OpenE2K
/
gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Make-lang.in (JAVA_LEX_C): Added chartables.h. 

* Make-lang.in (JAVA_LEX_C): Added chartables.h.
	* lex.c (java_ignorable_control_p): Removed.
	(java_letter_or_digit_p): Removed.
	(java_start_char_p): New function.
	(java_read_char): Return `int', not `unicode_t'.  Changed
	callers.
	(java_read_unicode): Likewise.
	(java_read_unicode_collapsing_terminators): Likewise.
	(java_get_unicode): Likewise.
	(java_new_lexer): Initialize hit_eof.
	(java_parse_end_comment): Take `int' argument.
	(java_parse_doc_section): Likewise.
	(java_parse_escape_sequence): Don't allow backlash-newline.
	Return `int'.
	* lex.h (JAVA_DIGIT_P): Removed.
	(_JAVA_LETTER_OR_DIGIT_P): Removed.
	(_JAVA_IDENTIFIER_IGNORABLE): Removed.
	(JAVA_START_CHAR_P): Renamed from JAVA_ID_CHAR_P.
	(JAVA_PART_CHAR_P): New macro.
	(UEOF): Now -1.
	(JAVA_CHAR_ERROR): Now -2.
	(java_lexer): New field `hit_eof'.
	* chartables.h: New file.
	* gen-table.pl: new file.

From-SVN: r38237
This commit is contained in:
Tom Tromey 2000-12-13 22:47:13 +00:00 committed by Tom Tromey
parent 568aac9cf7
commit 3f27e3f86a
6 changed files with 3616 additions and 364 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
gcc/java/ChangeLog
View File

@ -1,3 +1,30 @@
2000-11-07 Tom Tromey <tromey@cygnus.com>
* Make-lang.in (JAVA_LEX_C): Added chartables.h.
* lex.c (java_ignorable_control_p): Removed.
(java_letter_or_digit_p): Removed.
(java_start_char_p): New function.
(java_read_char): Return `int', not `unicode_t'. Changed
callers.
(java_read_unicode): Likewise.
(java_read_unicode_collapsing_terminators): Likewise.
(java_get_unicode): Likewise.
(java_new_lexer): Initialize hit_eof.
(java_parse_end_comment): Take `int' argument.
(java_parse_doc_section): Likewise.
(java_parse_escape_sequence): Don't allow backlash-newline.
Return `int'.
* lex.h (JAVA_DIGIT_P): Removed.
(_JAVA_LETTER_OR_DIGIT_P): Removed.
(_JAVA_IDENTIFIER_IGNORABLE): Removed.
(JAVA_START_CHAR_P): Renamed from JAVA_ID_CHAR_P.
(JAVA_PART_CHAR_P): New macro.
(UEOF): Now -1.
(JAVA_CHAR_ERROR): Now -2.
(java_lexer): New field `hit_eof'.
* chartables.h: New file.
* gen-table.pl: new file.
2000-11-20 Tom Tromey <tromey@cygnus.com>
Alexandre Petit-Bianco <apbianco@cygnus.com>

2
gcc/java/Make-lang.in
View File

@ -214,7 +214,7 @@ java.stage4: stage4-start
#
# .o:.h dependencies.
JAVA_TREE_H = $(TREE_H) java/java-tree.h java/java-tree.def
JAVA_LEX_C = java/lex.c java/keyword.h
JAVA_LEX_C = java/lex.c java/keyword.h java/chartables.h
java/parse.o: java/parse.c java/jcf-reader.c $(CONFIG_H) system.h \
function.h $(JAVA_TREE_H) $(JAVA_LEX_C) java/parse.h java/lex.h $(GGC_H)

3212
gcc/java/chartables.h Normal file
View File

File diff suppressed because it is too large Load Diff

256
gcc/java/gen-table.pl Normal file
View File

@ -0,0 +1,256 @@
#! /usr/bin/perl
# Copyright (C) 2000 Free Software Foundation
# 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 2, 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; if not, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
# 02111-1307, USA.
# gen-table.pl - Generate tables for gcj from Unicode data.
# Usage: perl gen-table.pl DATA-FILE
# Names of fields in Unicode data table.
$CODE = 0;
$NAME = 1;
$CATEGORY = 2;
$COMBINING_CLASSES = 3;
$BIDI_CATEGORY = 4;
$DECOMPOSITION = 5;
$DECIMAL_VALUE = 6;
$DIGIT_VALUE = 7;
$NUMERIC_VALUE = 8;
$MIRRORED = 9;
$OLD_NAME = 10;
$COMMENT = 11;
$UPPER = 12;
$LOWER = 13;
$TITLE = 14;
# Start of special-cased gaps in Unicode data table.
%gaps = (
0x4e00 => "CJK",
0xac00 => "Hangul",
0xd800 => "Unassigned High Surrogate",
0xdb80 => "Private Use High Surrogate",
0xdc00 => "Low Surrogate",
0xe000 => "Private Use"
);
# This lists control characters which are also considered whitespace.
# This is a somewhat odd list, taken from the JCL definition of
# Character.isIdentifierIgnorable.
%whitespace_controls =
(
0x0009 => 1,
0x000a => 1,
0x000b => 1,
0x000c => 1,
0x000d => 1,
0x001c => 1,
0x001d => 1,
0x001e => 1,
0x001f => 1
);
open (INPUT, "< $ARGV[0]") || exit 1;
$last_code = -1;
while (<INPUT>)
{
chop;
@fields = split (';', $_, 30);
if ($#fields != 14)
{
print STDERR "Entry for $fields[$CODE] has wrong number of fields\n";
}
$code = hex ($fields[$CODE]);
if ($code > $last_code + 1)
{
# Found a gap.
if (defined $gaps{$code})
{
# Fill the gap with the last character read.
@gfields = @fields;
}
else
{
# The gap represents undefined characters. Only the type
# matters.
@gfields = ('', '', 'Cn', '0', '', '', '', '', '', '', '',
'', '', '', '');
}
for (++$last_code; $last_code < $code; ++$last_code)
{
$gfields{$CODE} = sprintf ("%04x", $last_code);
&process_one ($last_code, @gfields);
}
}
&process_one ($code, @fields);
$last_code = $code;
}
close (INPUT);
@gfields = ('', '', 'Cn', '0', '', '', '', '', '', '', '',
'', '', '', '');
for (++$last_code; $last_code < 0x10000; ++$last_code)
{
$gfields{$CODE} = sprintf ("%04x", $last_code);
&process_one ($last_code, @gfields);
}
--$last_code; # Want last to be 0xFFFF.
&print_tables ($last_code);
exit 0;
# Process a single character.
sub process_one
{
my ($code, @fields) = @_;
my $value = '';
my $type = $fields[$CATEGORY];
# See if the character is a valid identifier start.
if ($type =~ /L./ # Letter
|| $type eq 'Pc' # Connecting punctuation
|| $type eq 'Sc') # Currency symbol
{
$value = 'LETTER_START';
}
# See if the character is a valid identifier member.
if ($type =~ /L./ # Letter
|| $type eq 'Pc' # Connecting punctuation
|| $type eq 'Sc' # Currency symbol
|| $type =~ /N[dl]/ # Number: decimal or letter
|| $type =~ /M[nc]/ # Mark: non-spacing or combining
|| ($type eq 'Cc' # Certain controls
&& ! defined $whitespace_controls{$code})
|| ($code >= 0x200c # Join controls
&& $code <= 0x200f)
|| ($code >= 0x202a # Bidi controls -- note that there
# is a typo in the JCL where these are
# concerned.
&& $code <= 0x202e)
|| ($code >= 0x206a # Format controls
&& $code <= 0x206f)
|| $code == 0xfeff) # ZWNBSP
{
if ($value eq '')
{
$value = 'LETTER_PART';
}
else
{
$value = 'LETTER_PART | ' . $value;
}
}
if ($value eq '')
{
$value = '0';
}
else
{
$value = '(' . $value . ')';
}
$map[$code] = $value;
}
sub print_tables
{
my ($last) = @_;
local ($bytes_out) = 0;
open (OUT, "> chartables.h");
print OUT "/* This file is automatically generated. DO NOT EDIT!\n";
print OUT " Instead, edit gen-table.pl and re-run. */\n\n";
print OUT "#ifndef CHARTABLES_H\n";
print OUT "#define CHARTABLES_H\n\n";
print OUT "#define LETTER_START 1\n";
print OUT "#define LETTER_PART 2\n\n";
for ($count = 0; $count <= $last; $count += 256)
{
$row[$count / 256] = &print_row ($count, '(char *) ', 'char', 1,
'page');
}
print OUT "static char *type_table[256] = {\n";
for ($count = 0; $count <= $last; $count += 256)
{
print OUT ",\n" if $count > 0;
print OUT " ", $row[$count / 256];
$bytes_out += 4;
}
print OUT "\n};\n\n";
print OUT "#endif /* CHARTABLES_H */\n";
close (OUT);
printf "Generated %d bytes\n", $bytes_out;
}
# Print a single "row" of a two-level table.
sub print_row
{
my ($start, $def_pfx, $typname, $typsize, $name) = @_;
my ($i);
my (@values);
my ($flag) = 1;
my ($off);
for ($off = 0; $off < 256; ++$off)
{
$values[$off] = $map[$off + $start];
if ($values[$off] ne $values[0])
{
$flag = 0;
}
}
if ($flag)
{
return $def_pfx . $values[0];
}
printf OUT "static %s %s%d[256] = {\n ", $typname, $name, $start / 256;
my ($column) = 2;
for ($i = $start; $i < $start + 256; ++$i)
{
print OUT ", "
if $i > $start;
my ($text) = $values[$i - $start];
if (length ($text) + $column + 2 > 78)
{
print OUT "\n ";
$column = 2;
}
print OUT $text;
$column += length ($text) + 2;
}
print OUT "\n};\n\n";
$bytes_out += 256 * $typsize;
return sprintf "%s%d", $name, $start / 256;
}

137
gcc/java/lex.c
View File

@ -36,6 +36,7 @@ The Free Software Foundation is independent of Sun Microsystems, Inc. */
#include "keyword.h"
#include "flags.h"
#include "chartables.h"
/* Function declaration */
static char *java_sprint_unicode PARAMS ((struct java_line *, int));
@ -46,17 +47,17 @@ static int java_is_eol PARAMS ((FILE *, int));
static tree build_wfl_node PARAMS ((tree));
#endif
static void java_store_unicode PARAMS ((struct java_line *, unicode_t, int));
static unicode_t java_parse_escape_sequence PARAMS ((void));
static int java_letter_or_digit_p PARAMS ((unicode_t));
static int java_ignorable_control_p PARAMS ((unicode_t));
static int java_parse_doc_section PARAMS ((unicode_t));
static void java_parse_end_comment PARAMS ((unicode_t));
static unicode_t java_get_unicode PARAMS ((void));
static unicode_t java_read_unicode PARAMS ((java_lexer *, int *));
static unicode_t java_read_unicode_collapsing_terminators
PARAMS ((java_lexer *, int *));
static int java_parse_escape_sequence PARAMS ((void));
static int java_start_char_p PARAMS ((unicode_t));
static int java_part_char_p PARAMS ((unicode_t));
static int java_parse_doc_section PARAMS ((int));
static void java_parse_end_comment PARAMS ((int));
static int java_get_unicode PARAMS ((void));
static int java_read_unicode PARAMS ((java_lexer *, int *));
static int java_read_unicode_collapsing_terminators PARAMS ((java_lexer *,
int *));
static void java_store_unicode PARAMS ((struct java_line *, unicode_t, int));
static unicode_t java_read_char PARAMS ((java_lexer *));
static int java_read_char PARAMS ((java_lexer *));
static void java_allocate_new_line PARAMS ((void));
static void java_unget_unicode PARAMS ((void));
static unicode_t java_sneak_unicode PARAMS ((void));
@ -217,6 +218,7 @@ java_new_lexer (finput, encoding)
lex->finput = finput;
lex->bs_count = 0;
lex->unget_value = 0;
lex->hit_eof = 0;
#ifdef HAVE_ICONV
lex->handle = iconv_open ("UCS-2", encoding);
@ -298,7 +300,7 @@ java_destroy_lexer (lex)
free (lex);
}
static unicode_t
static int
java_read_char (lex)
java_lexer *lex;
{
@ -496,12 +498,12 @@ java_store_unicode (l, c, unicode_escape_p)
l->unicode_escape_p [l->size++] = unicode_escape_p;
}
static unicode_t
static int
java_read_unicode (lex, unicode_escape_p)
java_lexer *lex;
int *unicode_escape_p;
{
unicode_t c;
int c;
c = java_read_char (lex);
*unicode_escape_p = 0;
@ -549,12 +551,12 @@ java_read_unicode (lex, unicode_escape_p)
return (unicode_t) '\\';
}
static unicode_t
static int
java_read_unicode_collapsing_terminators (lex, unicode_escape_p)
java_lexer *lex;
int *unicode_escape_p;
{
unicode_t c = java_read_unicode (lex, unicode_escape_p);
int c = java_read_unicode (lex, unicode_escape_p);
if (c == '\r')
{
@ -571,13 +573,18 @@ java_read_unicode_collapsing_terminators (lex, unicode_escape_p)
return c;
}
static unicode_t
static int
java_get_unicode ()
{
/* It's time to read a line when... */
if (!ctxp->c_line || ctxp->c_line->current == ctxp->c_line->size)
{
unicode_t c;
int c;
int found_chars = 0;
if (ctxp->lexer->hit_eof)
return UEOF;
java_allocate_new_line ();
if (ctxp->c_line->line[0] != '\n')
{
@ -586,15 +593,24 @@ java_get_unicode ()
int unicode_escape_p;
c = java_read_unicode_collapsing_terminators (ctxp->lexer,
&unicode_escape_p);
java_store_unicode (ctxp->c_line, c, unicode_escape_p);
if (ctxp->c_line->white_space_only
&& !JAVA_WHITE_SPACE_P (c)
&& c != '\n'
&& c != UEOF)
ctxp->c_line->white_space_only = 0;
if (c != UEOF)
{
found_chars = 1;
java_store_unicode (ctxp->c_line, c, unicode_escape_p);
if (ctxp->c_line->white_space_only
&& !JAVA_WHITE_SPACE_P (c)
&& c != '\n')
ctxp->c_line->white_space_only = 0;
}
if ((c == '\n') || (c == UEOF))
break;
}
if (c == UEOF && ! found_chars)
{
ctxp->lexer->hit_eof = 1;
return UEOF;
}
}
}
ctxp->c_line->char_col += JAVA_COLUMN_DELTA (0);
@ -606,9 +622,8 @@ java_get_unicode ()
* C is the first character following the '/' and '*'. */
static void
java_parse_end_comment (c)
unicode_t c;
int c;
{
for ( ;; c = java_get_unicode ())
{
switch (c)
@ -637,7 +652,7 @@ java_parse_end_comment (c)
static int
java_parse_doc_section (c)
unicode_t c;
int c;
{
int valid_tag = 0, seen_star = 0;
@ -655,10 +670,10 @@ java_parse_doc_section (c)
}
c = java_get_unicode();
}
if (c == UEOF)
java_lex_error ("Comment not terminated at end of input", 0);
if (seen_star && (c == '/'))
return 1; /* Goto step1 in caller */
@ -673,7 +688,7 @@ java_parse_doc_section (c)
c = java_get_unicode ();
tag [tag_index++] = c;
}
if (c == UEOF)
java_lex_error ("Comment not terminated at end of input", 0);
tag [tag_index] = '\0';
@ -685,28 +700,51 @@ java_parse_doc_section (c)
return 0;
}
/* This function to be used only by JAVA_ID_CHAR_P (), otherwise it
will return a wrong result. */
/* Return true if C is a valid start character for a Java identifier.
This is only called if C >= 128 -- smaller values are handled
inline. However, this function handles all values anyway. */
static int
java_letter_or_digit_p (c)
java_start_char_p (c)
unicode_t c;
{
return _JAVA_LETTER_OR_DIGIT_P (c);
unsigned int hi = c / 256;
char *page = type_table[hi];
unsigned long val = (unsigned long) page;
int flags;
if ((val & ~ (LETTER_PART | LETTER_START)) != 0)
flags = page[c & 255];
else
flags = val;
return flags & LETTER_START;
}
/* This function to be used only by JAVA_ID_CHAR_P (). */
/* Return true if C is a valid part character for a Java identifier.
This is only called if C >= 128 -- smaller values are handled
inline. However, this function handles all values anyway. */
static int
java_ignorable_control_p (c)
java_part_char_p (c)
unicode_t c;
{
return _JAVA_IDENTIFIER_IGNORABLE (c);
unsigned int hi = c / 256;
char *page = type_table[hi];
unsigned long val = (unsigned long) page;
int flags;
if ((val & ~ (LETTER_PART | LETTER_START)) != 0)
flags = page[c & 255];
else
flags = val;
return flags & LETTER_PART;
}
static unicode_t
static int
java_parse_escape_sequence ()
{
unicode_t char_lit;
unicode_t c;
int c;
switch (c = java_get_unicode ())
{
@ -754,8 +792,6 @@ java_parse_escape_sequence ()
return char_lit;
}
case '\n':
return '\n'; /* ULT, caught latter as a specific error */
default:
java_lex_error ("Invalid character in escape sequence", 0);
return JAVA_CHAR_ERROR;
@ -840,7 +876,8 @@ java_lex (java_lval)
#endif
YYSTYPE *java_lval;
{
unicode_t c, first_unicode;
int c;
unicode_t first_unicode;
int ascii_index, all_ascii;
char *string;
@ -863,7 +900,7 @@ java_lex (java_lval)
if ((c = java_get_unicode ()) == UEOF)
return 0; /* Ok here */
else
java_unget_unicode (); /* Caught latter at the end the function */
java_unget_unicode (); /* Caught later, at the end of the function */
}
/* Handle EOF here */
if (c == UEOF) /* Should probably do something here... */
@ -1189,7 +1226,7 @@ java_lex (java_lval)
/* Character literals */
if (c == '\'')
{
unicode_t char_lit;
int char_lit;
if ((c = java_get_unicode ()) == '\\')
char_lit = java_parse_escape_sequence ();
else
@ -1206,7 +1243,7 @@ java_lex (java_lval)
if (c != '\'')
java_lex_error ("Syntax error in character literal", 0);
if (c == JAVA_CHAR_ERROR)
if (char_lit == JAVA_CHAR_ERROR)
char_lit = 0; /* We silently convert it to zero */
JAVA_LEX_CHAR_LIT (char_lit);
@ -1225,7 +1262,11 @@ java_lex (java_lval)
{
if (c == '\\')
c = java_parse_escape_sequence ();
no_error &= (c != JAVA_CHAR_ERROR ? 1 : 0);
if (c == JAVA_CHAR_ERROR)
{
no_error = 0;
c = 0; /* We silently convert it to zero. */
}
java_unicode_2_utf8 (c);
}
if (c == '\n' || c == UEOF) /* ULT */
@ -1469,7 +1510,7 @@ java_lex (java_lval)
/* Keyword, boolean literal or null literal */
for (first_unicode = c, all_ascii = 1, ascii_index = 0;
JAVA_ID_CHAR_P (c); c = java_get_unicode ())
JAVA_PART_CHAR_P (c); c = java_get_unicode ())
{
java_unicode_2_utf8 (c);
if (all_ascii && c >= 128)
@ -1554,8 +1595,8 @@ java_lex (java_lval)
}
}
/* We may have and ID here */
if (JAVA_ID_CHAR_P(first_unicode) && !JAVA_DIGIT_P (first_unicode))
/* We may have an ID here */
if (JAVA_START_CHAR_P (first_unicode))
{
JAVA_LEX_ID (string);
java_lval->node = BUILD_ID_WFL (GET_IDENTIFIER (string));

346
gcc/java/lex.h
View File

@ -78,7 +78,7 @@ typedef unsigned short unicode_t;
/* Line information containers */
struct java_line {
unicode_t *line; /* The line's unicode */
char *unicode_escape_p; /* The maching char was a unicode escape */
char *unicode_escape_p; /* The matching char was a unicode escape */
unicode_t ahead[1]; /* Character ahead */
char unicode_escape_ahead_p; /* Character ahead is a unicode escape */
int max; /* buffer's max size */
@ -114,6 +114,9 @@ typedef struct java_lexer
/* If nonzero, a value that was pushed back. */
unicode_t unget_value;
/* If nonzero, we've hit EOF. Used only by java_get_unicode(). */
int hit_eof : 1;
#ifdef HAVE_ICONV
/* Nonzero if we've read any bytes. We only recognize the
byte-order-marker (BOM) as the first word. */
@ -141,7 +144,7 @@ typedef struct java_lexer
/* This is a buffer of characters already converted by iconv. We
use `char' here because we're assuming that iconv() converts to
big-endian UCS-2, and then we convert it ourselves. */
UCS-2, and then we convert it ourselves. */
unsigned char out_buffer[1024];
/* Index of first valid output character. -1 if no valid
@ -251,325 +254,38 @@ extern void set_float_handler PARAMS ((jmp_buf));
/* Macros to decode character ranges */
#define RANGE(c, l, h) (((c) >= l && (c) <= h))
#define JAVA_WHITE_SPACE_P(c) (c == ' ' || c == '\t' || c == '\f')
#define JAVA_ID_CHAR_P(c) ((c < 128 && (RANGE (c, 'A', 'Z') || \
RANGE (c, 'a', 'z') || \
RANGE (c, '0', '9') || \
c == '_' || \
c == '$')) || \
java_ignorable_control_p (c) || \
(c > 127 && java_letter_or_digit_p (c)))
#define JAVA_ASCII_DIGIT(c) RANGE(c,'0', '9')
#define JAVA_ASCII_OCTDIGIT(c) RANGE(c,'0', '7')
#define JAVA_ASCII_HEXDIGIT(c) (RANGE(c,'0', '9') || \
RANGE(c,'a', 'f') || \
RANGE(c,'A', 'F'))
#define JAVA_ASCII_FPCHAR(c) (RANGE(c,'d', 'f') || RANGE(c,'D', 'F') || \
#define JAVA_START_CHAR_P(c) ((c < 128 \
&& (RANGE (c, 'A', 'Z') \
|| RANGE (c, 'a', 'z') \
|| c == '_' \
|| c == '$')) \
|| (c >= 128 && java_start_char_p (c)))
#define JAVA_PART_CHAR_P(c) ((c < 128 \
&& (RANGE (c, 'A', 'Z') \
|| RANGE (c, 'a', 'z') \
|| RANGE (c, '0', '9') \
|| c == '_' \
|| c == '$' \
|| c == 0x0000 \
|| RANGE (c, 0x01, 0x08) \
|| RANGE (c, 0x0e, 0x1b) \
|| c == 0x7f)) \
|| (c >= 128 && java_part_char_p (c)))
#define JAVA_ASCII_DIGIT(c) RANGE (c, '0', '9')
#define JAVA_ASCII_OCTDIGIT(c) RANGE (c, '0', '7')
#define JAVA_ASCII_HEXDIGIT(c) (RANGE (c, '0', '9') || \
RANGE (c, 'a', 'f') || \
RANGE (c, 'A', 'F'))
#define JAVA_ASCII_FPCHAR(c) (RANGE (c, 'd', 'f') || RANGE (c, 'D', 'F') || \
c == '.' || JAVA_ASCII_DIGIT (c))
#define JAVA_FP_SUFFIX(c) (c == 'D' || c == 'd' || c == 'f' || c == 'F')
#define JAVA_FP_EXP(c) (c == 'E' || c == 'F')
#define JAVA_FP_PM(c) (c == '-' || c == '+')
#define JAVA_ASCII_LETTER(c) (RANGE(c,'a', 'z') || RANGE(c,'A', 'Z'))
#define JAVA_DIGIT_P(c) \
(RANGE (c, 0x030, 0x039) || /* ISO-Latin-1 (and ASCII) digits ('0'-'9') */ \
RANGE (c, 0x660, 0x669) || /* Arabic-Indic digits */ \
RANGE (c, 0x6F0, 0x6F9) || /* Eastern Arabic-Indic digits */ \
RANGE (c, 0x966, 0x96F) || /* Devanagari digits */ \
RANGE (c, 0x9E6, 0x9EF) || /* Bengali digits */ \
RANGE (c, 0xA66, 0xA6F) || /* Gurmukhi digits */ \
RANGE (c, 0xAE6, 0xAEF) || /* Gujarati digits */ \
RANGE (c, 0xB66, 0xB6F) || /* Oriya digits */ \
RANGE (c, 0xBE7, 0xBEF) || /* Tamil digits */ \
RANGE (c, 0xC66, 0xC6F) || /* Telugu digits */ \
RANGE (c, 0xCE6, 0xCEF) || /* Kannada digits */ \
RANGE (c, 0xD66, 0xD6F) || /* Malayalam digits */ \
RANGE (c, 0xE50, 0xE59) || /* Thai digits */ \
RANGE (c, 0xED0, 0xED9)) /* Lao digits */
/* This is not to be used as a stand alone macro. Use JAVA_ID_CHAR_P()
or the forcoming JAVA_LETTER_OR_DIGIT_P() instead.
It need to be split by region. FIXME. */
#define _JAVA_LETTER_OR_DIGIT_P(c) \
(RANGE (c, 0x00C0, 0x00D6) || \
RANGE (c, 0x00D8, 0x00F6) || \
RANGE (c, 0x00F8, 0x01F5) || \
RANGE (c, 0x01FA, 0x0217) || \
RANGE (c, 0x0250, 0x02A8) || \
RANGE (c, 0x02B0, 0x02DE) || \
RANGE (c, 0x02E0, 0x02E9) || \
RANGE (c, 0x0300, 0x0345) || \
RANGE (c, 0x0360, 0x0361) || \
RANGE (c, 0x0374, 0x0375) || \
c == 0x037A || \
c == 0x037E || \
RANGE (c, 0x0384, 0x038A) || \
c == 0x038C || \
c == 0x038E || \
RANGE (c, 0x038F, 0x03A1) || \
RANGE (c, 0x03A3, 0x03CE) || \
RANGE (c, 0x03D0, 0x03D6) || \
RANGE (c, 0x03DA, 0x03E2) || \
c == 0x03DA || \
c == 0x03DC || \
c == 0x03DE || \
c == 0x03E0 || \
RANGE (c, 0x03E2, 0x03F3) || \
RANGE (c, 0x0401, 0x040C) || \
RANGE (c, 0x040E, 0x044F) || \
RANGE (c, 0x0451, 0x045C) || \
RANGE (c, 0x045E, 0x0486) || \
RANGE (c, 0x0490, 0x04C4) || \
RANGE (c, 0x04C7, 0x04C8) || \
RANGE (c, 0x04CB, 0x04CC) || \
RANGE (c, 0x04D0, 0x04EB) || \
RANGE (c, 0x04EE, 0x04F5) || \
RANGE (c, 0x04F8, 0x04F9) || \
RANGE (c, 0x0531, 0x0556) || \
RANGE (c, 0x0559, 0x055F) || \
RANGE (c, 0x0561, 0x0587) || \
c == 0x0589 || \
RANGE (c, 0x05B0, 0x05B9) || \
RANGE (c, 0x05BB, 0x05C3) || \
RANGE (c, 0x05D0, 0x05EA) || \
RANGE (c, 0x05F0, 0x05F4) || \
c == 0x060C || \
c == 0x061B || \
c == 0x061F || \
c == 0x0621 || \
RANGE (c, 0x0622, 0x063A) || \
RANGE (c, 0x0640, 0x0652) || \
RANGE (c, 0x0660, 0x066D) || \
RANGE (c, 0x0670, 0x06B7) || \
RANGE (c, 0x06BA, 0x06BE) || \
RANGE (c, 0x06C0, 0x06CE) || \
RANGE (c, 0x06D0, 0x06ED) || \
RANGE (c, 0x06F0, 0x06F9) || \
RANGE (c, 0x0901, 0x0903) || \
RANGE (c, 0x0905, 0x0939) || \
RANGE (c, 0x093C, 0x094D) || \
RANGE (c, 0x0950, 0x0954) || \
RANGE (c, 0x0958, 0x0970) || \
RANGE (c, 0x0981, 0x0983) || \
RANGE (c, 0x0985, 0x098C) || \
RANGE (c, 0x098F, 0x0990) || \
RANGE (c, 0x0993, 0x09A8) || \
RANGE (c, 0x09AA, 0x09B0) || \
c == 0x09B2 || \
RANGE (c, 0x09B6, 0x09B9) || \
c == 0x09BC || \
c == 0x09BE || \
RANGE (c, 0x09BF, 0x09C4) || \
RANGE (c, 0x09C7, 0x09C8) || \
RANGE (c, 0x09CB, 0x09CD) || \
c == 0x09D7 || \
RANGE (c, 0x09DC, 0x09DD) || \
RANGE (c, 0x09DF, 0x09E3) || \
RANGE (c, 0x09E6, 0x09FA) || \
c == 0x0A02 || \
RANGE (c, 0x0A05, 0x0A0A) || \
RANGE (c, 0x0A0F, 0x0A10) || \
RANGE (c, 0x0A13, 0x0A28) || \
RANGE (c, 0x0A2A, 0x0A30) || \
RANGE (c, 0x0A32, 0x0A33) || \
RANGE (c, 0x0A35, 0x0A36) || \
RANGE (c, 0x0A38, 0x0A39) || \
c == 0x0A3C || \
c == 0x0A3E || \
RANGE (c, 0x0A3F, 0x0A42) || \
RANGE (c, 0x0A47, 0x0A48) || \
RANGE (c, 0x0A4B, 0x0A4D) || \
RANGE (c, 0x0A59, 0x0A5C) || \
c == 0x0A5E || \
RANGE (c, 0x0A66, 0x0A74) || \
RANGE (c, 0x0A81, 0x0A83) || \
RANGE (c, 0x0A85, 0x0A8B) || \
c == 0x0A8D || \
c == 0x0A8F || \
RANGE (c, 0x0A90, 0x0A91) || \
RANGE (c, 0x0A93, 0x0AA8) || \
RANGE (c, 0x0AAA, 0x0AB0) || \
RANGE (c, 0x0AB2, 0x0AB3) || \
RANGE (c, 0x0AB5, 0x0AB9) || \
RANGE (c, 0x0ABC, 0x0AC5) || \
RANGE (c, 0x0AC7, 0x0AC9) || \
RANGE (c, 0x0ACB, 0x0ACD) || \
c == 0x0AD0 || \
c == 0x0AE0 || \
RANGE (c, 0x0AE6, 0x0AEF) || \
RANGE (c, 0x0B01, 0x0B03) || \
RANGE (c, 0x0B05, 0x0B0C) || \
RANGE (c, 0x0B0F, 0x0B10) || \
RANGE (c, 0x0B13, 0x0B28) || \
RANGE (c, 0x0B2A, 0x0B30) || \
RANGE (c, 0x0B32, 0x0B33) || \
RANGE (c, 0x0B36, 0x0B39) || \
RANGE (c, 0x0B3C, 0x0B43) || \
RANGE (c, 0x0B47, 0x0B48) || \
RANGE (c, 0x0B4B, 0x0B4D) || \
RANGE (c, 0x0B56, 0x0B57) || \
RANGE (c, 0x0B5C, 0x0B5D) || \
RANGE (c, 0x0B5F, 0x0B61) || \
RANGE (c, 0x0B66, 0x0B70) || \
RANGE (c, 0x0B82, 0x0B83) || \
RANGE (c, 0x0B85, 0x0B8A) || \
RANGE (c, 0x0B8E, 0x0B90) || \
RANGE (c, 0x0B92, 0x0B95) || \
RANGE (c, 0x0B99, 0x0B9A) || \
c == 0x0B9C || \
c == 0x0B9E || \
c == 0x0B9F || \
RANGE (c, 0x0BA3, 0x0BA4) || \
RANGE (c, 0x0BA8, 0x0BAA) || \
RANGE (c, 0x0BAE, 0x0BB5) || \
RANGE (c, 0x0BB7, 0x0BB9) || \
RANGE (c, 0x0BBE, 0x0BC2) || \
RANGE (c, 0x0BC6, 0x0BC8) || \
RANGE (c, 0x0BCA, 0x0BCD) || \
c == 0x0BD7 || \
RANGE (c, 0x0BE7, 0x0BF2) || \
RANGE (c, 0x0C01, 0x0C03) || \
RANGE (c, 0x0C05, 0x0C0C) || \
RANGE (c, 0x0C0E, 0x0C10) || \
RANGE (c, 0x0C12, 0x0C28) || \
RANGE (c, 0x0C2A, 0x0C33) || \
RANGE (c, 0x0C35, 0x0C39) || \
RANGE (c, 0x0C3E, 0x0C44) || \
RANGE (c, 0x0C46, 0x0C48) || \
RANGE (c, 0x0C4A, 0x0C4D) || \
RANGE (c, 0x0C55, 0x0C56) || \
RANGE (c, 0x0C60, 0x0C61) || \
RANGE (c, 0x0C66, 0x0C6F) || \
RANGE (c, 0x0C82, 0x0C83) || \
RANGE (c, 0x0C85, 0x0C8C) || \
RANGE (c, 0x0C8E, 0x0C90) || \
RANGE (c, 0x0C92, 0x0CA8) || \
RANGE (c, 0x0CAA, 0x0CB3) || \
RANGE (c, 0x0CB5, 0x0CB9) || \
RANGE (c, 0x0CBE, 0x0CC4) || \
RANGE (c, 0x0CC6, 0x0CC8) || \
RANGE (c, 0x0CCA, 0x0CCD) || \
RANGE (c, 0x0CD5, 0x0CD6) || \
c == 0x0CDE || \
c == 0x0CE0 || \
c == 0x0CE1 || \
RANGE (c, 0x0CE6, 0x0CEF) || \
RANGE (c, 0x0D02, 0x0D03) || \
RANGE (c, 0x0D05, 0x0D0C) || \
RANGE (c, 0x0D0E, 0x0D10) || \
RANGE (c, 0x0D12, 0x0D28) || \
RANGE (c, 0x0D2A, 0x0D39) || \
RANGE (c, 0x0D3E, 0x0D43) || \
RANGE (c, 0x0D46, 0x0D48) || \
RANGE (c, 0x0D4A, 0x0D4D) || \
c == 0x0D57 || \
RANGE (c, 0x0D60, 0x0D61) || \
RANGE (c, 0x0D66, 0x0D6F) || \
RANGE (c, 0x0E01, 0x0E3A) || \
RANGE (c, 0x0E3F, 0x0E5B) || \
RANGE (c, 0x0E81, 0x0E82) || \
c == 0x0E84 || \
RANGE (c, 0x0E87, 0x0E88) || \
c == 0x0E8A || \
c == 0x0E8D || \
RANGE (c, 0x0E94, 0x0E97) || \
RANGE (c, 0x0E99, 0x0E9F) || \
RANGE (c, 0x0EA1, 0x0EA3) || \
c == 0x0EA5 || \
c == 0x0EA7 || \
RANGE (c, 0x0EAA, 0x0EAB) || \
RANGE (c, 0x0EAD, 0x0EB9) || \
RANGE (c, 0x0EBB, 0x0EBD) || \
RANGE (c, 0x0EC0, 0x0EC4) || \
c == 0x0EC6 || \
c == 0x0EC8 || \
RANGE (c, 0x0EC9, 0x0ECD) || \
RANGE (c, 0x0ED0, 0x0ED9) || \
RANGE (c, 0x0EDC, 0x0EDD) || \
RANGE (c, 0x10A0, 0x10C5) || \
RANGE (c, 0x10D0, 0x10F6) || \
c == 0x10FB || \
RANGE (c, 0x1100, 0x1159) || \
RANGE (c, 0x115F, 0x11A2) || \
RANGE (c, 0x11A8, 0x11F9) || \
RANGE (c, 0x1E00, 0x1E9A) || \
RANGE (c, 0x1EA0, 0x1EF9) || \
RANGE (c, 0x1F00, 0x1F15) || \
RANGE (c, 0x1F18, 0x1F1D) || \
RANGE (c, 0x1F20, 0x1F45) || \
RANGE (c, 0x1F48, 0x1F4D) || \
RANGE (c, 0x1F50, 0x1F57) || \
c == 0x1F59 || \
c == 0x1F5B || \
c == 0x1F5D || \
RANGE (c, 0x1F5F, 0x1F7D) || \
RANGE (c, 0x1F80, 0x1FB4) || \
RANGE (c, 0x1FB6, 0x1FC4) || \
RANGE (c, 0x1FC6, 0x1FD3) || \
RANGE (c, 0x1FD6, 0x1FDB) || \
RANGE (c, 0x1FDD, 0x1FEF) || \
RANGE (c, 0x1FF2, 0x1FF4) || \
RANGE (c, 0x1FF6, 0x1FFE) || \
RANGE (c, 0x3041, 0x3094) || \
RANGE (c, 0x3099, 0x309E) || \
RANGE (c, 0x30A1, 0x30FE) || \
RANGE (c, 0x3105, 0x312C) || \
RANGE (c, 0x3131, 0x318E) || \
RANGE (c, 0x3190, 0x319F) || \
RANGE (c, 0x3200, 0x321C) || \
RANGE (c, 0x3220, 0x3243) || \
RANGE (c, 0x3260, 0x327B) || \
RANGE (c, 0x327F, 0x32B0) || \
RANGE (c, 0x32C0, 0x32CB) || \
RANGE (c, 0x32D0, 0x32FE) || \
RANGE (c, 0x3300, 0x3376) || \
RANGE (c, 0x337B, 0x33DD) || \
RANGE (c, 0x33E0, 0x33FE) || \
RANGE (c, 0x3400, 0x9FA5) || \
RANGE (c, 0xF900, 0xFA2D) || \
RANGE (c, 0xFB00, 0xFB06) || \
RANGE (c, 0xFB13, 0xFB17) || \
RANGE (c, 0xFB1E, 0xFB36) || \
RANGE (c, 0xFB38, 0xFB3C) || \
c == 0xFB3E || \
c == 0xFB40 || \
c == 0xFB41 || \
c == 0xFB43 || \
c == 0xFB44 || \
c == 0xFB46 || \
RANGE (c, 0xFB47, 0xFBB1) || \
RANGE (c, 0xFBD3, 0xFD3F) || \
RANGE (c, 0xFD50, 0xFD8F) || \
RANGE (c, 0xFD92, 0xFDC7) || \
RANGE (c, 0xFDF0, 0xFDFB) || \
RANGE (c, 0xFE70, 0xFE72) || \
c == 0xFE74 || \
c == 0xFE76 || \
RANGE (c, 0xFE77, 0xFEFC) || \
RANGE (c, 0xFF10, 0xFF19) || \
RANGE (c, 0xFF21, 0xFF3A) || \
RANGE (c, 0xFF41, 0xFF5A) || \
RANGE (c, 0xFF66, 0xFFBE) || \
RANGE (c, 0xFFC2, 0xFFC7) || \
RANGE (c, 0xFFCA, 0xFFCF) || \
RANGE (c, 0xFFD2, 0xFFD7) || \
RANGE (c, 0xFFDA, 0xFFDC))
/* Identifier-ignorable characters. This should not be used
standalone. Note that the JCL says 200a->200e. That is a typo.
The correct values are 202a->202e. Note also that we test against
0x0000 separately to avoid a warning. */
#define _JAVA_IDENTIFIER_IGNORABLE(c) \
(c == 0x0000 \
|| RANGE (c, 0x0001, 0x0008) \
|| RANGE (c, 0x000e, 0x001b) \
|| RANGE (c, 0x007f, 0x009f) \
|| RANGE (c, 0x200c, 0x200f) \
|| RANGE (c, 0x202a, 0x202e) \
|| RANGE (c, 0x206a, 0x206f) \
|| c == 0xfeff)
#define JAVA_ASCII_LETTER(c) (RANGE (c, 'a', 'z') || RANGE (c, 'A', 'Z'))
/* Constants */
#define JAVA_CHAR_ERROR 0xFFC1 /* This is an illegal unicode!?! FIXME */
#define JAVA_READ_BUFFER 256
#define UEOF (unicode_t)0xffff
#define JAVA_CHAR_ERROR -2
#define UEOF -1
#endif