tests/test-iswxdigit.c

   1 /* Test of iswxdigit() 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 <wctype.h>
  20
  21 #include "signature.h"
  22 SIGNATURE_CHECK (iswxdigit, 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 iswxdigit 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   wchar_t wc;
  37   size_t ret;
  38
  39   memset (&state, '\0', sizeof (mbstate_t));
  40   wc = (wchar_t) 0xBADFACE;
  41   ret = mbrtowc (&wc, s, n, &state);
  42   if (ret == n)
  43     return iswxdigit (wc);
  44   else
  45     return 0;
  46 }
  47
  48 int
  49 main (int argc, char *argv[])
  50 {
  51   int is;
  52   char buf[4];
  53
  54   /* configure should already have checked that the locale is supported.  */
  55   if (setlocale (LC_ALL, "") == NULL)
  56     return 1;
  57
  58   /* Test WEOF.  */
  59   is = iswxdigit (WEOF);
  60   ASSERT (is == 0);
  61
  62   /* Test single-byte characters.
  63      ISO C 99 sections 7.25.2.1.12 and 6.4.4.1 specify that the hexadecimal
  64      digits include only the ASCII 0 ... 9 A ... F a ... f characters.  */
  65   {
  66     int c;
  67
  68     for (c = 0; c < 0x100; c++)
  69       switch (c)
  70         {
  71         case '\t': case '\v': case '\f':
  72         case ' ': case '!': case '"': case '#': case '%':
  73         case '&': case '\'': case '(': case ')': case '*':
  74         case '+': case ',': case '-': case '.': case '/':
  75         case '0': case '1': case '2': case '3': case '4':
  76         case '5': case '6': case '7': case '8': case '9':
  77         case ':': case ';': case '<': case '=': case '>':
  78         case '?':
  79         case 'A': case 'B': case 'C': case 'D': case 'E':
  80         case 'F': case 'G': case 'H': case 'I': case 'J':
  81         case 'K': case 'L': case 'M': case 'N': case 'O':
  82         case 'P': case 'Q': case 'R': case 'S': case 'T':
  83         case 'U': case 'V': case 'W': case 'X': case 'Y':
  84         case 'Z':
  85         case '[': case '\\': case ']': case '^': case '_':
  86         case 'a': case 'b': case 'c': case 'd': case 'e':
  87         case 'f': case 'g': case 'h': case 'i': case 'j':
  88         case 'k': case 'l': case 'm': case 'n': case 'o':
  89         case 'p': case 'q': case 'r': case 's': case 't':
  90         case 'u': case 'v': case 'w': case 'x': case 'y':
  91         case 'z': case '{': case '|': case '}': case '~':
  92           /* c is in the ISO C "basic character set".  */
  93           buf[0] = (unsigned char) c;
  94           is = for_character (buf, 1);
  95           switch (c)
  96             {
  97             case '0': case '1': case '2': case '3': case '4':
  98             case '5': case '6': case '7': case '8': case '9':
  99             case 'A': case 'B': case 'C': case 'D': case 'E': case 'F':
 100             case 'a': case 'b': case 'c': case 'd': case 'e': case 'f':
 101               ASSERT (is != 0);
 102               break;
 103             default:
 104               ASSERT (is == 0);
 105               break;
 106             }
 107           break;
 108         }
 109   }
 110
 111   if (argc > 1)
 112     switch (argv[1][0])
 113       {
 114       case '0':
 115         /* C locale; tested above.  */
 116         return 0;
 117
 118       case '1':
 119         /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
 120         {
 121           /* U+00B2 SUPERSCRIPT TWO */
 122           is = for_character ("\262", 1);
 123           ASSERT (is == 0);
 124           /* U+00B3 SUPERSCRIPT THREE */
 125           is = for_character ("\263", 1);
 126           ASSERT (is == 0);
 127           /* U+00B9 SUPERSCRIPT ONE */
 128           is = for_character ("\271", 1);
 129           ASSERT (is == 0);
 130         }
 131         return 0;
 132
 133       case '2':
 134         /* Locale encoding is EUC-JP.  */
 135         {
 136           /* U+FF11 FULLWIDTH DIGIT ONE */
 137           is = for_character ("\243\261", 2);
 138           ASSERT (is == 0);
 139           /* U+FF21 FULLWIDTH LATIN CAPITAL LETTER A */
 140           is = for_character ("\243\301", 2);
 141           ASSERT (is == 0);
 142           /* U+FF41 FULLWIDTH LATIN SMALL LETTER A */
 143           is = for_character ("\243\341", 2);
 144           ASSERT (is == 0);
 145         }
 146         return 0;
 147
 148       case '3':
 149         /* Locale encoding is UTF-8.  */
 150         {
 151           /* U+00B2 SUPERSCRIPT TWO */
 152           is = for_character ("\302\262", 2);
 153           ASSERT (is == 0);
 154           /* U+00B3 SUPERSCRIPT THREE */
 155           is = for_character ("\302\263", 2);
 156           ASSERT (is == 0);
 157           /* U+00B9 SUPERSCRIPT ONE */
 158           is = for_character ("\302\271", 2);
 159           ASSERT (is == 0);
 160           /* U+0663 ARABIC-INDIC DIGIT THREE */
 161           is = for_character ("\331\243", 2);
 162           ASSERT (is == 0);
 163           /* U+2070 SUPERSCRIPT ZERO */
 164           is = for_character ("\342\201\260", 3);
 165           ASSERT (is == 0);
 166           /* U+2079 SUPERSCRIPT NINE */
 167           is = for_character ("\342\201\271", 3);
 168           ASSERT (is == 0);
 169           /* U+FF11 FULLWIDTH DIGIT ONE */
 170           is = for_character ("\357\274\221", 3);
 171           ASSERT (is == 0);
 172           /* U+FF21 FULLWIDTH LATIN CAPITAL LETTER A */
 173           is = for_character ("\357\274\241", 3);
 174           ASSERT (is == 0);
 175           /* U+FF41 FULLWIDTH LATIN SMALL LETTER A */
 176           is = for_character ("\357\275\201", 3);
 177           ASSERT (is == 0);
 178           /* U+1D7D1 MATHEMATICAL BOLD DIGIT THREE */
 179           is = for_character ("\360\235\237\221", 4);
 180           ASSERT (is == 0);
 181           /* U+1D7DB MATHEMATICAL DOUBLE-STRUCK DIGIT THREE */
 182           is = for_character ("\360\235\237\233", 4);
 183           ASSERT (is == 0);
 184           /* U+1D7E5 MATHEMATICAL SANS-SERIF DIGIT THREE */
 185           is = for_character ("\360\235\237\245", 4);
 186           ASSERT (is == 0);
 187           /* U+1D7EF MATHEMATICAL SANS-SERIF BOLD DIGIT THREE */
 188           is = for_character ("\360\235\237\257", 4);
 189           ASSERT (is == 0);
 190           /* U+1D7F9 MATHEMATICAL MONOSPACE DIGIT THREE */
 191           is = for_character ("\360\235\237\271", 4);
 192           ASSERT (is == 0);
 193           /* U+E0033 TAG DIGIT THREE */
 194           is = for_character ("\363\240\200\263", 4);
 195           ASSERT (is == 0);
 196           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 197           is = for_character ("\363\240\201\201", 4);
 198           ASSERT (is == 0);
 199         }
 200         return 0;
 201
 202       case '4':
 203         /* Locale encoding is GB18030.  */
 204         {
 205           /* U+00B2 SUPERSCRIPT TWO */
 206           is = for_character ("\201\060\205\065", 4);
 207           ASSERT (is == 0);
 208           /* U+00B3 SUPERSCRIPT THREE */
 209           is = for_character ("\201\060\205\066", 4);
 210           ASSERT (is == 0);
 211           /* U+00B9 SUPERSCRIPT ONE */
 212           is = for_character ("\201\060\206\061", 4);
 213           ASSERT (is == 0);
 214           /* U+0663 ARABIC-INDIC DIGIT THREE */
 215           is = for_character ("\201\061\211\071", 4);
 216           ASSERT (is == 0);
 217           /* U+2070 SUPERSCRIPT ZERO */
 218           is = for_character ("\201\066\255\062", 4);
 219           ASSERT (is == 0);
 220           /* U+2079 SUPERSCRIPT NINE */
 221           is = for_character ("\201\066\256\061", 4);
 222           ASSERT (is == 0);
 223           /* U+FF11 FULLWIDTH DIGIT ONE */
 224           is = for_character ("\243\261", 2);
 225           ASSERT (is == 0);
 226           /* U+FF21 FULLWIDTH LATIN CAPITAL LETTER A */
 227           is = for_character ("\243\301", 2);
 228           ASSERT (is == 0);
 229           /* U+FF41 FULLWIDTH LATIN SMALL LETTER A */
 230           is = for_character ("\243\341", 2);
 231           ASSERT (is == 0);
 232           /* U+1D7D1 MATHEMATICAL BOLD DIGIT THREE */
 233           is = for_character ("\224\063\353\071", 4);
 234           ASSERT (is == 0);
 235           /* U+1D7DB MATHEMATICAL DOUBLE-STRUCK DIGIT THREE */
 236           is = for_character ("\224\063\354\071", 4);
 237           ASSERT (is == 0);
 238           /* U+1D7E5 MATHEMATICAL SANS-SERIF DIGIT THREE */
 239           is = for_character ("\224\063\355\071", 4);
 240           ASSERT (is == 0);
 241           /* U+1D7EF MATHEMATICAL SANS-SERIF BOLD DIGIT THREE */
 242           is = for_character ("\224\063\356\071", 4);
 243           ASSERT (is == 0);
 244           /* U+1D7F9 MATHEMATICAL MONOSPACE DIGIT THREE */
 245           is = for_character ("\224\063\357\071", 4);
 246           ASSERT (is == 0);
 247           /* U+E0033 TAG DIGIT THREE */
 248           is = for_character ("\323\066\232\071", 4);
 249           ASSERT (is == 0);
 250           /* U+E0041 TAG LATIN CAPITAL LETTER A */
 251           is = for_character ("\323\066\234\063", 4);
 252           ASSERT (is == 0);
 253         }
 254         return 0;
 255
 256       }
 257
 258   return 1;
 259 }