mirror of
https://sourceware.org/git/glibc.git
synced 2024-11-08 14:20:07 +00:00
bb5bbc2070
Unicode 15.1.0 Support: Character encoding, character type info, and
transliteration tables are all updated to Unicode 15.1.0, using
the generator scripts contributed by Mike FABIAN (Red Hat).
Total removed characters in newly generated CHARMAP: 0
Total changed characters in newly generated CHARMAP: 0
Total added characters in newly generated CHARMAP: 627
Total removed characters in newly generated WIDTH: 0
Total changed characters in newly generated WIDTH: 0
Total added characters in newly generated WIDTH: 627
alpha: Added 622 characters in new ctype which were not in old ctype
graph: Added 627 characters in new ctype which were not in old ctype
print: Added 627 characters in new ctype which were not in old ctype
punct: Added 5 characters in new ctype which were not in old ctype
The five characters added to punct are:
2FFC;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM RIGHT;So;0;ON;;;;;N;;;;;
2FFD;IDEOGRAPHIC DESCRIPTION CHARACTER SURROUND FROM LOWER RIGHT;So;0;ON;;;;;N;;;;;
2FFE;IDEOGRAPHIC DESCRIPTION CHARACTER HORIZONTAL REFLECTION;So;0;ON;;;;;N;;;;;
2FFF;IDEOGRAPHIC DESCRIPTION CHARACTER ROTATION;So;0;ON;;;;;N;;;;;
31EF;IDEOGRAPHIC DESCRIPTION CHARACTER SUBTRACTION;So;0;ON;;;;;N;;;;;
The Unicode announcement blog entry says "[...] adds 627
characters, [...] additions include 622 CJK unified ideographs in
a new block, [...]", so that looks OK. The Unicode
blog mentions "six completely new emoji" but they don't appear here as
they are all sequences and not single code points.
Resolves: BZ #30854
Reviewed-by: Carlos O'Donell <carlos@redhat.com>
146 lines
5.3 KiB
Makefile
146 lines
5.3 KiB
Makefile
# Copyright (C) 2015-2023 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
|
|
# <https://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 = 15.1.0
|
|
|
|
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/$@
|