(root)/
coreutils-9.4/
gnulib-tests/
test-c32isdigit.c
       1  /* Test of c32isdigit() 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 (c32isdigit, 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 c32isdigit 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 c32isdigit (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 = c32isdigit (WEOF);
      59    ASSERT (is == 0);
      60  
      61    /* Test single-byte characters.
      62       ISO C 99 sections 7.25.2.1.5 and 5.2.1 specify that the decimal digits
      63       include only the ASCII 0 ... 9 characters.  */
      64    {
      65      int c;
      66  
      67      for (c = 0; c < 0x100; c++)
      68        switch (c)
      69          {
      70          case '\t': case '\v': case '\f':
      71          case ' ': case '!': case '"': case '#': case '%':
      72          case '&': case '\'': case '(': case ')': case '*':
      73          case '+': case ',': case '-': case '.': case '/':
      74          case '0': case '1': case '2': case '3': case '4':
      75          case '5': case '6': case '7': case '8': case '9':
      76          case ':': case ';': case '<': case '=': case '>':
      77          case '?':
      78          case 'A': case 'B': case 'C': case 'D': case 'E':
      79          case 'F': case 'G': case 'H': case 'I': case 'J':
      80          case 'K': case 'L': case 'M': case 'N': case 'O':
      81          case 'P': case 'Q': case 'R': case 'S': case 'T':
      82          case 'U': case 'V': case 'W': case 'X': case 'Y':
      83          case 'Z':
      84          case '[': case '\\': case ']': case '^': 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': case '{': case '|': case '}': case '~':
      91            /* c is in the ISO C "basic character set".  */
      92            buf[0] = (unsigned char) c;
      93            is = for_character (buf, 1);
      94            switch (c)
      95              {
      96              case '0': case '1': case '2': case '3': case '4':
      97              case '5': case '6': case '7': case '8': case '9':
      98                ASSERT (is != 0);
      99                break;
     100              default:
     101                ASSERT (is == 0);
     102                break;
     103              }
     104            break;
     105          }
     106    }
     107  
     108    if (argc > 1)
     109      switch (argv[1][0])
     110        {
     111        case '0':
     112          /* C locale; tested above.  */
     113          return 0;
     114  
     115        case '1':
     116          /* Locale encoding is ISO-8859-1 or ISO-8859-15.  */
     117          {
     118            /* U+00B2 SUPERSCRIPT TWO */
     119            is = for_character ("\262", 1);
     120            ASSERT (is == 0);
     121            /* U+00B3 SUPERSCRIPT THREE */
     122            is = for_character ("\263", 1);
     123            ASSERT (is == 0);
     124            /* U+00B9 SUPERSCRIPT ONE */
     125            is = for_character ("\271", 1);
     126            ASSERT (is == 0);
     127          }
     128          return 0;
     129  
     130        case '2':
     131          /* Locale encoding is EUC-JP.  */
     132          {
     133            /* U+FF11 FULLWIDTH DIGIT ONE */
     134            is = for_character ("\243\261", 2);
     135            ASSERT (is == 0);
     136          }
     137          return 0;
     138  
     139        case '3':
     140          /* Locale encoding is UTF-8.  */
     141          {
     142            /* U+00B2 SUPERSCRIPT TWO */
     143            is = for_character ("\302\262", 2);
     144            ASSERT (is == 0);
     145            /* U+00B3 SUPERSCRIPT THREE */
     146            is = for_character ("\302\263", 2);
     147            ASSERT (is == 0);
     148            /* U+00B9 SUPERSCRIPT ONE */
     149            is = for_character ("\302\271", 2);
     150            ASSERT (is == 0);
     151            /* U+0663 ARABIC-INDIC DIGIT THREE */
     152            is = for_character ("\331\243", 2);
     153            ASSERT (is == 0);
     154            /* U+2070 SUPERSCRIPT ZERO */
     155            is = for_character ("\342\201\260", 3);
     156            ASSERT (is == 0);
     157            /* U+2079 SUPERSCRIPT NINE */
     158            is = for_character ("\342\201\271", 3);
     159            ASSERT (is == 0);
     160            /* U+FF11 FULLWIDTH DIGIT ONE */
     161            is = for_character ("\357\274\221", 3);
     162            ASSERT (is == 0);
     163            /* U+1D7D1 MATHEMATICAL BOLD DIGIT THREE */
     164            is = for_character ("\360\235\237\221", 4);
     165            ASSERT (is == 0);
     166            /* U+1D7DB MATHEMATICAL DOUBLE-STRUCK DIGIT THREE */
     167            is = for_character ("\360\235\237\233", 4);
     168            ASSERT (is == 0);
     169            /* U+1D7E5 MATHEMATICAL SANS-SERIF DIGIT THREE */
     170            is = for_character ("\360\235\237\245", 4);
     171            ASSERT (is == 0);
     172            /* U+1D7EF MATHEMATICAL SANS-SERIF BOLD DIGIT THREE */
     173            is = for_character ("\360\235\237\257", 4);
     174            ASSERT (is == 0);
     175            /* U+1D7F9 MATHEMATICAL MONOSPACE DIGIT THREE */
     176            is = for_character ("\360\235\237\271", 4);
     177            ASSERT (is == 0);
     178            /* U+E0033 TAG DIGIT THREE */
     179            is = for_character ("\363\240\200\263", 4);
     180            ASSERT (is == 0);
     181          }
     182          return 0;
     183  
     184        case '4':
     185          /* Locale encoding is GB18030.  */
     186          #if (defined __GLIBC__ && __GLIBC__ == 2 && __GLIBC_MINOR__ >= 13 && __GLIBC_MINOR__ <= 15) || (GL_CHAR32_T_IS_UNICODE && (defined __NetBSD__ || defined __sun))
     187          fputs ("Skipping test: The GB18030 converter in this system's iconv is broken.\n", stderr);
     188          return 77;
     189          #endif
     190          {
     191            /* U+00B2 SUPERSCRIPT TWO */
     192            is = for_character ("\201\060\205\065", 4);
     193            ASSERT (is == 0);
     194            /* U+00B3 SUPERSCRIPT THREE */
     195            is = for_character ("\201\060\205\066", 4);
     196            ASSERT (is == 0);
     197            /* U+00B9 SUPERSCRIPT ONE */
     198            is = for_character ("\201\060\206\061", 4);
     199            ASSERT (is == 0);
     200            /* U+0663 ARABIC-INDIC DIGIT THREE */
     201            is = for_character ("\201\061\211\071", 4);
     202            ASSERT (is == 0);
     203            /* U+2070 SUPERSCRIPT ZERO */
     204            is = for_character ("\201\066\255\062", 4);
     205            ASSERT (is == 0);
     206            /* U+2079 SUPERSCRIPT NINE */
     207            is = for_character ("\201\066\256\061", 4);
     208            ASSERT (is == 0);
     209            /* U+FF11 FULLWIDTH DIGIT ONE */
     210            is = for_character ("\243\261", 2);
     211            ASSERT (is == 0);
     212            /* U+1D7D1 MATHEMATICAL BOLD DIGIT THREE */
     213            is = for_character ("\224\063\353\071", 4);
     214            ASSERT (is == 0);
     215            /* U+1D7DB MATHEMATICAL DOUBLE-STRUCK DIGIT THREE */
     216            is = for_character ("\224\063\354\071", 4);
     217            ASSERT (is == 0);
     218            /* U+1D7E5 MATHEMATICAL SANS-SERIF DIGIT THREE */
     219            is = for_character ("\224\063\355\071", 4);
     220            ASSERT (is == 0);
     221            /* U+1D7EF MATHEMATICAL SANS-SERIF BOLD DIGIT THREE */
     222            is = for_character ("\224\063\356\071", 4);
     223            ASSERT (is == 0);
     224            /* U+1D7F9 MATHEMATICAL MONOSPACE DIGIT THREE */
     225            is = for_character ("\224\063\357\071", 4);
     226            ASSERT (is == 0);
     227            /* U+E0033 TAG DIGIT THREE */
     228            is = for_character ("\323\066\232\071", 4);
     229            ASSERT (is == 0);
     230          }
     231          return 0;
     232  
     233        }
     234  
     235    return 1;
     236  }