Unicode 7.0.0 update; added generator scripts.

for  localedata/ChangeLog

	[BZ #17588]
	[BZ #13064]
	[BZ #14094]
	[BZ #17998]
	* unicode-gen/Makefile: New.
	* unicode-gen/unicode-license.txt: New, from Unicode.
	* unicode-gen/UnicodeData.txt: New, from Unicode.
	* unicode-gen/DerivedCoreProperties.txt: New, from Unicode.
	* unicode-gen/EastAsianWidth.txt: New, from Unicode.
	* unicode-gen/gen_unicode_ctype.py: New generator, from Mike
	FABIAN <mfabian@redhat.com>.
	* unicode-gen/ctype_compatibility.py: New verifier, from
	Pravin Satpute <psatpute@redhat.com> and Mike FABIAN.
	* unicode-gen/ctype_compatibility_test_cases.py: New verifier
	module, from Mike FABIAN.
	* unicode-gen/utf8_gen.py: New generator, from Pravin Satpute
	and Mike FABIAN.
	* unicode-gen/utf8_compatibility.py: New verifier, from Pravin
	Satpute and Mike FABIAN.
	* charmaps/UTF-8: Update.
	* locales/i18n: Update.
	* gen-unicode-ctype.c: Remove.
	* tst-ctype-de_DE.ISO-8859-1.in: Adjust, islower now returns
	true for ordinal indicators.

1 files changed, 99 insertions, 0 deletions

diff --git a/localedata/unicode-gen/Makefile b/localedata/unicode-gen/Makefile
new file mode 100644
index 0000000000..166ee310d8
--- /dev/null
+++ b/localedata/unicode-gen/Makefile
@@ -0,0 +1,99 @@
+# Copyright (C) 2015 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
+# 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 = 7.0.0
+
+PYTHON3 = python3
+WGET = wget
+
+DOWNLOADS = UnicodeData.txt DerivedCoreProperties.txt EastAsianWidth.txt
+GENERATED = i18n UTF-8
+REPORTS = i18n-report UTF-8-report
+
+all: $(GENERATED)
+
+check: check-i18n check-UTF-8
+
+install:
+	cp -p i18n ../locales/i18n
+	cp -p UTF-8 ../charmaps/UTF-8
+
+clean: mostlyclean
+	-rm -rf __pycache__
+mostlyclean:
+	-rm -f $(REPORTS) $(GENERATED)
+
+.PHONY: all check clean mostlyclean install
+
+i18n: UnicodeData.txt DerivedCoreProperties.txt
+i18n: ../locales/i18n # Preserve non-ctype information.
+i18n: gen_unicode_ctype.py
+	$(PYTHON3) gen_unicode_ctype.py -u UnicodeData.txt \
+	  -d DerivedCoreProperties.txt -i ../locales/i18n -o $@ \
+	  --unicode_version $(UNICODE_VERSION)
+
+i18n-report: i18n ../locales/i18n
+i18n-report: ctype_compatibility.py ctype_compatibility_test_cases.py
+	$(PYTHON3) ./ctype_compatibility.py -o ../locales/i18n \
+	  -n i18n -a -m > $@
+
+check-i18n: i18n-report
+	@if grep '\(Missing\|Added\) [^0]\|^Number of errors[^=]* = [^0]' \
+		i18n-report; \
+	then echo manual verification required; false; else true; fi
+
+UTF-8: UnicodeData.txt EastAsianWidth.txt
+UTF-8: utf8_gen.py
+	$(PYTHON3) utf8_gen.py UnicodeData.txt EastAsianWidth.txt
+
+UTF-8-report: UTF-8 ../charmaps/UTF-8
+UTF-8-report: utf8_compatibility.py
+	$(PYTHON3) ./utf8_compatibility.py -o ../charmaps/UTF-8 \
+	  -n UTF-8 -a -m > $@
+
+check-UTF-8: UTF-8-report
+	@if grep '^Total.*: [^0]' UTF-8-report; \
+	then echo manual verification required; false; else true; fi
+
+
+.PHONY: downloads clean-downloads
+downloads: $(DOWNLOADS)
+clean-downloads:
+	-rm -f $(DOWNLOADS)
+
+$(DOWNLOADS):
+	$(WGET) http://www.unicode.org/Public/$(UNICODE_VERSION)/ucd/$@