1 #!/usr/bin/python3
2 # -*- coding: utf-8 -*-
3 #
4 # Generate a translit_font file from a UnicodeData file.
5 # Copyright (C) 2015-2023 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_font file from UnicodeData.txt
24
25 To see how this script is used, call it with the “-h” option:
26
27 $ ./gen_translit_font -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_font 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 font equivalents.\n')
68 translit_file.write('% Generated automatically from UnicodeData.txt '
69 + 'by gen_translit_font.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('<font>'):
94 decomposition = decomposition[7:]
95 decomposed_code_points = [[int(x, 16)
96 for x in decomposition.split(' ')]]
97 if decomposed_code_points[0]:
98 translit_file.write('{:s} '.format(
99 unicode_utils.ucs_symbol(code_point)))
100 for index in range(0, len(decomposed_code_points)):
101 if index > 0:
102 translit_file.write(';')
103 if len(decomposed_code_points[index]) > 1:
104 translit_file.write('"')
105 for decomposed_code_point in decomposed_code_points[index]:
106 translit_file.write('{:s}'.format(
107 unicode_utils.ucs_symbol(decomposed_code_point)))
108 if len(decomposed_code_points[index]) > 1:
109 translit_file.write('"')
110 translit_file.write(' % {:s}\n'.format(name))
111 translit_file.write('\n')
112
113 if __name__ == "__main__":
114 PARSER = argparse.ArgumentParser(
115 description='''
116 Generate a translit_font file from UnicodeData.txt.
117 ''')
118 PARSER.add_argument(
119 '-u', '--unicode_data_file',
120 nargs='?',
121 type=str,
122 default='UnicodeData.txt',
123 help=('The UnicodeData.txt file to read, '
124 + 'default: %(default)s'))
125 PARSER.add_argument(
126 '-i', '--input_file',
127 nargs='?',
128 type=str,
129 help=''' The original glibc/localedata/locales/translit_font
130 file.''')
131 PARSER.add_argument(
132 '-o', '--output_file',
133 nargs='?',
134 type=str,
135 default='translit_font.new',
136 help='''The new translit_font file, default: %(default)s. If the
137 original glibc/localedata/locales/translit_font file has
138 been given as an option, the header up to the
139 “translit_start” line and the tail from the “translit_end”
140 line to the end of the file will be copied unchanged into the
141 output file. ''')
142 PARSER.add_argument(
143 '--unicode_version',
144 nargs='?',
145 required=True,
146 type=str,
147 help='The Unicode version of the input files used.')
148 ARGS = PARSER.parse_args()
149
150 unicode_utils.fill_attributes(ARGS.unicode_data_file)
151 HEAD = TAIL = ''
152 if ARGS.input_file:
153 (HEAD, TAIL) = read_input_file(ARGS.input_file)
154 with open(ARGS.output_file, mode='w') as TRANSLIT_FILE:
155 output_head(TRANSLIT_FILE, ARGS.unicode_version, head=HEAD)
156 output_transliteration(TRANSLIT_FILE)
157 output_tail(TRANSLIT_FILE, tail=TAIL)