(root)/
coreutils-9.4/
gnulib-tests/
test-c32isalpha.c
       1  /* Test of c32isalpha() function.
       2     Copyright (C) 2020-2023 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 (c32isalpha, 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 c32isalpha 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 c32isalpha (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 = c32isalpha (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 alphabetic characters include the uppercase and
      66           lowercase characters and, consequently, include the A ... Z and a ... z
      67           characters.
      68         - in the "POSIX" locale (which is usually the same as the "C" locale),
      69           the alphabetic characters include only the ASCII A ... Z and a ... z
      70           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 'A': case 'B': case 'C': case 'D': case 'E':
     104              case 'F': case 'G': case 'H': case 'I': case 'J':
     105              case 'K': case 'L': case 'M': case 'N': case 'O':
     106              case 'P': case 'Q': case 'R': case 'S': case 'T':
     107              case 'U': case 'V': case 'W': case 'X': case 'Y':
     108              case 'Z':
     109              case 'a': case 'b': case 'c': case 'd': case 'e':
     110              case 'f': case 'g': case 'h': case 'i': case 'j':
     111              case 'k': case 'l': case 'm': case 'n': case 'o':
     112              case 'p': case 'q': case 'r': case 's': case 't':
     113              case 'u': case 'v': case 'w': case 'x': case 'y':
     114              case 'z':
     115                ASSERT (is != 0);
     116                break;
     117              default:
     118                ASSERT (is == 0);
     119                break;
     120              }
     121            break;
     122          }
     123    }
     124  
     125    if (argc > 1)
     126      switch (argv[1][0])
     127        {
     128        case '0':
     129          /* C locale; tested above.  */
     130          return 0;
     131  
     132        case '1':
     133          /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
     134          {
     135            /* U+00D7 MULTIPLICATION SIGN */
     136            is = for_character ("\327", 1);
     137            ASSERT (is == 0);
     138            /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
     139            is = for_character ("\330", 1);
     140            ASSERT (is != 0);
     141          }
     142          return 0;
     143  
     144        case '2':
     145          /* Locale encoding is EUC-JP.  */
     146          {
     147            /* U+00D7 MULTIPLICATION SIGN */
     148            is = for_character ("\241\337", 2);
     149            ASSERT (is == 0);
     150          #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__)
     151            /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
     152            is = for_character ("\217\251\254", 3);
     153            ASSERT (is != 0);
     154            /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
     155            is = for_character ("\217\251\250", 3);
     156            ASSERT (is != 0);
     157          #endif
     158            /* U+3001 IDEOGRAPHIC COMMA */
     159            is = for_character ("\241\242", 2);
     160            ASSERT (is == 0);
     161          #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __NetBSD__ || defined __sun || defined __CYGWIN__)
     162            /* U+FF11 FULLWIDTH DIGIT ONE */
     163            is = for_character ("\243\261", 2);
     164            ASSERT (is == 0);
     165          #endif
     166          #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__)
     167            /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
     168            is = for_character ("\243\355", 2);
     169            ASSERT (is != 0);
     170          #endif
     171          }
     172          return 0;
     173  
     174        case '3':
     175          /* Locale encoding is UTF-8.  */
     176          {
     177            /* U+00D7 MULTIPLICATION SIGN */
     178            is = for_character ("\303\227", 2);
     179            ASSERT (is == 0);
     180            /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
     181            is = for_character ("\303\230", 2);
     182            ASSERT (is != 0);
     183            /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
     184            is = for_character ("\305\201", 2);
     185            ASSERT (is != 0);
     186            /* U+3001 IDEOGRAPHIC COMMA */
     187            is = for_character ("\343\200\201", 3);
     188            ASSERT (is == 0);
     189          #if !(defined __GLIBC__ || defined MUSL_LIBC || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __NetBSD__ || defined _AIX || defined __sun || defined __CYGWIN__)
     190            /* U+FF11 FULLWIDTH DIGIT ONE */
     191            is = for_character ("\357\274\221", 3);
     192            ASSERT (is == 0);
     193          #endif
     194            /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
     195            is = for_character ("\357\275\215", 3);
     196            ASSERT (is != 0);
     197          #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
     198            /* U+10330 GOTHIC LETTER AHSA */
     199            is = for_character ("\360\220\214\260", 4);
     200            ASSERT (is != 0);
     201          #endif
     202            /* U+1D100 MUSICAL SYMBOL SINGLE BARLINE */
     203            is = for_character ("\360\235\204\200", 4);
     204            ASSERT (is == 0);
     205            /* U+E0061 TAG LATIN SMALL LETTER A */
     206            is = for_character ("\363\240\201\241", 4);
     207            ASSERT (is == 0);
     208          }
     209          return 0;
     210  
     211        case '4':
     212          /* Locale encoding is GB18030.  */
     213          #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __NetBSD__ || defined __sun))
     214          fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
     215          return 77;
     216          #endif
     217          {
     218            /* U+00D7 MULTIPLICATION SIGN */
     219            is = for_character ("\241\301", 2);
     220            ASSERT (is == 0);
     221          #if !(defined __FreeBSD__ || defined __DragonFly__ || defined __sun)
     222            /* U+00D8 LATIN CAPITAL LETTER O WITH STROKE */
     223            is = for_character ("\201\060\211\061", 4);
     224            ASSERT (is != 0);
     225            /* U+0141 LATIN CAPITAL LETTER L WITH STROKE */
     226            is = for_character ("\201\060\221\071", 4);
     227            ASSERT (is != 0);
     228          #endif
     229            /* U+3001 IDEOGRAPHIC COMMA */
     230            is = for_character ("\241\242", 2);
     231            ASSERT (is == 0);
     232          #if !(defined __GLIBC__ || (defined __APPLE__ && defined __MACH__) || defined __FreeBSD__)
     233            /* U+FF11 FULLWIDTH DIGIT ONE */
     234            is = for_character ("\243\261", 2);
     235            ASSERT (is == 0);
     236          #endif
     237          #if !defined __DragonFly__
     238            /* U+FF4D FULLWIDTH LATIN SMALL LETTER M */
     239            is = for_character ("\243\355", 2);
     240            ASSERT (is != 0);
     241          #endif
     242          #if !((defined __APPLE__ && defined __MACH__) || defined __FreeBSD__ || defined __DragonFly__ || defined __NetBSD__ || defined __sun)
     243            /* U+10330 GOTHIC LETTER AHSA */
     244            is = for_character ("\220\060\322\066", 4);
     245            ASSERT (is != 0);
     246          #endif
     247            /* U+1D100 MUSICAL SYMBOL SINGLE BARLINE */
     248            is = for_character ("\224\062\273\064", 4);
     249            ASSERT (is == 0);
     250            /* U+E0061 TAG LATIN SMALL LETTER A */
     251            is = for_character ("\323\066\237\065", 4);
     252            ASSERT (is == 0);
     253          }
     254          return 0;
     255  
     256        }
     257  
     258    return 1;
     259  }