about summary refs log tree commit diff
path: root/localedata/unicode-gen/utf8_compatibility.py
blob: 32566363c60c55c1e1caa82d6679e0dd59ea6d67 (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
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
#!/usr/bin/python3
# -*- coding: utf-8 -*-
# Copyright (C) 2014-2024 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
# <https://www.gnu.org/licenses/>.

'''
This script is useful for checking backward compatibility of newly
generated UTF-8 file from utf8_gen.py script

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

    $ ./utf8_compatibility.py -h
    … prints usage message …
'''

import sys
import re
import argparse
import unicode_utils

def create_charmap_dictionary(file_name):
    '''Create a dictionary for all code points found in the CHARMAP
    section of a file
    '''
    with open(file_name, mode='r') as utf8_file:
        charmap_dictionary = {}
        for line in utf8_file:
            if line.startswith('CHARMAP'):
                break
        for line in utf8_file:
            if line.startswith('END CHARMAP'):
                return charmap_dictionary
            if line.startswith('%'):
                continue
            match = re.match(
                r'^<U(?P<codepoint1>[0-9A-F]{4,8})>'
                +r'(:?\.\.<U(?P<codepoint2>[0-9-A-F]{4,8})>)?'
                +r'\s+(?P<hexutf8>(/x[0-9a-f]{2}){1,4})',
                line)
            if not match:
                continue
            codepoint1 = match.group('codepoint1')
            codepoint2 = match.group('codepoint2')
            if not codepoint2:
                codepoint2 = codepoint1
            for i in range(int(codepoint1, 16),
                           int(codepoint2, 16) + 1):
                charmap_dictionary[i] = match.group('hexutf8')
        sys.stderr.write('No “CHARMAP” or no “END CHARMAP” found in %s\n'
                         %file_name)
        exit(1)

def check_charmap(original_file_name, new_file_name):
    '''Report differences in the CHARMAP section between the old and the
    new file
    '''
    print('************************************************************')
    print('Report on CHARMAP:')
    ocharmap = create_charmap_dictionary(original_file_name)
    ncharmap = create_charmap_dictionary(new_file_name)
    print('------------------------------------------------------------')
    print('Total removed characters in newly generated CHARMAP: %d'
          %len(set(ocharmap)-set(ncharmap)))
    if ARGS.show_missing_characters:
        for key in sorted(set(ocharmap)-set(ncharmap)):
            print('removed: {:s}     {:s} {:s}'.format(
                unicode_utils.ucs_symbol(key),
                ocharmap[key],
                unicode_utils.UNICODE_ATTRIBUTES[key]['name'] \
                if key in unicode_utils.UNICODE_ATTRIBUTES else 'None'))
    print('------------------------------------------------------------')
    changed_charmap = {}
    for key in set(ocharmap).intersection(set(ncharmap)):
        if ocharmap[key] != ncharmap[key]:
            changed_charmap[key] = (ocharmap[key], ncharmap[key])
    print('Total changed characters in newly generated CHARMAP: %d'
          %len(changed_charmap))
    if ARGS.show_changed_characters:
        for key in sorted(changed_charmap):
            print('changed: {:s}     {:s}->{:s} {:s}'.format(
                unicode_utils.ucs_symbol(key),
                changed_charmap[key][0],
                changed_charmap[key][1],
                unicode_utils.UNICODE_ATTRIBUTES[key]['name'] \
                if key in unicode_utils.UNICODE_ATTRIBUTES else 'None'))
    print('------------------------------------------------------------')
    print('Total added characters in newly generated CHARMAP: %d'
          %len(set(ncharmap)-set(ocharmap)))
    if ARGS.show_added_characters:
        for key in sorted(set(ncharmap)-set(ocharmap)):
            print('added: {:s}     {:s} {:s}'.format(
                unicode_utils.ucs_symbol(key),
                ncharmap[key],
                unicode_utils.UNICODE_ATTRIBUTES[key]['name'] \
                if key in unicode_utils.UNICODE_ATTRIBUTES else 'None'))

def create_width_dictionary(file_name):
    '''Create a dictionary for all code points found in the WIDTH
    section of a file
    '''
    with open(file_name, mode='r') as utf8_file:
        width_dictionary = {}
        for line in utf8_file:
            if line.startswith('WIDTH'):
                break
        for line in utf8_file:
            if line.startswith('END WIDTH'):
                return width_dictionary
            match = re.match(
                r'^<U(?P<codepoint1>[0-9A-F]{4,8})>'
                +r'(:?\.\.\.<U(?P<codepoint2>[0-9-A-F]{4,8})>)?'
                +r'\s+(?P<width>[02])',
                line)
            if not match:
                continue
            codepoint1 = match.group('codepoint1')
            codepoint2 = match.group('codepoint2')
            if not codepoint2:
                codepoint2 = codepoint1
            for i in range(int(codepoint1, 16),
                           int(codepoint2, 16) + 1):
                width_dictionary[i] = int(match.group('width'))
        sys.stderr.write('No “WIDTH” or no “END WIDTH” found in %s\n' %file)

def check_width(original_file_name, new_file_name):
    '''Report differences in the WIDTH section between the old and the new
    file
    '''
    print('************************************************************')
    print('Report on WIDTH:')
    owidth = create_width_dictionary(original_file_name)
    nwidth = create_width_dictionary(new_file_name)
    print('------------------------------------------------------------')
    print('Total removed characters in newly generated WIDTH: %d'
          %len(set(owidth)-set(nwidth)))
    print('(Characters not in WIDTH get width 1 by default, '
          + 'i.e. these have width 1 now.)')
    if ARGS.show_missing_characters:
        for key in sorted(set(owidth)-set(nwidth)):
            print('removed: {:s} '.format(unicode_utils.ucs_symbol(key))
                  + '{:d} : '.format(owidth[key])
                  + 'eaw={:s} '.format(
                      unicode_utils.EAST_ASIAN_WIDTHS[key]
                      if key in unicode_utils.EAST_ASIAN_WIDTHS else 'None')
                  + 'category={:2s} '.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['category']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None')
                  + 'bidi={:3s} '.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['bidi']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None')
                  + 'name={:s}'.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['name']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None'))
    print('------------------------------------------------------------')
    changed_width = {}
    for key in set(owidth).intersection(set(nwidth)):
        if owidth[key] != nwidth[key]:
            changed_width[key] = (owidth[key], nwidth[key])
    print('Total changed characters in newly generated WIDTH: %d'
          %len(changed_width))
    if ARGS.show_changed_characters:
        for key in sorted(changed_width):
            print('changed width: {:s} '.format(unicode_utils.ucs_symbol(key))
                  + '{:d}->{:d} : '.format(changed_width[key][0],
                                          changed_width[key][1])
                  + 'eaw={:s} '.format(
                      unicode_utils.EAST_ASIAN_WIDTHS[key]
                      if key in unicode_utils.EAST_ASIAN_WIDTHS else 'None')
                  + 'category={:2s} '.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['category']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None')
                  + 'bidi={:3s} '.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['bidi']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None')
                  + 'name={:s}'.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['name']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None'))
    print('------------------------------------------------------------')
    print('Total added characters in newly generated WIDTH: %d'
          %len(set(nwidth)-set(owidth)))
    print('(Characters not in WIDTH get width 1 by default, '
          + 'i.e. these had width 1 before.)')
    if ARGS.show_added_characters:
        for key in sorted(set(nwidth)-set(owidth)):
            print('added: {:s} '.format(unicode_utils.ucs_symbol(key))
                  + '{:d} : '.format(nwidth[key])
                  + 'eaw={:s} '.format(
                      unicode_utils.EAST_ASIAN_WIDTHS[key]
                      if key in unicode_utils.EAST_ASIAN_WIDTHS else 'None')
                  + 'category={:2s} '.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['category']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None')
                  + 'bidi={:3s} '.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['bidi']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None')
                  + 'name={:s}'.format(
                      unicode_utils.UNICODE_ATTRIBUTES[key]['name']
                      if key in unicode_utils.UNICODE_ATTRIBUTES else 'None'))

if __name__ == "__main__":
    PARSER = argparse.ArgumentParser(
        description='''
        Compare the contents of LC_CTYPE in two files and check for errors.
        ''')
    PARSER.add_argument(
        '-o', '--old_utf8_file',
        nargs='?',
        required=True,
        type=str,
        help='The old UTF-8 file.')
    PARSER.add_argument(
        '-n', '--new_utf8_file',
        nargs='?',
        required=True,
        type=str,
        help='The new UTF-8 file.')
    PARSER.add_argument(
        '-u', '--unicode_data_file',
        nargs='?',
        type=str,
        help='The UnicodeData.txt file to read.')
    PARSER.add_argument(
        '-e', '--east_asian_width_file',
        nargs='?',
        type=str,
        help='The EastAsianWidth.txt file to read.')
    PARSER.add_argument(
        '-a', '--show_added_characters',
        action='store_true',
        help='Show characters which were added in detail.')
    PARSER.add_argument(
        '-m', '--show_missing_characters',
        action='store_true',
        help='Show characters which were removed in detail.')
    PARSER.add_argument(
        '-c', '--show_changed_characters',
        action='store_true',
        help='Show characters whose width was changed in detail.')
    ARGS = PARSER.parse_args()

    if ARGS.unicode_data_file:
        unicode_utils.fill_attributes(ARGS.unicode_data_file)
    if ARGS.east_asian_width_file:
        unicode_utils.fill_east_asian_widths(ARGS.east_asian_width_file)
    check_charmap(ARGS.old_utf8_file, ARGS.new_utf8_file)
    check_width(ARGS.old_utf8_file, ARGS.new_utf8_file)