tests/test-mbrtoc32-regular.c

   1 /* Test of conversion of multibyte character to 32-bit wide character.
   2    Copyright (C) 2023-2025 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 /* Written by Bruno Haible <bruno@clisp.org>, 2023.  */
  18
  19 #include <config.h>
  20
  21 #include <uchar.h>
  22
  23 #include <locale.h>
  24 #include <stdio.h>
  25 #include <stdlib.h>
  26 #include <string.h>
  27 #include <uchar.h>
  28 #include <wchar.h>
  29
  30 #include "macros.h"
  31
  32 int
  33 main (int argc, char *argv[])
  34 {
  35   /* The only locales in which mbrtoc32 may map a multibyte character to a
  36      sequence of two or more Unicode characters are those with BIG5-HKSCS
  37      encoding.  See
  38      <https://lists.gnu.org/archive/html/bug-gnulib/2023-06/msg00134.html>
  39      <https://lists.gnu.org/archive/html/bug-gnulib/2023-07/msg00014.html>  */
  40   if (setlocale (LC_ALL, "zh_HK.BIG5-HKSCS") == NULL)
  41     {
  42       fprintf (stderr, "Skipping test: found no locale with BIG5-HKSCS encoding.\n");
  43       return 77;
  44     }
  45
  46   /* The problematic BIG5-HKSCS characters are:
  47
  48        input         maps to                          name
  49        -----         -------                          ----
  50      0x88 0x62    U+00CA U+0304    LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND MACRON
  51      0x88 0x64    U+00CA U+030C    LATIN CAPITAL LETTER E WITH CIRCUMFLEX AND CARON
  52      0x88 0xA3    U+00EA U+0304    LATIN SMALL LETTER E WITH CIRCUMFLEX AND MACRON
  53      0x88 0xA5    U+00EA U+030C    LATIN SMALL LETTER E WITH CIRCUMFLEX AND CARON
  54
  55      Test one of them.
  56      See <https://sourceware.org/bugzilla/show_bug.cgi?id=30611>.  */
  57   mbstate_t state;
  58   memset (&state, '\0', sizeof (mbstate_t));
  59   char32_t c32 = (char32_t) 0xBADFACE;
  60   size_t ret = mbrtoc32 (&c32, "\210\142", 2, &state);
  61   /* It is OK if this conversion fails.  */
  62   if (ret != (size_t)(-1))
  63     {
  64       /* mbrtoc32 being regular, means that STATE is in an initial state.  */
  65       ASSERT (mbsinit (&state));
  66       ret = mbrtoc32 (&c32, "", 0, &state);
  67       /* mbrtoc32 being regular, means that it returns (size_t)(-2), not
  68          (size_t)(-3), here.  */
  69       ASSERT (ret == (size_t)(-2));
  70       ret = mbrtoc32 (&c32, "", 1, &state);
  71       /* mbrtoc32 being regular, means that it returns the null 32-bit wide
  72          character, here, not any remnant from the previous multibyte
  73          character.  */
  74       ASSERT (ret == 0);
  75       ASSERT (c32 == 0);
  76     }
  77
  78   return test_exit_status;
  79 }