about summary refs log tree commit diff
path: root/localedata/unicode-gen/gen_translit_cjk_compat.py
blob: 627ff6bdd9887e243b5473ae1ac73a484e0a3db9 (plain) (blame)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
#!/usr/bin/python3
# -*- coding: utf-8 -*-
#
# Generate a translit_cjk_compat file from a UnicodeData file.
# 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/>.

'''
Generate a translit_cjk_compat file from UnicodeData.txt

To see how this script is used, call it with the “-h” option:

    $ ./gen_translit_cjk_compat -h
    … prints usage message …
'''

import argparse
import time
import sys
import unicode_utils

def read_input_file(filename):
    '''Reads the original glibc translit_cjk_compat 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('\n')
        translit_file.write('% Transliterations of CJK compatibility ')
        translit_file.write('characters.\n')
        translit_file.write('% Generated automatically from UnicodeData.txt '
                            + 'by gen_translit_cjk_compat.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 special_decompose(code_point_list):
    '''
    Decompositions which are not in UnicodeData.txt at all but which
    were used in the original translit_cjk_compat file in glibc and
    which seem to make sense.  I want to keep the update of
    translit_cjk_compat close to the spirit of the original file,
    therefore I added this special decomposition rules here.
    '''
    special_decompose_dict = {
        (0x2215,): [0x002F], # ∕ → /
        (0x00B2,): [0x005E, 0x0032], # ² → ^2
        (0x03BC,): [0x00B5], # μ → µ (GREEK SMALL LETTER MU → MICRO SIGN)
        (0x2113,): [0x006C], # ℓ → l
        (0x00B3,): [0x005E, 0x0033], # ³ → ^3
        (0x00B5,): [0x0075], # µ → u
        (0x03BC, 0x2113): [0x03BC, 0x006C], # μℓ → μl
        (0x0072, 0x0061, 0x0064, 0x2215, 0x0073, 0x00B2): [
            0x0072, 0x0061, 0x0064, 0x002F, 0x0073, 0x00B2],
        (0x006D, 0x2215, 0x0073, 0x00B2): [0x006D, 0x002F, 0x0073, 0x00B2],
    }
    if tuple(code_point_list) in special_decompose_dict:
        return special_decompose_dict[tuple(code_point_list)]
    else:
        return code_point_list

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('<square>'):
            decomposition = decomposition[9:]
            decomposed_code_points = [[int(x, 16)
                                       for x in decomposition.split(' ')]]
            if decomposed_code_points[0]:
                while True:
                    special_decomposed_code_points = special_decompose(
                        decomposed_code_points[-1])
                    if (special_decomposed_code_points
                            != decomposed_code_points[-1]):
                        decomposed_code_points.append(
                            special_decomposed_code_points)
                        continue
                    special_decomposed_code_points = []
                    for decomposed_code_point in decomposed_code_points[-1]:
                        special_decomposed_code_points += special_decompose(
                            [decomposed_code_point])
                    if (special_decomposed_code_points
                            == decomposed_code_points[-1]):
                        break
                    decomposed_code_points.append(
                        special_decomposed_code_points)
                translit_file.write('% {:s}\n'.format(name))
                translit_file.write('{:s} '.format(
                    unicode_utils.ucs_symbol(code_point)))
                for index in range(0, len(decomposed_code_points)):
                    if index > 0:
                        translit_file.write(';')
                    if len(decomposed_code_points[index]) > 1:
                        translit_file.write('"')
                    for decomposed_code_point in decomposed_code_points[index]:
                        translit_file.write('{:s}'.format(
                            unicode_utils.ucs_symbol(decomposed_code_point)))
                    if len(decomposed_code_points[index]) > 1:
                        translit_file.write('"')
                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 and name.startswith('CJK COMPATIBILITY IDEOGRAPH'):
            decomposed_code_points = [int(x, 16)
                                      for x in decomposition.split(' ')]
            if len(decomposed_code_points) != 1:
                sys.stderr.write(
                    'Unexpected decomposition length {:x} {:s} {:s}\n'.format(
                        code_point, name, decomposition))
                exit(1)
            translit_file.write('% {:s}\n'.format(name))
            translit_file.write('{:s} '.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('\n')
    translit_file.write('\n')

if __name__ == "__main__":
    PARSER = argparse.ArgumentParser(
        description='''
        Generate a translit_cjk_compat 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_cjk_compat
        file.''')
    PARSER.add_argument(
        '-o', '--output_file',
        nargs='?',
        type=str,
        default='translit_cjk_compat.new',
        help='''The new translit_cjk_compat file, default: %(default)s.  If the
        original glibc/localedata/locales/translit_cjk_compat 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)