tests/test-c32isalnum.c

   1 /* Test of c32isalnum() function.
   2    Copyright (C) 2020-2024 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 (c32isalnum, 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 c32isalnum 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 c32isalnum (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 = c32isalnum (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 alphanumeric characters include the uppercase and
  66          lowercase characters and digits and, consequently, include the A ... Z
  67          and a ... z and 0 ... 9 characters.
  68        - in the "POSIX" locale (which is usually the same as the "C" locale),
  69          the alphanumeric characters include only the ASCII A ... Z and a ... z
  70          and 0 ... 9 characters.  */
  71   {
  72     int c;
  73
  74     for (c = 0; c < 0x100; c++)
  75       switch (c)
  76         {
  77         case '\t': case '\v': case '\f':
  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".  */
  99           buf[0] = (unsigned char) c;
 100           is = for_character (buf, 1);
 101           switch (c)
 102             {
 103             case '0': case '1': case '2': case '3': case '4':
 104             case '5': case '6': case '7': case '8': case '9':
 105             case 'A': case 'B': case 'C': case 'D': case 'E':
 106             case 'F': case 'G': case 'H': case 'I': case 'J':
 107             case 'K': case 'L': case 'M': case 'N': case 'O':
 108             case 'P': case 'Q': case 'R': case 'S': case 'T':
 109             case 'U': case 'V': case 'W': case 'X': case 'Y':
 110             case 'Z':
 111             case 'a': case 'b': case 'c': case 'd': case 'e':
 112             case 'f': case 'g': case 'h': case 'i': case 'j':
 113             case 'k': case 'l': case 'm': case 'n': case 'o':
 114             case 'p': case 'q': case 'r': case 's': case 't':
 115             case 'u': case 'v': case 'w': case 'x': case 'y':
 116             case 'z':
 117               ASSERT (is != 0);
 118               break;
 119             default:
 120               ASSERT (is == 0);
 121               break;
 122             }
 123           break;
 124         }
 125   }
 126
 127   if (argc > 1)
 128     switch (argv[1][0])
 129       {
 130       case '0':
 131         /* C locale; tested above.  */
 132         return test_exit_status;
 133
 134       case '1':
 135         /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
 136         {
 137           /* U+00D7 MULTIPLICATION SIGN */
 138           is = for_character ("\327", 1);
 139           ASSERT (is == 0);
 140           /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
 141           is = for_character ("\330", 1);
 142           ASSERT (is != 0);
 143         }
 144         return test_exit_status;
 145
 146       case '2':
 147         /* Locale encoding is EUC-JP.  */
 148         {
 149           /* U+00D7 MULTIPLICATION SIGN */
 150           is = for_character ("\241\337", 2);
 151           ASSERT (is == 0);
 152         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__)
 153           /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
 154           is = for_character ("\217\251\254", 3);
 155           ASSERT (is != 0);
 156           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 157           is = for_character ("\217\251\250", 3);
 158           ASSERT (is != 0);
 159         #endif
 160           /* U+3001 IDEOGRAPHIC COMMA */
 161           is = for_character ("\241\242", 2);
 162           ASSERT (is == 0);
 163         #if defined __GLIBC__
 164           /* U+FF11 FULLWIDTH DIGIT ONE */
 165           is = for_character ("\243\261", 2);
 166           ASSERT (is != 0);
 167         #endif
 168         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__)
 169           /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
 170           is = for_character ("\243\355", 2);
 171           ASSERT (is != 0);
 172         #endif
 173         }
 174         return test_exit_status;
 175
 176       case '3':
 177         /* Locale encoding is UTF-8.  */
 178         {
 179           /* U+00D7 MULTIPLICATION SIGN */
 180           is = for_character ("\303\227", 2);
 181           ASSERT (is == 0);
 182           /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
 183           is = for_character ("\303\230", 2);
 184           ASSERT (is != 0);
 185           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 186           is = for_character ("\305\201", 2);
 187           ASSERT (is != 0);
 188           /* U+3001 IDEOGRAPHIC COMMA */
 189           is = for_character ("\343\200\201", 3);
 190           ASSERT (is == 0);
 191         #if defined __GLIBC__
 192           /* U+FF11 FULLWIDTH DIGIT ONE */
 193           is = for_character ("\357\274\221", 3);
 194           ASSERT (is != 0);
 195         #endif
 196           /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
 197           is = for_character ("\357\275\215", 3);
 198           ASSERT (is != 0);
 199         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
 200           /* U+10330 GOTHIC LETTER AHSA */
 201           is = for_character ("\360\220\214\260", 4);
 202           ASSERT (is != 0);
 203         #endif
 204           /* U+1D100 MUSICAL SYMBOL SINGLE BARLINE */
 205           is = for_character ("\360\235\204\200", 4);
 206           ASSERT (is == 0);
 207           /* U+E0061 TAG LATIN SMALL LETTER A */
 208           is = for_character ("\363\240\201\241", 4);
 209           ASSERT (is == 0);
 210         }
 211         return test_exit_status;
 212
 213       case '4':
 214         /* Locale encoding is GB18030.  */
 215         #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __FreeBSD__ || defined __NetBSD__ || defined __sun))
 216         if (test_exit_status != EXIT_SUCCESS)
 217           return test_exit_status;
 218         fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
 219         return 77;
 220         #endif
 221         {
 222           /* U+00D7 MULTIPLICATION SIGN */
 223           is = for_character ("\241\301", 2);
 224           ASSERT (is == 0);
 225         #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
 226           /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
 227           is = for_character ("\201\060\211\061", 4);
 228           ASSERT (is != 0);
 229           /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
 230           is = for_character ("\201\060\221\071", 4);
 231           ASSERT (is != 0);
 232         #endif
 233           /* U+3001 IDEOGRAPHIC COMMA */
 234           is = for_character ("\241\242", 2);
 235           ASSERT (is == 0);
 236         #if defined __GLIBC__
 237           /* U+FF11 FULLWIDTH DIGIT ONE */
 238           is = for_character ("\243\261", 2);
 239           ASSERT (is != 0);
 240         #endif
 241         #if !defined __DragonFly__
 242           /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
 243           is = for_character ("\243\355", 2);
 244           ASSERT (is != 0);
 245         #endif
 246         #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
 247           /* U+10330 GOTHIC LETTER AHSA */
 248           is = for_character ("\220\060\322\066", 4);
 249           ASSERT (is != 0);
 250         #endif
 251           /* U+1D100 MUSICAL SYMBOL SINGLE BARLINE */
 252           is = for_character ("\224\062\273\064", 4);
 253           ASSERT (is == 0);
 254           /* U+E0061 TAG LATIN SMALL LETTER A */
 255           is = for_character ("\323\066\237\065", 4);
 256           ASSERT (is == 0);
 257         }
 258         return test_exit_status;
 259
 260       }
 261
 262   return 1;
 263 }