summaryrefslogtreecommitdiff
path: root/tests/test-c32ispunct.c
blob: 1b9f8e3b3ce8e88f6d524a4592e244424a36651d (plain)
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
/* Test of c32ispunct() function.
   Copyright (C) 2020-2024 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/>.  */

#include <config.h>

#include <uchar.h>

#include "signature.h"
SIGNATURE_CHECK (c32ispunct, int, (wint_t));

#include <locale.h>
#include <stdlib.h>
#include <string.h>
#include <wchar.h>

#include "macros.h"

/* Returns the value of c32ispunct for the multibyte character s[0..n-1].  */
static int
for_character (const char *s, size_t n)
{
  mbstate_t state;
  char32_t wc;
  size_t ret;

  memset (&state, '\0', sizeof (mbstate_t));
  wc = (char32_t) 0xBADFACE;
  ret = mbrtoc32 (&wc, s, n, &state);
  ASSERT (ret == n);

  return c32ispunct (wc);
}

int
main (int argc, char *argv[])
{
  int is;
  char buf[4];

  /* configure should already have checked that the locale is supported.  */
  if (setlocale (LC_ALL, "") == NULL)
    return 1;

  /* Test WEOF.  */
  is = c32ispunct (WEOF);
  ASSERT (is == 0);

  /* Test single-byte characters.
     POSIX specifies in
       <https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html>
     no explicit list of punctuation or symbol characters.  */
  {
    int c;

    for (c = 0; c < 0x100; c++)
      switch (c)
        {
        case '\t': case '\v': case '\f':
        case ' ': case '!': case '"': case '#': case '%':
        case '&': case '\'': case '(': case ')': case '*':
        case '+': case ',': case '-': case '.': case '/':
        case '0': case '1': case '2': case '3': case '4':
        case '5': case '6': case '7': case '8': case '9':
        case ':': case ';': case '<': case '=': case '>':
        case '?':
        case 'A': case 'B': case 'C': case 'D': case 'E':
        case 'F': case 'G': case 'H': case 'I': case 'J':
        case 'K': case 'L': case 'M': case 'N': case 'O':
        case 'P': case 'Q': case 'R': case 'S': case 'T':
        case 'U': case 'V': case 'W': case 'X': case 'Y':
        case 'Z':
        case '[': case '\\': case ']': case '^': case '_':
        case 'a': case 'b': case 'c': case 'd': case 'e':
        case 'f': case 'g': case 'h': case 'i': case 'j':
        case 'k': case 'l': case 'm': case 'n': case 'o':
        case 'p': case 'q': case 'r': case 's': case 't':
        case 'u': case 'v': case 'w': case 'x': case 'y':
        case 'z': case '{': case '|': case '}': case '~':
          /* c is in the ISO C "basic character set".  */
          buf[0] = (unsigned char) c;
          is = for_character (buf, 1);
          switch (c)
            {
            case ' ':
            case '0': case '1': case '2': case '3': case '4':
            case '5': case '6': case '7': case '8': case '9':
            case 'A': case 'B': case 'C': case 'D': case 'E':
            case 'F': case 'G': case 'H': case 'I': case 'J':
            case 'K': case 'L': case 'M': case 'N': case 'O':
            case 'P': case 'Q': case 'R': case 'S': case 'T':
            case 'U': case 'V': case 'W': case 'X': case 'Y':
            case 'Z':
            case 'a': case 'b': case 'c': case 'd': case 'e':
            case 'f': case 'g': case 'h': case 'i': case 'j':
            case 'k': case 'l': case 'm': case 'n': case 'o':
            case 'p': case 'q': case 'r': case 's': case 't':
            case 'u': case 'v': case 'w': case 'x': case 'y':
            case 'z':
              /* c is an alphanumeric or space character.  */
              ASSERT (is == 0);
              break;
            case '!': case '"': case '#': case '%':
            case '&': case '\'': case '(': case ')': case '*':
            case '+': case ',': case '-': case '.': case '/':
            case ':': case ';': case '<': case '=': case '>':
            case '?':
            case '[': case '\\': case ']': case '^': case '_':
            case '{': case '|': case '}': case '~':
              /* These characters are usually expected to be punctuation or
                 symbol characters.  */
              ASSERT (is != 0);
              break;
            default:
              ASSERT (is == 0);
              break;
            }
          break;
        }
  }

  if (argc > 1)
    switch (argv[1][0])
      {
      case '0':
        /* C locale; tested above.  */
        /* These characters are not in the ISO C "basic character set", but
           are nevertheless usually expected to be punctuation or symbol
           characters.  */
        is = for_character ("$", 1);
        ASSERT (is != 0);
        is = for_character ("@", 1);
        ASSERT (is != 0);
        is = for_character ("`", 1);
        ASSERT (is != 0);
        return 0;

      case '1':
        /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
        {
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+00BF INVERTED QUESTION MARK */
          is = for_character ("\277", 1);
          ASSERT (is != 0);
        #endif
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
          /* U+00D7 MULTIPLICATION SIGN */
          is = for_character ("\327", 1);
          ASSERT (is != 0);
        #endif
          /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
          is = for_character ("\330", 1);
          ASSERT (is == 0);
          /* U+00DF LATIN SMALL LETTER SHARP S */
          is = for_character ("\337", 1);
          ASSERT (is == 0);
        }
        return 0;

      case '2':
        /* Locale encoding is EUC-JP.  */
        {
        #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__)
          /* U+00BF INVERTED QUESTION MARK */
          is = for_character ("\217\242\304", 3);
          ASSERT (is != 0);
        #endif
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+00D7 MULTIPLICATION SIGN */
          is = for_character ("\241\337", 2);
          ASSERT (is != 0);
        #endif
          /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
          is = for_character ("\217\251\254", 3);
          ASSERT (is == 0);
          /* U+00DF LATIN SMALL LETTER SHARP S */
          is = for_character ("\217\251\316", 3);
          ASSERT (is == 0);
          /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
          is = for_character ("\217\251\250", 3);
          ASSERT (is == 0);
        #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__)
          /* U+2192 RIGHTWARDS ARROW */
          is = for_character ("\242\252", 2);
          ASSERT (is != 0);
        #endif
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+3001 IDEOGRAPHIC COMMA */
          is = for_character ("\241\242", 2);
          ASSERT (is != 0);
        #endif
          /* U+FF11 FULLWIDTH DIGIT ONE */
          is = for_character ("\243\261", 2);
          ASSERT (is == 0);
          /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
          is = for_character ("\243\355", 2);
          ASSERT (is == 0);
        }
        return 0;

      case '3':
        /* Locale encoding is UTF-8.  */
        {
          /* U+00BF INVERTED QUESTION MARK */
          is = for_character ("\302\277", 2);
          ASSERT (is != 0);
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
          /* U+00D7 MULTIPLICATION SIGN */
          is = for_character ("\303\227", 2);
          ASSERT (is != 0);
        #endif
          /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
          is = for_character ("\303\230", 2);
          ASSERT (is == 0);
          /* U+00DF LATIN SMALL LETTER SHARP S */
          is = for_character ("\303\237", 2);
          ASSERT (is == 0);
          /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
          is = for_character ("\305\201", 2);
          ASSERT (is == 0);
          /* U+05F3 HEBREW PUNCTUATION GERESH */
          is = for_character ("\327\263", 2);
          ASSERT (is != 0);
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun || (defined _WIN32 && !defined __CYGWIN__))
          /* U+2192 RIGHTWARDS ARROW */
          is = for_character ("\342\206\222", 3);
          ASSERT (is != 0);
        #endif
          /* U+3001 IDEOGRAPHIC COMMA */
          is = for_character ("\343\200\201", 3);
          ASSERT (is != 0);
          /* U+FF11 FULLWIDTH DIGIT ONE */
          is = for_character ("\357\274\221", 3);
          ASSERT (is == 0);
          /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
          is = for_character ("\357\275\215", 3);
          ASSERT (is == 0);
          /* U+10330 GOTHIC LETTER AHSA */
          is = for_character ("\360\220\214\260", 4);
          ASSERT (is == 0);
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
          /* U+1D100 MUSICAL SYMBOL SINGLE BARLINE */
          is = for_character ("\360\235\204\200", 4);
          ASSERT (is != 0);
        #endif
        #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __NetBSD__ || defined _AIX || defined __sun || defined __CYGWIN__ || (defined _WIN32 && !defined __CYGWIN__))
          /* U+E003A TAG COLON */
          is = for_character ("\363\240\200\272", 4);
          ASSERT (is == 0);
        #endif
        }
        return 0;

      case '4':
        /* Locale encoding is GB18030.  */
        #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __FreeBSD__ || defined __NetBSD__ || defined __sun))
        fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
        return 77;
        #endif
        {
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
          /* U+00BF INVERTED QUESTION MARK */
          is = for_character ("\201\060\206\067", 4);
          ASSERT (is != 0);
        #endif
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+00D7 MULTIPLICATION SIGN */
          is = for_character ("\241\301", 2);
          ASSERT (is != 0);
        #endif
          /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
          is = for_character ("\201\060\211\061", 4);
          ASSERT (is == 0);
          /* U+00DF LATIN SMALL LETTER SHARP S */
          is = for_character ("\201\060\211\070", 4);
          ASSERT (is == 0);
          /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
          is = for_character ("\201\060\221\071", 4);
          ASSERT (is == 0);
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
          /* U+05F3 HEBREW PUNCTUATION GERESH */
          is = for_character ("\201\060\374\067", 4);
          ASSERT (is != 0);
        #endif
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+2192 RIGHTWARDS ARROW */
          is = for_character ("\241\372", 2);
          ASSERT (is != 0);
          /* U+3001 IDEOGRAPHIC COMMA */
          is = for_character ("\241\242", 2);
          ASSERT (is != 0);
        #endif
          /* U+FF11 FULLWIDTH DIGIT ONE */
          is = for_character ("\243\261", 2);
          ASSERT (is == 0);
          /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
          is = for_character ("\243\355", 2);
          ASSERT (is == 0);
          /* U+10330 GOTHIC LETTER AHSA */
          is = for_character ("\220\060\322\066", 4);
          ASSERT (is == 0);
        #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
          /* U+1D100 MUSICAL SYMBOL SINGLE BARLINE */
          is = for_character ("\224\062\273\064", 4);
          ASSERT (is != 0);
        #endif
        #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__)
          /* U+E003A TAG COLON */
          is = for_character ("\323\066\233\066", 4);
          ASSERT (is == 0);
        #endif
        }
        return 0;

      }

  return 1;
}