glibc/localedata/unicode-gen/gen_translit_circle.py

152 lines
5.6 KiB
Python
Raw Normal View History

#!/usr/bin/python3
# -*- coding: utf-8 -*-
#
# Generate a translit_circle file from a UnicodeData file.
# Copyright (C) 2015-2021 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
Prefer https to http for gnu.org and fsf.org URLs Also, change sources.redhat.com to sourceware.org. This patch was automatically generated by running the following shell script, which uses GNU sed, and which avoids modifying files imported from upstream: sed -ri ' s,(http|ftp)(://(.*\.)?(gnu|fsf|sourceware)\.org($|[^.]|\.[^a-z])),https\2,g s,(http|ftp)(://(.*\.)?)sources\.redhat\.com($|[^.]|\.[^a-z]),https\2sourceware.org\4,g ' \ $(find $(git ls-files) -prune -type f \ ! -name '*.po' \ ! -name 'ChangeLog*' \ ! -path COPYING ! -path COPYING.LIB \ ! -path manual/fdl-1.3.texi ! -path manual/lgpl-2.1.texi \ ! -path manual/texinfo.tex ! -path scripts/config.guess \ ! -path scripts/config.sub ! -path scripts/install-sh \ ! -path scripts/mkinstalldirs ! -path scripts/move-if-change \ ! -path INSTALL ! -path locale/programs/charmap-kw.h \ ! -path po/libc.pot ! -path sysdeps/gnu/errlist.c \ ! '(' -name configure \ -execdir test -f configure.ac -o -f configure.in ';' ')' \ ! '(' -name preconfigure \ -execdir test -f preconfigure.ac ';' ')' \ -print) and then by running 'make dist-prepare' to regenerate files built from the altered files, and then executing the following to cleanup: chmod a+x sysdeps/unix/sysv/linux/riscv/configure # Omit irrelevant whitespace and comment-only changes, # perhaps from a slightly-different Autoconf version. git checkout -f \ sysdeps/csky/configure \ sysdeps/hppa/configure \ sysdeps/riscv/configure \ sysdeps/unix/sysv/linux/csky/configure # Omit changes that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/powerpc/powerpc64/ppc-mcount.S: trailing lines git checkout -f \ sysdeps/powerpc/powerpc64/ppc-mcount.S \ sysdeps/unix/sysv/linux/s390/s390-64/syscall.S # Omit change that caused a pre-commit check to fail like this: # remote: *** error: sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S: last line does not end in newline git checkout -f sysdeps/sparc/sparc64/multiarch/memcpy-ultra3.S
2019-09-07 05:40:42 +00:00
# <https://www.gnu.org/licenses/>.
'''
Generate a translit_circle file from UnicodeData.txt
To see how this script is used, call it with the -h option:
$ ./gen_translit_circle -h
prints usage message
'''
import argparse
import time
import unicode_utils
def read_input_file(filename):
'''Reads the original glibc translit_circle file to get the
original head and tail.
We want to replace only the part of the file between
translit_start and translit_end
'''
head = tail = ''
with open(filename, mode='r') as translit_file:
for line in translit_file:
head = head + line
if line.startswith('translit_start'):
break
for line in translit_file:
if line.startswith('translit_end'):
tail = line
break
for line in translit_file:
tail = tail + line
return (head, tail)
def output_head(translit_file, unicode_version, head=''):
'''Write the header of the output file, i.e. the part of the file
before the translit_start line.
'''
if ARGS.input_file and head:
translit_file.write(head)
else:
translit_file.write('escape_char /\n')
translit_file.write('comment_char %\n')
translit_file.write(unicode_utils.COMMENT_HEADER)
translit_file.write('\n')
translit_file.write('% Transliterations of encircled characters.\n')
translit_file.write('% Generated automatically from UnicodeData.txt '
+ 'by gen_translit_circle.py '
+ 'on {:s} '.format(time.strftime('%Y-%m-%d'))
+ 'for Unicode {:s}.\n'.format(unicode_version))
translit_file.write('\n')
translit_file.write('LC_CTYPE\n')
translit_file.write('\n')
translit_file.write('translit_start\n')
def output_tail(translit_file, tail=''):
'''Write the tail of the output file'''
if ARGS.input_file and tail:
translit_file.write(tail)
else:
translit_file.write('translit_end\n')
translit_file.write('\n')
translit_file.write('END LC_CTYPE\n')
def output_transliteration(translit_file):
'''Write the new transliteration to the output file'''
translit_file.write('\n')
for code_point in sorted(unicode_utils.UNICODE_ATTRIBUTES):
name = unicode_utils.UNICODE_ATTRIBUTES[code_point]['name']
decomposition = unicode_utils.UNICODE_ATTRIBUTES[
code_point]['decomposition']
if decomposition.startswith('<circle>'):
decomposition = decomposition[9:]
decomposed_code_points = [int(x, 16)
for x in decomposition.split(' ')]
translit_file.write('% {:s}\n'.format(name))
translit_file.write('{:s} "<U0028>'.format(
unicode_utils.ucs_symbol(code_point)))
for decomposed_code_point in decomposed_code_points:
translit_file.write('{:s}'.format(
unicode_utils.ucs_symbol(decomposed_code_point)))
translit_file.write('<U0029>"\n')
translit_file.write('\n')
if __name__ == "__main__":
PARSER = argparse.ArgumentParser(
description='''
Generate a translit_circle file from UnicodeData.txt.
''')
PARSER.add_argument(
'-u', '--unicode_data_file',
nargs='?',
type=str,
default='UnicodeData.txt',
help=('The UnicodeData.txt file to read, '
+ 'default: %(default)s'))
PARSER.add_argument(
'-i', '--input_file',
nargs='?',
type=str,
help=''' The original glibc/localedata/locales/translit_combining
file.''')
PARSER.add_argument(
'-o', '--output_file',
nargs='?',
type=str,
default='translit_circle.new',
help='''The new translit_circle file, default: %(default)s. If the
original glibc/localedata/locales/translit_circle file has
been given as an option, the header up to the
translit_start line and the tail from the translit_end
line to the end of the file will be copied unchanged into the
output file. ''')
PARSER.add_argument(
'--unicode_version',
nargs='?',
required=True,
type=str,
help='The Unicode version of the input files used.')
ARGS = PARSER.parse_args()
unicode_utils.fill_attributes(ARGS.unicode_data_file)
HEAD = TAIL = ''
if ARGS.input_file:
(HEAD, TAIL) = read_input_file(ARGS.input_file)
with open(ARGS.output_file, mode='w') as TRANSLIT_FILE:
output_head(TRANSLIT_FILE, ARGS.unicode_version, head=HEAD)
output_transliteration(TRANSLIT_FILE)
output_tail(TRANSLIT_FILE, tail=TAIL)