwise. */
extern bool
_cpp_valid_utf8 (cpp_reader *pfile,
const uchar **pstr,
const uchar *limit,
int identifier_pos,
struct normalize_state *nst,
cppchar_t *cp)
{
const uchar *base = *pstr;
size_t inbytesleft = limit - base;
if (one_utf8_to_cppchar (pstr, &inbytesleft, cp))
{
/* No diagnostic here as this byte will rather become a
new token. */
*cp = 0;
return false;
}
if (identifier_pos)
{
switch (ucn_valid_in_identifier (pfile, *cp, nst))
{
case 0:
/* In C++, this is an error for invalid character in an identifier
because logically, the UTF-8 was converted to a UCN during
translation phase 1 (even though we don't physically do it that
way). In C, this byte rather becomes grammatically a separate
token. */
if (CPP_OPTION (pfile, cplusplus))
cpp_error (pfile, CPP_DL_ERROR,
"extended character %.*s is not valid in an identifier",
(int) (*pstr - base), base);
else
{
*pstr = base;
return false;
}
break;
case 2:
if (identifier_pos == 1)
{
/* This is treated the same way in C++ or C99 -- lexed as an
identifier which is then invalid because an identifier is
not allowed to start with this character. */
cpp_error (pfile, CPP_DL_ERROR,
"extended character %.*s is not valid at the start of an identifier",
(int) (*pstr - base), base);
}
break;
}
}
return true;
}
/* Subroutine of convert_hex and convert_oct. N is the representation
in the execution character set of a numeric escape; write it into the
string buffer TBUF and update the end-of-string pointer therein. WIDE
is true if it's a wide string that's being assembled in TBUF. This
function issues no diagnostics and never fails. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static void
emit_numeric_escape (cpp_reader *pfile, cppchar_t n,
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
struct _cpp_strbuf *tbuf, struct cset_converter cvt)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
size_t width = cvt.width;
if (width != CPP_OPTION (pfile, char_precision))
{
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* We have to render this into the target byte order, which may not
be our byte order. */
bool bigend = CPP_OPTION (pfile, bytes_big_endian);
size_t cwidth = CPP_OPTION (pfile, char_precision);
size_t cmask = width_to_mask (cwidth);
size_t nbwc = width / cwidth;
size_t i;
size_t off = tbuf->len;
cppchar_t c;
if (tbuf->len + nbwc > tbuf->asize)
{
tbuf->asize += OUTBUF_BLOCK_SIZE;
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
tbuf->text = XRESIZEVEC (uchar, tbuf->text, tbuf->asize);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
for (i = 0; i < nbwc; i++)
{
c = n & cmask;
n >>= cwidth;
tbuf->text[off + (bigend ? nbwc - i - 1 : i)] = c;
}
tbuf->len += nbwc;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else
{
/* Note: this code does not handle the case where the target
and host have a different number of bits in a byte. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
if (tbuf->len + 1 > tbuf->asize)
{
tbuf->asize += OUTBUF_BLOCK_SIZE;
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
tbuf->text = XRESIZEVEC (uchar, tbuf->text, tbuf->asize);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
tbuf->text[tbuf->len++] = n;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Convert a hexadecimal escape, pointed to by FROM, to the execution
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
character set and write it into the string buffer TBUF (if non-NULL).
Returns an advanced pointer, and issues diagnostics as necessary.
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
No character set translation occurs; this routine always produces the
execution-set character with numeric value equal to the given hex
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
number. You can, e.g. generate surrogate pairs this way.
If LOC_READER is non-NULL, then RANGES must be non-NULL and CHAR_RANGE
contains the location of the character so far: location information
is read from *LOC_READER, and *RANGES is updated accordingly. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static const uchar *
convert_hex (cpp_reader *pfile, const uchar *from, const uchar *limit,
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
struct _cpp_strbuf *tbuf, struct cset_converter cvt,
source_range char_range,
cpp_string_location_reader *loc_reader,
cpp_substring_ranges *ranges)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
cppchar_t c, n = 0, overflow = 0;
int digits_found = 0;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
size_t width = cvt.width;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
size_t mask = width_to_mask (width);
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* loc_reader and ranges must either be both NULL, or both be non-NULL. */
gcc_assert ((loc_reader != NULL) == (ranges != NULL));
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
if (CPP_WTRADITIONAL (pfile))
diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * c-tree.h (c_cpp_error): Add warning reason argument. * opts.c (_warning_as_error_callback): New. (register_warning_as_error_callback): Store callback for warnings enabled via enable_warning_as_error. (enable_warning_as_error): Call callback, minor code tidy. * opts.h (register_warning_as_error_callback): Declare. * c-opts.c (warning_as_error_callback): New, set cpp_opts flag in response to -Werror=. (c_common_init_options): Register warning_as_error_callback in opts.c. * common.opt: Add -Wno-cpp option. * c-common.c (struct reason_option_codes_t): Map cpp warning reason codes to gcc option indexes. * (c_option_controlling_cpp_error): New function, lookup the gcc option index for a cpp warning reason code. * (c_cpp_error): Add warning reason argument, call c_option_controlling_cpp_error for diagnostic_override_option_index. * doc/invoke.texi: Document -Wno-cpp. * cpp.c (cb_cpp_error): Add warning reason argument, set a value for diagnostic_override_option_index if CPP_W_WARNING_DIRECTIVE. * directives.c (do_diagnostic): Add warning reason argument, call appropriate error reporting function for code. (directive_diagnostics): Call specific warning functions with warning reason where appropriate. (do_error, do_warning, do_pragma_dependency): Add warning reason argument to do_diagnostic calls. * macro.c (_cpp_warn_if_unused_macro, enter_macro_context, _cpp_create_definition): Call specific warning functions with warning reason where appropriate. * Makefile.in: Add new diagnostic functions to gettext translations. * include/cpplib.h (struct cpp_callbacks): Add warning reason code to error callback. (CPP_DL_WARNING, CPP_DL_WARNING_SYSHDR, CPP_DL_PEDWARN, CPP_DL_ERROR, CPP_DL_ICE, CPP_DL_NOTE, CPP_DL_FATAL): Replace macros with enums. (CPP_W_NONE, CPP_W_DEPRECATED, CPP_W_COMMENTS, CPP_W_MISSING_INCLUDE_DIRS, CPP_W_TRIGRAPHS, CPP_W_MULTICHAR, CPP_W_TRADITIONAL, CPP_W_LONG_LONG, CPP_W_ENDIF_LABELS, CPP_W_NUM_SIGN_CHANGE, CPP_W_VARIADIC_MACROS, CPP_W_BUILTIN_MACRO_REDEFINED, CPP_W_DOLLARS, CPP_W_UNDEF, CPP_W_UNUSED_MACROS, CPP_W_CXX_OPERATOR_NAMES, CPP_W_NORMALIZE, CPP_W_INVALID_PCH, CPP_W_WARNING_DIRECTIVE): New enums for cpp warning reason codes. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * pch.c (cpp_valid_state): Call specific warning functions with warning reason where appropriate. * errors.c (cpp_diagnostic, cpp_diagnostic_with_line): New central diagnostic handlers. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * expr.c (cpp_classify_number, eval_token, num_unary_op): Call specific warning functions with warning reason where appropriate. * lex.c (_cpp_process_line_notes, _cpp_skip_block_comment, warn_about_normalization, lex_identifier_intern, lex_identifier, _cpp_lex_direct): Ditto. * charset.c (_cpp_valid_ucn, convert_hex, convert_escape, narrow_str_to_charconst): Ditto. * gcc.dg/cpp/warn-undef-2.c: New. * gcc.dg/cpp/warn-traditional-2.c: New. * gcc.dg/cpp/warn-comments-2.c: New. * gcc.dg/cpp/warning-directive-1.c: New. * gcc.dg/cpp/warn-long-long.c: New. * gcc.dg/cpp/warn-traditional.c: New. * gcc.dg/cpp/warn-variadic-2.c: New. * gcc.dg/cpp/warn-undef.c: New. * gcc.dg/cpp/warn-normalized-1.c: New. * gcc.dg/cpp/warning-directive-2.c: New. * gcc.dg/cpp/warn-long-long-2.c: New. * gcc.dg/cpp/warn-variadic.c: New. * gcc.dg/cpp/warn-normalized-2.c: New. * gcc.dg/cpp/warning-directive-3.c: New. * gcc.dg/cpp/warn-deprecated-2.c: New. * gcc.dg/cpp/warn-trigraphs-1.c: New. * gcc.dg/cpp/warn-multichar-2.c: New. * gcc.dg/cpp/warn-normalized-3.c: New. * gcc.dg/cpp/warning-directive-4.c: New. * gcc.dg/cpp/warn-unused-macros.c: New. * gcc.dg/cpp/warn-trigraphs-2.c: New. * gcc.dg/cpp/warn-cxx-compat-2.c: New. * gcc.dg/cpp/warn-cxx-compat.c: New. * gcc.dg/cpp/warn-redefined.c: New. * gcc.dg/cpp/warn-trigraphs-3.c: New. * gcc.dg/cpp/warn-unused-macros-2.c: New. * gcc.dg/cpp/warn-deprecated.c: New. * gcc.dg/cpp/warn-trigraphs-4.c: New. * gcc.dg/cpp/warn-redefined-2.c: New. * gcc.dg/cpp/warn-comments.c: New. * gcc.dg/cpp/warn-multichar.c: New. * g++.dg/cpp/warning-directive-1.C: New. * g++.dg/cpp/warning-directive-2.C: New. * g++.dg/cpp/warning-directive-3.C: New. * g++.dg/cpp/warning-directive-4.C: New. * gfortran.dg/warning-directive-1.F90: New. * gfortran.dg/warning-directive-3.F90: New. * gfortran.dg/warning-directive-2.F90: New. * gfortran.dg/warning-directive-4.F90: New. From-SVN: r158079
2010-04-07 19:18:10 +02:00
cpp_warning (pfile, CPP_W_TRADITIONAL,
"the meaning of '\\x' is different in traditional C");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* Skip 'x'. */
from++;
/* The 'x' is part of the spelling of this character. */
if (loc_reader)
char_range.m_finish = loc_reader->get_next ().m_finish;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
while (from < limit)
{
c = *from;
if (! hex_p (c))
break;
from++;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (loc_reader)
char_range.m_finish = loc_reader->get_next ().m_finish;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
overflow |= n ^ (n << 4 >> 4);
n = (n << 4) + hex_value (c);
digits_found = 1;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
if (!digits_found)
{
cpp_error (pfile, CPP_DL_ERROR,
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
"\\x used with no following hex digits");
return from;
}
if (overflow | (n != (n & mask)))
{
cpp_error (pfile, CPP_DL_PEDWARN,
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
"hex escape sequence out of range");
n &= mask;
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (tbuf)
emit_numeric_escape (pfile, n, tbuf, cvt);
if (ranges)
ranges->add_range (char_range);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return from;
}
/* Convert an octal escape, pointed to by FROM, to the execution
character set and write it into the string buffer TBUF. Returns an
advanced pointer, and issues diagnostics as necessary.
No character set translation occurs; this routine always produces the
execution-set character with numeric value equal to the given octal
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
number.
If LOC_READER is non-NULL, then RANGES must be non-NULL and CHAR_RANGE
contains the location of the character so far: location information
is read from *LOC_READER, and *RANGES is updated accordingly. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static const uchar *
convert_oct (cpp_reader *pfile, const uchar *from, const uchar *limit,
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
struct _cpp_strbuf *tbuf, struct cset_converter cvt,
source_range char_range,
cpp_string_location_reader *loc_reader,
cpp_substring_ranges *ranges)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
size_t count = 0;
cppchar_t c, n = 0;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
size_t width = cvt.width;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
size_t mask = width_to_mask (width);
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* loc_reader and ranges must either be both NULL, or both be non-NULL. */
gcc_assert ((loc_reader != NULL) == (ranges != NULL));
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
while (from < limit && count++ < 3)
{
c = *from;
if (c < '0' || c > '7')
break;
from++;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (loc_reader)
char_range.m_finish = loc_reader->get_next ().m_finish;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
n = (n << 3) + c - '0';
}
if (n != (n & mask))
{
cpp_error (pfile, CPP_DL_PEDWARN,
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
"octal escape sequence out of range");
n &= mask;
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (tbuf)
emit_numeric_escape (pfile, n, tbuf, cvt);
if (ranges)
ranges->add_range (char_range);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return from;
}
/* Convert an escape sequence (pointed to by FROM) to its value on
the target, and to the execution character set. Do not scan past
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
LIMIT. Write the converted value into TBUF, if TBUF is non-NULL.
Returns an advanced pointer. Handles all relevant diagnostics.
If LOC_READER is non-NULL, then RANGES must be non-NULL: location
information is read from *LOC_READER, and *RANGES is updated
accordingly. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static const uchar *
convert_escape (cpp_reader *pfile, const uchar *from, const uchar *limit,
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
struct _cpp_strbuf *tbuf, struct cset_converter cvt,
cpp_string_location_reader *loc_reader,
cpp_substring_ranges *ranges)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
/* Values of \a \b \e \f \n \r \t \v respectively. */
#if HOST_CHARSET == HOST_CHARSET_ASCII
static const uchar charconsts[] = { 7, 8, 27, 12, 10, 13, 9, 11 };
#elif HOST_CHARSET == HOST_CHARSET_EBCDIC
static const uchar charconsts[] = { 47, 22, 39, 12, 21, 13, 5, 11 };
#else
#error "unknown host character set"
#endif
uchar c;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* Record the location of the backslash. */
source_range char_range;
if (loc_reader)
char_range = loc_reader->get_next ();
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
c = *from;
switch (c)
{
/* UCNs, hex escapes, and octal escapes are processed separately. */
case 'u': case 'U':
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
return convert_ucn (pfile, from, limit, tbuf, cvt,
char_range, loc_reader, ranges);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
case 'x':
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
return convert_hex (pfile, from, limit, tbuf, cvt,
char_range, loc_reader, ranges);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
case '0': case '1': case '2': case '3':
case '4': case '5': case '6': case '7':
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
return convert_oct (pfile, from, limit, tbuf, cvt,
char_range, loc_reader, ranges);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Various letter escapes. Get the appropriate host-charset
value into C. */
case '\\': case '\'': case '"': case '?': break;
case '(': case '{': case '[': case '%':
/* '\(', etc, can be used at the beginning of a line in a long
string split onto multiple lines with \-newline, to prevent
Emacs or other text editors from getting confused. '\%' can
be used to prevent SCCS from mangling printf format strings. */
if (CPP_PEDANTIC (pfile))
goto unknown;
break;
case 'b': c = charconsts[1]; break;
case 'f': c = charconsts[3]; break;
case 'n': c = charconsts[4]; break;
case 'r': c = charconsts[5]; break;
case 't': c = charconsts[6]; break;
case 'v': c = charconsts[7]; break;
case 'a':
if (CPP_WTRADITIONAL (pfile))
diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * c-tree.h (c_cpp_error): Add warning reason argument. * opts.c (_warning_as_error_callback): New. (register_warning_as_error_callback): Store callback for warnings enabled via enable_warning_as_error. (enable_warning_as_error): Call callback, minor code tidy. * opts.h (register_warning_as_error_callback): Declare. * c-opts.c (warning_as_error_callback): New, set cpp_opts flag in response to -Werror=. (c_common_init_options): Register warning_as_error_callback in opts.c. * common.opt: Add -Wno-cpp option. * c-common.c (struct reason_option_codes_t): Map cpp warning reason codes to gcc option indexes. * (c_option_controlling_cpp_error): New function, lookup the gcc option index for a cpp warning reason code. * (c_cpp_error): Add warning reason argument, call c_option_controlling_cpp_error for diagnostic_override_option_index. * doc/invoke.texi: Document -Wno-cpp. * cpp.c (cb_cpp_error): Add warning reason argument, set a value for diagnostic_override_option_index if CPP_W_WARNING_DIRECTIVE. * directives.c (do_diagnostic): Add warning reason argument, call appropriate error reporting function for code. (directive_diagnostics): Call specific warning functions with warning reason where appropriate. (do_error, do_warning, do_pragma_dependency): Add warning reason argument to do_diagnostic calls. * macro.c (_cpp_warn_if_unused_macro, enter_macro_context, _cpp_create_definition): Call specific warning functions with warning reason where appropriate. * Makefile.in: Add new diagnostic functions to gettext translations. * include/cpplib.h (struct cpp_callbacks): Add warning reason code to error callback. (CPP_DL_WARNING, CPP_DL_WARNING_SYSHDR, CPP_DL_PEDWARN, CPP_DL_ERROR, CPP_DL_ICE, CPP_DL_NOTE, CPP_DL_FATAL): Replace macros with enums. (CPP_W_NONE, CPP_W_DEPRECATED, CPP_W_COMMENTS, CPP_W_MISSING_INCLUDE_DIRS, CPP_W_TRIGRAPHS, CPP_W_MULTICHAR, CPP_W_TRADITIONAL, CPP_W_LONG_LONG, CPP_W_ENDIF_LABELS, CPP_W_NUM_SIGN_CHANGE, CPP_W_VARIADIC_MACROS, CPP_W_BUILTIN_MACRO_REDEFINED, CPP_W_DOLLARS, CPP_W_UNDEF, CPP_W_UNUSED_MACROS, CPP_W_CXX_OPERATOR_NAMES, CPP_W_NORMALIZE, CPP_W_INVALID_PCH, CPP_W_WARNING_DIRECTIVE): New enums for cpp warning reason codes. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * pch.c (cpp_valid_state): Call specific warning functions with warning reason where appropriate. * errors.c (cpp_diagnostic, cpp_diagnostic_with_line): New central diagnostic handlers. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * expr.c (cpp_classify_number, eval_token, num_unary_op): Call specific warning functions with warning reason where appropriate. * lex.c (_cpp_process_line_notes, _cpp_skip_block_comment, warn_about_normalization, lex_identifier_intern, lex_identifier, _cpp_lex_direct): Ditto. * charset.c (_cpp_valid_ucn, convert_hex, convert_escape, narrow_str_to_charconst): Ditto. * gcc.dg/cpp/warn-undef-2.c: New. * gcc.dg/cpp/warn-traditional-2.c: New. * gcc.dg/cpp/warn-comments-2.c: New. * gcc.dg/cpp/warning-directive-1.c: New. * gcc.dg/cpp/warn-long-long.c: New. * gcc.dg/cpp/warn-traditional.c: New. * gcc.dg/cpp/warn-variadic-2.c: New. * gcc.dg/cpp/warn-undef.c: New. * gcc.dg/cpp/warn-normalized-1.c: New. * gcc.dg/cpp/warning-directive-2.c: New. * gcc.dg/cpp/warn-long-long-2.c: New. * gcc.dg/cpp/warn-variadic.c: New. * gcc.dg/cpp/warn-normalized-2.c: New. * gcc.dg/cpp/warning-directive-3.c: New. * gcc.dg/cpp/warn-deprecated-2.c: New. * gcc.dg/cpp/warn-trigraphs-1.c: New. * gcc.dg/cpp/warn-multichar-2.c: New. * gcc.dg/cpp/warn-normalized-3.c: New. * gcc.dg/cpp/warning-directive-4.c: New. * gcc.dg/cpp/warn-unused-macros.c: New. * gcc.dg/cpp/warn-trigraphs-2.c: New. * gcc.dg/cpp/warn-cxx-compat-2.c: New. * gcc.dg/cpp/warn-cxx-compat.c: New. * gcc.dg/cpp/warn-redefined.c: New. * gcc.dg/cpp/warn-trigraphs-3.c: New. * gcc.dg/cpp/warn-unused-macros-2.c: New. * gcc.dg/cpp/warn-deprecated.c: New. * gcc.dg/cpp/warn-trigraphs-4.c: New. * gcc.dg/cpp/warn-redefined-2.c: New. * gcc.dg/cpp/warn-comments.c: New. * gcc.dg/cpp/warn-multichar.c: New. * g++.dg/cpp/warning-directive-1.C: New. * g++.dg/cpp/warning-directive-2.C: New. * g++.dg/cpp/warning-directive-3.C: New. * g++.dg/cpp/warning-directive-4.C: New. * gfortran.dg/warning-directive-1.F90: New. * gfortran.dg/warning-directive-3.F90: New. * gfortran.dg/warning-directive-2.F90: New. * gfortran.dg/warning-directive-4.F90: New. From-SVN: r158079
2010-04-07 19:18:10 +02:00
cpp_warning (pfile, CPP_W_TRADITIONAL,
"the meaning of '\\a' is different in traditional C");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
c = charconsts[0];
break;
case 'e': case 'E':
if (CPP_PEDANTIC (pfile))
cpp_error (pfile, CPP_DL_PEDWARN,
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
"non-ISO-standard escape sequence, '\\%c'", (int) c);
c = charconsts[2];
break;
default:
unknown:
if (ISGRAPH (c))
cpp_error (pfile, CPP_DL_PEDWARN,
"unknown escape sequence: '\\%c'", (int) c);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else
{
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
encoding_rich_location rich_loc (pfile);
Change references of .c files to .cc files ChangeLog: * MAINTAINERS: Rename .c names to .cc. contrib/ChangeLog: * filter-clang-warnings.py: Rename .c names to .cc. * gcc_update: Likewise. * paranoia.cc: Likewise. contrib/header-tools/ChangeLog: * README: Rename .c names to .cc. gcc/ChangeLog: * Makefile.in: Rename .c names to .cc. * alias.h: Likewise. * asan.cc: Likewise. * auto-profile.h: Likewise. * basic-block.h (struct basic_block_d): Likewise. * btfout.cc: Likewise. * builtins.cc (expand_builtin_longjmp): Likewise. (validate_arg): Likewise. (access_ref::offset_bounded): Likewise. * caller-save.cc (reg_restore_code): Likewise. (setup_save_areas): Likewise. * calls.cc (initialize_argument_information): Likewise. (expand_call): Likewise. (emit_library_call_value_1): Likewise. * cfg-flags.def (RTL): Likewise. (SIBCALL): Likewise. (CAN_FALLTHRU): Likewise. * cfganal.cc (post_order_compute): Likewise. * cfgcleanup.cc (try_simplify_condjump): Likewise. (merge_blocks_move_predecessor_nojumps): Likewise. (merge_blocks_move_successor_nojumps): Likewise. (merge_blocks_move): Likewise. (old_insns_match_p): Likewise. (try_crossjump_bb): Likewise. * cfgexpand.cc (expand_gimple_stmt): Likewise. * cfghooks.cc (split_block_before_cond_jump): Likewise. (profile_record_check_consistency): Likewise. * cfghooks.h: Likewise. * cfgrtl.cc (pass_free_cfg::execute): Likewise. (rtl_can_merge_blocks): Likewise. (try_redirect_by_replacing_jump): Likewise. (make_pass_outof_cfg_layout_mode): Likewise. (cfg_layout_can_merge_blocks_p): Likewise. * cgraph.cc (release_function_body): Likewise. (cgraph_node::get_fun): Likewise. * cgraph.h (struct cgraph_node): Likewise. (asmname_hasher::equal): Likewise. (cgraph_inline_failed_type): Likewise. (thunk_adjust): Likewise. (dump_callgraph_transformation): Likewise. (record_references_in_initializer): Likewise. (ipa_discover_variable_flags): Likewise. * cgraphclones.cc (GTY): Likewise. * cgraphunit.cc (symbol_table::finalize_compilation_unit): Likewise. * collect-utils.h (GCC_COLLECT_UTILS_H): Likewise. * collect2-aix.h (GCC_COLLECT2_AIX_H): Likewise. * collect2.cc (maybe_run_lto_and_relink): Likewise. * combine-stack-adj.cc: Likewise. * combine.cc (setup_incoming_promotions): Likewise. (combine_simplify_rtx): Likewise. (count_rtxs): Likewise. * common.opt: Likewise. * common/config/aarch64/aarch64-common.cc: Likewise. * common/config/arm/arm-common.cc (arm_asm_auto_mfpu): Likewise. * common/config/avr/avr-common.cc: Likewise. * common/config/i386/i386-isas.h (struct _isa_names_table): Likewise. * conditions.h: Likewise. * config.gcc: Likewise. * config/aarch64/aarch64-builtins.cc (aarch64_resolve_overloaded_memtag): Likewise. * config/aarch64/aarch64-protos.h (aarch64_classify_address): Likewise. (aarch64_get_extension_string_for_isa_flags): Likewise. * config/aarch64/aarch64-sve-builtins.cc (function_builder::add_function): Likewise. * config/aarch64/aarch64.cc (aarch64_regmode_natural_size): Likewise. (aarch64_sched_first_cycle_multipass_dfa_lookahead): Likewise. (aarch64_option_valid_attribute_p): Likewise. (aarch64_short_vector_p): Likewise. (aarch64_float_const_representable_p): Likewise. * config/aarch64/aarch64.h (DBX_REGISTER_NUMBER): Likewise. (ASM_OUTPUT_POOL_EPILOGUE): Likewise. (GTY): Likewise. * config/aarch64/cortex-a57-fma-steering.cc: Likewise. * config/aarch64/driver-aarch64.cc (contains_core_p): Likewise. * config/aarch64/t-aarch64: Likewise. * config/aarch64/x-aarch64: Likewise. * config/aarch64/x-darwin: Likewise. * config/alpha/alpha-protos.h: Likewise. * config/alpha/alpha.cc (alpha_scalar_mode_supported_p): Likewise. * config/alpha/alpha.h (LONG_DOUBLE_TYPE_SIZE): Likewise. (enum reg_class): Likewise. * config/alpha/alpha.md: Likewise. * config/alpha/driver-alpha.cc (AMASK_LOCKPFTCHOK): Likewise. * config/alpha/x-alpha: Likewise. * config/arc/arc-protos.h (arc_eh_uses): Likewise. * config/arc/arc.cc (ARC_OPT): Likewise. (arc_ccfsm_advance): Likewise. (arc_arg_partial_bytes): Likewise. (conditionalize_nonjump): Likewise. * config/arc/arc.md: Likewise. * config/arc/builtins.def: Likewise. * config/arc/t-arc: Likewise. * config/arm/arm-c.cc (arm_resolve_overloaded_builtin): Likewise. (arm_pragma_target_parse): Likewise. * config/arm/arm-protos.h (save_restore_target_globals): Likewise. (arm_cpu_cpp_builtins): Likewise. * config/arm/arm.cc (vfp3_const_double_index): Likewise. (shift_op): Likewise. (thumb2_final_prescan_insn): Likewise. (arm_final_prescan_insn): Likewise. (arm_asm_output_labelref): Likewise. (arm_small_register_classes_for_mode_p): Likewise. * config/arm/arm.h: Likewise. * config/arm/arm.md: Likewise. * config/arm/driver-arm.cc: Likewise. * config/arm/symbian.h: Likewise. * config/arm/t-arm: Likewise. * config/arm/thumb1.md: Likewise. * config/arm/x-arm: Likewise. * config/avr/avr-c.cc (avr_register_target_pragmas): Likewise. * config/avr/avr-fixed.md: Likewise. * config/avr/avr-log.cc (avr_log_vadump): Likewise. * config/avr/avr-mcus.def: Likewise. * config/avr/avr-modes.def (FRACTIONAL_INT_MODE): Likewise. * config/avr/avr-passes.def (INSERT_PASS_BEFORE): Likewise. * config/avr/avr-protos.h (make_avr_pass_casesi): Likewise. * config/avr/avr.cc (avr_option_override): Likewise. (avr_build_builtin_va_list): Likewise. (avr_mode_dependent_address_p): Likewise. (avr_function_arg_advance): Likewise. (avr_asm_output_aligned_decl_common): Likewise. * config/avr/avr.h (RETURN_ADDR_RTX): Likewise. (SUPPORTS_INIT_PRIORITY): Likewise. * config/avr/avr.md: Likewise. * config/avr/builtins.def: Likewise. * config/avr/gen-avr-mmcu-specs.cc (IN_GEN_AVR_MMCU_TEXI): Likewise. * config/avr/gen-avr-mmcu-texi.cc (IN_GEN_AVR_MMCU_TEXI): Likewise. (main): Likewise. * config/avr/t-avr: Likewise. * config/bfin/bfin.cc (frame_related_constant_load): Likewise. * config/bpf/bpf-protos.h (GCC_BPF_PROTOS_H): Likewise. * config/bpf/bpf.h (enum reg_class): Likewise. * config/bpf/t-bpf: Likewise. * config/c6x/c6x-protos.h (GCC_C6X_PROTOS_H): Likewise. * config/cr16/cr16-protos.h: Likewise. * config/cris/cris.cc (cris_address_cost): Likewise. (cris_side_effect_mode_ok): Likewise. (cris_init_machine_status): Likewise. (cris_emit_movem_store): Likewise. * config/cris/cris.h (INDEX_REG_CLASS): Likewise. (enum reg_class): Likewise. (struct cum_args): Likewise. * config/cris/cris.opt: Likewise. * config/cris/sync.md: Likewise. * config/csky/csky.cc (csky_expand_prologue): Likewise. * config/darwin-c.cc: Likewise. * config/darwin-f.cc: Likewise. * config/darwin-sections.def (zobj_const_section): Likewise. * config/darwin.cc (output_objc_section_asm_op): Likewise. (fprintf): Likewise. * config/darwin.h (GTY): Likewise. * config/elfos.h: Likewise. * config/epiphany/epiphany-sched.md: Likewise. * config/epiphany/epiphany.cc (epiphany_function_value): Likewise. * config/epiphany/epiphany.h (GTY): Likewise. (NO_FUNCTION_CSE): Likewise. * config/epiphany/mode-switch-use.cc: Likewise. * config/epiphany/predicates.md: Likewise. * config/epiphany/t-epiphany: Likewise. * config/fr30/fr30-protos.h: Likewise. * config/frv/frv-protos.h: Likewise. * config/frv/frv.cc (TLS_BIAS): Likewise. * config/frv/frv.h (ASM_OUTPUT_ALIGNED_LOCAL): Likewise. * config/ft32/ft32-protos.h: Likewise. * config/gcn/gcn-hsa.h (ASM_APP_OFF): Likewise. * config/gcn/gcn.cc (gcn_init_libfuncs): Likewise. * config/gcn/mkoffload.cc (copy_early_debug_info): Likewise. * config/gcn/t-gcn-hsa: Likewise. * config/gcn/t-omp-device: Likewise. * config/h8300/h8300-protos.h (GCC_H8300_PROTOS_H): Likewise. (same_cmp_following_p): Likewise. * config/h8300/h8300.cc (F): Likewise. * config/h8300/h8300.h (struct cum_arg): Likewise. (BRANCH_COST): Likewise. * config/i386/cygming.h (DEFAULT_PCC_STRUCT_RETURN): Likewise. * config/i386/djgpp.h (TARGET_ASM_LTO_END): Likewise. * config/i386/dragonfly.h (NO_PROFILE_COUNTERS): Likewise. * config/i386/driver-i386.cc (detect_caches_intel): Likewise. * config/i386/freebsd.h (NO_PROFILE_COUNTERS): Likewise. * config/i386/i386-c.cc (ix86_target_macros): Likewise. * config/i386/i386-expand.cc (get_mode_wider_vector): Likewise. * config/i386/i386-options.cc (ix86_set_func_type): Likewise. * config/i386/i386-protos.h (ix86_extract_perm_from_pool_constant): Likewise. (ix86_register_pragmas): Likewise. (ix86_d_has_stdcall_convention): Likewise. (i386_pe_seh_init_sections): Likewise. * config/i386/i386.cc (ix86_function_arg_regno_p): Likewise. (ix86_function_value_regno_p): Likewise. (ix86_compute_frame_layout): Likewise. (legitimize_pe_coff_symbol): Likewise. (output_pic_addr_const): Likewise. * config/i386/i386.h (defined): Likewise. (host_detect_local_cpu): Likewise. (CONSTANT_ADDRESS_P): Likewise. (DEFAULT_LARGE_SECTION_THRESHOLD): Likewise. (struct machine_frame_state): Likewise. * config/i386/i386.md: Likewise. * config/i386/lynx.h (ASM_OUTPUT_ALIGN): Likewise. * config/i386/mmx.md: Likewise. * config/i386/sse.md: Likewise. * config/i386/t-cygming: Likewise. * config/i386/t-djgpp: Likewise. * config/i386/t-gnu-property: Likewise. * config/i386/t-i386: Likewise. * config/i386/t-intelmic: Likewise. * config/i386/t-omp-device: Likewise. * config/i386/winnt-cxx.cc (i386_pe_type_dllimport_p): Likewise. (i386_pe_adjust_class_at_definition): Likewise. * config/i386/winnt.cc (gen_stdcall_or_fastcall_suffix): Likewise. (i386_pe_mangle_decl_assembler_name): Likewise. (i386_pe_encode_section_info): Likewise. * config/i386/x-cygwin: Likewise. * config/i386/x-darwin: Likewise. * config/i386/x-i386: Likewise. * config/i386/x-mingw32: Likewise. * config/i386/x86-tune-sched-core.cc: Likewise. * config/i386/x86-tune.def: Likewise. * config/i386/xm-djgpp.h (STANDARD_STARTFILE_PREFIX_1): Likewise. * config/ia64/freebsd.h: Likewise. * config/ia64/hpux.h (REGISTER_TARGET_PRAGMAS): Likewise. * config/ia64/ia64-protos.h (ia64_except_unwind_info): Likewise. * config/ia64/ia64.cc (ia64_function_value_regno_p): Likewise. (ia64_secondary_reload_class): Likewise. (bundling): Likewise. * config/ia64/ia64.h: Likewise. * config/ia64/ia64.md: Likewise. * config/ia64/predicates.md: Likewise. * config/ia64/sysv4.h: Likewise. * config/ia64/t-ia64: Likewise. * config/iq2000/iq2000.h (FUNCTION_MODE): Likewise. * config/iq2000/iq2000.md: Likewise. * config/linux.h (TARGET_HAS_BIONIC): Likewise. (if): Likewise. * config/m32c/m32c.cc (m32c_function_needs_enter): Likewise. * config/m32c/m32c.h (MAX_REGS_PER_ADDRESS): Likewise. * config/m32c/t-m32c: Likewise. * config/m32r/m32r-protos.h: Likewise. * config/m32r/m32r.cc (m32r_print_operand): Likewise. * config/m32r/m32r.h: Likewise. * config/m32r/m32r.md: Likewise. * config/m68k/m68k-isas.def: Likewise. * config/m68k/m68k-microarchs.def: Likewise. * config/m68k/m68k-protos.h (strict_low_part_peephole_ok): Likewise. (m68k_epilogue_uses): Likewise. * config/m68k/m68k.cc (m68k_call_tls_get_addr): Likewise. (m68k_sched_adjust_cost): Likewise. (m68k_sched_md_init): Likewise. * config/m68k/m68k.h (__transfer_from_trampoline): Likewise. (enum m68k_function_kind): Likewise. * config/m68k/m68k.md: Likewise. * config/m68k/m68kemb.h: Likewise. * config/m68k/uclinux.h (ENDFILE_SPEC): Likewise. * config/mcore/mcore-protos.h: Likewise. * config/mcore/mcore.cc (mcore_expand_insv): Likewise. (mcore_expand_prolog): Likewise. * config/mcore/mcore.h (TARGET_MCORE): Likewise. * config/mcore/mcore.md: Likewise. * config/microblaze/microblaze-protos.h: Likewise. * config/microblaze/microblaze.cc (microblaze_legitimate_pic_operand): Likewise. (microblaze_function_prologue): Likewise. (microblaze_function_epilogue): Likewise. (microblaze_select_section): Likewise. (microblaze_asm_output_mi_thunk): Likewise. (microblaze_eh_return): Likewise. * config/microblaze/microblaze.h: Likewise. * config/microblaze/microblaze.md: Likewise. * config/microblaze/t-microblaze: Likewise. * config/mips/driver-native.cc: Likewise. * config/mips/loongson2ef.md: Likewise. * config/mips/mips-protos.h (mips_expand_vec_cmp_expr): Likewise. * config/mips/mips.cc (mips_rtx_costs): Likewise. (mips_output_filename): Likewise. (mips_output_function_prologue): Likewise. (mips_output_function_epilogue): Likewise. (mips_output_mi_thunk): Likewise. * config/mips/mips.h: Likewise. * config/mips/mips.md: Likewise. * config/mips/t-mips: Likewise. * config/mips/x-native: Likewise. * config/mmix/mmix-protos.h: Likewise. * config/mmix/mmix.cc (mmix_option_override): Likewise. (mmix_dbx_register_number): Likewise. (mmix_expand_prologue): Likewise. * config/mmix/mmix.h: Likewise. * config/mmix/mmix.md: Likewise. * config/mmix/predicates.md: Likewise. * config/mn10300/mn10300.cc (mn10300_symbolic_operand): Likewise. (mn10300_legitimate_pic_operand_p): Likewise. * config/mn10300/mn10300.h (enum reg_class): Likewise. (NO_FUNCTION_CSE): Likewise. * config/moxie/moxie-protos.h: Likewise. * config/moxie/uclinux.h (TARGET_LIBC_HAS_FUNCTION): Likewise. * config/msp430/msp430-devices.cc (extract_devices_dir_from_exec_prefix): Likewise. * config/msp430/msp430.cc (msp430_gimplify_va_arg_expr): Likewise. (msp430_incoming_return_addr_rtx): Likewise. * config/msp430/msp430.h (msp430_get_linker_devices_include_path): Likewise. * config/msp430/t-msp430: Likewise. * config/nds32/nds32-cost.cc (nds32_rtx_costs_speed_prefer): Likewise. (nds32_rtx_costs_size_prefer): Likewise. (nds32_init_rtx_costs): Likewise. * config/nds32/nds32-doubleword.md: Likewise. * config/nds32/nds32.cc (nds32_memory_move_cost): Likewise. (nds32_builtin_decl): Likewise. * config/nds32/nds32.h (enum nds32_16bit_address_type): Likewise. (enum nds32_isr_nested_type): Likewise. (enum reg_class): Likewise. * config/nds32/predicates.md: Likewise. * config/nds32/t-nds32: Likewise. * config/nios2/nios2.cc (nios2_pragma_target_parse): Likewise. * config/nvptx/nvptx-protos.h: Likewise. * config/nvptx/nvptx.cc (nvptx_goacc_expand_var_decl): Likewise. * config/nvptx/nvptx.h (TARGET_CPU_CPP_BUILTINS): Likewise. * config/nvptx/t-nvptx: Likewise. * config/nvptx/t-omp-device: Likewise. * config/pa/elf.h: Likewise. * config/pa/pa-linux.h (GLOBAL_ASM_OP): Likewise. * config/pa/pa-netbsd.h (GLOBAL_ASM_OP): Likewise. * config/pa/pa-openbsd.h (TARGET_ASM_GLOBALIZE_LABEL): Likewise. * config/pa/pa-protos.h (pa_eh_return_handler_rtx): Likewise. (pa_legitimize_reload_address): Likewise. (pa_can_use_return_insn): Likewise. * config/pa/pa.cc (mem_shadd_or_shadd_rtx_p): Likewise. (som_output_text_section_asm_op): Likewise. * config/pa/pa.h (PROFILE_BEFORE_PROLOGUE): Likewise. * config/pa/pa.md: Likewise. * config/pa/som.h: Likewise. * config/pa/t-pa: Likewise. * config/pdp11/pdp11.cc (decode_pdp11_d): Likewise. * config/pdp11/pdp11.h: Likewise. * config/pdp11/pdp11.md: Likewise. * config/pdp11/t-pdp11: Likewise. * config/pru/pru.md: Likewise. * config/pru/t-pru: Likewise. * config/riscv/riscv-protos.h (NUM_SYMBOL_TYPES): Likewise. (riscv_gpr_save_operation_p): Likewise. (riscv_d_register_target_info): Likewise. (riscv_init_builtins): Likewise. * config/riscv/riscv.cc (riscv_output_mi_thunk): Likewise. * config/riscv/riscv.h (CSW_MAX_OFFSET): Likewise. * config/riscv/t-riscv: Likewise. * config/rl78/rl78.cc (rl78_asm_ctor_dtor): Likewise. * config/rl78/t-rl78: Likewise. * config/rs6000/aix.h: Likewise. * config/rs6000/aix71.h (ASM_SPEC_COMMON): Likewise. * config/rs6000/aix72.h (ASM_SPEC_COMMON): Likewise. * config/rs6000/aix73.h (ASM_SPEC_COMMON): Likewise. * config/rs6000/darwin.h (TARGET_ASM_GLOBALIZE_LABEL): Likewise. * config/rs6000/driver-rs6000.cc: Likewise. * config/rs6000/freebsd.h: Likewise. * config/rs6000/freebsd64.h: Likewise. * config/rs6000/lynx.h (ASM_OUTPUT_ALIGN): Likewise. * config/rs6000/rbtree.cc: Likewise. * config/rs6000/rbtree.h: Likewise. * config/rs6000/rs6000-c.cc (rs6000_target_modify_macros): Likewise. * config/rs6000/rs6000-call.cc (rs6000_invalid_builtin): Likewise. (rs6000_expand_builtin): Likewise. (rs6000_init_builtins): Likewise. * config/rs6000/rs6000-cpus.def: Likewise. * config/rs6000/rs6000-gen-builtins.cc (write_init_ovld_table): Likewise. * config/rs6000/rs6000-internal.h (ALTIVEC_REG_BIT): Likewise. (quad_address_offset_p): Likewise. * config/rs6000/rs6000-logue.cc (interesting_frame_related_regno): Likewise. (rs6000_emit_epilogue): Likewise. * config/rs6000/rs6000-overload.def: Likewise. * config/rs6000/rs6000-p8swap.cc: Likewise. * config/rs6000/rs6000-protos.h (GCC_RS6000_PROTOS_H): Likewise. (rs6000_const_f32_to_i32): Likewise. * config/rs6000/rs6000.cc (legitimate_lo_sum_address_p): Likewise. (rs6000_debug_legitimize_address): Likewise. (rs6000_mode_dependent_address): Likewise. (rs6000_adjust_priority): Likewise. (rs6000_c_mode_for_suffix): Likewise. * config/rs6000/rs6000.h (defined): Likewise. (LONG_DOUBLE_TYPE_SIZE): Likewise. * config/rs6000/rs6000.md: Likewise. * config/rs6000/sysv4.h: Likewise. * config/rs6000/t-linux: Likewise. * config/rs6000/t-linux64: Likewise. * config/rs6000/t-rs6000: Likewise. * config/rs6000/x-darwin: Likewise. * config/rs6000/x-darwin64: Likewise. * config/rs6000/x-rs6000: Likewise. * config/rs6000/xcoff.h (ASM_OUTPUT_LABELREF): Likewise. * config/rx/rx.cc (rx_expand_builtin): Likewise. * config/s390/constraints.md: Likewise. * config/s390/driver-native.cc: Likewise. * config/s390/htmxlintrin.h: Likewise. * config/s390/s390-builtins.def (B_DEF): Likewise. (OB_DEF_VAR): Likewise. * config/s390/s390-builtins.h: Likewise. * config/s390/s390-c.cc: Likewise. * config/s390/s390-opts.h: Likewise. * config/s390/s390-protos.h (s390_check_symref_alignment): Likewise. (s390_register_target_pragmas): Likewise. * config/s390/s390.cc (s390_init_builtins): Likewise. (s390_expand_plus_operand): Likewise. (s390_expand_atomic): Likewise. (s390_valid_target_attribute_inner_p): Likewise. * config/s390/s390.h (LONG_DOUBLE_TYPE_SIZE): Likewise. * config/s390/s390.md: Likewise. * config/s390/t-s390: Likewise. * config/s390/vx-builtins.md: Likewise. * config/s390/x-native: Likewise. * config/sh/divtab-sh4-300.cc (main): Likewise. * config/sh/divtab-sh4.cc (main): Likewise. * config/sh/divtab.cc (main): Likewise. * config/sh/elf.h: Likewise. * config/sh/sh-protos.h (sh_fsca_int2sf): Likewise. * config/sh/sh.cc (SYMBOL_FLAG_FUNCVEC_FUNCTION): Likewise. (sh_struct_value_rtx): Likewise. (sh_remove_reg_dead_or_unused_notes): Likewise. * config/sh/sh.h (MIN_UNITS_PER_WORD): Likewise. * config/sh/t-sh: Likewise. * config/sol2-protos.h (solaris_override_options): Likewise. * config/sol2.h: Likewise. * config/sparc/driver-sparc.cc: Likewise. * config/sparc/freebsd.h: Likewise. * config/sparc/sparc-protos.h (make_pass_work_around_errata): Likewise. * config/sparc/sparc.cc (sparc_output_mi_thunk): Likewise. (sparc_asan_shadow_offset): Likewise. * config/sparc/sparc.h: Likewise. * config/sparc/sparc.md: Likewise. * config/sparc/t-sparc: Likewise. * config/sparc/x-sparc: Likewise. * config/stormy16/stormy16.cc (xstormy16_mode_dependent_address_p): Likewise. * config/t-darwin: Likewise. * config/t-dragonfly: Likewise. * config/t-freebsd: Likewise. * config/t-glibc: Likewise. * config/t-linux: Likewise. * config/t-netbsd: Likewise. * config/t-openbsd: Likewise. * config/t-pnt16-warn: Likewise. * config/t-sol2: Likewise. * config/t-vxworks: Likewise. * config/t-winnt: Likewise. * config/tilegx/t-tilegx: Likewise. * config/tilegx/tilegx-c.cc: Likewise. * config/tilegx/tilegx-protos.h (tilegx_function_profiler): Likewise. * config/tilegx/tilegx.md: Likewise. * config/tilepro/t-tilepro: Likewise. * config/tilepro/tilepro-c.cc: Likewise. * config/v850/t-v850: Likewise. * config/v850/v850-protos.h: Likewise. * config/v850/v850.cc (F): Likewise. * config/v850/v850.h (enum reg_class): Likewise. (SLOW_BYTE_ACCESS): Likewise. * config/vax/vax.cc (vax_mode_dependent_address_p): Likewise. * config/vax/vax.h (enum reg_class): Likewise. * config/vax/vax.md: Likewise. * config/visium/visium.cc (visium_legitimate_address_p): Likewise. * config/visium/visium.h: Likewise. * config/vms/t-vms: Likewise. * config/vms/vms-crtlmap.map: Likewise. * config/vms/vms-protos.h (vms_c_get_vms_ver): Likewise. * config/vx-common.h: Likewise. * config/x-darwin: Likewise. * config/x-hpux: Likewise. * config/x-linux: Likewise. * config/x-netbsd: Likewise. * config/x-openbsd: Likewise. * config/x-solaris: Likewise. * config/xtensa/xtensa-protos.h (xtensa_mem_offset): Likewise. * config/xtensa/xtensa.cc (xtensa_option_override): Likewise. * config/xtensa/xtensa.h: Likewise. * configure.ac: Likewise. * context.cc: Likewise. * convert.h: Likewise. * coretypes.h: Likewise. * coverage.cc: Likewise. * coverage.h: Likewise. * cppdefault.h (struct default_include): Likewise. * cprop.cc (local_cprop_pass): Likewise. (one_cprop_pass): Likewise. * cse.cc (hash_rtx_cb): Likewise. (fold_rtx): Likewise. * ctfc.h (ctfc_get_num_vlen_bytes): Likewise. * data-streamer.h (bp_unpack_var_len_int): Likewise. (streamer_write_widest_int): Likewise. * dbgcnt.def: Likewise. * dbxout.cc (dbxout_early_global_decl): Likewise. (dbxout_common_check): Likewise. * dbxout.h: Likewise. * debug.h (struct gcc_debug_hooks): Likewise. (dump_go_spec_init): Likewise. * df-core.cc: Likewise. * df-scan.cc (df_insn_info_delete): Likewise. (df_insn_delete): Likewise. * df.h (debug_df_chain): Likewise. (can_move_insns_across): Likewise. * dfp.cc (decimal_from_binary): Likewise. * diagnostic-color.cc: Likewise. * diagnostic-event-id.h: Likewise. * diagnostic-show-locus.cc (test_one_liner_labels): Likewise. * diagnostic.cc (bt_callback): Likewise. (num_digits): Likewise. * doc/avr-mmcu.texi: Likewise. * doc/cfg.texi: Likewise. * doc/contrib.texi: Likewise. * doc/cppinternals.texi: Likewise. * doc/extend.texi: Likewise. * doc/generic.texi: Likewise. * doc/gimple.texi: Likewise. * doc/gty.texi: Likewise. * doc/invoke.texi: Likewise. * doc/loop.texi: Likewise. * doc/lto.texi: Likewise. * doc/match-and-simplify.texi: Likewise. * doc/md.texi: Likewise. * doc/optinfo.texi: Likewise. * doc/options.texi: Likewise. * doc/passes.texi: Likewise. * doc/plugins.texi: Likewise. * doc/rtl.texi: Likewise. * doc/sourcebuild.texi: Likewise. * doc/tm.texi: Likewise. * doc/tm.texi.in: Likewise. * doc/tree-ssa.texi: Likewise. * dojump.cc (do_jump): Likewise. * dojump.h: Likewise. * dumpfile.cc (test_impl_location): Likewise. (test_capture_of_dump_calls): Likewise. * dumpfile.h (enum dump_kind): Likewise. (class dump_location_t): Likewise. (dump_enabled_p): Likewise. (enable_rtl_dump_file): Likewise. (dump_combine_total_stats): Likewise. * dwarf2asm.cc (dw2_asm_output_delta_uleb128): Likewise. * dwarf2ctf.h (ctf_debug_finish): Likewise. * dwarf2out.cc (dwarf2out_begin_prologue): Likewise. (struct loc_descr_context): Likewise. (rtl_for_decl_location): Likewise. (gen_subprogram_die): Likewise. (gen_label_die): Likewise. (is_trivial_indirect_ref): Likewise. (dwarf2out_late_global_decl): Likewise. (dwarf_file_hasher::hash): Likewise. (dwarf2out_end_source_file): Likewise. (dwarf2out_define): Likewise. (dwarf2out_early_finish): Likewise. * dwarf2out.h (struct dw_fde_node): Likewise. (struct dw_discr_list_node): Likewise. (output_loc_sequence_raw): Likewise. * emit-rtl.cc (gen_raw_REG): Likewise. (maybe_set_max_label_num): Likewise. * emit-rtl.h (struct rtl_data): Likewise. * errors.cc (internal_error): Likewise. (trim_filename): Likewise. * et-forest.cc: Likewise. * except.cc (init_eh_for_function): Likewise. * explow.cc (promote_ssa_mode): Likewise. (get_dynamic_stack_size): Likewise. * explow.h: Likewise. * expmed.h: Likewise. * expr.cc (safe_from_p): Likewise. (expand_expr_real_2): Likewise. (expand_expr_real_1): Likewise. * file-prefix-map.cc (remap_filename): Likewise. * final.cc (app_enable): Likewise. (make_pass_compute_alignments): Likewise. (final_scan_insn_1): Likewise. (final_scan_insn): Likewise. * fixed-value.h (fixed_from_string): Likewise. * flag-types.h (NO_DEBUG): Likewise. (DWARF2_DEBUG): Likewise. (VMS_DEBUG): Likewise. (BTF_DEBUG): Likewise. (enum ctf_debug_info_levels): Likewise. * fold-const.cc (const_binop): Likewise. (fold_binary_loc): Likewise. (fold_checksum_tree): Likewise. * fp-test.cc: Likewise. * function.cc (expand_function_end): Likewise. * function.h (struct function): Likewise. * fwprop.cc (should_replace_address): Likewise. * gcc-main.cc: Likewise. * gcc-rich-location.h (class gcc_rich_location): Likewise. * gcc-symtab.h: Likewise. * gcc.cc (MIN_FATAL_STATUS): Likewise. (driver_handle_option): Likewise. (quote_spec_arg): Likewise. (driver::finalize): Likewise. * gcc.h (set_input): Likewise. * gcov-dump.cc: Likewise. * gcov.cc (solve_flow_graph): Likewise. * gcse-common.cc: Likewise. * gcse.cc (make_pass_rtl_hoist): Likewise. * genattr-common.cc: Likewise. * genattrtab.cc (min_fn): Likewise. (write_const_num_delay_slots): Likewise. * genautomata.cc: Likewise. * genconditions.cc (write_one_condition): Likewise. * genconstants.cc: Likewise. * genemit.cc (gen_exp): Likewise. * generic-match-head.cc: Likewise. * genextract.cc: Likewise. * gengenrtl.cc (always_void_p): Likewise. * gengtype-parse.cc (gtymarker_opt): Likewise. * gengtype-state.cc (state_writer::state_writer): Likewise. (write_state_trailer): Likewise. (equals_type_number): Likewise. (read_state): Likewise. * gengtype.cc (open_base_files): Likewise. (struct file_rule_st): Likewise. (header_dot_h_frul): Likewise. * gengtype.h: Likewise. * genmatch.cc (main): Likewise. * genmddeps.cc: Likewise. * genmodes.cc (emit_mode_inner): Likewise. (emit_mode_unit_size): Likewise. * genpeep.cc (gen_peephole): Likewise. * genpreds.cc (write_tm_preds_h): Likewise. * genrecog.cc (validate_pattern): Likewise. (write_header): Likewise. (main): Likewise. * gensupport.cc (change_subst_attribute): Likewise. (traverse_c_tests): Likewise. (add_predicate): Likewise. (init_predicate_table): Likewise. * gensupport.h (struct optab_pattern): Likewise. (get_num_insn_codes): Likewise. (maybe_eval_c_test): Likewise. (struct pred_data): Likewise. * ggc-internal.h: Likewise. * gimple-fold.cc (maybe_fold_reference): Likewise. (get_range_strlen_tree): Likewise. * gimple-fold.h (gimple_stmt_integer_valued_real_p): Likewise. * gimple-low.cc: Likewise. * gimple-match-head.cc (directly_supported_p): Likewise. * gimple-pretty-print.h: Likewise. * gimple-ssa-sprintf.cc (format_percent): Likewise. (adjust_range_for_overflow): Likewise. * gimple-streamer.h: Likewise. * gimple.h (struct GTY): Likewise. (is_gimple_resx): Likewise. * gimplify.cc (gimplify_expr): Likewise. (gimplify_init_constructor): Likewise. (omp_construct_selector_matches): Likewise. (gimplify_omp_target_update): Likewise. (gimplify_omp_ordered): Likewise. (gimplify_va_arg_expr): Likewise. * graphite-isl-ast-to-gimple.cc (should_copy_to_new_region): Likewise. * haifa-sched.cc (increase_insn_priority): Likewise. (try_ready): Likewise. (sched_create_recovery_edges): Likewise. * ifcvt.cc (find_if_case_1): Likewise. (find_if_case_2): Likewise. * inchash.h: Likewise. * incpath.cc (add_env_var_paths): Likewise. * input.cc (dump_location_info): Likewise. (assert_loceq): Likewise. (test_lexer_string_locations_concatenation_1): Likewise. (test_lexer_string_locations_concatenation_2): Likewise. (test_lexer_string_locations_concatenation_3): Likewise. * input.h (BUILTINS_LOCATION): Likewise. (class string_concat_db): Likewise. * internal-fn.cc (expand_MUL_OVERFLOW): Likewise. (expand_LOOP_VECTORIZED): Likewise. * ipa-cp.cc (make_pass_ipa_cp): Likewise. * ipa-fnsummary.cc (remap_freqcounting_preds_after_dup): Likewise. (ipa_fn_summary_t::duplicate): Likewise. (make_pass_ipa_fn_summary): Likewise. * ipa-fnsummary.h (enum ipa_hints_vals): Likewise. * ipa-free-lang-data.cc (fld_simplified_type): Likewise. (free_lang_data_in_decl): Likewise. * ipa-inline.cc (compute_inlined_call_time): Likewise. (inline_always_inline_functions): Likewise. * ipa-inline.h (free_growth_caches): Likewise. (inline_account_function_p): Likewise. * ipa-modref.cc (modref_access_analysis::analyze_stmt): Likewise. (modref_eaf_analysis::analyze_ssa_name): Likewise. * ipa-param-manipulation.cc (ipa_param_body_adjustments::mark_dead_statements): Likewise. (ipa_param_body_adjustments::remap_with_debug_expressions): Likewise. * ipa-prop.cc (ipa_set_node_agg_value_chain): Likewise. * ipa-prop.h (IPA_UNDESCRIBED_USE): Likewise. (unadjusted_ptr_and_unit_offset): Likewise. * ipa-reference.cc (make_pass_ipa_reference): Likewise. * ipa-reference.h (GCC_IPA_REFERENCE_H): Likewise. * ipa-split.cc (consider_split): Likewise. * ipa-sra.cc (isra_read_node_info): Likewise. * ipa-utils.h (struct ipa_dfs_info): Likewise. (recursive_call_p): Likewise. (ipa_make_function_pure): Likewise. * ira-build.cc (ira_create_allocno): Likewise. (ira_flattening): Likewise. * ira-color.cc (do_coloring): Likewise. (update_curr_costs): Likewise. * ira-conflicts.cc (process_regs_for_copy): Likewise. * ira-int.h (struct ira_emit_data): Likewise. (ira_prohibited_mode_move_regs): Likewise. (ira_get_dup_out_num): Likewise. (ira_destroy): Likewise. (ira_tune_allocno_costs): Likewise. (ira_implicitly_set_insn_hard_regs): Likewise. (ira_build_conflicts): Likewise. (ira_color): Likewise. * ira-lives.cc (process_bb_node_lives): Likewise. * ira.cc (class ira_spilled_reg_stack_slot): Likewise. (setup_uniform_class_p): Likewise. (def_dominates_uses): Likewise. * ira.h (ira_nullify_asm_goto): Likewise. * langhooks.cc (lhd_post_options): Likewise. * langhooks.h (class substring_loc): Likewise. (struct lang_hooks_for_tree_inlining): Likewise. (struct lang_hooks_for_types): Likewise. (struct lang_hooks): Likewise. * libfuncs.h (synchronize_libfunc): Likewise. * loop-doloop.cc (doloop_condition_get): Likewise. * loop-init.cc (fix_loop_structure): Likewise. * loop-invariant.cc: Likewise. * lower-subreg.h: Likewise. * lra-constraints.cc (curr_insn_transform): Likewise. * lra-int.h (struct lra_insn_reg): Likewise. (lra_undo_inheritance): Likewise. (lra_setup_reload_pseudo_preferenced_hard_reg): Likewise. (lra_split_hard_reg_for): Likewise. (lra_coalesce): Likewise. (lra_final_code_change): Likewise. * lra-spills.cc (lra_final_code_change): Likewise. * lra.cc (lra_process_new_insns): Likewise. * lto-compress.h (struct lto_compression_stream): Likewise. * lto-streamer-out.cc (DFS::DFS_write_tree_body): Likewise. (write_symbol): Likewise. * lto-streamer.h (enum LTO_tags): Likewise. (lto_value_range_error): Likewise. (lto_append_block): Likewise. (lto_streamer_hooks_init): Likewise. (stream_read_tree_ref): Likewise. (lto_prepare_function_for_streaming): Likewise. (select_what_to_stream): Likewise. (omp_lto_input_declare_variant_alt): Likewise. (cl_optimization_stream_in): Likewise. * lto-wrapper.cc (append_compiler_options): Likewise. * machmode.def: Likewise. * machmode.h (struct int_n_data_t): Likewise. * main.cc (main): Likewise. * match.pd: Likewise. * omp-builtins.def (BUILT_IN_GOMP_CRITICAL_NAME_END): Likewise. (BUILT_IN_GOMP_LOOP_ULL_ORDERED_RUNTIME_NEXT): Likewise. * omp-expand.cc (expand_omp_atomic_fetch_op): Likewise. (make_pass_expand_omp_ssa): Likewise. * omp-low.cc (struct omp_context): Likewise. (struct omp_taskcopy_context): Likewise. (lower_omp): Likewise. * omp-oacc-neuter-broadcast.cc (omp_sese_active_worker_call): Likewise. (mask_name): Likewise. (omp_sese_dump_pars): Likewise. (worker_single_simple): Likewise. * omp-offload.cc (omp_finish_file): Likewise. (execute_oacc_loop_designation): Likewise. * optabs-query.cc (lshift_cheap_p): Likewise. * optc-gen.awk: Likewise. * optc-save-gen.awk: Likewise. * optinfo-emit-json.cc (optrecord_json_writer::optrecord_json_writer): Likewise. * opts-common.cc: Likewise. * output.h (app_enable): Likewise. (output_operand_lossage): Likewise. (insn_current_reference_address): Likewise. (get_insn_template): Likewise. (output_quoted_string): Likewise. * pass_manager.h (struct register_pass_info): Likewise. * plugin.cc: Likewise. * plugin.def (PLUGIN_ANALYZER_INIT): Likewise. * plugin.h (invoke_plugin_callbacks): Likewise. * pointer-query.cc (handle_mem_ref): Likewise. * postreload-gcse.cc (alloc_mem): Likewise. * predict.h (enum prediction): Likewise. (add_reg_br_prob_note): Likewise. * prefix.h: Likewise. * profile.h (get_working_sets): Likewise. * read-md.cc: Likewise. * read-md.h (struct mapping): Likewise. (class md_reader): Likewise. (class noop_reader): Likewise. * read-rtl-function.cc (function_reader::create_function): Likewise. (function_reader::extra_parsing_for_operand_code_0): Likewise. * read-rtl.cc (initialize_iterators): Likewise. * real.cc: Likewise. * real.h (struct real_value): Likewise. (format_helper::format_helper): Likewise. (real_hash): Likewise. (real_can_shorten_arithmetic): Likewise. * recog.cc (struct target_recog): Likewise. (offsettable_nonstrict_memref_p): Likewise. (constrain_operands): Likewise. * recog.h (MAX_RECOG_ALTERNATIVES): Likewise. (which_op_alt): Likewise. (struct insn_gen_fn): Likewise. * reg-notes.def (REG_NOTE): Likewise. * reg-stack.cc: Likewise. * regs.h (reg_is_parm_p): Likewise. * regset.h: Likewise. * reload.cc (push_reload): Likewise. (find_reloads): Likewise. (find_reloads_address_1): Likewise. (find_replacement): Likewise. (refers_to_regno_for_reload_p): Likewise. (refers_to_mem_for_reload_p): Likewise. * reload.h (push_reload): Likewise. (deallocate_reload_reg): Likewise. * reload1.cc (emit_input_reload_insns): Likewise. * reorg.cc (relax_delay_slots): Likewise. * rtl.def (UNKNOWN): Likewise. (SEQUENCE): Likewise. (BARRIER): Likewise. (ASM_OPERANDS): Likewise. (EQ_ATTR_ALT): Likewise. * rtl.h (struct GTY): Likewise. (LABEL_NAME): Likewise. (LABEL_ALT_ENTRY_P): Likewise. (SUBREG_BYTE): Likewise. (get_stack_check_protect): Likewise. (dump_rtx_statistics): Likewise. (unwrap_const_vec_duplicate): Likewise. (subreg_promoted_mode): Likewise. (gen_lowpart_common): Likewise. (operand_subword): Likewise. (immed_wide_int_const): Likewise. (decide_function_section): Likewise. (active_insn_p): Likewise. (delete_related_insns): Likewise. (try_split): Likewise. (val_signbit_known_clear_p): Likewise. (simplifiable_subregs): Likewise. (set_insn_deleted): Likewise. (subreg_get_info): Likewise. (remove_free_EXPR_LIST_node): Likewise. (finish_subregs_of_mode): Likewise. (get_mem_attrs): Likewise. (lookup_constant_def): Likewise. (rtx_to_tree_code): Likewise. (hash_rtx): Likewise. (condjump_in_parallel_p): Likewise. (validate_subreg): Likewise. (make_compound_operation): Likewise. (schedule_ebbs): Likewise. (print_inline_rtx): Likewise. (fixup_args_size_notes): Likewise. (expand_dec): Likewise. (prepare_copy_insn): Likewise. (mark_elimination): Likewise. (valid_mode_changes_for_regno): Likewise. (make_debug_expr_from_rtl): Likewise. (delete_vta_debug_insns): Likewise. (simplify_using_condition): Likewise. (set_insn_locations): Likewise. (fatal_insn_not_found): Likewise. (word_register_operation_p): Likewise. * rtlanal.cc (get_call_fndecl): Likewise. (side_effects_p): Likewise. (subreg_nregs): Likewise. (rtx_cost): Likewise. (canonicalize_condition): Likewise. * rtlanal.h (rtx_properties::try_to_add_note): Likewise. * run-rtl-passes.cc (run_rtl_passes): Likewise. * sanitizer.def (BUILT_IN_ASAN_VERSION_MISMATCH_CHECK): Likewise. * sched-deps.cc (add_dependence_1): Likewise. * sched-ebb.cc (begin_move_insn): Likewise. (add_deps_for_risky_insns): Likewise. (advance_target_bb): Likewise. * sched-int.h (reemit_notes): Likewise. (struct _haifa_insn_data): Likewise. (HID): Likewise. (DEP_CANCELLED): Likewise. (debug_ds): Likewise. (number_in_ready): Likewise. (schedule_ebbs_finish): Likewise. (find_modifiable_mems): Likewise. * sched-rgn.cc (debug_rgn_dependencies): Likewise. * sel-sched-dump.cc (dump_lv_set): Likewise. * sel-sched-dump.h: Likewise. * sel-sched-ir.cc (sel_insn_rtx_cost): Likewise. (setup_id_reg_sets): Likewise. (has_dependence_p): Likewise. (sel_num_cfg_preds_gt_1): Likewise. (bb_ends_ebb_p): Likewise. * sel-sched-ir.h (struct _list_node): Likewise. (struct idata_def): Likewise. (bb_next_bb): Likewise. * sel-sched.cc (vinsn_writes_one_of_regs_p): Likewise. (choose_best_pseudo_reg): Likewise. (verify_target_availability): Likewise. (can_speculate_dep_p): Likewise. (sel_rank_for_schedule): Likewise. * selftest-run-tests.cc (selftest::run_tests): Likewise. * selftest.h (class auto_fix_quotes): Likewise. * shrink-wrap.cc (handle_simple_exit): Likewise. * shrink-wrap.h: Likewise. * simplify-rtx.cc (simplify_context::simplify_associative_operation): Likewise. (simplify_context::simplify_gen_vec_select): Likewise. * spellcheck-tree.h: Likewise. * spellcheck.h: Likewise. * statistics.h (struct function): Likewise. * stmt.cc (conditional_probability): Likewise. * stmt.h: Likewise. * stor-layout.h: Likewise. * streamer-hooks.h: Likewise. * stringpool.h: Likewise. * symtab.cc (symbol_table::change_decl_assembler_name): Likewise. * target.def (HOOK_VECTOR_END): Likewise. (type.): Likewise. * target.h (union cumulative_args_t): Likewise. (by_pieces_ninsns): Likewise. (class predefined_function_abi): Likewise. * targhooks.cc (default_translate_mode_attribute): Likewise. * timevar.def: Likewise. * timevar.h (class timer): Likewise. * toplev.h (enable_rtl_dump_file): Likewise. * trans-mem.cc (collect_bb2reg): Likewise. * tree-call-cdce.cc (gen_conditions_for_pow): Likewise. * tree-cfg.cc (remove_bb): Likewise. (verify_gimple_debug): Likewise. (remove_edge_and_dominated_blocks): Likewise. (push_fndecl): Likewise. * tree-cfgcleanup.h (GCC_TREE_CFGCLEANUP_H): Likewise. * tree-complex.cc (expand_complex_multiplication): Likewise. (expand_complex_div_straight): Likewise. * tree-core.h (enum tree_index): Likewise. (enum operand_equal_flag): Likewise. * tree-eh.cc (honor_protect_cleanup_actions): Likewise. * tree-if-conv.cc (if_convertible_gimple_assign_stmt_p): Likewise. * tree-inline.cc (initialize_inlined_parameters): Likewise. * tree-inline.h (force_value_to_type): Likewise. * tree-nested.cc (get_chain_decl): Likewise. (walk_all_functions): Likewise. * tree-object-size.h: Likewise. * tree-outof-ssa.cc: Likewise. * tree-parloops.cc (create_parallel_loop): Likewise. * tree-pretty-print.cc (print_generic_expr_to_str): Likewise. (dump_generic_node): Likewise. * tree-profile.cc (tree_profiling): Likewise. * tree-sra.cc (maybe_add_sra_candidate): Likewise. * tree-ssa-address.cc: Likewise. * tree-ssa-alias.cc: Likewise. * tree-ssa-alias.h (ao_ref::max_size_known_p): Likewise. (dump_alias_stats): Likewise. * tree-ssa-ccp.cc: Likewise. * tree-ssa-coalesce.h: Likewise. * tree-ssa-live.cc (remove_unused_scope_block_p): Likewise. * tree-ssa-loop-manip.cc (copy_phi_node_args): Likewise. * tree-ssa-loop-unswitch.cc: Likewise. * tree-ssa-math-opts.cc: Likewise. * tree-ssa-operands.cc (class operands_scanner): Likewise. * tree-ssa-pre.cc: Likewise. * tree-ssa-reassoc.cc (optimize_ops_list): Likewise. (debug_range_entry): Likewise. * tree-ssa-sccvn.cc (eliminate_dom_walker::eliminate_stmt): Likewise. * tree-ssa-sccvn.h (TREE_SSA_SCCVN_H): Likewise. * tree-ssa-scopedtables.cc (add_expr_commutative): Likewise. (equal_mem_array_ref_p): Likewise. * tree-ssa-strlen.cc (is_strlen_related_p): Likewise. * tree-ssa-strlen.h (get_range_strlen_dynamic): Likewise. * tree-ssa-tail-merge.cc (stmt_local_def): Likewise. * tree-ssa-ter.h: Likewise. * tree-ssa-threadupdate.h (enum bb_dom_status): Likewise. * tree-streamer-in.cc (lto_input_ts_block_tree_pointers): Likewise. * tree-streamer-out.cc (pack_ts_block_value_fields): Likewise. (write_ts_block_tree_pointers): Likewise. * tree-streamer.h (struct streamer_tree_cache_d): Likewise. (streamer_read_tree_bitfields): Likewise. (streamer_write_integer_cst): Likewise. * tree-vect-patterns.cc (apply_binop_and_append_stmt): Likewise. (vect_synth_mult_by_constant): Likewise. * tree-vect-stmts.cc (vectorizable_operation): Likewise. * tree-vectorizer.cc: Likewise. * tree-vectorizer.h (class auto_purge_vect_location): Likewise. (vect_update_inits_of_drs): Likewise. (vect_get_mask_type_for_stmt): Likewise. (vect_rgroup_iv_might_wrap_p): Likewise. (cse_and_gimplify_to_preheader): Likewise. (vect_free_slp_tree): Likewise. (vect_pattern_recog): Likewise. (vect_stmt_dominates_stmt_p): Likewise. * tree.cc (initialize_tree_contains_struct): Likewise. (need_assembler_name_p): Likewise. (type_with_interoperable_signedness): Likewise. * tree.def (SWITCH_EXPR): Likewise. * tree.h (TYPE_SYMTAB_ADDRESS): Likewise. (poly_int_tree_p): Likewise. (inlined_function_outer_scope_p): Likewise. (tree_code_for_canonical_type_merging): Likewise. * value-prof.cc: Likewise. * value-prof.h (get_nth_most_common_value): Likewise. (find_func_by_profile_id): Likewise. * value-range.cc (vrp_operand_equal_p): Likewise. * value-range.h: Likewise. * var-tracking.cc: Likewise. * varasm.cc (default_function_section): Likewise. (function_section_1): Likewise. (assemble_variable): Likewise. (handle_vtv_comdat_section): Likewise. * vec.h (struct vec_prefix): Likewise. * vmsdbgout.cc (full_name): Likewise. * vtable-verify.cc: Likewise. * vtable-verify.h (struct vtv_graph_node): Likewise. * xcoffout.cc: Likewise. * xcoffout.h (DEBUG_SYMS_TEXT): Likewise. gcc/ada/ChangeLog: * Make-generated.in: Rename .c names to .cc. * adaint.c: Likewise. * ctrl_c.c (dummy_handler): Likewise. * gcc-interface/Makefile.in: Likewise. * gcc-interface/config-lang.in: Likewise. * gcc-interface/decl.cc (concat_name): Likewise. (init_gnat_decl): Likewise. * gcc-interface/gigi.h (concat_name): Likewise. (init_gnat_utils): Likewise. (build_call_raise_range): Likewise. (gnat_mark_addressable): Likewise. (gnat_protect_expr): Likewise. (gnat_rewrite_reference): Likewise. * gcc-interface/lang-specs.h (ADA_DUMPS_OPTIONS): Likewise. * gcc-interface/utils.cc (GTY): Likewise. (add_deferred_type_context): Likewise. (init_gnat_utils): Likewise. * gcc-interface/utils2.cc (gnat_stable_expr_p): Likewise. (gnat_protect_expr): Likewise. (gnat_stabilize_reference_1): Likewise. (gnat_rewrite_reference): Likewise. * gsocket.h: Likewise. * init.cc (__gnat_error_handler): Likewise. * libgnarl/s-intman.ads: Likewise. * libgnarl/s-osinte__android.ads: Likewise. * libgnarl/s-osinte__darwin.ads: Likewise. * libgnarl/s-osinte__hpux.ads: Likewise. * libgnarl/s-osinte__linux.ads: Likewise. * libgnarl/s-osinte__qnx.ads: Likewise. * libgnarl/s-taskin.ads: Likewise. * rtfinal.cc: Likewise. * s-oscons-tmplt.c (CND): Likewise. * set_targ.ads: Likewise. gcc/analyzer/ChangeLog: * analyzer.cc (is_special_named_call_p): Rename .c names to .cc. (is_named_call_p): Likewise. * region-model-asm.cc (deterministic_p): Likewise. * region.cc (field_region::get_relative_concrete_offset): Likewise. * sm-malloc.cc (method_p): Likewise. * supergraph.cc (superedge::dump_dot): Likewise. gcc/c-family/ChangeLog: * c-ada-spec.cc: Rename .c names to .cc. * c-ada-spec.h: Likewise. * c-common.cc (c_build_vec_convert): Likewise. (warning_candidate_p): Likewise. * c-common.h (enum rid): Likewise. (build_real_imag_expr): Likewise. (finish_label_address_expr): Likewise. (c_get_substring_location): Likewise. (c_build_bind_expr): Likewise. (conflict_marker_get_final_tok_kind): Likewise. (c_parse_error): Likewise. (check_missing_format_attribute): Likewise. (invalid_array_size_error): Likewise. (warn_for_multistatement_macros): Likewise. (build_attr_access_from_parms): Likewise. * c-cppbuiltin.cc (c_cpp_builtins): Likewise. * c-format.cc: Likewise. * c-gimplify.cc (c_gimplify_expr): Likewise. * c-indentation.h: Likewise. * c-objc.h (objc_prop_attr_kind_for_rid): Likewise. * c-omp.cc (c_omp_predetermined_mapping): Likewise. * c-opts.cc (c_common_post_options): Likewise. (set_std_cxx23): Likewise. * c-pragma.cc (handle_pragma_redefine_extname): Likewise. * c-pretty-print.h: Likewise. gcc/c/ChangeLog: * Make-lang.in: Rename .c names to .cc. * c-convert.cc: Likewise. * c-decl.cc (struct lang_identifier): Likewise. (pop_scope): Likewise. (finish_decl): Likewise. * c-objc-common.h (GCC_C_OBJC_COMMON): Likewise. * c-parser.cc (c_parser_skip_to_end_of_block_or_statement): Likewise. * c-parser.h (GCC_C_PARSER_H): Likewise. * c-tree.h (c_keyword_starts_typename): Likewise. (finish_declspecs): Likewise. (c_get_alias_set): Likewise. (enum c_oracle_request): Likewise. (tag_exists_p): Likewise. (set_c_expr_source_range): Likewise. * c-typeck.cc (c_common_type): Likewise. (c_finish_omp_clauses): Likewise. * config-lang.in: Likewise. gcc/cp/ChangeLog: * Make-lang.in: Rename .c names to .cc. * config-lang.in: Likewise. * constexpr.cc (cxx_eval_constant_expression): Likewise. * coroutines.cc (morph_fn_to_coro): Likewise. * cp-gimplify.cc (cp_gimplify_expr): Likewise. * cp-lang.cc (struct lang_hooks): Likewise. (get_template_argument_pack_elems_folded): Likewise. * cp-objcp-common.cc (cp_tree_size): Likewise. (cp_unit_size_without_reusable_padding): Likewise. (pop_file_scope): Likewise. (cp_pushdecl): Likewise. * cp-objcp-common.h (GCC_CP_OBJCP_COMMON): Likewise. (cxx_simulate_record_decl): Likewise. * cp-tree.h (struct named_label_entry): Likewise. (current_function_return_value): Likewise. (more_aggr_init_expr_args_p): Likewise. (get_function_version_dispatcher): Likewise. (common_enclosing_class): Likewise. (strip_fnptr_conv): Likewise. (current_decl_namespace): Likewise. (do_aggregate_paren_init): Likewise. (cp_check_const_attributes): Likewise. (qualified_name_lookup_error): Likewise. (generic_targs_for): Likewise. (mark_exp_read): Likewise. (is_global_friend): Likewise. (maybe_reject_flexarray_init): Likewise. (module_token_lang): Likewise. (handle_module_option): Likewise. (literal_integer_zerop): Likewise. (build_extra_args): Likewise. (build_if_nonnull): Likewise. (maybe_check_overriding_exception_spec): Likewise. (finish_omp_target_clauses): Likewise. (maybe_warn_zero_as_null_pointer_constant): Likewise. (cxx_print_error_function): Likewise. (decl_in_std_namespace_p): Likewise. (merge_exception_specifiers): Likewise. (mangle_module_global_init): Likewise. (cxx_block_may_fallthru): Likewise. (fold_builtin_source_location): Likewise. (enum cp_oracle_request): Likewise. (subsumes): Likewise. (cp_finish_injected_record_type): Likewise. (vtv_build_vtable_verify_fndecl): Likewise. (cp_tree_c_finish_parsing): Likewise. * cvt.cc (diagnose_ref_binding): Likewise. (convert_to_void): Likewise. (convert_force): Likewise. (type_promotes_to): Likewise. * decl.cc (make_unbound_class_template_raw): Likewise. (cxx_init_decl_processing): Likewise. (check_class_member_definition_namespace): Likewise. (cxx_maybe_build_cleanup): Likewise. * decl2.cc (maybe_emit_vtables): Likewise. * error.cc (dump_function_name): Likewise. * init.cc (is_class_type): Likewise. (build_new_1): Likewise. * lang-specs.h: Likewise. * method.cc (make_alias_for_thunk): Likewise. * module.cc (specialization_add): Likewise. (module_state::read_cluster): Likewise. * name-lookup.cc (check_extern_c_conflict): Likewise. * name-lookup.h (struct cxx_binding): Likewise. * parser.cc (cp_parser_identifier): Likewise. * parser.h (struct cp_parser): Likewise. * pt.cc (has_value_dependent_address): Likewise. (push_tinst_level_loc): Likewise. * semantics.cc (finish_omp_clauses): Likewise. (finish_omp_atomic): Likewise. * tree.cc (cp_save_expr): Likewise. (cp_free_lang_data): Likewise. * typeck.cc (cp_common_type): Likewise. (strip_array_domain): Likewise. (rationalize_conditional_expr): Likewise. (check_return_expr): Likewise. * vtable-class-hierarchy.cc: Likewise. gcc/d/ChangeLog: * d-gimplify.cc: Rename .c names to .cc. * d-incpath.cc: Likewise. * lang-specs.h: Likewise. gcc/fortran/ChangeLog: * check.cc (gfc_check_all_any): Rename .c names to .cc. * class.cc (find_intrinsic_vtab): Likewise. * config-lang.in: Likewise. * cpp.cc (cpp_define_builtins): Likewise. * data.cc (get_array_index): Likewise. * decl.cc (match_clist_expr): Likewise. (get_proc_name): Likewise. (gfc_verify_c_interop_param): Likewise. (gfc_get_pdt_instance): Likewise. (gfc_match_formal_arglist): Likewise. (gfc_get_type_attr_spec): Likewise. * dependency.cc: Likewise. * error.cc (gfc_format_decoder): Likewise. * expr.cc (check_restricted): Likewise. (gfc_build_default_init_expr): Likewise. * f95-lang.cc: Likewise. * gfc-internals.texi: Likewise. * gfortran.h (enum match): Likewise. (enum procedure_type): Likewise. (enum oacc_routine_lop): Likewise. (gfc_get_pdt_instance): Likewise. (gfc_end_source_files): Likewise. (gfc_mpz_set_hwi): Likewise. (gfc_get_option_string): Likewise. (gfc_find_sym_in_expr): Likewise. (gfc_errors_to_warnings): Likewise. (gfc_real_4_kind): Likewise. (gfc_free_finalizer): Likewise. (gfc_sym_get_dummy_args): Likewise. (gfc_check_intrinsic_standard): Likewise. (gfc_free_case_list): Likewise. (gfc_resolve_oacc_routines): Likewise. (gfc_check_vardef_context): Likewise. (gfc_free_association_list): Likewise. (gfc_implicit_pure_function): Likewise. (gfc_ref_dimen_size): Likewise. (gfc_compare_actual_formal): Likewise. (gfc_resolve_wait): Likewise. (gfc_dt_upper_string): Likewise. (gfc_generate_module_code): Likewise. (gfc_delete_bbt): Likewise. (debug): Likewise. (gfc_build_block_ns): Likewise. (gfc_dep_difference): Likewise. (gfc_invalid_null_arg): Likewise. (gfc_is_finalizable): Likewise. (gfc_fix_implicit_pure): Likewise. (gfc_is_size_zero_array): Likewise. (gfc_is_reallocatable_lhs): Likewise. * gfortranspec.cc: Likewise. * interface.cc (compare_actual_expr): Likewise. * intrinsic.cc (add_functions): Likewise. * iresolve.cc (gfc_resolve_matmul): Likewise. (gfc_resolve_alarm_sub): Likewise. * iso-c-binding.def: Likewise. * lang-specs.h: Likewise. * libgfortran.h (GFC_STDERR_UNIT_NUMBER): Likewise. * match.cc (gfc_match_label): Likewise. (gfc_match_symbol): Likewise. (match_derived_type_spec): Likewise. (copy_ts_from_selector_to_associate): Likewise. * match.h (gfc_match_call): Likewise. (gfc_get_common): Likewise. (gfc_match_omp_end_single): Likewise. (gfc_match_volatile): Likewise. (gfc_match_bind_c): Likewise. (gfc_match_literal_constant): Likewise. (gfc_match_init_expr): Likewise. (gfc_match_array_constructor): Likewise. (gfc_match_end_interface): Likewise. (gfc_match_print): Likewise. (gfc_match_expr): Likewise. * matchexp.cc (next_operator): Likewise. * mathbuiltins.def: Likewise. * module.cc (free_true_name): Likewise. * openmp.cc (gfc_resolve_omp_parallel_blocks): Likewise. (gfc_omp_save_and_clear_state): Likewise. * parse.cc (parse_union): Likewise. (set_syms_host_assoc): Likewise. * resolve.cc (resolve_actual_arglist): Likewise. (resolve_elemental_actual): Likewise. (check_host_association): Likewise. (resolve_typebound_function): Likewise. (resolve_typebound_subroutine): Likewise. (gfc_resolve_expr): Likewise. (resolve_assoc_var): Likewise. (resolve_typebound_procedures): Likewise. (resolve_equivalence_derived): Likewise. * simplify.cc (simplify_bound): Likewise. * symbol.cc (gfc_set_default_type): Likewise. (gfc_add_ext_attribute): Likewise. * target-memory.cc (gfc_target_interpret_expr): Likewise. * target-memory.h (gfc_target_interpret_expr): Likewise. * trans-array.cc (gfc_get_cfi_dim_sm): Likewise. (gfc_conv_shift_descriptor_lbound): Likewise. (gfc_could_be_alias): Likewise. (gfc_get_dataptr_offset): Likewise. * trans-const.cc: Likewise. * trans-decl.cc (trans_function_start): Likewise. (gfc_trans_deferred_vars): Likewise. (generate_local_decl): Likewise. (gfc_generate_function_code): Likewise. * trans-expr.cc (gfc_vptr_size_get): Likewise. (gfc_trans_class_array_init_assign): Likewise. (POWI_TABLE_SIZE): Likewise. (gfc_conv_procedure_call): Likewise. (gfc_trans_arrayfunc_assign): Likewise. * trans-intrinsic.cc (gfc_conv_intrinsic_len): Likewise. (gfc_conv_intrinsic_loc): Likewise. (conv_intrinsic_event_query): Likewise. * trans-io.cc (gfc_build_st_parameter): Likewise. * trans-openmp.cc (gfc_omp_check_optional_argument): Likewise. (gfc_omp_unshare_expr_r): Likewise. (gfc_trans_omp_array_section): Likewise. (gfc_trans_omp_clauses): Likewise. * trans-stmt.cc (trans_associate_var): Likewise. (gfc_trans_deallocate): Likewise. * trans-stmt.h (gfc_trans_class_init_assign): Likewise. (gfc_trans_deallocate): Likewise. (gfc_trans_oacc_declare): Likewise. * trans-types.cc: Likewise. * trans-types.h (enum gfc_packed): Likewise. * trans.cc (N_): Likewise. (trans_code): Likewise. * trans.h (gfc_build_compare_string): Likewise. (gfc_conv_expr_type): Likewise. (gfc_trans_deferred_vars): Likewise. (getdecls): Likewise. (gfc_get_array_descr_info): Likewise. (gfc_omp_firstprivatize_type_sizes): Likewise. (GTY): Likewise. gcc/go/ChangeLog: * config-lang.in: Rename .c names to .cc. * go-backend.cc: Likewise. * go-lang.cc: Likewise. * gospec.cc: Likewise. * lang-specs.h: Likewise. gcc/jit/ChangeLog: * config-lang.in: Rename .c names to .cc. * docs/_build/texinfo/libgccjit.texi: Likewise. * docs/internals/index.rst: Likewise. * jit-builtins.cc (builtins_manager::make_builtin_function): Likewise. * jit-playback.cc (fold_const_var): Likewise. (playback::context::~context): Likewise. (new_field): Likewise. (new_bitfield): Likewise. (new_compound_type): Likewise. (playback::compound_type::set_fields): Likewise. (global_set_init_rvalue): Likewise. (load_blob_in_ctor): Likewise. (new_global_initialized): Likewise. (double>): Likewise. (new_string_literal): Likewise. (as_truth_value): Likewise. (build_call): Likewise. (playback::context::build_cast): Likewise. (new_array_access): Likewise. (new_field_access): Likewise. (dereference): Likewise. (postprocess): Likewise. (add_jump): Likewise. (add_switch): Likewise. (build_goto_operands): Likewise. (playback::context::read_dump_file): Likewise. (init_types): Likewise. * jit-recording.cc (recording::context::get_int_type): Likewise. * jit-recording.h: Likewise. * libgccjit.cc (compatible_types): Likewise. (gcc_jit_context_acquire): Likewise. (gcc_jit_context_release): Likewise. (gcc_jit_context_new_child_context): Likewise. (gcc_jit_type_as_object): Likewise. (gcc_jit_context_get_type): Likewise. (gcc_jit_context_get_int_type): Likewise. (gcc_jit_type_get_pointer): Likewise. (gcc_jit_type_get_const): Likewise. (gcc_jit_type_get_volatile): Likewise. (gcc_jit_type_dyncast_array): Likewise. (gcc_jit_type_is_bool): Likewise. (gcc_jit_type_is_pointer): Likewise. (gcc_jit_type_is_integral): Likewise. (gcc_jit_type_dyncast_vector): Likewise. (gcc_jit_type_is_struct): Likewise. (gcc_jit_vector_type_get_num_units): Likewise. (gcc_jit_vector_type_get_element_type): Likewise. (gcc_jit_type_unqualified): Likewise. (gcc_jit_type_dyncast_function_ptr_type): Likewise. (gcc_jit_function_type_get_return_type): Likewise. (gcc_jit_function_type_get_param_count): Likewise. (gcc_jit_function_type_get_param_type): Likewise. (gcc_jit_context_new_array_type): Likewise. (gcc_jit_context_new_field): Likewise. (gcc_jit_field_as_object): Likewise. (gcc_jit_context_new_struct_type): Likewise. (gcc_jit_struct_as_type): Likewise. (gcc_jit_struct_set_fields): Likewise. (gcc_jit_struct_get_field_count): Likewise. (gcc_jit_context_new_union_type): Likewise. (gcc_jit_context_new_function_ptr_type): Likewise. (gcc_jit_param_as_rvalue): Likewise. (gcc_jit_context_new_function): Likewise. (gcc_jit_function_get_return_type): Likewise. (gcc_jit_function_dump_to_dot): Likewise. (gcc_jit_block_get_function): Likewise. (gcc_jit_global_set_initializer_rvalue): Likewise. (gcc_jit_rvalue_get_type): Likewise. (gcc_jit_context_new_rvalue_from_int): Likewise. (gcc_jit_context_one): Likewise. (gcc_jit_context_new_rvalue_from_double): Likewise. (gcc_jit_context_null): Likewise. (gcc_jit_context_new_string_literal): Likewise. (valid_binary_op_p): Likewise. (gcc_jit_context_new_binary_op): Likewise. (gcc_jit_context_new_comparison): Likewise. (gcc_jit_context_new_call): Likewise. (is_valid_cast): Likewise. (gcc_jit_context_new_cast): Likewise. (gcc_jit_object_get_context): Likewise. (gcc_jit_object_get_debug_string): Likewise. (gcc_jit_lvalue_access_field): Likewise. (gcc_jit_rvalue_access_field): Likewise. (gcc_jit_rvalue_dereference_field): Likewise. (gcc_jit_rvalue_dereference): Likewise. (gcc_jit_lvalue_get_address): Likewise. (gcc_jit_lvalue_set_tls_model): Likewise. (gcc_jit_lvalue_set_link_section): Likewise. (gcc_jit_function_new_local): Likewise. (gcc_jit_block_add_eval): Likewise. (gcc_jit_block_add_assignment): Likewise. (is_bool): Likewise. (gcc_jit_block_end_with_conditional): Likewise. (gcc_jit_block_add_comment): Likewise. (gcc_jit_block_end_with_jump): Likewise. (gcc_jit_block_end_with_return): Likewise. (gcc_jit_block_end_with_void_return): Likewise. (case_range_validator::case_range_validator): Likewise. (case_range_validator::validate): Likewise. (case_range_validator::get_wide_int): Likewise. (gcc_jit_block_end_with_switch): Likewise. (gcc_jit_context_set_str_option): Likewise. (gcc_jit_context_set_int_option): Likewise. (gcc_jit_context_set_bool_option): Likewise. (gcc_jit_context_set_bool_allow_unreachable_blocks): Likewise. (gcc_jit_context_set_bool_use_external_driver): Likewise. (gcc_jit_context_add_command_line_option): Likewise. (gcc_jit_context_add_driver_option): Likewise. (gcc_jit_context_enable_dump): Likewise. (gcc_jit_context_compile): Likewise. (gcc_jit_context_compile_to_file): Likewise. (gcc_jit_context_set_logfile): Likewise. (gcc_jit_context_dump_reproducer_to_file): Likewise. (gcc_jit_context_get_first_error): Likewise. (gcc_jit_context_get_last_error): Likewise. (gcc_jit_result_get_code): Likewise. (gcc_jit_result_get_global): Likewise. (gcc_jit_rvalue_set_bool_require_tail_call): Likewise. (gcc_jit_type_get_aligned): Likewise. (gcc_jit_type_get_vector): Likewise. (gcc_jit_function_get_address): Likewise. (gcc_jit_version_patchlevel): Likewise. (gcc_jit_block_add_extended_asm): Likewise. (gcc_jit_extended_asm_as_object): Likewise. (gcc_jit_extended_asm_set_volatile_flag): Likewise. (gcc_jit_extended_asm_set_inline_flag): Likewise. (gcc_jit_extended_asm_add_output_operand): Likewise. (gcc_jit_extended_asm_add_input_operand): Likewise. (gcc_jit_extended_asm_add_clobber): Likewise. * notes.txt: Likewise. gcc/lto/ChangeLog: * config-lang.in: Rename .c names to .cc. * lang-specs.h: Likewise. * lto-common.cc (gimple_register_canonical_type_1): Likewise. * lto-common.h: Likewise. * lto-dump.cc (lto_main): Likewise. * lto-lang.cc (handle_fnspec_attribute): Likewise. (lto_getdecls): Likewise. (lto_init): Likewise. * lto.cc (lto_main): Likewise. * lto.h: Likewise. gcc/objc/ChangeLog: * Make-lang.in: Rename .c names to .cc. * config-lang.in: Likewise. * lang-specs.h: Likewise. * objc-act.cc (objc_build_component_ref): Likewise. (objc_copy_binfo): Likewise. (lookup_method_in_hash_lists): Likewise. (objc_finish_foreach_loop): Likewise. * objc-act.h (objc_common_init_ts): Likewise. * objc-gnu-runtime-abi-01.cc: Likewise. * objc-lang.cc (struct lang_hooks): Likewise. * objc-map.cc: Likewise. * objc-next-runtime-abi-01.cc (generate_objc_symtab_decl): Likewise. * objc-runtime-shared-support.cc: Likewise. * objc-runtime-shared-support.h (build_protocol_initializer): Likewise. gcc/objcp/ChangeLog: * Make-lang.in: Rename .c names to .cc. * config-lang.in: Likewise. * lang-specs.h: Likewise. * objcp-decl.cc (objcp_end_compound_stmt): Likewise. * objcp-lang.cc (struct lang_hooks): Likewise. gcc/po/ChangeLog: * EXCLUDES: Rename .c names to .cc. libcpp/ChangeLog: * Makefile.in: Rename .c names to .cc. * charset.cc (convert_escape): Likewise. * directives.cc (directive_diagnostics): Likewise. (_cpp_handle_directive): Likewise. (lex_macro_node): Likewise. * include/cpplib.h (struct _cpp_file): Likewise. (PURE_ZERO): Likewise. (cpp_defined): Likewise. (cpp_error_at): Likewise. (cpp_forall_identifiers): Likewise. (cpp_compare_macros): Likewise. (cpp_get_converted_source): Likewise. (cpp_read_state): Likewise. (cpp_directive_only_process): Likewise. (struct cpp_decoded_char): Likewise. * include/line-map.h (enum lc_reason): Likewise. (enum location_aspect): Likewise. * include/mkdeps.h: Likewise. * init.cc (cpp_destroy): Likewise. (cpp_finish): Likewise. * internal.h (struct cpp_reader): Likewise. (_cpp_defined_macro_p): Likewise. (_cpp_backup_tokens_direct): Likewise. (_cpp_destroy_hashtable): Likewise. (_cpp_has_header): Likewise. (_cpp_expand_op_stack): Likewise. (_cpp_commit_buff): Likewise. (_cpp_restore_special_builtin): Likewise. (_cpp_bracket_include): Likewise. (_cpp_replacement_text_len): Likewise. (ufputs): Likewise. * line-map.cc (linemap_macro_loc_to_exp_point): Likewise. (linemap_check_files_exited): Likewise. (line_map_new_raw): Likewise. * traditional.cc (enum ls): Likewise.
2022-01-14 16:57:02 +01:00
/* diagnostic.cc does not support "%03o". When it does, this
code can use %03o directly in the diagnostic again. */
char buf[32];
sprintf(buf, "%03o", (int) c);
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
cpp_error_at (pfile, CPP_DL_PEDWARN, &rich_loc,
"unknown escape sequence: '\\%s'", buf);
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (tbuf)
/* Now convert what we have to the execution character set. */
if (!APPLY_CONVERSION (cvt, &c, 1, tbuf))
cpp_errno (pfile, CPP_DL_ERROR,
"converting escape sequence to execution character set");
if (loc_reader)
{
char_range.m_finish = loc_reader->get_next ().m_finish;
ranges->add_range (char_range);
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return from + 1;
}
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
/* TYPE is a token type. The return value is the conversion needed to
convert from source to execution character set for the given type. */
static struct cset_converter
converter_for_type (cpp_reader *pfile, enum cpp_ttype type)
{
switch (type)
{
default:
return pfile->narrow_cset_desc;
Implement N4197 - Adding u8 character literals libcpp: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * include/cpplib.h (UTF8CHAR, UTF8CHAR_USERDEF): New cpp tokens; (struct cpp_options): Add utf8_char_literals. * init.c (struct lang_flags): Add utf8_char_literals; (struct lang_flags lang_defaults): Add column for utf8_char_literals. * macro.c (stringify_arg()): Treat CPP_UTF8CHAR token; * expr.c (cpp_userdef_char_remove_type(), cpp_userdef_char_add_type()): Treat CPP_UTF8CHAR_USERDEF, CPP_UTF8CHAR tokens; (cpp_userdef_char_p()): Treat CPP_UTF8CHAR_USERDEF token; (eval_token(), _cpp_parse_expr()): Treat CPP_UTF8CHAR token. * lex.c (lex_string(), _cpp_lex_direct()): Include CPP_UTF8CHAR tokens. * charset.c (converter_for_type(), cpp_interpret_charconst()): Treat CPP_UTF8CHAR token. gcc/c-family: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * c-family/c-ada-spec.c (print_ada_macros()): Treat CPP_UTF8CHAR like CPP_CHAR. * c-family/c-common.c (c_parse_error()): print CPP_UTF8CHAR and CPP_UTF8CHAR_USERDEF tokens. * c-family/c-lex.c (c_lex_with_flags()): Treat CPP_UTF8CHAR_USERDEF and CPP_UTF8CHAR tokens; (lex_charconst()): Treat CPP_UTF8CHAR token. gcc/cp: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * parser.c (cp_parser_primary_expression()): Treat CPP_UTF8CHAR and CPP_UTF8CHAR_USERDEF tokens; (cp_parser_parenthesized_expression_list()): Treat CPP_UTF8CHAR token. gcc/testsuite: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * g++.dg/cpp1z/utf8.C: New. * g++.dg/cpp1z/utf8-neg.C: New. * g++.dg/cpp1z/udlit-utf8char.C: New. From-SVN: r225185
2015-06-30 14:58:48 +02:00
case CPP_UTF8CHAR:
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
case CPP_UTF8STRING:
return pfile->utf8_cset_desc;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
case CPP_CHAR16:
case CPP_STRING16:
return pfile->char16_cset_desc;
case CPP_CHAR32:
case CPP_STRING32:
return pfile->char32_cset_desc;
case CPP_WCHAR:
case CPP_WSTRING:
return pfile->wide_cset_desc;
}
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* FROM is an array of cpp_string structures of length COUNT. These
are to be converted from the source to the execution character set,
escape sequences translated, and finally all are to be
concatenated. WIDE indicates whether or not to produce a wide
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
string. If TO is non-NULL, the result is written into TO.
If LOC_READERS and OUT are non-NULL, then location information
is read from LOC_READERS (which must be an array of length COUNT),
and location information is written to *RANGES.
Returns true for success, false for failure. */
static bool
cpp_interpret_string_1 (cpp_reader *pfile, const cpp_string *from, size_t count,
cpp_string *to, enum cpp_ttype type,
cpp_string_location_reader *loc_readers,
cpp_substring_ranges *out)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
struct _cpp_strbuf tbuf;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
const uchar *p, *base, *limit;
size_t i;
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
struct cset_converter cvt = converter_for_type (pfile, type);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* loc_readers and out must either be both NULL, or both be non-NULL. */
gcc_assert ((loc_readers != NULL) == (out != NULL));
if (to)
{
tbuf.asize = MAX (OUTBUF_BLOCK_SIZE, from->len);
tbuf.text = XNEWVEC (uchar, tbuf.asize);
tbuf.len = 0;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
Provide location information for terminator characters (PR preprocessor/77672) substring_loc::get_location currently fails for the final terminator character in a STRING_CST from the C frontend, so that format_warning_va falls back to using the location of the string as a whole. This patch tweaks things [1] so that we use the final closing quote as the location of the terminator character, as requested in PR preprocessor/77672. [1] specifically, cpp_interpret_string_1. gcc/ChangeLog: PR preprocessor/77672 * input.c (selftest::test_lexer_string_locations_simple): Update test to expect location information of the terminator character at the location of the final closing quote. (selftest::test_lexer_string_locations_hex): Likewise. (selftest::test_lexer_string_locations_oct): Likewise. (selftest::test_lexer_string_locations_letter_escape_1): Likewise. (selftest::test_lexer_string_locations_letter_escape_2): Likewise. (selftest::test_lexer_string_locations_ucn4): Likewise. (selftest::test_lexer_string_locations_ucn8): Likewise. (selftest::test_lexer_string_locations_u8): Likewise. (selftest::test_lexer_string_locations_utf8_source): Likewise. (selftest::test_lexer_string_locations_concatenation_1): Likewise. (selftest::test_lexer_string_locations_concatenation_2): Likewise. (selftest::test_lexer_string_locations_concatenation_3): Likewise. (selftest::test_lexer_string_locations_macro): Likewise. (selftest::test_lexer_string_locations_long_line): Likewise. gcc/testsuite/ChangeLog: PR preprocessor/77672 * gcc.dg/plugin/diagnostic-test-string-literals-1.c (test_terminator_location): New function. libcpp/ChangeLog: PR preprocessor/77672 * charset.c (cpp_interpret_string_1): Add a source_range for the NUL-terminator, using the location of the trailing quote of the final string. From-SVN: r240434
2016-09-23 16:14:52 +02:00
cpp_string_location_reader *loc_reader = NULL;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
for (i = 0; i < count; i++)
{
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (loc_readers)
loc_reader = &loc_readers[i];
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
p = from[i].text;
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
if (*p == 'u')
{
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
p++;
if (loc_reader)
loc_reader->get_next ();
if (*p == '8')
{
p++;
if (loc_reader)
loc_reader->get_next ();
}
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
}
else if (*p == 'L' || *p == 'U') p++;
if (*p == 'R')
{
const uchar *prefix;
/* Skip over 'R"'. */
p += 2;
if (loc_reader)
{
loc_reader->get_next ();
loc_reader->get_next ();
}
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
prefix = p;
while (*p != '(')
{
p++;
if (loc_reader)
loc_reader->get_next ();
}
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
p++;
if (loc_reader)
loc_reader->get_next ();
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
limit = from[i].text + from[i].len;
if (limit >= p + (p - prefix) + 1)
limit -= (p - prefix) + 1;
/* Raw strings are all normal characters; these can be fed
directly to convert_cset. */
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (to)
if (!APPLY_CONVERSION (cvt, p, limit - p, &tbuf))
goto fail;
if (loc_reader)
{
/* If generating source ranges, assume we have a 1:1
correspondence between bytes in the source encoding and bytes
in the execution encoding (e.g. if we have a UTF-8 to UTF-8
conversion), so that this run of bytes in the source file
corresponds to a run of bytes in the execution string.
This requirement is guaranteed by an early-reject in
cpp_interpret_string_ranges. */
gcc_assert (cvt.func == convert_no_conversion);
out->add_n_ranges (limit - p, *loc_reader);
}
charset.c (cpp_init_iconv): Initialize utf8_cset_desc. * charset.c (cpp_init_iconv): Initialize utf8_cset_desc. (_cpp_destroy_iconv): Destroy utf8_cset_desc, char16_cset_desc and char32_cset_desc. (converter_for_type): Handle CPP_UTF8STRING. (cpp_interpret_string): Handle CPP_UTF8STRING and raw-strings. * directives.c (get__Pragma_string): Handle CPP_UTF8STRING. (parse_include): Reject raw strings. * include/cpplib.h (CPP_UTF8STRING): New token type. * internal.h (struct cpp_reader): Add utf8_cset_desc field. * lex.c (lex_raw_string): New function. (lex_string): Handle u8 string literals, call lex_raw_string for raw string literals. (_cpp_lex_direct): Call lex_string even for u8" and {,u,U,L,u8}R" sequences. * macro.c (stringify_arg): Handle CPP_UTF8STRING. * c-common.c (c_parse_error): Handle CPP_UTF8STRING. * c-lex.c (c_lex_with_flags): Likewise. Test C_LEX_STRING_NO_JOIN instead of C_LEX_RAW_STRINGS. (lex_string): Handle CPP_UTF8STRING. * c-parser.c (c_parser_postfix_expression): Likewise. * c-pragma.h (C_LEX_RAW_STRINGS): Rename to ... (C_LEX_STRING_NO_JOIN): ... this. * parser.c (cp_lexer_print_token, cp_parser_is_string_literal, cp_parser_string_literal, cp_parser_primary_expression): Likewise. (cp_lexer_get_preprocessor_token): Use C_LEX_STRING_JOIN instead of C_LEX_RAW_STRINGS. * gcc.dg/raw-string-1.c: New test. * gcc.dg/raw-string-2.c: New test. * gcc.dg/raw-string-3.c: New test. * gcc.dg/raw-string-4.c: New test. * gcc.dg/raw-string-5.c: New test. * gcc.dg/raw-string-6.c: New test. * gcc.dg/raw-string-7.c: New test. * gcc.dg/utf8-1.c: New test. * gcc.dg/utf8-2.c: New test. * gcc.dg/utf-badconcat2.c: New test. * gcc.dg/utf-dflt2.c: New test. * gcc.dg/cpp/include6.c: New test. * g++.dg/ext/raw-string-1.C: New test. * g++.dg/ext/raw-string-2.C: New test. * g++.dg/ext/raw-string-3.C: New test. * g++.dg/ext/raw-string-4.C: New test. * g++.dg/ext/raw-string-5.C: New test. * g++.dg/ext/raw-string-6.C: New test. * g++.dg/ext/raw-string-7.C: New test. * g++.dg/ext/utf8-1.C: New test. * g++.dg/ext/utf8-2.C: New test. * g++.dg/ext/utf-badconcat2.C: New test. * g++.dg/ext/utf-dflt2.C: New test. From-SVN: r152995
2009-10-19 23:41:15 +02:00
continue;
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* If we don't now have a leading quote, something has gone wrong.
This can occur if cpp_interpret_string_ranges is handling a
stringified macro argument, but should not be possible otherwise. */
if (*p != '"' && *p != '\'')
{
gcc_assert (out != NULL);
cpp_error (pfile, CPP_DL_ERROR, "missing open quote");
if (to)
free (tbuf.text);
return false;
}
/* Skip leading quote. */
p++;
if (loc_reader)
loc_reader->get_next ();
limit = from[i].text + from[i].len - 1; /* Skip trailing quote. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
for (;;)
{
base = p;
while (p < limit && *p != '\\')
p++;
if (p > base)
{
/* We have a run of normal characters; these can be fed
directly to convert_cset. */
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (to)
if (!APPLY_CONVERSION (cvt, base, p - base, &tbuf))
goto fail;
/* Similar to above: assumes we have a 1:1 correspondence
between bytes in the source encoding and bytes in the
execution encoding. */
if (loc_reader)
{
gcc_assert (cvt.func == convert_no_conversion);
out->add_n_ranges (p - base, *loc_reader);
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (p >= limit)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
break;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
struct _cpp_strbuf *tbuf_ptr = to ? &tbuf : NULL;
p = convert_escape (pfile, p + 1, limit, tbuf_ptr, cvt,
loc_reader, out);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (to)
{
/* NUL-terminate the 'to' buffer and translate it to a cpp_string
structure. */
emit_numeric_escape (pfile, 0, &tbuf, cvt);
tbuf.text = XRESIZEVEC (uchar, tbuf.text, tbuf.len);
to->text = tbuf.text;
to->len = tbuf.len;
}
Provide location information for terminator characters (PR preprocessor/77672) substring_loc::get_location currently fails for the final terminator character in a STRING_CST from the C frontend, so that format_warning_va falls back to using the location of the string as a whole. This patch tweaks things [1] so that we use the final closing quote as the location of the terminator character, as requested in PR preprocessor/77672. [1] specifically, cpp_interpret_string_1. gcc/ChangeLog: PR preprocessor/77672 * input.c (selftest::test_lexer_string_locations_simple): Update test to expect location information of the terminator character at the location of the final closing quote. (selftest::test_lexer_string_locations_hex): Likewise. (selftest::test_lexer_string_locations_oct): Likewise. (selftest::test_lexer_string_locations_letter_escape_1): Likewise. (selftest::test_lexer_string_locations_letter_escape_2): Likewise. (selftest::test_lexer_string_locations_ucn4): Likewise. (selftest::test_lexer_string_locations_ucn8): Likewise. (selftest::test_lexer_string_locations_u8): Likewise. (selftest::test_lexer_string_locations_utf8_source): Likewise. (selftest::test_lexer_string_locations_concatenation_1): Likewise. (selftest::test_lexer_string_locations_concatenation_2): Likewise. (selftest::test_lexer_string_locations_concatenation_3): Likewise. (selftest::test_lexer_string_locations_macro): Likewise. (selftest::test_lexer_string_locations_long_line): Likewise. gcc/testsuite/ChangeLog: PR preprocessor/77672 * gcc.dg/plugin/diagnostic-test-string-literals-1.c (test_terminator_location): New function. libcpp/ChangeLog: PR preprocessor/77672 * charset.c (cpp_interpret_string_1): Add a source_range for the NUL-terminator, using the location of the trailing quote of the final string. From-SVN: r240434
2016-09-23 16:14:52 +02:00
/* Use the location of the trailing quote as the location of the
NUL-terminator. */
if (loc_reader)
{
source_range range = loc_reader->get_next ();
out->add_range (range);
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return true;
fail:
cpp_errno (pfile, CPP_DL_ERROR, "converting to execution character set");
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (to)
free (tbuf.text);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return false;
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* FROM is an array of cpp_string structures of length COUNT. These
are to be converted from the source to the execution character set,
escape sequences translated, and finally all are to be
concatenated. WIDE indicates whether or not to produce a wide
string. The result is written into TO. Returns true for success,
false for failure. */
bool
cpp_interpret_string (cpp_reader *pfile, const cpp_string *from, size_t count,
cpp_string *to, enum cpp_ttype type)
{
return cpp_interpret_string_1 (pfile, from, count, to, type, NULL, NULL);
}
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
/* A "do nothing" diagnostic-handling callback for use by
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
cpp_interpret_string_ranges, so that it can temporarily suppress
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
diagnostic-handling. */
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
static bool
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
noop_diagnostic_cb (cpp_reader *, enum cpp_diagnostic_level,
enum cpp_warning_reason, rich_location *,
const char *, va_list *)
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
{
/* no-op. */
return true;
}
/* This function mimics the behavior of cpp_interpret_string, but
rather than generating a string in the execution character set,
*OUT is written to with the source code ranges of the characters
in such a string.
FROM and LOC_READERS should both be arrays of length COUNT.
Returns NULL for success, or an error message for failure. */
const char *
cpp_interpret_string_ranges (cpp_reader *pfile, const cpp_string *from,
cpp_string_location_reader *loc_readers,
size_t count,
cpp_substring_ranges *out,
enum cpp_ttype type)
{
/* There are a couple of cases in the range-handling in
cpp_interpret_string_1 that rely on there being a 1:1 correspondence
between bytes in the source encoding and bytes in the execution
encoding, so that each byte in the execution string can correspond
to the location of a byte in the source string.
This holds for the typical case of a UTF-8 to UTF-8 conversion.
Enforce this requirement by only attempting to track substring
locations if we have source encoding == execution encoding.
This is a stronger condition than we need, since we could e.g.
have ASCII to EBCDIC (with 1 byte per character before and after),
but it seems to be a reasonable restriction. */
struct cset_converter cvt = converter_for_type (pfile, type);
if (cvt.func != convert_no_conversion)
return "execution character set != source character set";
/* For on-demand strings we have already lexed the strings, so there
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
should be no diagnostics. However, if we have bogus source location
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
data (or stringified macro arguments), the attempt to lex the
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
strings could fail with an diagnostic. Temporarily install an
diagnostic-handler to catch the diagnostic, so that it can lead to this call
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
failing, rather than being emitted as a user-visible diagnostic.
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
If an diagnostic does occur, we should see it via the return value of
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
cpp_interpret_string_1. */
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
bool (*saved_diagnostic_handler) (cpp_reader *, enum cpp_diagnostic_level,
enum cpp_warning_reason, rich_location *,
const char *, va_list *)
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
ATTRIBUTE_FPTR_PRINTF(5,0);
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
saved_diagnostic_handler = pfile->cb.diagnostic;
pfile->cb.diagnostic = noop_diagnostic_cb;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
bool result = cpp_interpret_string_1 (pfile, from, count, NULL, type,
loc_readers, out);
Cleanup of libcpp diagnostic callbacks This patch renames the "error" callback within libcpp to "diagnostic", and uses the pair of enums in cpplib.h, rather than passing two different kinds of "int" around. gcc/c-family/ChangeLog: * c-common.c (c_option_controlling_cpp_error): Rename to... (c_option_controlling_cpp_diagnostic): ...this, and convert "reason" from int to enum. (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-common.h (c_cpp_error): Rename to... (c_cpp_diagnostic): ...this, converting level and reason to enums. * c-opts.c (c_common_init_options): Update for renaming. gcc/fortran/ChangeLog: * cpp.c (gfc_cpp_init_0): Update for renamings. (cb_cpp_error): Rename to... (cb_cpp_diagnostic): ...this, converting level and reason to enums. gcc/ChangeLog: * genmatch.c (error_cb): Rename to... (diagnostic_cb): ...this, converting int params to enums. (fatal_at): Update for renaming. (warning_at): Likewise. (main): Likewise. * input.c (selftest::ebcdic_execution_charset::apply): Update for renaming of... (selftest::ebcdic_execution_charset::on_error): ...this, renaming to... (selftest::ebcdic_execution_charset::on_diagnostic): ...this, converting level and reason to enums. (class selftest::lexer_error_sink): Rename to... (class selftest::lexer_test_options): ...this, renaming field "m_errors" to "m_diagnostics". (selftest::lexer_test_options::apply): Update for renaming of... (selftest::lexer_test_options::on_error): ...this, renaming to... (selftest::lexer_test_options::on_diagnostic): ...this converting level and reason to enums. (selftest::test_lexer_string_locations_raw_string_unterminated): Update for renamings. * opth-gen.awk (struct cpp_reason_option_codes_t): Use enum for "reason". libcpp/ChangeLog: * charset.c (noop_error_cb): Rename to... (noop_diagnostic_cb): ...this, converting params to enums. (cpp_interpret_string_ranges): Update for renaming and enums. * directives.c (check_eol_1): Convert reason to enum. (do_diagnostic): Convert code and reason to enum. (do_error): Use CPP_W_NONE rather than 0. (do_pragma_dependency): Likewise. * errors.c (cpp_diagnostic_at): Convert level and reason to enums. Update for renaming. (cpp_diagnostic): Convert level and reason to enums. (cpp_error): Convert level to enum. (cpp_warning): Convert reason to enums. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_diagnostic_with_line): Convert level and reason to enums. Update for renaming. (cpp_error_with_line): Convert level to enum. (cpp_warning_with_line): Convert reason to enums. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert level to enum. (cpp_errno): Likewise. (cpp_errno_filename): Likewise. * include/cpplib.h (enum cpp_diagnostic_level): Name this enum, and move to before struct cpp_callbacks. (enum cpp_warning_reason): Likewise. (cpp_callbacks::diagnostic): Convert params from int to enums. (cpp_error): Convert int param to enum cpp_diagnostic_level. (cpp_warning): Convert int param to enum cpp_warning_reason. (cpp_pedwarning): Likewise. (cpp_warning_syshdr): Likewise. (cpp_errno): Convert int param to enum cpp_diagnostic_level. (cpp_errno_filename): Likewise. (cpp_error_with_line): Likewise. (cpp_warning_with_line): Convert int param to enum cpp_warning_reason. (cpp_pedwarning_with_line): Likewise. (cpp_warning_with_line_syshdr): Likewise. (cpp_error_at): Convert int param to enum cpp_diagnostic_level. * macro.c (create_iso_definition): Convert int to enum. (_cpp_create_definition): Likewise. From-SVN: r264999
2018-10-10 01:37:19 +02:00
/* Restore the saved diagnostic-handler. */
pfile->cb.diagnostic = saved_diagnostic_handler;
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
if (!result)
return "cpp_interpret_string_1 failed";
/* Success. */
return NULL;
}
/* Subroutine of do_line and do_linemarker. Convert escape sequences
in a string, but do not perform character set conversion. */
bool
cpp_interpret_string_notranslate (cpp_reader *pfile, const cpp_string *from,
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
size_t count, cpp_string *to,
enum cpp_ttype type ATTRIBUTE_UNUSED)
{
struct cset_converter save_narrow_cset_desc = pfile->narrow_cset_desc;
bool retval;
pfile->narrow_cset_desc.func = convert_no_conversion;
pfile->narrow_cset_desc.cd = (iconv_t) -1;
pfile->narrow_cset_desc.width = CPP_OPTION (pfile, char_precision);
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
retval = cpp_interpret_string (pfile, from, count, to, CPP_STRING);
pfile->narrow_cset_desc = save_narrow_cset_desc;
return retval;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Subroutine of cpp_interpret_charconst which performs the conversion
to a number, for narrow strings. STR is the string structure returned
by cpp_interpret_string. PCHARS_SEEN and UNSIGNEDP are as for
cpp_interpret_charconst. TYPE is the token type. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static cppchar_t
narrow_str_to_charconst (cpp_reader *pfile, cpp_string str,
unsigned int *pchars_seen, int *unsignedp,
enum cpp_ttype type)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
size_t width = CPP_OPTION (pfile, char_precision);
size_t max_chars = CPP_OPTION (pfile, int_precision) / width;
size_t mask = width_to_mask (width);
size_t i;
cppchar_t result, c;
bool unsigned_p;
/* The value of a multi-character character constant, or a
single-character character constant whose representation in the
execution character set is more than one byte long, is
implementation defined. This implementation defines it to be the
number formed by interpreting the byte sequence in memory as a
big-endian binary number. If overflow occurs, the high bytes are
lost, and a warning is issued.
We don't want to process the NUL terminator handed back by
cpp_interpret_string. */
result = 0;
for (i = 0; i < str.len - 1; i++)
{
c = str.text[i] & mask;
if (width < BITS_PER_CPPCHAR_T)
result = (result << width) | c;
else
result = c;
}
if (type == CPP_UTF8CHAR)
max_chars = 1;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
if (i > max_chars)
{
i = max_chars;
cpp_error (pfile, type == CPP_UTF8CHAR ? CPP_DL_ERROR : CPP_DL_WARNING,
"character constant too long for its type");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
}
else if (i > 1 && CPP_OPTION (pfile, warn_multichar))
diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * diagnostic.h (diagnostic_override_option_index): New macro to set a diagnostic's option_index. * c-tree.h (c_cpp_error): Add warning reason argument. * opts.c (_warning_as_error_callback): New. (register_warning_as_error_callback): Store callback for warnings enabled via enable_warning_as_error. (enable_warning_as_error): Call callback, minor code tidy. * opts.h (register_warning_as_error_callback): Declare. * c-opts.c (warning_as_error_callback): New, set cpp_opts flag in response to -Werror=. (c_common_init_options): Register warning_as_error_callback in opts.c. * common.opt: Add -Wno-cpp option. * c-common.c (struct reason_option_codes_t): Map cpp warning reason codes to gcc option indexes. * (c_option_controlling_cpp_error): New function, lookup the gcc option index for a cpp warning reason code. * (c_cpp_error): Add warning reason argument, call c_option_controlling_cpp_error for diagnostic_override_option_index. * doc/invoke.texi: Document -Wno-cpp. * cpp.c (cb_cpp_error): Add warning reason argument, set a value for diagnostic_override_option_index if CPP_W_WARNING_DIRECTIVE. * directives.c (do_diagnostic): Add warning reason argument, call appropriate error reporting function for code. (directive_diagnostics): Call specific warning functions with warning reason where appropriate. (do_error, do_warning, do_pragma_dependency): Add warning reason argument to do_diagnostic calls. * macro.c (_cpp_warn_if_unused_macro, enter_macro_context, _cpp_create_definition): Call specific warning functions with warning reason where appropriate. * Makefile.in: Add new diagnostic functions to gettext translations. * include/cpplib.h (struct cpp_callbacks): Add warning reason code to error callback. (CPP_DL_WARNING, CPP_DL_WARNING_SYSHDR, CPP_DL_PEDWARN, CPP_DL_ERROR, CPP_DL_ICE, CPP_DL_NOTE, CPP_DL_FATAL): Replace macros with enums. (CPP_W_NONE, CPP_W_DEPRECATED, CPP_W_COMMENTS, CPP_W_MISSING_INCLUDE_DIRS, CPP_W_TRIGRAPHS, CPP_W_MULTICHAR, CPP_W_TRADITIONAL, CPP_W_LONG_LONG, CPP_W_ENDIF_LABELS, CPP_W_NUM_SIGN_CHANGE, CPP_W_VARIADIC_MACROS, CPP_W_BUILTIN_MACRO_REDEFINED, CPP_W_DOLLARS, CPP_W_UNDEF, CPP_W_UNUSED_MACROS, CPP_W_CXX_OPERATOR_NAMES, CPP_W_NORMALIZE, CPP_W_INVALID_PCH, CPP_W_WARNING_DIRECTIVE): New enums for cpp warning reason codes. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * pch.c (cpp_valid_state): Call specific warning functions with warning reason where appropriate. * errors.c (cpp_diagnostic, cpp_diagnostic_with_line): New central diagnostic handlers. (cpp_warning, cpp_pedwarning, cpp_warning_syshdr, cpp_warning_with_line, cpp_pedwarning_with_line, cpp_warning_with_line_syshdr): New specific error reporting functions. * expr.c (cpp_classify_number, eval_token, num_unary_op): Call specific warning functions with warning reason where appropriate. * lex.c (_cpp_process_line_notes, _cpp_skip_block_comment, warn_about_normalization, lex_identifier_intern, lex_identifier, _cpp_lex_direct): Ditto. * charset.c (_cpp_valid_ucn, convert_hex, convert_escape, narrow_str_to_charconst): Ditto. * gcc.dg/cpp/warn-undef-2.c: New. * gcc.dg/cpp/warn-traditional-2.c: New. * gcc.dg/cpp/warn-comments-2.c: New. * gcc.dg/cpp/warning-directive-1.c: New. * gcc.dg/cpp/warn-long-long.c: New. * gcc.dg/cpp/warn-traditional.c: New. * gcc.dg/cpp/warn-variadic-2.c: New. * gcc.dg/cpp/warn-undef.c: New. * gcc.dg/cpp/warn-normalized-1.c: New. * gcc.dg/cpp/warning-directive-2.c: New. * gcc.dg/cpp/warn-long-long-2.c: New. * gcc.dg/cpp/warn-variadic.c: New. * gcc.dg/cpp/warn-normalized-2.c: New. * gcc.dg/cpp/warning-directive-3.c: New. * gcc.dg/cpp/warn-deprecated-2.c: New. * gcc.dg/cpp/warn-trigraphs-1.c: New. * gcc.dg/cpp/warn-multichar-2.c: New. * gcc.dg/cpp/warn-normalized-3.c: New. * gcc.dg/cpp/warning-directive-4.c: New. * gcc.dg/cpp/warn-unused-macros.c: New. * gcc.dg/cpp/warn-trigraphs-2.c: New. * gcc.dg/cpp/warn-cxx-compat-2.c: New. * gcc.dg/cpp/warn-cxx-compat.c: New. * gcc.dg/cpp/warn-redefined.c: New. * gcc.dg/cpp/warn-trigraphs-3.c: New. * gcc.dg/cpp/warn-unused-macros-2.c: New. * gcc.dg/cpp/warn-deprecated.c: New. * gcc.dg/cpp/warn-trigraphs-4.c: New. * gcc.dg/cpp/warn-redefined-2.c: New. * gcc.dg/cpp/warn-comments.c: New. * gcc.dg/cpp/warn-multichar.c: New. * g++.dg/cpp/warning-directive-1.C: New. * g++.dg/cpp/warning-directive-2.C: New. * g++.dg/cpp/warning-directive-3.C: New. * g++.dg/cpp/warning-directive-4.C: New. * gfortran.dg/warning-directive-1.F90: New. * gfortran.dg/warning-directive-3.F90: New. * gfortran.dg/warning-directive-2.F90: New. * gfortran.dg/warning-directive-4.F90: New. From-SVN: r158079
2010-04-07 19:18:10 +02:00
cpp_warning (pfile, CPP_W_MULTICHAR, "multi-character character constant");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Multichar constants are of type int and therefore signed. */
if (i > 1)
unsigned_p = 0;
Support UTF-8 character constants for C2x. C2x adds u8'' character constants to C. This patch adds the corresponding GCC support. Most of the support was already present for C++ and just needed enabling for C2x. However, in C2x these constants have type unsigned char, which required corresponding adjustments in the compiler and the preprocessor to give them that type for C. For C, it seems clear to me that having type unsigned char means the constants are unsigned in the preprocessor (and thus treated as having type uintmax_t in #if conditionals), so this patch implements that. I included a conditional in the libcpp change to avoid affecting signedness for C++, but I'm not sure if in fact these constants should also be unsigned in the preprocessor for C++ in which case that !CPP_OPTION (pfile, cplusplus) conditional would not be needed. Bootstrapped with no regressions on x86_64-pc-linux-gnu. gcc/c: * c-parser.c (c_parser_postfix_expression) (c_parser_check_literal_zero): Handle CPP_UTF8CHAR. * gimple-parser.c (c_parser_gimple_postfix_expression): Likewise. gcc/c-family: * c-lex.c (lex_charconst): Make CPP_UTF8CHAR constants unsigned char for C. gcc/testsuite: * gcc.dg/c11-utf8char-1.c, gcc.dg/c2x-utf8char-1.c, gcc.dg/c2x-utf8char-2.c, gcc.dg/c2x-utf8char-3.c, gcc.dg/gnu2x-utf8char-1.c: New tests. libcpp: * charset.c (narrow_str_to_charconst): Make CPP_UTF8CHAR constants unsigned for C. * init.c (lang_defaults): Set utf8_char_literals for GNUC2X and STDC2X. From-SVN: r278265
2019-11-14 21:18:33 +01:00
else if (type == CPP_UTF8CHAR && !CPP_OPTION (pfile, cplusplus))
unsigned_p = 1;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else
unsigned_p = CPP_OPTION (pfile, unsigned_char);
/* Truncate the constant to its natural width, and simultaneously
sign- or zero-extend to the full width of cppchar_t.
For single-character constants, the value is WIDTH bits wide.
For multi-character constants, the value is INT_PRECISION bits wide. */
if (i > 1)
width = CPP_OPTION (pfile, int_precision);
if (width < BITS_PER_CPPCHAR_T)
{
mask = ((cppchar_t) 1 << width) - 1;
if (unsigned_p || !(result & (1 << (width - 1))))
result &= mask;
else
result |= ~mask;
}
*pchars_seen = i;
*unsignedp = unsigned_p;
return result;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Subroutine of cpp_interpret_charconst which performs the conversion
to a number, for wide strings. STR is the string structure returned
by cpp_interpret_string. PCHARS_SEEN and UNSIGNEDP are as for
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
cpp_interpret_charconst. TYPE is the token type. */
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
static cppchar_t
wide_str_to_charconst (cpp_reader *pfile, cpp_string str,
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
unsigned int *pchars_seen, int *unsignedp,
enum cpp_ttype type)
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
bool bigend = CPP_OPTION (pfile, bytes_big_endian);
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
size_t width = converter_for_type (pfile, type).width;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
size_t cwidth = CPP_OPTION (pfile, char_precision);
size_t mask = width_to_mask (width);
size_t cmask = width_to_mask (cwidth);
size_t nbwc = width / cwidth;
size_t off, i;
cppchar_t result = 0, c;
if (str.len <= nbwc)
{
/* Error recovery, if no errors have been diagnosed previously,
there should be at least two wide characters. Empty literals
are diagnosed earlier and we can get just the zero terminator
only if there were errors diagnosed during conversion. */
*pchars_seen = 0;
*unsignedp = 0;
return 0;
}
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* This is finicky because the string is in the target's byte order,
which may not be our byte order. Only the last character, ignoring
the NUL terminator, is relevant. */
off = str.len - (nbwc * 2);
result = 0;
for (i = 0; i < nbwc; i++)
{
c = bigend ? str.text[off + i] : str.text[off + nbwc - i - 1];
result = (result << cwidth) | (c & cmask);
}
/* Wide character constants have type wchar_t, and a single
character exactly fills a wchar_t, so a multi-character wide
character constant is guaranteed to overflow. */
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
if (str.len > nbwc * 2)
cpp_error (pfile, (CPP_OPTION (pfile, cplusplus)
&& (type == CPP_CHAR16 || type == CPP_CHAR32))
? CPP_DL_ERROR : CPP_DL_WARNING,
"character constant too long for its type");
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
/* Truncate the constant to its natural width, and simultaneously
sign- or zero-extend to the full width of cppchar_t. */
if (width < BITS_PER_CPPCHAR_T)
{
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
if (type == CPP_CHAR16 || type == CPP_CHAR32
|| CPP_OPTION (pfile, unsigned_wchar)
|| !(result & (1 << (width - 1))))
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
result &= mask;
else
result |= ~mask;
}
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
if (type == CPP_CHAR16 || type == CPP_CHAR32
|| CPP_OPTION (pfile, unsigned_wchar))
*unsignedp = 1;
else
*unsignedp = 0;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
*pchars_seen = 1;
return result;
}
/* Interpret a (possibly wide) character constant in TOKEN.
PCHARS_SEEN points to a variable that is filled in with the number
of characters seen, and UNSIGNEDP to a variable that indicates
whether the result has signed type. */
cppchar_t
cpp_interpret_charconst (cpp_reader *pfile, const cpp_token *token,
unsigned int *pchars_seen, int *unsignedp)
{
cpp_string str = { 0, 0 };
Implement N4197 - Adding u8 character literals libcpp: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * include/cpplib.h (UTF8CHAR, UTF8CHAR_USERDEF): New cpp tokens; (struct cpp_options): Add utf8_char_literals. * init.c (struct lang_flags): Add utf8_char_literals; (struct lang_flags lang_defaults): Add column for utf8_char_literals. * macro.c (stringify_arg()): Treat CPP_UTF8CHAR token; * expr.c (cpp_userdef_char_remove_type(), cpp_userdef_char_add_type()): Treat CPP_UTF8CHAR_USERDEF, CPP_UTF8CHAR tokens; (cpp_userdef_char_p()): Treat CPP_UTF8CHAR_USERDEF token; (eval_token(), _cpp_parse_expr()): Treat CPP_UTF8CHAR token. * lex.c (lex_string(), _cpp_lex_direct()): Include CPP_UTF8CHAR tokens. * charset.c (converter_for_type(), cpp_interpret_charconst()): Treat CPP_UTF8CHAR token. gcc/c-family: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * c-family/c-ada-spec.c (print_ada_macros()): Treat CPP_UTF8CHAR like CPP_CHAR. * c-family/c-common.c (c_parse_error()): print CPP_UTF8CHAR and CPP_UTF8CHAR_USERDEF tokens. * c-family/c-lex.c (c_lex_with_flags()): Treat CPP_UTF8CHAR_USERDEF and CPP_UTF8CHAR tokens; (lex_charconst()): Treat CPP_UTF8CHAR token. gcc/cp: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * parser.c (cp_parser_primary_expression()): Treat CPP_UTF8CHAR and CPP_UTF8CHAR_USERDEF tokens; (cp_parser_parenthesized_expression_list()): Treat CPP_UTF8CHAR token. gcc/testsuite: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * g++.dg/cpp1z/utf8.C: New. * g++.dg/cpp1z/utf8-neg.C: New. * g++.dg/cpp1z/udlit-utf8char.C: New. From-SVN: r225185
2015-06-30 14:58:48 +02:00
bool wide = (token->type != CPP_CHAR && token->type != CPP_UTF8CHAR);
int u8 = 2 * int(token->type == CPP_UTF8CHAR);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
cppchar_t result;
Implement N4197 - Adding u8 character literals libcpp: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * include/cpplib.h (UTF8CHAR, UTF8CHAR_USERDEF): New cpp tokens; (struct cpp_options): Add utf8_char_literals. * init.c (struct lang_flags): Add utf8_char_literals; (struct lang_flags lang_defaults): Add column for utf8_char_literals. * macro.c (stringify_arg()): Treat CPP_UTF8CHAR token; * expr.c (cpp_userdef_char_remove_type(), cpp_userdef_char_add_type()): Treat CPP_UTF8CHAR_USERDEF, CPP_UTF8CHAR tokens; (cpp_userdef_char_p()): Treat CPP_UTF8CHAR_USERDEF token; (eval_token(), _cpp_parse_expr()): Treat CPP_UTF8CHAR token. * lex.c (lex_string(), _cpp_lex_direct()): Include CPP_UTF8CHAR tokens. * charset.c (converter_for_type(), cpp_interpret_charconst()): Treat CPP_UTF8CHAR token. gcc/c-family: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * c-family/c-ada-spec.c (print_ada_macros()): Treat CPP_UTF8CHAR like CPP_CHAR. * c-family/c-common.c (c_parse_error()): print CPP_UTF8CHAR and CPP_UTF8CHAR_USERDEF tokens. * c-family/c-lex.c (c_lex_with_flags()): Treat CPP_UTF8CHAR_USERDEF and CPP_UTF8CHAR tokens; (lex_charconst()): Treat CPP_UTF8CHAR token. gcc/cp: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * parser.c (cp_parser_primary_expression()): Treat CPP_UTF8CHAR and CPP_UTF8CHAR_USERDEF tokens; (cp_parser_parenthesized_expression_list()): Treat CPP_UTF8CHAR token. gcc/testsuite: 2015-06-30 Edward Smith-Rowland <3dw4rd@verizon.net> Implement N4197 - Adding u8 character literals * g++.dg/cpp1z/utf8.C: New. * g++.dg/cpp1z/utf8-neg.C: New. * g++.dg/cpp1z/udlit-utf8char.C: New. From-SVN: r225185
2015-06-30 14:58:48 +02:00
/* An empty constant will appear as L'', u'', U'', u8'', or '' */
if (token->val.str.len == (size_t) (2 + wide + u8))
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
{
cpp_error (pfile, CPP_DL_ERROR, "empty character constant");
*pchars_seen = 0;
*unsignedp = 0;
return 0;
}
else if (!cpp_interpret_string (pfile, &token->val.str, 1, &str,
token->type))
{
*pchars_seen = 0;
*unsignedp = 0;
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
return 0;
}
if (wide)
cpp-id-data.h (UC): Was U, conflicts with U... libcpp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * include/cpp-id-data.h (UC): Was U, conflicts with U... literal. * include/cpplib.h (CHAR16, CHAR32, STRING16, STRING32): New tokens. (struct cpp_options): Added uliterals. (cpp_interpret_string): Update prototype. (cpp_interpret_string_notranslate): Idem. * charset.c (init_iconv_desc): New width member in cset_converter. (cpp_init_iconv): Add support for char{16,32}_cset_desc. (convert_ucn): Idem. (emit_numeric_escape): Idem. (convert_hex): Idem. (convert_oct): Idem. (convert_escape): Idem. (converter_for_type): New function. (cpp_interpret_string): Use converter_for_type, support u and U prefix. (cpp_interpret_string_notranslate): Match changed prototype. (wide_str_to_charconst): Use converter_for_type. (cpp_interpret_charconst): Add support for CPP_CHAR{16,32}. * directives.c (linemarker_dir): Macro U changed to UC. (parse_include): Idem. (register_pragma_1): Idem. (restore_registered_pragmas): Idem. (get__Pragma_string): Support CPP_STRING{16,32}. * expr.c (eval_token): Support CPP_CHAR{16,32}. * init.c (struct lang_flags): Added uliterals. (lang_defaults): Idem. * internal.h (struct cset_converter) <width>: New field. (struct cpp_reader) <char16_cset_desc>: Idem. (struct cpp_reader) <char32_cset_desc>: Idem. * lex.c (digraph_spellings): Macro U changed to UC. (OP, TK): Idem. (lex_string): Add support for u'...', U'...', u... and U.... (_cpp_lex_direct): Idem. * macro.c (_cpp_builtin_macro_text): Macro U changed to UC. (stringify_arg): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * c-common.c (CHAR16_TYPE, CHAR32_TYPE): New macros. (fname_as_string): Match updated cpp_interpret_string prototype. (fix_string_type): Support char16_t* and char32_t*. (c_common_nodes_and_builtins): Add char16_t and char32_t (and derivative) nodes. Register as builtin if C++0x. (c_parse_error): Support CPP_CHAR{16,32}. * c-common.h (RID_CHAR16, RID_CHAR32): New elements. (enum c_tree_index) <CTI_CHAR16_TYPE, CTI_SIGNED_CHAR16_TYPE, CTI_UNSIGNED_CHAR16_TYPE, CTI_CHAR32_TYPE, CTI_SIGNED_CHAR32_TYPE, CTI_UNSIGNED_CHAR32_TYPE, CTI_CHAR16_ARRAY_TYPE, CTI_CHAR32_ARRAY_TYPE>: New elements. (char16_type_node, signed_char16_type_node, unsigned_char16_type_node, char32_type_node, signed_char32_type_node, char16_array_type_node, char32_array_type_node): New defines. * c-lex.c (cb_ident): Match updated cpp_interpret_string prototype. (c_lex_with_flags): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (lex_string): Support CPP_STRING{16,32}, match updated cpp_interpret_string and cpp_interpret_string_notranslate prototypes. (lex_charconst): Support CPP_CHAR{16,32}. * c-parser.c (c_parser_postfix_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. gcc/cp/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * cvt.c (type_promotes_to): Support char16_t and char32_t. * decl.c (grokdeclarator): Disallow signed/unsigned/short/long on char16_t and char32_t. * lex.c (reswords): Add char16_t and char32_t (for c++0x). * mangle.c (write_builtin_type): Mangle char16_t/char32_t as vendor extended builtin type u8char32_t. * parser.c (cp_lexer_next_token_is_decl_specifier_keyword): Support RID_CHAR{16,32}. (cp_lexer_print_token): Support CPP_STRING{16,32}. (cp_parser_is_string_literal): Idem. (cp_parser_string_literal): Idem. (cp_parser_primary_expression): Support CPP_CHAR{16,32} and CPP_STRING{16,32}. (cp_parser_simple_type_specifier): Support RID_CHAR{16,32}. * tree.c (char_type_p): Support char16_t and char32_t as char types. * typeck.c (string_conv_p): Support char16_t and char32_t. gcc/testsuite/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> Tests for char16_t and char32_t support. * g++.dg/ext/utf-cvt.C: New * g++.dg/ext/utf-cxx0x.C: New * g++.dg/ext/utf-cxx98.C: New * g++.dg/ext/utf-dflt.C: New * g++.dg/ext/utf-gnuxx0x.C: New * g++.dg/ext/utf-gnuxx98.C: New * g++.dg/ext/utf-mangle.C: New * g++.dg/ext/utf-typedef-cxx0x.C: New * g++.dg/ext/utf-typedef- * g++.dg/ext/utf-typespec.C: New * g++.dg/ext/utf16-1.C: New * g++.dg/ext/utf16-2.C: New * g++.dg/ext/utf16-3.C: New * g++.dg/ext/utf16-4.C: New * g++.dg/ext/utf32-1.C: New * g++.dg/ext/utf32-2.C: New * g++.dg/ext/utf32-3.C: New * g++.dg/ext/utf32-4.C: New * gcc.dg/utf-cvt.c: New * gcc.dg/utf-dflt.c: New * gcc.dg/utf16-1.c: New * gcc.dg/utf16-2.c: New * gcc.dg/utf16-3.c: New * gcc.dg/utf16-4.c: New * gcc.dg/utf32-1.c: New * gcc.dg/utf32-2.c: New * gcc.dg/utf32-3.c: New * gcc.dg/utf32-4.c: New libiberty/ChangeLog: 2008-04-14 Kris Van Hees <kris.van.hees@oracle.com> * testsuite/demangle-expected: Added tests for char16_t and char32_t. From-SVN: r134438
2008-04-18 15:58:08 +02:00
result = wide_str_to_charconst (pfile, str, pchars_seen, unsignedp,
token->type);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
else
result = narrow_str_to_charconst (pfile, str, pchars_seen, unsignedp,
token->type);
cpplib.h (CPP_AT_NAME, [...]): New token types. * cpplib.h (CPP_AT_NAME, CPP_OBJC_STRING): New token types. (struct cpp_options): Add narrow_charset, wide_charset, bytes_big_endian fields. Remove EBCDIC field. (cpp_init_iconv, cpp_interpret_string): New external interfaces. * cpphash.h: Include <iconv.h> if we have it, otherwise provide a dummy definition of iconv_t. (struct cpp_reader): Add narrow_cset_desc and wide_cset_desc fields. (_cpp_valid_ucn): Update prototype. (_cpp_destroy_iconv): New prototype. * doc/cpp.texi: Document character set handling. * doc/cppopts.texi: Document -fexec-charset= and -fexec-wide-charset=. * doc/extend.texi: Delete entire section on multiline strings. Rewrite section on __FUNCTION__ etc now that these are variables in C. * cppucnid.tab, cppucnid.pl: New files. * cppucnid.h: New generated file. * cppcharset.c: Include cppucnid.h. Lots of commentary added. (iconv_open, iconv, iconv_close): Provide dummy definitions if !HAVE_ICONV. (SOURCE_CHARSET, struct strbuf, init_iconv_desc, cpp_init_iconv, _cpp_destroy_iconv, convert_cset, width_to_mask, convert_ucn, emit_numeric_escape, convert_hex, convert_oct, convert_escape, cpp_interpret_string, narrow_str_to_charconst, wide_str_to_charconst): New. (ucn_valid_in_identifier): Use a binary search through the ucnranges table defined in cppucnid.h, not a long chain of if statements. (_cpp_valid_ucn): Add a limit pointer. Downgrade "universal character names are only valid in C++ and C99" to a warning. Issue the "meaning of \[uU] is different in traditional C" warning here. Take care not to let iconv see an invalid UCS value if we get a malformed UCN. Issue an error if we don't have iconv. (cpp_interpret_charconst): Moved here from cpplex.c. Use cpp_interpret_string to do the heavy lifting. * cppinit.c (cpp_create_reader): Initialize bytes_big_endian, narrow_charset, wide_charset fields of options structure. (cpp_destroy): Call _cpp_destroy_iconv. * cpplex.c (forms_identifier_p): Adjust call to _cpp_valid_ucn. (maybe_read_ucn, hex_digit_value, cpp_parse_escape): Delete. (cpp_interpret_charconst): Moved to cppcharset.c. * cpplib.c (dequote_string): Delete. (interpret_string_notranslate): New. (do_line, do_linemarker): Use interpret_string_notranslate. * Makefile.in (cppcharset.o): Depend on cppucnid.h. * c-common.c (fname_string, combine_strings): Delete. * c-common.h (fname_string, combine_strings): Delete prototypes. * c-lex.c (ignore_escape_flag): Delete. (cb_ident): Use cpp_interpret_string, not lex_string. (get_nonpadding_token): New function. (c_lex): Handle Objective-C @-prefixed identifiers and strings here. Adjust calls to lex_string. Don't write *value twice. (lex_string): Now handles string constant concatenation. Most of the work handed off to cpp_interpret_string. Call fix_string_type here. * c-parse.in (STRING_FUNC_NAME, VAR_FUNC_NAME): Replace with FUNC_NAME, throughout. (OBJC_STRING): New token type. (primary:STRING): No need to call fix_string_type here. (primary:objc_string): Make that OBJC_STRING. (objc_string nonterminal): Delete. (yylexname): Delete code to handle fake string constants. (yylexstring): Delete entirely. (_yylex): Handle CPP_AT_NAME and CPP_OBJC_STRING. No need to handle CPP_ATSIGN. * c.opt (-fexec-charset=, -fwide-exec-charset=): New options. * c-opts.c (missing_arg, c_common_handle_option): Handle OPT_fexec_charset_ and OPT_fwide_exec_charset_. (c_common_init): Set cpp_opts->bytes_big_endian, not cpp_opts->EBCDIC. Call cpp_init_iconv. (print_help): Document -fexec-charset= and -fexec-wide-charset=. (TARGET_EBCDIC): Delete default definition. * objc/objc-act.c (build_objc_string_object): No need to handle string constant concatenation. cp: * parser.c (cp_lexer_read_token): No need to handle string constant concatenation. testsuite: * gcc.c-torture/execute/wchar_t-1.x: New file; XFAIL wchar_t-1.c everywhere. * gcc.dg/concat.c: Concatenation of string constants with __FUNCTION__ / __PRETTY_FUNCTION__ is now a hard error. * gcc.dg/wtr-strcat-1.c: Loosen dg-warning regexp. * gcc.dg/cpp/escape-2.c: Use wide character constants where necessary to avoid multi-character character constant warning. * gcc.dg/cpp/escape.c: Likewise. * gcc.dg/cpp/ucs.c: Likewise. Remove backslashes from dg-bogus comments, as they confuse Tcl. Fix a typo. libstdc++-v3: * testsuite/22_locale/collate/compare/wchar_t/2.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/hash/wchar_t/2.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc * testsuite/22_locale/collate/transform/wchar_t/2.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: XFAIL on all targets. From-SVN: r68952
2003-07-05 02:24:00 +02:00
if (str.text != token->val.str.text)
free ((void *)str.text);
return result;
}
/* Convert an identifier denoted by ID and LEN, which might contain
Support extended characters in C/C++ identifiers (PR c/67224) libcpp/ChangeLog 2019-09-19 Lewis Hyatt <lhyatt@gmail.com> PR c/67224 * charset.c (_cpp_valid_utf8): New function to help lex UTF-8 tokens. * internal.h (_cpp_valid_utf8): Declare. * lex.c (forms_identifier_p): Use it to recognize UTF-8 identifiers. (_cpp_lex_direct): Handle UTF-8 in identifiers and CPP_OTHER tokens. Do all work in "default" case to avoid slowing down typical code paths. Also handle $ and UCN in the default case for consistency. gcc/Changelog 2019-09-19 Lewis Hyatt <lhyatt@gmail.com> PR c/67224 * doc/cpp.texi: Document support for extended characters in identifiers. * doc/cppopts.texi: Likewise. gcc/testsuite/ChangeLog 2019-09-19 Lewis Hyatt <lhyatt@gmail.com> PR c/67224 * c-c++-common/cpp/ucnid-2011-1-utf8.c: New test. * g++.dg/cpp/ucnid-1-utf8.C: New test. * g++.dg/cpp/ucnid-2-utf8.C: New test. * g++.dg/cpp/ucnid-3-utf8.C: New test. * g++.dg/cpp/ucnid-4-utf8.C: New test. * g++.dg/other/ucnid-1-utf8.C: New test. * gcc.dg/cpp/ucnid-1-utf8.c: New test. * gcc.dg/cpp/ucnid-10-utf8.c: New test. * gcc.dg/cpp/ucnid-11-utf8.c: New test. * gcc.dg/cpp/ucnid-12-utf8.c: New test. * gcc.dg/cpp/ucnid-13-utf8.c: New test. * gcc.dg/cpp/ucnid-14-utf8.c: New test. * gcc.dg/cpp/ucnid-15-utf8.c: New test. * gcc.dg/cpp/ucnid-2-utf8.c: New test. * gcc.dg/cpp/ucnid-3-utf8.c: New test. * gcc.dg/cpp/ucnid-4-utf8.c: New test. * gcc.dg/cpp/ucnid-6-utf8.c: New test. * gcc.dg/cpp/ucnid-7-utf8.c: New test. * gcc.dg/cpp/ucnid-9-utf8.c: New test. * gcc.dg/ucnid-1-utf8.c: New test. * gcc.dg/ucnid-10-utf8.c: New test. * gcc.dg/ucnid-11-utf8.c: New test. * gcc.dg/ucnid-12-utf8.c: New test. * gcc.dg/ucnid-13-utf8.c: New test. * gcc.dg/ucnid-14-utf8.c: New test. * gcc.dg/ucnid-15-utf8.c: New test. * gcc.dg/ucnid-16-utf8.c: New test. * gcc.dg/ucnid-2-utf8.c: New test. * gcc.dg/ucnid-3-utf8.c: New test. * gcc.dg/ucnid-4-utf8.c: New test. * gcc.dg/ucnid-5-utf8.c: New test. * gcc.dg/ucnid-6-utf8.c: New test. * gcc.dg/ucnid-7-utf8.c: New test. * gcc.dg/ucnid-8-utf8.c: New test. * gcc.dg/ucnid-9-utf8.c: New test. From-SVN: r275979
2019-09-19 21:56:11 +02:00
UCN escapes or UTF-8 multibyte chars, to the source character set,
either UTF-8 or UTF-EBCDIC. Assumes that the identifier is actually
a valid identifier. */
cpp_hashnode *
_cpp_interpret_identifier (cpp_reader *pfile, const uchar *id, size_t len)
{
/* It turns out that a UCN escape always turns into fewer characters
than the escape itself, so we can allocate a temporary in advance. */
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
uchar * buf = (uchar *) alloca (len + 1);
uchar * bufp = buf;
size_t idp;
for (idp = 0; idp < len; idp++)
if (id[idp] != '\\')
*bufp++ = id[idp];
else
{
unsigned length = id[idp+1] == 'u' ? 4 : 8;
cppchar_t value = 0;
size_t bufleft = len - (bufp - buf);
int rval;
idp += 2;
while (length && idp < len && ISXDIGIT (id[idp]))
{
value = (value << 4) + hex_value (id[idp]);
idp++;
length--;
}
idp--;
/* Special case for EBCDIC: if the identifier contains
a '$' specified using a UCN, translate it to EBCDIC. */
if (value == 0x24)
{
*bufp++ = '$';
continue;
}
rval = one_cppchar_to_utf8 (value, &bufp, &bufleft);
if (rval)
{
errno = rval;
cpp_errno (pfile, CPP_DL_ERROR,
"converting UCN to source character set");
break;
}
}
return CPP_HASHNODE (ht_lookup (pfile->hash_table,
buf, bufp - buf, HT_ALLOC));
}
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
/* Utility to strip a UTF-8 byte order marking from the beginning
of a buffer. Returns the number of bytes to skip, which currently
will be either 0 or 3. */
int
cpp_check_utf8_bom (const char *data, size_t data_length)
{
#if HOST_CHARSET == HOST_CHARSET_ASCII
const unsigned char *udata = (const unsigned char *) data;
if (data_length >= 3 && udata[0] == 0xef && udata[1] == 0xbb
&& udata[2] == 0xbf)
return 3;
#endif
return 0;
}
/* Convert an input buffer (containing the complete contents of one
source file) from INPUT_CHARSET to the source character set. INPUT
points to the input buffer, SIZE is its allocated size, and LEN is
the length of the meaningful data within the buffer. The
translated buffer is returned, *ST_SIZE is set to the length of
the meaningful data within the translated buffer, and *BUFFER_START
is set to the start of the returned buffer. *BUFFER_START may
differ from the return value in the case of a BOM or other ignored
marker information.
INPUT is expected to have been allocated with xmalloc. This
function will either set *BUFFER_START to INPUT, or free it and set
*BUFFER_START to a pointer to another xmalloc-allocated block of
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
memory.
PFILE is only used to generate diagnostics; setting it to NULL suppresses
diagnostics, and causes a return of NULL if there was any error instead. */
uchar *
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
_cpp_convert_input (cpp_reader *pfile, const char *input_charset,
uchar *input, size_t size, size_t len,
const unsigned char **buffer_start, off_t *st_size)
{
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
struct cset_converter input_cset;
struct _cpp_strbuf to;
unsigned char *buffer;
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
input_cset = init_iconv_desc (pfile, SOURCE_CHARSET, input_charset);
if (input_cset.func == convert_no_conversion)
{
to.text = input;
to.asize = size;
to.len = len;
}
else
{
to.asize = MAX (65536, len);
configure.ac: Check declarations for asprintf and vasprintf. * configure.ac: Check declarations for asprintf and vasprintf. * config.in: Regenerate. * configure: Likewise. * charset.c (conversion_loop): Use XRESIZEVEC. (convert_no_conversion): Likewise. (convert_using_iconv): Likewise. (init_iconv_desc): Cast return value of alloca. (cpp_host_to_exec_charset): Use XNEWVEC. (emit_numeric_escape): Use XRESIZEVEC. (cpp_interpret_string): Use XNEWVEC. (cpp_interpret_string): Use XRESIZEVEC. (_cpp_interpret_identifier): Cast return value of alloca. (_cpp_convert_input): Use XNEWVEC and XRESIZEVEC. * directives.c (glue_header_name): Use XNEWVEC and XRESIZEVEC. (parse_include): Use XNEWVEC. (insert_pragma_entry): Rename local variable "new" to "new_entry". (save_registered_pragmas): Cast return value of xmemdup. (destringize_and_run): Same for alloca. (parse_assertion): Likewise. (do_assert): Cast allocated storage to proper type. (cpp_define): Likewise. (_cpp_define_builtin): Likewise. (cpp_undef): Likewise. (handle_assertion): Likewise. (cpp_push_buffer): Rename local variable "new" to "new_buffer". * expr.c (CPP_UPLUS): Cast value to type cpp_ttype. (CPP_UMINUS): Likewise. (struct cpp_operator): Rename from struct operator. (_cpp_expand_op_stack): Use XRESIZEVEC. * files.c (pch_open_file): Use XNEWVEC. (pch_open_file): Use XRESIZEVEC. (read_file_guts): Use XNEWVEC and XRESIZEVEC. (dir_name_of_file): Use XNEWVEC. (make_cpp_file): Use XCNEW. (make_cpp_dir): Likewise. (allocate_file_hash_entries): USE XNEWVEC. (cpp_included): Cast return value of htab_find_with_hash. (append_file_to_dir): Use XNEWVEC. (read_filename_string): Likewise. Use XRESIZEVEC too. (read_name_map): Cast return value of alloca. Use XRESIZEVEC. (remap_filename): Use XNEWVEC. (struct pchf_entry): Move definition out of struct pchf_data. (_cpp_save_file_entries): Use XCNEWVAR. (_cpp_read_file_entries): Use XNEWVAR. * identifiers.c (alloc_node): Use XOBNEW. * init.c (cpp_create_reader): Use XCNEW. (cpp_init_builtins): Cast of b->value to enum builtin_type. (read_original_directory): Cast return value of alloca. * lex.c (add_line_note): Use XRESIZEVEC. (warn_about_normalization): Use XNEWVEC. (_cpp_lex_direct): Cast node->directive_index to (enum cpp_ttype). (new_buff): Use XNEWVEC. * line-map.c (linemap_add): Use XRESIZEVEC. * macro.c (builtin_macro): Cast return value of alloca. (paste_tokens): Likewise. (expand_arg): Use XNEWVEC and XRESIZEVEC. (_cpp_save_parameter): Use XRESIZEVEC. (create_iso_definition): Cast allocated storage to proper type. (_cpp_create_definition): Likewise. (cpp_macro_definition): Use XRESIZEVEC. * makedepend.c (add_clm): Use XNEW. (add_dir): Likewise. * mkdeps.c (munge): Use XNEWVEC. (deps_init): Use XCNEW. (deps_add_target): Use XRESIZEVEC. (deps_add_default_target): Cast return value of alloca. (deps_add_dep): Use XRESIZEVEC. (deps_add_vpath): Likewise. Use XNEWVEC too. (deps_restore): Likewise. * pch.c (save_idents): Use XNEW and XNEWVEC. (cpp_save_state): Use XNEW. (count_defs): Cast return value of htab_find. (write_defs): Likewise. (cpp_write_pch_deps): Use XNEWVEC. (collect_ht_nodes): Use XRESIZEVEC. (cpp_valid_state): Use XNEWVEC. (save_macros): Use XRESIZEVEC. Cast return value of xmemdup. * symtab.c (ht_create): Use XCNEW. (ht_lookup_with_hash): Cast return value of obstack_copy0. (ht_expand): Use XCNEWVEC. * system.h (HAVE_DESIGNATED_INITIALIZERS): False if __cplusplus. (bool): Do not define if __cplusplus. From-SVN: r100295
2005-05-28 17:52:48 +02:00
to.text = XNEWVEC (uchar, to.asize);
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
to.len = 0;
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
const bool ok = APPLY_CONVERSION (input_cset, input, len, &to);
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
free (input);
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
/* Clean up the mess. */
if (input_cset.func == convert_using_iconv)
iconv_close (input_cset.cd);
/* Handle conversion failure. */
if (!ok)
{
if (!pfile)
{
XDELETEVEC (to.text);
*buffer_start = NULL;
*st_size = 0;
return NULL;
}
cpp_error (pfile, CPP_DL_ERROR, "failure to convert %s to %s",
input_charset, SOURCE_CHARSET);
}
}
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
/* Resize buffer if we allocated substantially too much, or if we
haven't enough space for the \n-terminator or following
15 bytes of padding (used to quiet warnings from valgrind or
Address Sanitizer, when the optimized lexer accesses aligned
16-byte memory chunks, including the bytes after the malloced,
area, and stops lexing on '\n'). */
if (to.len + 4096 < to.asize || to.len + 16 > to.asize)
to.text = XRESIZEVEC (uchar, to.text, to.len + 16);
memset (to.text + to.len, '\0', 16);
/* If the file is using old-school Mac line endings (\r only),
terminate with another \r, not an \n, so that we do not mistake
the \r\n sequence for a single DOS line ending and erroneously
issue the "No newline at end of file" diagnostic. */
if (to.len && to.text[to.len - 1] == '\r')
to.text[to.len] = '\r';
else
to.text[to.len] = '\n';
buffer = to.text;
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
*st_size = to.len;
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
/* Ignore a UTF-8 BOM if we see one and the source charset is UTF-8. Note
that glib'c UTF-8 iconv() provider (as of glibc 2.7) does not ignore a
BOM -- however, even if it did, we would still need this code due
to the 'convert_no_conversion' case. */
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
const int bom_len = cpp_check_utf8_bom ((const char *) to.text, to.len);
*st_size -= bom_len;
buffer += bom_len;
*buffer_start = to.text;
return buffer;
}
/* Decide on the default encoding to assume for input files. */
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
const char *
_cpp_default_encoding (void)
{
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
const char *current_encoding = NULL;
Makefile.def (host_modules): add libcpp. ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Makefile.def (host_modules): add libcpp. * Makefile.tpl: Add dependencies on and for libcpp. * Makefile.in: Regenerate. * configure.in: Add libcpp host module. * configure: Regenerate. config/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * acx.m4 (ACX_HEADER_STDBOOL, ACX_HEADER_STRING): From gcc. gcc/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Move libcpp to the toplevel. * Makefile.in: Remove references to libcpp files, use CPPLIBS instead of libcpp.a. Define SYMTAB_H and change hashtable.h to that. * aclocal.m4 (gcc_AC_HEADER_STDBOOL, gcc_AC_HEADER_STRING, gcc_AC_C__BOOL): Remove. * configure.ac (gcc_AC_C__BOOL, HAVE_UCHAR): Remove tests. * configure: Regenerate. * config.in: Regenerate. * c-ppoutput.c: Include ../libcpp/internal.h instead of cpphash.h. * cppcharset.c: Removed. * cpperror.c: Removed. * cppexp.c: Removed. * cppfiles.c: Removed. * cpphash.c: Removed. * cpphash.h: Removed. * cppinit.c: Removed. * cpplex.c: Removed. * cpplib.c: Removed. * cpplib.h: Removed. * cppmacro.c: Removed. * cpppch.c: Removed. * cpptrad.c: Removed. * cppucnid.h: Removed. * cppucnid.pl: Removed. * cppucnid.tab: Removed. * hashtable.c: Removed. * hashtable.h: Removed. * line-map.c: Removed. * line-map.h: Removed. * mkdeps.c: Removed. * mkdeps.h: Removed. * stringpool.h: Include symtab.h instead of hashtable.h. * tree.h: Include symtab.h instead of hashtable.h. * system.h (O_NONBLOCK, O_NOCTTY): Do not define. gcc/cp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: No need to specify $(LIBCPP). gcc/java/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: Link in $(LIBCPP) instead of mkdeps.o. libcpp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Moved libcpp from the gcc subdirectory to the toplevel. * Makefile.am: New file. * Makefile.in: Regenerate. * configure.ac: New file. * configure: Regenerate. * config.in: Regenerate. * charset.c: Moved from gcc/cppcharset.c. Add note about brokenness of input charset detection. Adjust for change in name of cppucnid.h. * errors.c: Moved from gcc/cpperror.c. Do not include intl.h. * expr.c: Moved from gcc/cppexp.c. * files.c: Moved from gcc/cppfiles.c. Do not include intl.h. Remove #define of O_BINARY, it is in system.h. * identifiers.c: Moved from gcc/cpphash.c. * internal.h: Moved from gcc/cpphash.h. Change header guard name. All other files adjusted to match name change. * init.c: Moved from gcc/cppinit.c. (init_library) [ENABLE_NLS]: Call bindtextdomain. * lex.c: Moved from gcc/cpplex.c. * directives.c: Moved from gcc/cpplib.c. * macro.c: Moved from gcc/cppmacro.c. * pch.c: Moved from gcc/cpppch.c. Do not include intl.h. * traditional.c: Moved from gcc/cpptrad.c. * ucnid.h: Moved from gcc/cppucnid.h. Change header guard name. * ucnid.pl: Moved from gcc/cppucnid.pl. * ucnid.tab: Moved from gcc/cppucnid.tab. Change header guard name. * symtab.c: Moved from gcc/hashtable.c. * line-map.c: Moved from gcc. Do not include intl.h. * mkdeps.c: Moved from gcc. * system.h: New file. libcpp/include/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * cpplib.h: Moved from gcc. Change header guard name. * line-map.h: Moved from gcc. Change header guard name. * mkdeps.h: Moved from gcc. Change header guard name. * symtab.h: Moved from gcc/hashtable.h. Change header guard name. libcpp/po/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * be.po: Extracted from gcc/po/be.po. * ca.po: Extracted from gcc/po/ca.po. * da.po: Extracted from gcc/po/da.po. * de.po: Extracted from gcc/po/de.po. * el.po: Extracted from gcc/po/el.po. * es.po: Extracted from gcc/po/es.po. * fr.po: Extracted from gcc/po/fr.po. * ja.po: Extracted from gcc/po/ja.po. * nl.po: Extracted from gcc/po/nl.po. * sv.po: Extracted from gcc/po/sv.po. * tr.po: Extracted from gcc/po/tr.po. From-SVN: r82199
2004-05-24 12:50:45 +02:00
/* We disable this because the default codeset is 7-bit ASCII on
most platforms, and this causes conversion failures on every
file in GCC that happens to have one of the upper 128 characters
in it -- most likely, as part of the name of a contributor.
We should definitely recognize in-band markers of file encoding,
like:
- the appropriate Unicode byte-order mark (FE FF) to recognize
UTF16 and UCS4 (in both big-endian and little-endian flavors)
and UTF8
Makefile.am: Add makedepend. libcpp: * Makefile.am: Add makedepend. * Makefile.in, aclocal.m4: Regenerate. * charset.c: Insert a space to avoid a warning. * directives.c: Include mkdeps.h. (_cpp_handle_directive): Reenable macro expander if appropriate. (undefine_macros): Inline body of _cpp_free_definition for speed. Do not call undef callback or _cpp_warn_if_unused_macro. (cpp_get_deps): New interface. * files.c (search_cache): Add pfile argument. Check for file that would be found by "" or <> search here... (_cpp_find_file): ...not here. Correct recorded start_dir of files found by directory-of-current-file search that would be found by "" or <> search. * init.c (cpp_add_dependency_target): Delete. * internal.h (struct lexer_state): Add discarding_output flag. * lex.c (lex_identifier): Compute hash function while scanning. * macro.c (cpp_scan_nooutput): Disable macro expansion outside directives. * makedepend.c: New file. * mkdeps.c (struct deps): Add vpath vector. (apply_vpath, deps_add_vpath): New function. (deps_free): Free vpath vector. (deps_add_dep, deps_add_target): Use apply_vpath. * symtab.c (calc_hash): Use HT_HASHSTEP and HT_FINISH. (ht_lookup_with_hash): New function. * cpplib.h, mkdeps.h: Update prototypes. * symtab.h: Update prototypes. (HT_HASHSTEP, HT_FINISH): New macros. gcc: * Makefile.in (MKDEPS_H): New shorthand. (c-opts.o): Update dependencies. * c-opts.c: Include mkdeps.h. (handle_deferred_opts): Use cpp_get_deps and deps_add_target, not cpp_add_dependency_target. From-SVN: r82654
2004-06-05 22:58:06 +02:00
- a "#i", "#d", "/ *", "//", " #p" or "#p" (for #pragma) to
Makefile.def (host_modules): add libcpp. ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Makefile.def (host_modules): add libcpp. * Makefile.tpl: Add dependencies on and for libcpp. * Makefile.in: Regenerate. * configure.in: Add libcpp host module. * configure: Regenerate. config/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * acx.m4 (ACX_HEADER_STDBOOL, ACX_HEADER_STRING): From gcc. gcc/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Move libcpp to the toplevel. * Makefile.in: Remove references to libcpp files, use CPPLIBS instead of libcpp.a. Define SYMTAB_H and change hashtable.h to that. * aclocal.m4 (gcc_AC_HEADER_STDBOOL, gcc_AC_HEADER_STRING, gcc_AC_C__BOOL): Remove. * configure.ac (gcc_AC_C__BOOL, HAVE_UCHAR): Remove tests. * configure: Regenerate. * config.in: Regenerate. * c-ppoutput.c: Include ../libcpp/internal.h instead of cpphash.h. * cppcharset.c: Removed. * cpperror.c: Removed. * cppexp.c: Removed. * cppfiles.c: Removed. * cpphash.c: Removed. * cpphash.h: Removed. * cppinit.c: Removed. * cpplex.c: Removed. * cpplib.c: Removed. * cpplib.h: Removed. * cppmacro.c: Removed. * cpppch.c: Removed. * cpptrad.c: Removed. * cppucnid.h: Removed. * cppucnid.pl: Removed. * cppucnid.tab: Removed. * hashtable.c: Removed. * hashtable.h: Removed. * line-map.c: Removed. * line-map.h: Removed. * mkdeps.c: Removed. * mkdeps.h: Removed. * stringpool.h: Include symtab.h instead of hashtable.h. * tree.h: Include symtab.h instead of hashtable.h. * system.h (O_NONBLOCK, O_NOCTTY): Do not define. gcc/cp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: No need to specify $(LIBCPP). gcc/java/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: Link in $(LIBCPP) instead of mkdeps.o. libcpp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Moved libcpp from the gcc subdirectory to the toplevel. * Makefile.am: New file. * Makefile.in: Regenerate. * configure.ac: New file. * configure: Regenerate. * config.in: Regenerate. * charset.c: Moved from gcc/cppcharset.c. Add note about brokenness of input charset detection. Adjust for change in name of cppucnid.h. * errors.c: Moved from gcc/cpperror.c. Do not include intl.h. * expr.c: Moved from gcc/cppexp.c. * files.c: Moved from gcc/cppfiles.c. Do not include intl.h. Remove #define of O_BINARY, it is in system.h. * identifiers.c: Moved from gcc/cpphash.c. * internal.h: Moved from gcc/cpphash.h. Change header guard name. All other files adjusted to match name change. * init.c: Moved from gcc/cppinit.c. (init_library) [ENABLE_NLS]: Call bindtextdomain. * lex.c: Moved from gcc/cpplex.c. * directives.c: Moved from gcc/cpplib.c. * macro.c: Moved from gcc/cppmacro.c. * pch.c: Moved from gcc/cpppch.c. Do not include intl.h. * traditional.c: Moved from gcc/cpptrad.c. * ucnid.h: Moved from gcc/cppucnid.h. Change header guard name. * ucnid.pl: Moved from gcc/cppucnid.pl. * ucnid.tab: Moved from gcc/cppucnid.tab. Change header guard name. * symtab.c: Moved from gcc/hashtable.c. * line-map.c: Moved from gcc. Do not include intl.h. * mkdeps.c: Moved from gcc. * system.h: New file. libcpp/include/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * cpplib.h: Moved from gcc. Change header guard name. * line-map.h: Moved from gcc. Change header guard name. * mkdeps.h: Moved from gcc. Change header guard name. * symtab.h: Moved from gcc/hashtable.h. Change header guard name. libcpp/po/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * be.po: Extracted from gcc/po/be.po. * ca.po: Extracted from gcc/po/ca.po. * da.po: Extracted from gcc/po/da.po. * de.po: Extracted from gcc/po/de.po. * el.po: Extracted from gcc/po/el.po. * es.po: Extracted from gcc/po/es.po. * fr.po: Extracted from gcc/po/fr.po. * ja.po: Extracted from gcc/po/ja.po. * nl.po: Extracted from gcc/po/nl.po. * sv.po: Extracted from gcc/po/sv.po. * tr.po: Extracted from gcc/po/tr.po. From-SVN: r82199
2004-05-24 12:50:45 +02:00
distinguish ASCII and EBCDIC.
- now we can parse something like "#pragma GCC encoding <xyz>
on the first line, or even Emacs/VIM's mode line tags (there's
a problem here in that VIM uses the last line, and Emacs has
its more elaborate "local variables" convention).
Makefile.def (host_modules): add libcpp. ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Makefile.def (host_modules): add libcpp. * Makefile.tpl: Add dependencies on and for libcpp. * Makefile.in: Regenerate. * configure.in: Add libcpp host module. * configure: Regenerate. config/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * acx.m4 (ACX_HEADER_STDBOOL, ACX_HEADER_STRING): From gcc. gcc/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Move libcpp to the toplevel. * Makefile.in: Remove references to libcpp files, use CPPLIBS instead of libcpp.a. Define SYMTAB_H and change hashtable.h to that. * aclocal.m4 (gcc_AC_HEADER_STDBOOL, gcc_AC_HEADER_STRING, gcc_AC_C__BOOL): Remove. * configure.ac (gcc_AC_C__BOOL, HAVE_UCHAR): Remove tests. * configure: Regenerate. * config.in: Regenerate. * c-ppoutput.c: Include ../libcpp/internal.h instead of cpphash.h. * cppcharset.c: Removed. * cpperror.c: Removed. * cppexp.c: Removed. * cppfiles.c: Removed. * cpphash.c: Removed. * cpphash.h: Removed. * cppinit.c: Removed. * cpplex.c: Removed. * cpplib.c: Removed. * cpplib.h: Removed. * cppmacro.c: Removed. * cpppch.c: Removed. * cpptrad.c: Removed. * cppucnid.h: Removed. * cppucnid.pl: Removed. * cppucnid.tab: Removed. * hashtable.c: Removed. * hashtable.h: Removed. * line-map.c: Removed. * line-map.h: Removed. * mkdeps.c: Removed. * mkdeps.h: Removed. * stringpool.h: Include symtab.h instead of hashtable.h. * tree.h: Include symtab.h instead of hashtable.h. * system.h (O_NONBLOCK, O_NOCTTY): Do not define. gcc/cp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: No need to specify $(LIBCPP). gcc/java/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * Make-lang.in: Link in $(LIBCPP) instead of mkdeps.o. libcpp/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> Moved libcpp from the gcc subdirectory to the toplevel. * Makefile.am: New file. * Makefile.in: Regenerate. * configure.ac: New file. * configure: Regenerate. * config.in: Regenerate. * charset.c: Moved from gcc/cppcharset.c. Add note about brokenness of input charset detection. Adjust for change in name of cppucnid.h. * errors.c: Moved from gcc/cpperror.c. Do not include intl.h. * expr.c: Moved from gcc/cppexp.c. * files.c: Moved from gcc/cppfiles.c. Do not include intl.h. Remove #define of O_BINARY, it is in system.h. * identifiers.c: Moved from gcc/cpphash.c. * internal.h: Moved from gcc/cpphash.h. Change header guard name. All other files adjusted to match name change. * init.c: Moved from gcc/cppinit.c. (init_library) [ENABLE_NLS]: Call bindtextdomain. * lex.c: Moved from gcc/cpplex.c. * directives.c: Moved from gcc/cpplib.c. * macro.c: Moved from gcc/cppmacro.c. * pch.c: Moved from gcc/cpppch.c. Do not include intl.h. * traditional.c: Moved from gcc/cpptrad.c. * ucnid.h: Moved from gcc/cppucnid.h. Change header guard name. * ucnid.pl: Moved from gcc/cppucnid.pl. * ucnid.tab: Moved from gcc/cppucnid.tab. Change header guard name. * symtab.c: Moved from gcc/hashtable.c. * line-map.c: Moved from gcc. Do not include intl.h. * mkdeps.c: Moved from gcc. * system.h: New file. libcpp/include/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * cpplib.h: Moved from gcc. Change header guard name. * line-map.h: Moved from gcc. Change header guard name. * mkdeps.h: Moved from gcc. Change header guard name. * symtab.h: Moved from gcc/hashtable.h. Change header guard name. libcpp/po/ChangeLog: 2004-05-23 Paolo Bonzini <bonzini@gnu.org> * be.po: Extracted from gcc/po/be.po. * ca.po: Extracted from gcc/po/ca.po. * da.po: Extracted from gcc/po/da.po. * de.po: Extracted from gcc/po/de.po. * el.po: Extracted from gcc/po/el.po. * es.po: Extracted from gcc/po/es.po. * fr.po: Extracted from gcc/po/fr.po. * ja.po: Extracted from gcc/po/ja.po. * nl.po: Extracted from gcc/po/nl.po. * sv.po: Extracted from gcc/po/sv.po. * tr.po: Extracted from gcc/po/tr.po. From-SVN: r82199
2004-05-24 12:50:45 +02:00
- investigate whether Java has another common convention, which
would be friendly to support.
(Zack Weinberg and Paolo Bonzini, May 20th 2004) */
#if defined (HAVE_LOCALE_H) && defined (HAVE_LANGINFO_CODESET) && 0
[multiple changes] 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * c-opts.c (c_common_handle_option): Add -finput-charset. * c.opt: Ditto. * cppcharset.c (one_iso88591_to_utf8): Remove. (convert_iso88591_utf8): Ditto. (conversion_tab): Remove 8859-1 converter. (_cpp_input_to_utf8): Remove. (_cpp_init_iconv_buffer): Ditto. (_cpp_close_iconv_buffer): Ditto. (_cpp_convert_input): New function. (_cpp_default_encoding): Ditto. * cpphash.h: Add/remove prototypes for above. * cppfiles.c (read_file_guts): Use _cpp_convert_input. * cppinit.c (cpp_create_reader): Use _cpp_default_encoding for narrow execution and input character sets. * cpplib.c (cpp_push_buffer): Delete uses of removed functions. * doc/cppopts.texi: Document -finput-charset. 2004-02-02 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * gcc.c-torture/execute/wchar_t-1.c: Add -finput-charset. 2004-01-29 Eric Christopher <echristo@redhat.com> Zack Weinberg <zack@codesourcery.com> * testsuite/22_locale/collate/compare/wchar_t/2.cc: Remove xfail. Use -finput-charset. * testsuite/22_locale/collate/compare/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/compare/wchar_t/wrapped_locale.cc: Ditto * testsuite/22_locale/collate/hash/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/hash/wchar_t/wrapped_locale.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/2.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_env.cc: Ditto. * testsuite/22_locale/collate/transform/wchar_t/wrapped_locale.cc: Ditto. From-SVN: r77136
2004-02-02 21:20:58 +01:00
setlocale (LC_CTYPE, "");
current_encoding = nl_langinfo (CODESET);
#endif
if (current_encoding == NULL || *current_encoding == '\0')
current_encoding = SOURCE_CHARSET;
return current_encoding;
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
diagnostics: Support for -finput-charset [PR93067] Adds the logic to handle -finput-charset in layout_get_source_line(), so that source lines are converted from their input encodings prior to being output by diagnostics machinery. Also adds the ability to strip a UTF-8 BOM similarly. gcc/c-family/ChangeLog: PR other/93067 * c-opts.c (c_common_input_charset_cb): New function. (c_common_post_options): Call new function diagnostic_initialize_input_context(). gcc/d/ChangeLog: PR other/93067 * d-lang.cc (d_input_charset_callback): New function. (d_init): Call new function diagnostic_initialize_input_context(). gcc/fortran/ChangeLog: PR other/93067 * cpp.c (gfc_cpp_post_options): Call new function diagnostic_initialize_input_context(). gcc/ChangeLog: PR other/93067 * coretypes.h (typedef diagnostic_input_charset_callback): Declare. * diagnostic.c (diagnostic_initialize_input_context): New function. * diagnostic.h (diagnostic_initialize_input_context): Declare. * input.c (default_charset_callback): New function. (file_cache::initialize_input_context): New function. (file_cache_slot::create): Added ability to convert the input according to the input context. (file_cache::file_cache): Initialize the new input context. (class file_cache_slot): Added new m_alloc_offset member. (file_cache_slot::file_cache_slot): Initialize the new member. (file_cache_slot::~file_cache_slot): Handle potentially offset buffer. (file_cache_slot::maybe_grow): Likewise. (file_cache_slot::needs_read_p): Handle NULL fp, which is now possible. (file_cache_slot::get_next_line): Likewise. * input.h (class file_cache): Added input context member. libcpp/ChangeLog: PR other/93067 * charset.c (init_iconv_desc): Adapt to permit PFILE argument to be NULL. (_cpp_convert_input): Likewise. Also move UTF-8 BOM logic to... (cpp_check_utf8_bom): ...here. New function. (cpp_input_conversion_is_trivial): New function. * files.c (read_file_guts): Allow PFILE argument to be NULL. Add INPUT_CHARSET argument as an alternate source of this information. (read_file): Pass the new argument to read_file_guts. (cpp_get_converted_source): New function. * include/cpplib.h (struct cpp_converted_source): Declare. (cpp_get_converted_source): Declare. (cpp_input_conversion_is_trivial): Declare. (cpp_check_utf8_bom): Declare. gcc/testsuite/ChangeLog: PR other/93067 * gcc.dg/diagnostic-input-charset-1.c: New test. * gcc.dg/diagnostic-input-utf8-bom.c: New test.
2021-08-25 01:30:44 +02:00
/* Check if the configured input charset requires no conversion, other than
possibly stripping a UTF-8 BOM. */
bool cpp_input_conversion_is_trivial (const char *input_charset)
{
return !strcasecmp (input_charset, SOURCE_CHARSET);
}
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
/* Implementation of class cpp_string_location_reader. */
/* Constructor for cpp_string_location_reader. */
cpp_string_location_reader::
Eliminate source_location in favor of location_t Historically GCC used location_t, while libcpp used source_location. This inconsistency has been annoying me for a while, so this patch removes source_location in favor of location_t throughout (as the latter is shorter). gcc/ChangeLog: * builtins.c: Replace "source_location" with "location_t". * diagnostic-show-locus.c: Likewise. * diagnostic.c: Likewise. * dumpfile.c: Likewise. * gcc-rich-location.h: Likewise. * genmatch.c: Likewise. * gimple.h: Likewise. * gimplify.c: Likewise. * input.c: Likewise. * input.h: Likewise. Eliminate the typedef. * omp-expand.c: Likewise. * selftest.h: Likewise. * substring-locations.h (get_source_location_for_substring): Rename to.. (get_location_within_string): ...this. * tree-cfg.c: Replace "source_location" with "location_t". * tree-cfgcleanup.c: Likewise. * tree-diagnostic.c: Likewise. * tree-into-ssa.c: Likewise. * tree-outof-ssa.c: Likewise. * tree-parloops.c: Likewise. * tree-phinodes.c: Likewise. * tree-phinodes.h: Likewise. * tree-ssa-loop-ivopts.c: Likewise. * tree-ssa-loop-manip.c: Likewise. * tree-ssa-phiopt.c: Likewise. * tree-ssa-phiprop.c: Likewise. * tree-ssa-threadupdate.c: Likewise. * tree-ssa.c: Likewise. * tree-ssa.h: Likewise. * tree-vect-loop-manip.c: Likewise. gcc/c-family/ChangeLog: * c-common.c (c_get_substring_location): Update for renaming of get_source_location_for_substring to get_location_within_string. * c-lex.c: Replace "source_location" with "location_t". * c-opts.c: Likewise. * c-ppoutput.c: Likewise. gcc/c/ChangeLog: * c-decl.c: Replace "source_location" with "location_t". * c-tree.h: Likewise. * c-typeck.c: Likewise. * gimple-parser.c: Likewise. gcc/cp/ChangeLog: * call.c: Replace "source_location" with "location_t". * cp-tree.h: Likewise. * cvt.c: Likewise. * name-lookup.c: Likewise. * parser.c: Likewise. * typeck.c: Likewise. gcc/fortran/ChangeLog: * cpp.c: Replace "source_location" with "location_t". * gfortran.h: Likewise. gcc/go/ChangeLog: * go-gcc-diagnostics.cc: Replace "source_location" with "location_t". * go-gcc.cc: Likewise. * go-linemap.cc: Likewise. * go-location.h: Likewise. * gofrontend/README: Likewise. gcc/jit/ChangeLog: * jit-playback.c: Replace "source_location" with "location_t". gcc/testsuite/ChangeLog: * g++.dg/plugin/comment_plugin.c: Replace "source_location" with "location_t". * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c: Likewise. libcc1/ChangeLog: * libcc1plugin.cc: Replace "source_location" with "location_t". (plugin_context::get_source_location): Rename to... (plugin_context::get_location_t): ...this. * libcp1plugin.cc: Likewise. libcpp/ChangeLog: * charset.c: Replace "source_location" with "location_t". * directives-only.c: Likewise. * directives.c: Likewise. * errors.c: Likewise. * expr.c: Likewise. * files.c: Likewise. * include/cpplib.h: Likewise. Rename MAX_SOURCE_LOCATION to MAX_LOCATION_T. * include/line-map.h: Likewise. * init.c: Likewise. * internal.h: Likewise. * lex.c: Likewise. * line-map.c: Likewise. * location-example.txt: Likewise. * macro.c: Likewise. * pch.c: Likewise. * traditional.c: Likewise. From-SVN: r266085
2018-11-13 21:05:03 +01:00
cpp_string_location_reader (location_t src_loc,
On-demand locations within string-literals gcc/c-family/ChangeLog: * c-common.c: Include "substring-locations.h". (get_cpp_ttype_from_string_type): New function. (g_string_concat_db): New global. (substring_loc::get_range): New method. * c-common.h (g_string_concat_db): New declaration. (class substring_loc): New class. * c-lex.c (lex_string): When concatenating strings, capture the locations of all tokens using a new obstack, and record the concatenation locations within g_string_concat_db. * c-opts.c (c_common_init_options): Construct g_string_concat_db on the ggc-heap. gcc/ChangeLog: * input.c (string_concat::string_concat): New constructor. (string_concat_db::string_concat_db): New constructor. (string_concat_db::record_string_concatenation): New method. (string_concat_db::get_string_concatenation): New method. (string_concat_db::get_key_loc): New method. (class auto_cpp_string_vec): New class. (get_substring_ranges_for_loc): New function. (get_source_range_for_substring): New function. (get_num_source_ranges_for_substring): New function. (class selftest::lexer_test_options): New class. (struct selftest::lexer_test): New struct. (class selftest::ebcdic_execution_charset): New class. (selftest::ebcdic_execution_charset::s_singleton): New variable. (selftest::lexer_test::lexer_test): New constructor. (selftest::lexer_test::~lexer_test): New destructor. (selftest::lexer_test::get_token): New method. (selftest::assert_char_at_range): New function. (ASSERT_CHAR_AT_RANGE): New macro. (selftest::assert_num_substring_ranges): New function. (ASSERT_NUM_SUBSTRING_RANGES): New macro. (selftest::assert_has_no_substring_ranges): New function. (ASSERT_HAS_NO_SUBSTRING_RANGES): New macro. (selftest::test_lexer_string_locations_simple): New function. (selftest::test_lexer_string_locations_ebcdic): New function. (selftest::test_lexer_string_locations_hex): New function. (selftest::test_lexer_string_locations_oct): New function. (selftest::test_lexer_string_locations_letter_escape_1): New function. (selftest::test_lexer_string_locations_letter_escape_2): New function. (selftest::test_lexer_string_locations_ucn4): New function. (selftest::test_lexer_string_locations_ucn8): New function. (selftest::uint32_from_big_endian): New function. (selftest::test_lexer_string_locations_wide_string): New function. (selftest::uint16_from_big_endian): New function. (selftest::test_lexer_string_locations_string16): New function. (selftest::test_lexer_string_locations_string32): New function. (selftest::test_lexer_string_locations_u8): New function. (selftest::test_lexer_string_locations_utf8_source): New function. (selftest::test_lexer_string_locations_concatenation_1): New function. (selftest::test_lexer_string_locations_concatenation_2): New function. (selftest::test_lexer_string_locations_concatenation_3): New function. (selftest::test_lexer_string_locations_macro): New function. (selftest::test_lexer_string_locations_stringified_macro_argument): New function. (selftest::test_lexer_string_locations_non_string): New function. (selftest::test_lexer_string_locations_long_line): New function. (selftest::test_lexer_char_constants): New function. (selftest::input_c_tests): Call the new test functions once per case within the line_table test matrix. * input.h (struct string_concat): New struct. (struct location_hash): New struct. (class string_concat_db): New class. * substring-locations.h: New header. gcc/testsuite/ChangeLog: * gcc.dg/plugin/diagnostic-test-string-literals-1.c: New file. * gcc.dg/plugin/diagnostic-test-string-literals-2.c: New file. * gcc.dg/plugin/diagnostic_plugin_test_string_literals.c: New file. * gcc.dg/plugin/plugin.exp (plugin_test_list): Add the above new files. libcpp/ChangeLog: * charset.c (cpp_substring_ranges::cpp_substring_ranges): New constructor. (cpp_substring_ranges::~cpp_substring_ranges): New destructor. (cpp_substring_ranges::add_range): New method. (cpp_substring_ranges::add_n_ranges): New method. (_cpp_valid_ucn): Add "char_range" and "loc_reader" params; if they are non-NULL, read position information from *loc_reader and update char_range->m_finish accordingly. (convert_ucn): Add "char_range", "loc_reader", and "ranges" params. If loc_reader is non-NULL, read location information from it, and update *ranges accordingly, using char_range. Conditionalize the conversion into tbuf on tbuf being non-NULL. (convert_hex): Likewise, conditionalizing the call to emit_numeric_escape on tbuf. (convert_oct): Likewise. (convert_escape): Add params "loc_reader" and "ranges". If loc_reader is non-NULL, read location information from it, and update *ranges accordingly. Conditionalize the conversion into tbuf on tbuf being non-NULL. (cpp_interpret_string): Rename to... (cpp_interpret_string_1): ...this, adding params "loc_readers" and "out". Use "to" to conditionalize the initialization and usage of "tbuf", such as running the converter. If "loc_readers" is non-NULL, use the instances within it, reading location information from them, and passing them to convert_escape; likewise write to "out" if loc_readers is non-NULL. Check for leading quote and issue an error if it is not present. Update boundary check from "== limit" to ">= limit" to protect against erroneous location values to calls that are not parsing string literals. (cpp_interpret_string): Reimplement in terms to cpp_interpret_string_1. (noop_error_cb): New function. (cpp_interpret_string_ranges): New function. (cpp_string_location_reader::cpp_string_location_reader): New constructor. (cpp_string_location_reader::get_next): New method. * include/cpplib.h (class cpp_string_location_reader): New class. (class cpp_substring_ranges): New class. (cpp_interpret_string_ranges): New prototype. * internal.h (_cpp_valid_ucn): Add params "char_range" and "loc_reader". * lex.c (forms_identifier_p): Pass NULL for new params to _cpp_valid_ucn. From-SVN: r239175
2016-08-05 20:08:33 +02:00
line_maps *line_table)
{
src_loc = get_range_from_loc (line_table, src_loc).m_start;
/* SRC_LOC might be a macro location. It only makes sense to do
column-by-column calculations on ordinary maps, so get the
corresponding location in an ordinary map. */
m_loc
= linemap_resolve_location (line_table, src_loc,
LRK_SPELLING_LOCATION, NULL);
const line_map_ordinary *map
= linemap_check_ordinary (linemap_lookup (line_table, m_loc));
m_offset_per_column = (1 << map->m_range_bits);
}
/* Get the range of the next source byte. */
source_range
cpp_string_location_reader::get_next ()
{
source_range result;
result.m_start = m_loc;
result.m_finish = m_loc;
if (m_loc <= LINE_MAP_MAX_LOCATION_WITH_COLS)
m_loc += m_offset_per_column;
return result;
}
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
cpp_display_width_computation::
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
cpp_display_width_computation (const char *data, int data_length,
const cpp_char_column_policy &policy) :
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
m_begin (data),
m_next (m_begin),
m_bytes_left (data_length),
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
m_policy (policy),
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
m_display_cols (0)
{
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
gcc_assert (policy.m_tabstop > 0);
gcc_assert (policy.m_width_cb);
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
}
/* The main implementation function for class cpp_display_width_computation.
m_next points on entry to the start of the UTF-8 encoding of the next
character, and is updated to point just after the last byte of the encoding.
m_bytes_left contains on entry the remaining size of the buffer into which
m_next points, and this is also updated accordingly. If m_next does not
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
point to a valid UTF-8-encoded sequence, then it will be treated as a single
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
byte with display width 1. m_cur_display_col is the current display column,
relative to which tab stops should be expanded. Returns the display width of
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
the codepoint just processed.
If OUT is non-NULL, it is populated. */
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
int
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
cpp_display_width_computation::process_next_codepoint (cpp_decoded_char *out)
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
{
cppchar_t c;
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
int next_width;
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
if (out)
out->m_start_byte = m_next;
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
if (*m_next == '\t')
{
++m_next;
--m_bytes_left;
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
next_width = m_policy.m_tabstop - (m_display_cols % m_policy.m_tabstop);
if (out)
{
out->m_ch = '\t';
out->m_valid_ch = true;
}
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
}
else if (one_utf8_to_cppchar ((const uchar **) &m_next, &m_bytes_left, &c)
!= 0)
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
{
/* Input is not convertible to UTF-8. This could be fine, e.g. in a
string literal, so don't complain. Just treat it as if it has a width
of one. */
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
++m_next;
--m_bytes_left;
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
next_width = m_policy.m_undecoded_byte_width;
if (out)
out->m_valid_ch = false;
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
}
else
{
/* one_utf8_to_cppchar() has updated m_next and m_bytes_left for us. */
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
next_width = m_policy.m_width_cb (c);
if (out)
{
out->m_ch = c;
out->m_valid_ch = true;
}
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
}
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
if (out)
out->m_next_byte = m_next;
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
m_display_cols += next_width;
return next_width;
}
/* Utility to advance the byte stream by the minimum amount needed to consume
N display columns. Returns the number of display columns that were
actually skipped. This could be less than N, if there was not enough data,
or more than N, if the last character to be skipped had a sufficiently large
display width. */
int
cpp_display_width_computation::advance_display_cols (int n)
{
const int start = m_display_cols;
const int target = start + n;
while (m_display_cols < target && !done ())
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
process_next_codepoint (NULL);
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
return m_display_cols - start;
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
}
/* For the string of length DATA_LENGTH bytes that begins at DATA, compute
how many display columns are occupied by the first COLUMN bytes. COLUMN
may exceed DATA_LENGTH, in which case the phantom bytes at the end are
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
treated as if they have display width 1. Tabs are expanded to the next tab
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
stop, relative to the start of DATA, and non-printable-ASCII characters
will be escaped as per POLICY. */
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
int
cpp_byte_column_to_display_column (const char *data, int data_length,
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
int column,
const cpp_char_column_policy &policy)
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
{
const int offset = MAX (0, column - data_length);
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
cpp_display_width_computation dw (data, column - offset, policy);
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
while (!dw.done ())
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
dw.process_next_codepoint (NULL);
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
return dw.display_cols_processed () + offset;
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
}
/* For the string of length DATA_LENGTH bytes that begins at DATA, compute
the least number of bytes that will result in at least DISPLAY_COL display
columns. The return value may exceed DATA_LENGTH if the entire string does
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
not occupy enough display columns. Non-printable-ASCII characters
will be escaped as per POLICY. */
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
int
cpp_display_column_to_byte_column (const char *data, int data_length,
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
int display_col,
const cpp_char_column_policy &policy)
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
{
diagnostics: escape non-ASCII source bytes for certain diagnostics This patch adds support to GCC's diagnostic subsystem for escaping certain bytes and Unicode characters when quoting source code. Specifically, this patch adds a new flag rich_location::m_escape_on_output which is a hint from a diagnostic that non-ASCII bytes in the pertinent lines of the user's source code should be escaped when printed. The patch sets this for the following diagnostics: - when complaining about stray bytes in the program (when these are non-printable) - when complaining about "null character(s) ignored"); - for -Wnormalized= (and generate source ranges for such warnings) The escaping is controlled by a new option: -fdiagnostics-escape-format=[unicode|bytes] For example, consider a diagnostic involing a source line containing the string "before" followed by the Unicode character U+03C0 ("GREEK SMALL LETTER PI", with UTF-8 encoding 0xCF 0x80) followed by the byte 0xBF (a stray UTF-8 trailing byte), followed by the string "after", where the diagnostic highlights the U+03C0 character. By default, this line will be printed verbatim to the user when reporting a diagnostic at it, as: beforeπXafter ^ (using X for the stray byte to avoid putting invalid UTF-8 in this commit message) If the diagnostic sets the "escape" flag, it will be printed as: before<U+03C0><BF>after ^~~~~~~~ with -fdiagnostics-escape-format=unicode (the default), or as: before<CF><80><BF>after ^~~~~~~~ if the user supplies -fdiagnostics-escape-format=bytes. This only affects how the source is printed; it does not affect how column numbers that are printed (as per -fdiagnostics-column-unit= and -fdiagnostics-column-origin=). gcc/c-family/ChangeLog: * c-lex.c (c_lex_with_flags): When complaining about non-printable CPP_OTHER tokens, set the "escape on output" flag. gcc/ChangeLog: * common.opt (fdiagnostics-escape-format=): New. (diagnostics_escape_format): New enum. (DIAGNOSTICS_ESCAPE_FORMAT_UNICODE): New enum value. (DIAGNOSTICS_ESCAPE_FORMAT_BYTES): Likewise. * diagnostic-format-json.cc (json_end_diagnostic): Add "escape-source" attribute. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Replace "tabstop" param with a cpp_char_column_policy and add an "aspect" param. Use these to compute m_display_col accordingly. (struct char_display_policy): New struct. (layout::m_policy): New field. (layout::m_escape_on_output): New field. (def_policy): New function. (make_range): Update for changes to exploc_with_display_col ctor. (default_print_decoded_ch): New. (width_per_escaped_byte): New. (escape_as_bytes_width): New. (escape_as_bytes_print): New. (escape_as_unicode_width): New. (escape_as_unicode_print): New. (make_policy): New. (layout::layout): Initialize new fields. Update m_exploc ctor call for above change to ctor. (layout::maybe_add_location_range): Update for changes to exploc_with_display_col ctor. (layout::calculate_x_offset_display): Update for change to cpp_display_width. (layout::print_source_line): Pass policy to cpp_display_width_computation. Capture cpp_decoded_char when calling process_next_codepoint. Move printing of source code to m_policy.m_print_cb. (line_label::line_label): Pass in policy rather than context. (layout::print_any_labels): Update for change to line_label ctor. (get_affected_range): Pass in policy rather than context, updating calls to location_compute_display_column accordingly. (get_printed_columns): Likewise, also for cpp_display_width. (correction::correction): Pass in policy rather than tabstop. (correction::compute_display_cols): Pass m_policy rather than m_tabstop to cpp_display_width. (correction::m_tabstop): Replace with... (correction::m_policy): ...this. (line_corrections::line_corrections): Pass in policy rather than context. (line_corrections::m_context): Replace with... (line_corrections::m_policy): ...this. (line_corrections::add_hint): Update to use m_policy rather than m_context. (line_corrections::add_hint): Likewise. (layout::print_trailing_fixits): Likewise. (selftest::test_display_widths): New. (selftest::test_layout_x_offset_display_utf8): Update to use policy rather than tabstop. (selftest::test_one_liner_labels_utf8): Add test of escaping source lines. (selftest::test_diagnostic_show_locus_one_liner_utf8): Update to use policy rather than tabstop. (selftest::test_overlapped_fixit_printing): Likewise. (selftest::test_overlapped_fixit_printing_utf8): Likewise. (selftest::test_overlapped_fixit_printing_2): Likewise. (selftest::test_tab_expansion): Likewise. (selftest::test_escaping_bytes_1): New. (selftest::test_escaping_bytes_2): New. (selftest::diagnostic_show_locus_c_tests): Call the new tests. * diagnostic.c (diagnostic_initialize): Initialize context->escape_format. (convert_column_unit): Update to use default character width policy. (selftest::test_diagnostic_get_location_text): Likewise. * diagnostic.h (enum diagnostics_escape_format): New enum. (diagnostic_context::escape_format): New field. * doc/invoke.texi (-fdiagnostics-escape-format=): New option. (-fdiagnostics-format=): Add "escape-source" attribute to examples of JSON output, and document it. * input.c (location_compute_display_column): Pass in "policy" rather than "tabstop", passing to cpp_byte_column_to_display_column. (selftest::test_cpp_utf8): Update to use cpp_char_column_policy. * input.h (class cpp_char_column_policy): New forward decl. (location_compute_display_column): Pass in "policy" rather than "tabstop". * opts.c (common_handle_option): Handle OPT_fdiagnostics_escape_format_. * selftest.c (temp_source_file::temp_source_file): New ctor overload taking a size_t. * selftest.h (temp_source_file::temp_source_file): Likewise. gcc/testsuite/ChangeLog: * c-c++-common/diagnostic-format-json-1.c: Add regexp to consume "escape-source" attribute. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise, twice. * c-c++-common/diagnostic-format-json-5.c: Likewise. * gcc.dg/cpp/warn-normalized-4-bytes.c: New test. * gcc.dg/cpp/warn-normalized-4-unicode.c: New test. * gcc.dg/encoding-issues-bytes.c: New test. * gcc.dg/encoding-issues-unicode.c: New test. * gfortran.dg/diagnostic-format-json-1.F90: Add regexp to consume "escape-source" attribute. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. libcpp/ChangeLog: * charset.c (convert_escape): Use encoding_rich_location when complaining about nonprintable unknown escape sequences. (cpp_display_width_computation::::cpp_display_width_computation): Pass in policy rather than tabstop. (cpp_display_width_computation::process_next_codepoint): Add "out" param and populate *out if non-NULL. (cpp_display_width_computation::advance_display_cols): Pass NULL to process_next_codepoint. (cpp_byte_column_to_display_column): Pass in policy rather than tabstop. Pass NULL to process_next_codepoint. (cpp_display_column_to_byte_column): Pass in policy rather than tabstop. * errors.c (cpp_diagnostic_get_current_location): New function, splitting out the logic from... (cpp_diagnostic): ...here. (cpp_warning_at): New function. (cpp_pedwarning_at): New function. * include/cpplib.h (cpp_warning_at): New decl for rich_location. (cpp_pedwarning_at): Likewise. (struct cpp_decoded_char): New. (struct cpp_char_column_policy): New. (cpp_display_width_computation::cpp_display_width_computation): Replace "tabstop" param with "policy". (cpp_display_width_computation::process_next_codepoint): Add "out" param. (cpp_display_width_computation::m_tabstop): Replace with... (cpp_display_width_computation::m_policy): ...this. (cpp_byte_column_to_display_column): Replace "tabstop" param with "policy". (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * include/line-map.h (rich_location::escape_on_output_p): New. (rich_location::set_escape_on_output): New. (rich_location::m_escape_on_output): New. * internal.h (cpp_diagnostic_get_current_location): New decl. (class encoding_rich_location): New. * lex.c (skip_whitespace): Use encoding_rich_location when complaining about null characters. (warn_about_normalization): Generate a source range when complaining about improperly normalized tokens, rather than just a point, and use encoding_rich_location so that the source code is escaped on printing. * line-map.c (rich_location::rich_location): Initialize m_escape_on_output. Signed-off-by: David Malcolm <dmalcolm@redhat.com>
2021-10-19 00:55:31 +02:00
cpp_display_width_computation dw (data, data_length, policy);
diagnostics: Support conversion of tabs to spaces [PR49973] [PR86904] Supports conversion of tabs to spaces when outputting diagnostics. Also adds -fdiagnostics-column-unit and -fdiagnostics-column-origin options to control how the column number is output, thereby resolving the two PRs. gcc/c-family/ChangeLog: PR other/86904 * c-indentation.c (should_warn_for_misleading_indentation): Get global tabstop from the new source. * c-opts.c (c_common_handle_option): Remove handling of -ftabstop, which is now a common option. * c.opt: Likewise. gcc/ChangeLog: PR preprocessor/49973 PR other/86904 * common.opt: Handle -ftabstop here instead of in c-family options. Add -fdiagnostics-column-unit= and -fdiagnostics-column-origin= options. * opts.c (common_handle_option): Handle the new options. * diagnostic-format-json.cc (json_from_expanded_location): Add diagnostic_context argument. Use it to convert column numbers as per the new options. (json_from_location_range): Likewise. (json_from_fixit_hint): Likewise. (json_end_diagnostic): Pass the new context argument to helper functions above. Add "column-origin" field to the output. (test_unknown_location): Add the new context argument to calls to helper functions. (test_bad_endpoints): Likewise. * diagnostic-show-locus.c (exploc_with_display_col::exploc_with_display_col): Support tabstop parameter. (layout_point::layout_point): Make use of class exploc_with_display_col. (layout_range::layout_range): Likewise. (struct line_bounds): Clarify that the units are now always display columns. Rename members accordingly. Add constructor. (layout::print_source_line): Add support for tab expansion. (make_range): Adapt to class layout_range changes. (layout::maybe_add_location_range): Likewise. (layout::layout): Adapt to class exploc_with_display_col changes. (layout::calculate_x_offset_display): Support tabstop parameter. (layout::print_annotation_line): Adapt to struct line_bounds changes. (layout::print_line): Likewise. (line_label::line_label): Add diagnostic_context argument. (get_affected_range): Likewise. (get_printed_columns): Likewise. (layout::print_any_labels): Adapt to struct line_label changes. (class correction): Add m_tabstop member. (correction::correction): Add tabstop argument. (correction::compute_display_cols): Use m_tabstop. (class line_corrections): Add m_context member. (line_corrections::line_corrections): Add diagnostic_context argument. (line_corrections::add_hint): Use m_context to handle tabstops. (layout::print_trailing_fixits): Adapt to class line_corrections changes. (test_layout_x_offset_display_utf8): Support tabstop parameter. (test_layout_x_offset_display_tab): New selftest. (test_one_liner_colorized_utf8): Likewise. (test_tab_expansion): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Call the new tests. (diagnostic_show_locus_c_tests): Likewise. (test_overlapped_fixit_printing): Adapt to helper class and function changes. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing_2): Likewise. * diagnostic.h (enum diagnostics_column_unit): New enum. (struct diagnostic_context): Add members for the new options. (diagnostic_converted_column): Declare. (json_from_expanded_location): Add new context argument. * diagnostic.c (diagnostic_initialize): Initialize new members. (diagnostic_converted_column): New function. (maybe_line_and_column): Be willing to output a column of 0. (diagnostic_get_location_text): Convert column number as per the new options. (diagnostic_report_current_module): Likewise. (assert_location_text): Add origin and column_unit arguments for testing the new functionality. (test_diagnostic_get_location_text): Test the new functionality. * doc/invoke.texi: Document the new options and behavior. * input.h (location_compute_display_column): Add tabstop argument. * input.c (location_compute_display_column): Likewise. (test_cpp_utf8): Add selftests for tab expansion. * tree-diagnostic-path.cc (default_tree_make_json_for_path): Pass the new context argument to json_from_expanded_location(). libcpp/ChangeLog: PR preprocessor/49973 PR other/86904 * include/cpplib.h (struct cpp_options): Removed support for -ftabstop, which is now handled by diagnostic_context. (class cpp_display_width_computation): New class. (cpp_byte_column_to_display_column): Add optional tabstop argument. (cpp_display_width): Likewise. (cpp_display_column_to_byte_column): Likewise. * charset.c (cpp_display_width_computation::cpp_display_width_computation): New function. (cpp_display_width_computation::advance_display_cols): Likewise. (compute_next_display_width): Removed and implemented this functionality in a new function... (cpp_display_width_computation::process_next_codepoint): ...here. (cpp_byte_column_to_display_column): Added tabstop argument. Reimplemented in terms of class cpp_display_width_computation. (cpp_display_column_to_byte_column): Likewise. * init.c (cpp_create_reader): Remove handling of -ftabstop, which is now handled by diagnostic_context. gcc/testsuite/ChangeLog: PR preprocessor/49973 PR other/86904 * c-c++-common/Wmisleading-indentation-3.c: Adjust expected output for new defaults. * c-c++-common/Wmisleading-indentation.c: Likewise. * c-c++-common/diagnostic-format-json-1.c: Likewise. * c-c++-common/diagnostic-format-json-2.c: Likewise. * c-c++-common/diagnostic-format-json-3.c: Likewise. * c-c++-common/diagnostic-format-json-4.c: Likewise. * c-c++-common/diagnostic-format-json-5.c: Likewise. * c-c++-common/missing-close-symbol.c: Likewise. * g++.dg/diagnostic/bad-binary-ops.C: Likewise. * g++.dg/parse/error4.C: Likewise. * g++.old-deja/g++.brendan/crash11.C: Likewise. * g++.old-deja/g++.pt/overload2.C: Likewise. * g++.old-deja/g++.robertl/eb109.C: Likewise. * gcc.dg/analyzer/malloc-paths-9.c: Likewise. * gcc.dg/bad-binary-ops.c: Likewise. * gcc.dg/format/branch-1.c: Likewise. * gcc.dg/format/pr79210.c: Likewise. * gcc.dg/plugin/diagnostic-test-expressions-1.c: Likewise. * gcc.dg/plugin/diagnostic-test-string-literals-1.c: Likewise. * gcc.dg/redecl-4.c: Likewise. * gfortran.dg/diagnostic-format-json-1.F90: Likewise. * gfortran.dg/diagnostic-format-json-2.F90: Likewise. * gfortran.dg/diagnostic-format-json-3.F90: Likewise. * go.dg/arrayclear.go: Add a comment explaining why adding a comment was necessary to work around a dejagnu bug. * c-c++-common/diagnostic-units-1.c: New test. * c-c++-common/diagnostic-units-2.c: New test. * c-c++-common/diagnostic-units-3.c: New test. * c-c++-common/diagnostic-units-4.c: New test. * c-c++-common/diagnostic-units-5.c: New test. * c-c++-common/diagnostic-units-6.c: New test. * c-c++-common/diagnostic-units-7.c: New test. * c-c++-common/diagnostic-units-8.c: New test.
2020-07-14 18:05:56 +02:00
const int avail_display = dw.advance_display_cols (display_col);
return dw.bytes_processed () + MAX (0, display_col - avail_display);
Byte vs column awareness for diagnostic-show-locus.c (PR 49973) contrib/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * unicode/from_glibc/unicode_utils.py: Support script from glibc (commit 464cd3) to extract character widths from Unicode data files. * unicode/from_glibc/utf8_gen.py: Likewise. * unicode/UnicodeData.txt: Unicode v. 12.1.0 data file. * unicode/EastAsianWidth.txt: Likewise. * unicode/PropList.txt: Likewise. * unicode/gen_wcwidth.py: New utility to generate libcpp/generated_cpp_wcwidth.h with help from the glibc support scripts and the Unicode data files. * unicode/unicode-license.txt: Added. * unicode/README: New explanatory file. libcpp/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * generated_cpp_wcwidth.h: New file generated by ../contrib/unicode/gen_wcwidth.py, supports new cpp_wcwidth function. * charset.c (compute_next_display_width): New function to help implement display columns. (cpp_byte_column_to_display_column): Likewise. (cpp_display_column_to_byte_column): Likewise. (cpp_wcwidth): Likewise. * include/cpplib.h (cpp_byte_column_to_display_column): Declare. (cpp_display_column_to_byte_column): Declare. (cpp_wcwidth): Declare. (cpp_display_width): New function. gcc/ChangeLog 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * input.c (location_compute_display_column): New function to help with multibyte awareness in diagnostics. (test_cpp_utf8): New self-test. (input_c_tests): Call the new test. * input.h (location_compute_display_column): Declare. * diagnostic-show-locus.c: Pervasive changes to add multibyte awareness to all classes and functions. (enum column_unit): New enum. (class exploc_with_display_col): New class. (class layout_point): Convert m_column member to array m_columns[2]. (layout_range::contains_point): Add col_unit argument. (test_layout_range_for_single_point): Pass new argument. (test_layout_range_for_single_line): Likewise. (test_layout_range_for_multiple_lines): Likewise. (line_bounds::convert_to_display_cols): New function. (layout::get_state_at_point): Add col_unit argument. (make_range): Use empty filename rather than dummy filename. (get_line_width_without_trailing_whitespace): Rename to... (get_line_bytes_without_trailing_whitespace): ...this. (test_get_line_width_without_trailing_whitespace): Rename to... (test_get_line_bytes_without_trailing_whitespace): ...this. (class layout): m_exploc changed to exploc_with_display_col from plain expanded_location. (layout::get_linenum_width): New accessor member function. (layout::get_x_offset_display): Likewise. (layout::calculate_linenum_width): New subroutine for the constuctor. (layout::calculate_x_offset_display): Likewise. (layout::layout): Use the new subroutines. Add multibyte awareness. (layout::print_source_line): Add multibyte awareness. (layout::print_line): Likewise. (layout::print_annotation_line): Likewise. (line_label::line_label): Likewise. (layout::print_any_labels): Likewise. (layout::annotation_line_showed_range_p): Likewise. (get_printed_columns): Likewise. (class line_label): Rename m_length to m_display_width. (get_affected_columns): Rename to... (get_affected_range): ...this; add col_unit argument and multibyte awareness. (class correction): Add m_affected_bytes and m_display_cols members. Rename m_len to m_byte_length for clarity. Add multibyte awareness throughout. (correction::insertion_p): Add multibyte awareness. (correction::compute_display_cols): New function. (correction::ensure_terminated): Use new member name m_byte_length. (line_corrections::add_hint): Add multibyte awareness. (layout::print_trailing_fixits): Likewise. (layout::get_x_bound_for_row): Likewise. (test_one_liner_simple_caret_utf8): New self-test analogous to the one with _utf8 suffix removed, testing multibyte awareness. (test_one_liner_caret_and_range_utf8): Likewise. (test_one_liner_multiple_carets_and_ranges_utf8): Likewise. (test_one_liner_fixit_insert_before_utf8): Likewise. (test_one_liner_fixit_insert_after_utf8): Likewise. (test_one_liner_fixit_remove_utf8): Likewise. (test_one_liner_fixit_replace_utf8): Likewise. (test_one_liner_fixit_replace_non_equal_range_utf8): Likewise. (test_one_liner_fixit_replace_equal_secondary_range_utf8): Likewise. (test_one_liner_fixit_validation_adhoc_locations_utf8): Likewise. (test_one_liner_many_fixits_1_utf8): Likewise. (test_one_liner_many_fixits_2_utf8): Likewise. (test_one_liner_labels_utf8): Likewise. (test_diagnostic_show_locus_one_liner_utf8): Likewise. (test_overlapped_fixit_printing_utf8): Likewise. (test_overlapped_fixit_printing): Adapt for changes to get_affected_columns, get_printed_columns and class corrections. (test_overlapped_fixit_printing_2): Likewise. (test_linenum_sep): New constant. (test_left_margin): Likewise. (test_offset_impl): Helper function for new test. (test_layout_x_offset_display_utf8): New test. (diagnostic_show_locus_c_tests): Call new tests. gcc/testsuite/ChangeLog: 2019-12-09 Lewis Hyatt <lhyatt@gmail.com> PR preprocessor/49973 * gcc.dg/plugin/diagnostic_plugin_test_show_locus.c (test_show_locus): Tweak so that expected output is the same as before the diagnostic-show-locus.c changes. * gcc.dg/cpp/pr66415-1.c: Likewise. From-SVN: r279137
2019-12-09 21:03:47 +01:00
}
/* Our own version of wcwidth(). We don't use the actual wcwidth() in glibc,
because that will inspect the user's locale, and in particular in an ASCII
locale, it will not return anything useful for extended characters. But GCC
in other respects (see e.g. _cpp_default_encoding()) behaves as if
everything is UTF-8. We also make some tweaks that are useful for the way
GCC needs to use this data, e.g. tabs and other control characters should be
treated as having width 1. The lookup tables are generated from
contrib/unicode/gen_wcwidth.py and were made by simply calling glibc
wcwidth() on all codepoints, then applying the small tweaks. These tables
are not highly optimized, but for the present purpose of outputting
diagnostics, they are sufficient. */
#include "generated_cpp_wcwidth.h"
int cpp_wcwidth (cppchar_t c)
{
if (__builtin_expect (c <= wcwidth_range_ends[0], true))
return wcwidth_widths[0];
/* Binary search the tables. */
int begin = 1;
static const int end
= sizeof wcwidth_range_ends / sizeof (*wcwidth_range_ends);
int len = end - begin;
do
{
int half = len/2;
int middle = begin + half;
if (c > wcwidth_range_ends[middle])
{
begin = middle + 1;
len -= half + 1;
}
else
len = half;
} while (len);
if (__builtin_expect (begin != end, true))
return wcwidth_widths[begin];
return 1;
}