summaryrefslogtreecommitdiff
path: root/tests/test-c32isspace.c
blob: 15cf387dcf726f1ced7c2a354513d3a4f7a68eed (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
/* Test of c32isspace() 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 (c32isspace, int, (wint_t));

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

#include "macros.h"

/* Returns the value of c32isspace 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 c32isspace (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 = c32isspace (WEOF);
  ASSERT (is == 0);

  /* Test single-byte characters.
     POSIX specifies in
       <https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html>
     that
       - in all locales, the white-space characters include the <space>,
         <form-feed>, <newline>, <carriage-return>, <tab>, <vertical-tab>
         characters,
       - in the "POSIX" locale (which is usually the same as the "C" locale),
         the white-space characters include only the ASCII <space>, <form-feed>,
         <newline>, <carriage-return>, <tab>, <vertical-tab> characters.  */
  {
    int c;

    for (c = 0; c < 0x100; c++)
      switch (c)
        {
        case '\f': case '\n': case '\r': case '\t': case '\v':
        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" or one of the explicitly
             mentioned white-space characters.  */
          buf[0] = (unsigned char) c;
          is = for_character (buf, 1);
          switch (c)
            {
            case ' ': case '\f': case '\n': case '\r': case '\t': case '\v':
              ASSERT (is != 0);
              break;
            default:
              ASSERT (is == 0);
              break;
            }
          break;
        }
  }

  if (argc > 1)
    switch (argv[1][0])
      {
      case '0':
        /* C locale; tested above.  */
        return 0;

      case '1':
        /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
        {
          /* U+00B7 MIDDLE DOT */
          is = for_character ("\267", 1);
          ASSERT (is == 0);
        }
        return 0;

      case '2':
        /* Locale encoding is EUC-JP.  */
        {
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+3000 IDEOGRAPHIC SPACE */
          is = for_character ("\241\241", 2);
          ASSERT (is != 0);
        #endif
          /* U+3001 IDEOGRAPHIC COMMA */
          is = for_character ("\241\242", 2);
          ASSERT (is == 0);
        }
        return 0;

      case '3':
        /* Locale encoding is UTF-8.  */
        {
          /* U+00B7 MIDDLE DOT */
          is = for_character ("\302\267", 2);
          ASSERT (is == 0);
          /* U+2002 EN SPACE */
          is = for_character ("\342\200\202", 3);
          ASSERT (is != 0);
          /* U+3000 IDEOGRAPHIC SPACE */
          is = for_character ("\343\200\200", 3);
          ASSERT (is != 0);
          /* U+3001 IDEOGRAPHIC COMMA */
          is = for_character ("\343\200\201", 3);
          ASSERT (is == 0);
          /* U+E0020 TAG SPACE */
          is = for_character ("\363\240\200\240", 4);
          ASSERT (is == 0);
        }
        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
        {
          /* U+00B7 MIDDLE DOT */
          is = for_character ("\241\244", 2);
          ASSERT (is == 0);
        #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
          /* U+2002 EN SPACE */
          is = for_character ("\201\066\243\070", 4);
          ASSERT (is != 0);
        #endif
        #if !(defined __FreeBSD__ || defined __DragonFly__)
          /* U+3000 IDEOGRAPHIC SPACE */
          is = for_character ("\241\241", 2);
          ASSERT (is != 0);
        #endif
          /* U+3001 IDEOGRAPHIC COMMA */
          is = for_character ("\241\242", 2);
          ASSERT (is == 0);
          /* U+E0020 TAG SPACE */
          is = for_character ("\323\066\231\060", 4);
          ASSERT (is == 0);
        }
        return 0;

      }

  return 1;
}