tests/test-c32isspace.c

   1 /* Test of c32isspace() function.
   2    Copyright (C) 2020 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify
   5    it under the terms of the GNU General Public License as published by
   6    the Free Software Foundation; either version 3 of the License, or
   7    (at your option) any later version.
   8
   9    This program is distributed in the hope that it will be useful,
  10    but WITHOUT ANY WARRANTY; without even the implied warranty of
  11    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12    GNU General Public License for more details.
  13
  14    You should have received a copy of the GNU General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16
  17 #include <config.h>
  18
  19 #include <uchar.h>
  20
  21 #include "signature.h"
  22 SIGNATURE_CHECK (c32isspace, int, (wint_t));
  23
  24 #include <locale.h>
  25 #include <stdlib.h>
  26 #include <string.h>
  27 #include <wchar.h>
  28
  29 #include "macros.h"
  30
  31 /* Returns the value of c32isspace for the multibyte character s[0..n-1].  */
  32 static int
  33 for_character (const char *s, size_t n)
  34 {
  35   mbstate_t state;
  36   char32_t wc;
  37   size_t ret;
  38
  39   memset (&state, '\0', sizeof (mbstate_t));
  40   wc = (char32_t) 0xBADFACE;
  41   ret = mbrtoc32 (&wc, s, n, &state);
  42   ASSERT (ret == n);
  43
  44   return c32isspace (wc);
  45 }
  46
  47 int
  48 main (int argc, char *argv[])
  49 {
  50   int is;
  51   char buf[4];
  52
  53   /* configure should already have checked that the locale is supported.  */
  54   if (setlocale (LC_ALL, "") == NULL)
  55     return 1;
  56
  57   /* Test WEOF.  */
  58   is = c32isspace (WEOF);
  59   ASSERT (is == 0);
  60
  61   /* Test single-byte characters.
  62      POSIX specifies in
  63        <https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap07.html>
  64      that
  65        - in all locales, the white-space characters include the <space>,
  66          <form-feed>, <newline>, <carriage-return>, <tab>, <vertical-tab>
  67          characters,
  68        - in the "POSIX" locale (which is usually the same as the "C" locale),
  69          the white-space characters include only the ASCII <space>, <form-feed>,
  70          <newline>, <carriage-return>, <tab>, <vertical-tab> characters.  */
  71   {
  72     int c;
  73
  74     for (c = 0; c < 0x100; c++)
  75       switch (c)
  76         {
  77         case '\f': case '\n': case '\r': case '\t': case '\v':
  78         case ' ': case '!': case '"': case '#': case '%':
  79         case '&': case '\'': case '(': case ')': case '*':
  80         case '+': case ',': case '-': case '.': case '/':
  81         case '0': case '1': case '2': case '3': case '4':
  82         case '5': case '6': case '7': case '8': case '9':
  83         case ':': case ';': case '<': case '=': case '>':
  84         case '?':
  85         case 'A': case 'B': case 'C': case 'D': case 'E':
  86         case 'F': case 'G': case 'H': case 'I': case 'J':
  87         case 'K': case 'L': case 'M': case 'N': case 'O':
  88         case 'P': case 'Q': case 'R': case 'S': case 'T':
  89         case 'U': case 'V': case 'W': case 'X': case 'Y':
  90         case 'Z':
  91         case '[': case '\\': case ']': case '^': case '_':
  92         case 'a': case 'b': case 'c': case 'd': case 'e':
  93         case 'f': case 'g': case 'h': case 'i': case 'j':
  94         case 'k': case 'l': case 'm': case 'n': case 'o':
  95         case 'p': case 'q': case 'r': case 's': case 't':
  96         case 'u': case 'v': case 'w': case 'x': case 'y':
  97         case 'z': case '{': case '|': case '}': case '~':
  98           /* c is in the ISO C "basic character set" or one of the explicitly
  99              mentioned white-space characters.  */
 100           buf[0] = (unsigned char) c;
 101           is = for_character (buf, 1);
 102           switch (c)
 103             {
 104             case ' ': case '\f': case '\n': case '\r': case '\t': case '\v':
 105               ASSERT (is != 0);
 106               break;
 107             default:
 108               ASSERT (is == 0);
 109               break;
 110             }
 111           break;
 112         }
 113   }
 114
 115   if (argc > 1)
 116     switch (argv[1][0])
 117       {
 118       case '0':
 119         /* C locale; tested above.  */
 120         return 0;
 121
 122       case '1':
 123         /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
 124         {
 125           /* U+00B7 MIDDLE DOT */
 126           is = for_character ("\267", 1);
 127           ASSERT (is == 0);
 128         }
 129         return 0;
 130
 131       case '2':
 132         /* Locale encoding is EUC-JP.  */
 133         {
 134         #if !(defined __FreeBSD__ || defined __DragonFly__)
 135           /* U+3000 IDEOGRAPHIC SPACE */
 136           is = for_character ("\241\241", 2);
 137           ASSERT (is != 0);
 138         #endif
 139           /* U+3001 IDEOGRAPHIC COMMA */
 140           is = for_character ("\241\242", 2);
 141           ASSERT (is == 0);
 142         }
 143         return 0;
 144
 145       case '3':
 146         /* Locale encoding is UTF-8.  */
 147         {
 148           /* U+00B7 MIDDLE DOT */
 149           is = for_character ("\302\267", 2);
 150           ASSERT (is == 0);
 151           /* U+2002 EN SPACE */
 152           is = for_character ("\342\200\202", 3);
 153           ASSERT (is != 0);
 154           /* U+3000 IDEOGRAPHIC SPACE */
 155           is = for_character ("\343\200\200", 3);
 156           ASSERT (is != 0);
 157           /* U+3001 IDEOGRAPHIC COMMA */
 158           is = for_character ("\343\200\201", 3);
 159           ASSERT (is == 0);
 160           /* U+E0020 TAG SPACE */
 161           is = for_character ("\363\240\200\240", 4);
 162           ASSERT (is == 0);
 163         }
 164         return 0;
 165
 166       case '4':
 167         /* Locale encoding is GB18030.  */
 168         {
 169           /* U+00B7 MIDDLE DOT */
 170           is = for_character ("\241\244", 2);
 171           ASSERT (is == 0);
 172         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 173           /* U+2002 EN SPACE */
 174           is = for_character ("\201\066\243\070", 4);
 175           ASSERT (is != 0);
 176         #endif
 177         #if !(defined __FreeBSD__ || defined __DragonFly__)
 178           /* U+3000 IDEOGRAPHIC SPACE */
 179           is = for_character ("\241\241", 2);
 180           ASSERT (is != 0);
 181         #endif
 182           /* U+3001 IDEOGRAPHIC COMMA */
 183           is = for_character ("\241\242", 2);
 184           ASSERT (is == 0);
 185           /* U+E0020 TAG SPACE */
 186           is = for_character ("\323\066\231\060", 4);
 187           ASSERT (is == 0);
 188         }
 189         return 0;
 190
 191       }
 192
 193   return 1;
 194 }