localedata/unicode-gen/gen_translit_circle.py

   1 #!/usr/bin/python3
   2 # -*- coding: utf-8 -*-
   3 #
   4 # Generate a translit_circle file from a UnicodeData file.
   5 # Copyright (C) 2015-2024 Free Software Foundation, Inc.
   6 # This file is part of the GNU C Library.
   7 #
   8 # The GNU C Library is free software; you can redistribute it and/or
   9 # modify it under the terms of the GNU Lesser General Public
  10 # License as published by the Free Software Foundation; either
  11 # version 2.1 of the License, or (at your option) any later version.
  12 #
  13 # The GNU C Library is distributed in the hope that it will be useful,
  14 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  15 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  16 # Lesser General Public License for more details.
  17 #
  18 # You should have received a copy of the GNU Lesser General Public
  19 # License along with the GNU C Library; if not, see
  20 # <https://www.gnu.org/licenses/>.
  21
  22 '''
  23 Generate a translit_circle file from UnicodeData.txt
  24
  25 To see how this script is used, call it with the “-h” option:
  26
  27     $ ./gen_translit_circle -h
  28     … prints usage message …
  29 '''
  30
  31 import argparse
  32 import time
  33 import unicode_utils
  34
  35 def read_input_file(filename):
  36     '''Reads the original glibc translit_circle file to get the
  37     original head and tail.
  38
  39     We want to replace only the part of the file between
  40     “translit_start” and “translit_end”
  41     '''
  42     head = tail = ''
  43     with open(filename, mode='r') as translit_file:
  44         for line in translit_file:
  45             head = head + line
  46             if line.startswith('translit_start'):
  47                 break
  48         for line in translit_file:
  49             if line.startswith('translit_end'):
  50                 tail = line
  51                 break
  52         for line in translit_file:
  53             tail = tail + line
  54     return (head, tail)
  55
  56 def output_head(translit_file, unicode_version, head=''):
  57     '''Write the header of the output file, i.e. the part of the file
  58     before the “translit_start” line.
  59     '''
  60     if ARGS.input_file and head:
  61         translit_file.write(head)
  62     else:
  63         translit_file.write('escape_char /\n')
  64         translit_file.write('comment_char %\n')
  65         translit_file.write(unicode_utils.COMMENT_HEADER)
  66         translit_file.write('\n')
  67         translit_file.write('% Transliterations of encircled characters.\n')
  68         translit_file.write('% Generated automatically from UnicodeData.txt '
  69                             + 'by gen_translit_circle.py '
  70                             + 'on {:s} '.format(time.strftime('%Y-%m-%d'))
  71                             + 'for Unicode {:s}.\n'.format(unicode_version))
  72         translit_file.write('\n')
  73         translit_file.write('LC_CTYPE\n')
  74         translit_file.write('\n')
  75         translit_file.write('translit_start\n')
  76
  77 def output_tail(translit_file, tail=''):
  78     '''Write the tail of the output file'''
  79     if ARGS.input_file and tail:
  80         translit_file.write(tail)
  81     else:
  82         translit_file.write('translit_end\n')
  83         translit_file.write('\n')
  84         translit_file.write('END LC_CTYPE\n')
  85
  86 def output_transliteration(translit_file):
  87     '''Write the new transliteration to the output file'''
  88     translit_file.write('\n')
  89     for code_point in sorted(unicode_utils.UNICODE_ATTRIBUTES):
  90         name = unicode_utils.UNICODE_ATTRIBUTES[code_point]['name']
  91         decomposition = unicode_utils.UNICODE_ATTRIBUTES[
  92             code_point]['decomposition']
  93         if decomposition.startswith('<circle>'):
  94             decomposition = decomposition[9:]
  95             decomposed_code_points = [int(x, 16)
  96                                       for x in decomposition.split(' ')]
  97             translit_file.write('% {:s}\n'.format(name))
  98             translit_file.write('{:s} "<U0028>'.format(
  99                 unicode_utils.ucs_symbol(code_point)))
 100             for decomposed_code_point in decomposed_code_points:
 101                 translit_file.write('{:s}'.format(
 102                     unicode_utils.ucs_symbol(decomposed_code_point)))
 103             translit_file.write('<U0029>"\n')
 104     translit_file.write('\n')
 105
 106
 107 if __name__ == "__main__":
 108     PARSER = argparse.ArgumentParser(
 109         description='''
 110         Generate a translit_circle file from UnicodeData.txt.
 111         ''')
 112     PARSER.add_argument(
 113         '-u', '--unicode_data_file',
 114         nargs='?',
 115         type=str,
 116         default='UnicodeData.txt',
 117         help=('The UnicodeData.txt file to read, '
 118               + 'default: %(default)s'))
 119     PARSER.add_argument(
 120         '-i', '--input_file',
 121         nargs='?',
 122         type=str,
 123         help=''' The original glibc/localedata/locales/translit_combining
 124         file.''')
 125     PARSER.add_argument(
 126         '-o', '--output_file',
 127         nargs='?',
 128         type=str,
 129         default='translit_circle.new',
 130         help='''The new translit_circle file, default: %(default)s.  If the
 131         original glibc/localedata/locales/translit_circle file has
 132         been given as an option, the header up to the
 133         “translit_start” line and the tail from the “translit_end”
 134         line to the end of the file will be copied unchanged into the
 135         output file.  ''')
 136     PARSER.add_argument(
 137         '--unicode_version',
 138         nargs='?',
 139         required=True,
 140         type=str,
 141         help='The Unicode version of the input files used.')
 142     ARGS = PARSER.parse_args()
 143
 144     unicode_utils.fill_attributes(ARGS.unicode_data_file)
 145     HEAD = TAIL = ''
 146     if ARGS.input_file:
 147         (HEAD, TAIL) = read_input_file(ARGS.input_file)
 148     with open(ARGS.output_file, mode='w') as TRANSLIT_FILE:
 149         output_head(TRANSLIT_FILE, ARGS.unicode_version, head=HEAD)
 150         output_transliteration(TRANSLIT_FILE)
 151         output_tail(TRANSLIT_FILE, tail=TAIL)