glibc/localedata/unicode-gen/Makefile

146 lines
5.3 KiB
Makefile
Raw Normal View History

# Copyright (C) 2015-2019 Free Software Foundation, Inc.
# This file is part of the GNU C Library.
# The GNU C Library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
# The GNU C Library 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
# Lesser General Public License for more details.
# You should have received a copy of the GNU Lesser General Public
# License along with the GNU C Library; if not, see
# <http://www.gnu.org/licenses/>.
# Makefile for generating and updating Unicode-extracted files.
# This Makefile is NOT used as part of the GNU libc build. It needs
# to be run manually, within the source tree, at Unicode upgrades
# (change UNICODE_VERSION below), to update ../locales/i18n_ctype ctype
# information (part of the file is preserved, so don't wipe it all
# out), and ../charmaps/UTF-8.
# Use make all to generate the files used in the glibc build out of
# the original Unicode files; make check to verify that they are what
# we expect; make install to copy them to the location expected by the
# glibc build; and make clean to remove all generated files.
# We keep a local copy of the downloaded Unicode files, to avoid
# running afoul of the LGPL corresponding sources requirements, even
# though it's not clear that they are preferred over the generated
# files for making modifications.
Bug 23308: Update to Unicode 11.0.0 Unicode 11.0.0 Support: Character encoding, character type info, and transliteration tables are all updated to Unicode 11.0.0, using the generator scripts contributed by Mike FABIAN (Red Hat). Some info about the number of characters added: Total added characters in newly generated CHARMAP: 684 Total added characters in newly generated WIDTH: 119 alpha: Added 380 characters in new ctype which were not in old ctype combining: Added 56 characters in new ctype which were not in old ctype combining_level3: Added 37 characters in new ctype which were not in old ctype graph: Added 684 characters in new ctype which were not in old ctype lower: Added 82 characters in new ctype which were not in old ctype print: Added 684 characters in new ctype which were not in old ctype punct: Added 304 characters in new ctype which were not in old ctype tolower: Added 79 characters in new ctype which were not in old ctype totitle: Added 33 characters in new ctype which were not in old ctype toupper: Added 79 characters in new ctype which were not in old ctype upper: Added 79 characters in new ctype which were not in old ctype No characters were removed. [BZ #23308] * unicode-gen/Makefile (UNICODE_VERSION): Set to 11.0.0. * localedata/unicode-gen/DerivedCoreProperties.txt: Update to Unicode 11.0.0. * localedata/unicode-gen/EastAsianWidth.txt: likewise. * localedata/unicode-gen/PropList.txt: likewise. * localedata/unicode-gen/UnicodeData.txt: likewise. * localedata/charmaps/UTF-8: Regenerate. * localedata/locales/i18n_ctype: likewise. * localedata/locales/tr_TR: likewise. * localedata/locales/translit_circle: likewise. * localedata/locales/translit_cjk_compat: likewise. * localedata/locales/translit_combining: likewise. * localedata/locales/translit_compat: likewise. * localedata/locales/translit_font: likewise. * localedata/locales/translit_fraction: likewise.
2018-06-18 18:23:44 +02:00
UNICODE_VERSION = 11.0.0
PYTHON3 = python3
WGET = wget
DOWNLOADS = UnicodeData.txt DerivedCoreProperties.txt EastAsianWidth.txt PropList.txt
GENERATED = i18n_ctype tr_TR UTF-8 translit_combining translit_compat translit_circle translit_cjk_compat translit_font translit_fraction
REPORTS = i18n_ctype-report UTF-8-report
all: $(GENERATED)
check: check-i18n_ctype check-UTF-8
install:
cp -p i18n_ctype ../locales/i18n_ctype
cp -p tr_TR ../locales/tr_TR
cp -p UTF-8 ../charmaps/UTF-8
cp -p translit_combining ../locales/translit_combining
cp -p translit_compat ../locales/translit_compat
cp -p translit_circle ../locales/translit_circle
cp -p translit_cjk_compat ../locales/translit_cjk_compat
cp -p translit_font ../locales/translit_font
cp -p translit_fraction ../locales/translit_fraction
clean: mostlyclean
-rm -rf __pycache__
mostlyclean:
-rm -f $(REPORTS) $(GENERATED)
.PHONY: all check clean mostlyclean install
i18n_ctype: UnicodeData.txt DerivedCoreProperties.txt
i18n_ctype: ../locales/i18n_ctype # Preserve non-ctype information.
i18n_ctype: gen_unicode_ctype.py
$(PYTHON3) gen_unicode_ctype.py -u UnicodeData.txt \
-d DerivedCoreProperties.txt -i ../locales/i18n_ctype -o $@ \
--unicode_version $(UNICODE_VERSION)
i18n_ctype-report: i18n_ctype ../locales/i18n_ctype
i18n_ctype-report: ctype_compatibility.py ctype_compatibility_test_cases.py
$(PYTHON3) ./ctype_compatibility.py -o ../locales/i18n_ctype \
-n i18n_ctype -a -m > $@
check-i18n_ctype: i18n_ctype-report
@if grep '\(Missing\|Added\) [^0]\|^Number of errors[^=]* = [^0]' \
i18n_ctype-report; \
then echo manual verification required; false; else true; fi
tr_TR: UnicodeData.txt DerivedCoreProperties.txt
tr_TR: ../locales/tr_TR # Preserve non-ctype information.
tr_TR: gen_unicode_ctype.py
$(PYTHON3) gen_unicode_ctype.py -u UnicodeData.txt \
-d DerivedCoreProperties.txt -i ../locales/tr_TR -o $@ \
--unicode_version $(UNICODE_VERSION) --turkish
UTF-8: UnicodeData.txt EastAsianWidth.txt
UTF-8: utf8_gen.py
$(PYTHON3) utf8_gen.py -u UnicodeData.txt \
-e EastAsianWidth.txt -p PropList.txt \
--unicode_version $(UNICODE_VERSION)
UTF-8-report: UTF-8 ../charmaps/UTF-8
UTF-8-report: utf8_compatibility.py
$(PYTHON3) ./utf8_compatibility.py -u UnicodeData.txt \
-e EastAsianWidth.txt -o ../charmaps/UTF-8 \
-n UTF-8 -a -m -c > $@
check-UTF-8: UTF-8-report
@if grep '^Total.*: [^0]' UTF-8-report; \
then echo manual verification required; false; else true; fi
translit_combining: UnicodeData.txt
translit_combining: gen_translit_combining.py
$(PYTHON3) ./gen_translit_combining.py -u UnicodeData.txt \
-o $@ --unicode_version $(UNICODE_VERSION)
translit_compat: UnicodeData.txt
translit_compat: gen_translit_compat.py
$(PYTHON3) ./gen_translit_compat.py -u UnicodeData.txt \
-o $@ --unicode_version $(UNICODE_VERSION)
translit_circle: UnicodeData.txt
translit_circle: gen_translit_circle.py
$(PYTHON3) ./gen_translit_circle.py -u UnicodeData.txt \
-o $@ --unicode_version $(UNICODE_VERSION)
translit_cjk_compat: UnicodeData.txt
translit_cjk_compat: gen_translit_cjk_compat.py
$(PYTHON3) ./gen_translit_cjk_compat.py -u UnicodeData.txt \
-o $@ --unicode_version $(UNICODE_VERSION)
translit_font: UnicodeData.txt
translit_font: gen_translit_font.py
$(PYTHON3) ./gen_translit_font.py -u UnicodeData.txt \
-o $@ --unicode_version $(UNICODE_VERSION)
translit_fraction: UnicodeData.txt
translit_fraction: gen_translit_fraction.py
$(PYTHON3) ./gen_translit_fraction.py -u UnicodeData.txt \
-o $@ --unicode_version $(UNICODE_VERSION)
.PHONY: downloads clean-downloads
downloads: $(DOWNLOADS)
clean-downloads:
-rm -f $(DOWNLOADS)
$(DOWNLOADS):
$(WGET) http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/$@