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
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
|
/* Test of case and normalization insensitive comparison of strings.
Copyright (C) 2009-2022 Free Software Foundation, Inc.
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3 of the License, or
(at your option) any later version.
This program 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 General Public License for more details.
You should have received a copy of the GNU General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>. */
/* Written by Bruno Haible <bruno@clisp.org>, 2009. */
#include <config.h>
#include "unicase.h"
#include <locale.h>
#include "macros.h"
#define UNIT char
#include "test-casecmp.h"
#undef UNIT
static void
test_iso_8859_1 (int (*my_casecmp) (const char *, size_t, const char *, size_t, const char *, uninorm_t, int *))
{
{
static const char input1[] = { 'H', 0xF6, 'h', 'l', 'e' };
static const char input2[] = { 'H', 0xD6, 'h', 'L', 'e' };
static const char input3[] = { 'H', 0xF6, 'h', 'l', 'e', 'n' };
static const char input4[] = { 'H', 0xD6, 'h', 'L', 'e', 'n' };
static const char input5[] = { 'H', 'u', 'r', 'z' };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input1, SIZEOF (input1), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input3, SIZEOF (input3), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input4, SIZEOF (input4), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input1, SIZEOF (input1), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input1, SIZEOF (input1), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input2, SIZEOF (input2), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
}
/* Uppercasing can increase the number of Unicode characters. */
{ /* "heiß" */
static const char input1[] = { 0x68, 0x65, 0x69, 0xDF };
static const char input2[] = { 0x68, 0x65, 0x69, 0x73, 0x73 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
}
static void
test_utf_8 (int (*my_casecmp) (const char *, size_t, const char *, size_t, const char *, uninorm_t, int *))
{
/* Normalization effects. */
{
static const char input1[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e' };
static const char input2[] = { 'H', 'O', 0xCC, 0x88, 'h', 'L', 'e' };
static const char input3[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e', 'n' };
static const char input4[] = { 'H', 'O', 0xCC, 0x88, 'h', 'L', 'e', 'n' };
static const char input5[] = { 'H', 'u', 'r', 'z' };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input1, SIZEOF (input1), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input3, SIZEOF (input3), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input4, SIZEOF (input4), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input1, SIZEOF (input1), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input1, SIZEOF (input1), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input2, SIZEOF (input2), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == -1);
}
{ /* LATIN CAPITAL LETTER A WITH DIAERESIS */
static const char input1[] = { 0xC3, 0x84 };
static const char input2[] = { 0x41, 0xCC, 0x88 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
static const char input1[] = { 0xC7, 0x9E };
static const char input2[] = { 0x41, 0xCC, 0x88, 0xCC, 0x84 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* GREEK DIALYTIKA AND PERISPOMENI */
static const char input1[] = { 0xE1, 0xBF, 0x81 };
static const char input2[] = { 0xC2, 0xA8, 0xCD, 0x82 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* HANGUL SYLLABLE GEUL */
static const char input1[] = { 0xEA, 0xB8, 0x80 };
static const char input2[] = { 0xEA, 0xB7, 0xB8, 0xE1, 0x86, 0xAF };
static const char input3[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3, 0xE1, 0x86, 0xAF };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* HANGUL SYLLABLE GEU */
static const char input1[] = { 0xEA, 0xB7, 0xB8 };
static const char input2[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
/* Simple string. */
{ /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
static const char input1[] =
{ 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
'!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
};
static const char input2[] =
{ 'g', 'r', 0xC3, 0xBC, 0x73, 0x73, ' ', 'g', 'o', 't', 't', '.', ' ',
0xD0, 0xB7, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
'!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
};
static const char input3[] =
{ 'G', 'R', 0xC3, 0x9C, 0x53, 0x53, ' ', 'G', 'O', 'T', 'T', '.', ' ',
0xD0, 0x97, 0xD0, 0x94, 0xD0, 0xA0, 0xD0, 0x90, 0xD0, 0x92, 0xD0, 0xA1,
0xD0, 0xA2, 0xD0, 0x92, 0xD0, 0xA3, 0xD0, 0x99, 0xD0, 0xA2, 0xD0, 0x95,
'!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'Q', 'R', 'T', '(',
'B', 0xC2, 0xB2, '-', '4', 'A', 'C', ')', ')', '/', '(', '2', 'A', ')',
' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
};
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
/* Case mapping can increase the number of Unicode characters. */
{ /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
static const char input1[] = { 0xC5, 0x89 };
static const char input2[] = { 0xCA, 0xBC, 0x6E };
static const char input3[] = { 0xCA, 0xBC, 0x4E };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
static const char input1[] = { 0xCE, 0x90 };
static const char input2[] = { 0xCE, 0xB9, 0xCC, 0x88, 0xCC, 0x81 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
/* Turkish letters i İ ı I */
{ /* LATIN CAPITAL LETTER I */
static const char input[] = { 0x49 };
static const char casefolded[] = { 0x69 };
static const char casefolded_tr[] = { 0xC4, 0xB1 };
int cmp;
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* LATIN SMALL LETTER I */
static const char input[] = { 0x69 };
static const char casefolded[] = { 0x49 };
static const char casefolded_tr[] = { 0xC4, 0xB0 };
int cmp;
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
static const char input[] = { 0xC4, 0xB0 };
static const char casefolded[] = { 0x69, 0xCC, 0x87 };
static const char casefolded_tr[] = { 0x69 };
int cmp;
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* LATIN SMALL LETTER DOTLESS I */
static const char input[] = { 0xC4, 0xB1 };
static const char casefolded[] = { 0x49 };
int cmp;
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 1);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
{ /* "topkapı" */
static const char input[] =
{ 0x54, 0x4F, 0x50, 0x4B, 0x41, 0x50, 0x49 };
static const char casefolded[] =
{ 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
int cmp;
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
ASSERT (cmp == -1);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
/* Uppercasing can increase the number of Unicode characters. */
{ /* "heiß" */
static const char input1[] = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
static const char input2[] = { 0x68, 0x65, 0x69, 0x73, 0x73 };
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
/* Case mappings for some characters can depend on the surrounding characters. */
{ /* "περισσότερες πληροφορίες" */
static const char input1[] =
{
0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
};
static const char input2[] =
{
0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x83,
' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x83
};
static const char input3[] =
{
0xCE, 0xA0, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x99, 0xCE, 0xA3, 0xCE, 0xA3,
0xCE, 0x8C, 0xCE, 0xA4, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x95, 0xCE, 0xA3,
' ', 0xCE, 0xA0, 0xCE, 0x9B, 0xCE, 0x97, 0xCE, 0xA1, 0xCE, 0x9F,
0xCE, 0xA6, 0xCE, 0x9F, 0xCE, 0xA1, 0xCE, 0x8A, 0xCE, 0x95, 0xCE, 0xA3
};
int cmp;
ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
}
/* Case mapping can require subsequent normalization. */
{ /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
static const char input[] = { 0xC7, 0xB0, 0xCC, 0xA3 };
static const char casefolded[] = { 0x6A, 0xCC, 0x8C, 0xCC, 0xA3 };
static const char casefolded_decomposed[] = { 0x6A, 0xCC, 0xA3, 0xCC, 0x8C };
int cmp;
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, NULL, &cmp) == 0);
ASSERT (cmp != 0);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, UNINORM_NFD, &cmp) == 0);
ASSERT (cmp == 0);
}
}
int
main (int argc, char *argv[])
{
/* configure should already have checked that the locale is supported. */
if (setlocale (LC_ALL, "") == NULL)
return 1;
test_ascii (ulc_casecmp, UNINORM_NFD);
if (argc > 1)
switch (argv[1][0])
{
case '1':
/* Locale encoding is ISO-8859-1 or ISO-8859-15. */
test_iso_8859_1 (ulc_casecmp);
return 0;
case '2':
/* Locale encoding is UTF-8. */
test_utf_8 (ulc_casecmp);
return 0;
}
return 1;
}
|