mirror of
https://sourceware.org/git/glibc.git
synced 2025-01-12 12:10:16 +00:00
86bdd49d93
Unicode 12.0.0 Support: Character encoding, character type info, and
transliteration tables are all updated to Unicode 12.0.0, using
the generator scripts contributed by Mike FABIAN (Red Hat).
Some info about the number of characters added or changed:
Total added characters in newly generated CHARMAP: 554
Total added characters in newly generated WIDTH: 106
alpha: Missing 8 characters of old ctype in new ctype
(These are combining marks, apparently they were removed from alpha
on purpose)
alpha: Added 295 characters in new ctype which were not in old ctype
combining: Missing 2 characters of old ctype in new ctype
(U+1CF2 VEDIC SIGN ARDHAVISARGA and U+1CF3 VEDIC SIGN ROTATED ARDHAVISARGA,
these are now "Alphabetic" in Unicode 12.0.0)
combining: Added 37 characters in new ctype which were not in old ctype
combining_level3: Missing 2 characters of old ctype in new ctype
(U+1CF2 VEDIC SIGN ARDHAVISARGA and U+1CF3 VEDIC SIGN ROTATED ARDHAVISARGA,
these are now "Alphabetic" in Unicode 12.0.0)
combining_level3: Added 26 characters in new ctype which were not in old ctype
graph: Added 554 characters in new ctype which were not in old ctype
lower: Added 6 characters in new ctype which were not in old ctype
print: Added 554 characters in new ctype which were not in old ctype
punct: Missing 29 characters of old ctype in new ctype
(These characters have all become "Alphabetic" in Unicode 12.0.0.
Therefore, they are not in "punct" anymore (see: is_punct() in unicode_utils.py))
punct: Added 296 characters in new ctype which were not in old ctype
tolower: Added 7 characters in new ctype which were not in old ctype
totitle: Added 7 characters in new ctype which were not in old ctype
toupper: Added 7 characters in new ctype which were not in old ctype
upper: Added 7 characters in new ctype which were not in old ctype
[BZ #24307]
* localedata/unicode-gen/Makefile (UNICODE_VERSION): Set to 12.0.0.
* localedata/unicode-gen/DerivedCoreProperties.txt: Update to Unicode 12.0.0.
* localedata/unicode-gen/EastAsianWidth.txt: Likewise.
* localedata/unicode-gen/PropList.txt: Likewise.
* localedata/unicode-gen/UnicodeData.txt: Likewise.
* localedata/unicode-gen/ctype_compatibility_test_cases.py: U+108D became
"Alphabetic" in Unicode 12.0.0. Adapt test case.
* 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.
146 lines
5.3 KiB
Makefile
146 lines
5.3 KiB
Makefile
# 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.
|
|
|
|
|
|
UNICODE_VERSION = 12.0.0
|
|
|
|
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/$@
|