tests/unigbrk/test-u32-grapheme-breaks.c

   1 /* Grapheme cluster breaks test.
   2    Copyright (C) 2010-2025 Free Software Foundation, Inc.
   3
   4    This program is free software: you can redistribute it and/or modify it
   5    under the terms of the GNU Lesser General Public License as published
   6    by 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 GNU
  12    Lesser General Public License for more details.
  13
  14    You should have received a copy of the GNU Lesser General Public License
  15    along with this program.  If not, see <https://www.gnu.org/licenses/>.  */
  16
  17 /* Written by Ben Pfaff <blp@cs.stanford.edu>, 2010. */
  18
  19 #include <config.h>
  20
  21 /* Specification. */
  22 #include <unigbrk.h>
  23
  24 #include <stdarg.h>
  25 #include <stdio.h>
  26 #include <stdlib.h>
  27 #include <string.h>
  28
  29 #include "macros.h"
  30
  31 static void
  32 test_u32_grapheme_breaks (const char *expected, ...)
  33 {
  34   size_t n = strlen (expected);
  35   uint32_t s[16];
  36   va_list args;
  37   char breaks[16];
  38   size_t i;
  39
  40   ASSERT (n <= 16);
  41
  42   memset (breaks, 0xcc, n);
  43
  44   va_start (args, expected);
  45   for (i = 0; i < n; i++)
  46     {
  47       int unit = va_arg (args, int);
  48       ASSERT (unit >= 0);
  49       s[i] = unit;
  50     }
  51   ASSERT (va_arg (args, int) == -1);
  52   va_end (args);
  53
  54   u32_grapheme_breaks (s, n, breaks);
  55   for (i = 0; i < n; i++)
  56     if (breaks[i] != (expected[i] == '#'))
  57       {
  58         size_t j;
  59
  60         fprintf (stderr, "wrong grapheme breaks:\n");
  61
  62         fprintf (stderr, "   input:");
  63         for (j = 0; j < n; j++)
  64           fprintf (stderr, " %04X", s[j]);
  65         putc ('\n', stderr);
  66
  67         fprintf (stderr, "expected:");
  68         for (j = 0; j < n; j++)
  69           fprintf (stderr, "    %d", expected[j] == '#');
  70         putc ('\n', stderr);
  71
  72         fprintf (stderr, "  actual:");
  73         for (j = 0; j < n; j++)
  74           fprintf (stderr, "    %d", breaks[j]);
  75         putc ('\n', stderr);
  76
  77         fflush (stderr);
  78         abort ();
  79       }
  80 }
  81
  82 int
  83 main (void)
  84 {
  85   /* Standalone 1-unit graphemes.  */
  86   test_u32_grapheme_breaks ("#", 'a', -1);
  87   test_u32_grapheme_breaks ("##", 'a', 'b', -1);
  88   test_u32_grapheme_breaks ("###", 'a', 'b', 'c', -1);
  89
  90 #define HIRAGANA_A 0x3042       /* あ: Hiragana letter 'a'. */
  91   test_u32_grapheme_breaks ("#", HIRAGANA_A, -1);
  92   test_u32_grapheme_breaks ("##", HIRAGANA_A, 'x', -1);
  93   test_u32_grapheme_breaks ("##", HIRAGANA_A, HIRAGANA_A, -1);
  94
  95   /* Combining accents. */
  96 #define GRAVE 0x0300            /* Combining grave accent. */
  97 #define ACUTE 0x0301            /* Combining acute accent. */
  98   test_u32_grapheme_breaks ("#_", 'e', ACUTE, -1);
  99   test_u32_grapheme_breaks ("#__", 'e', ACUTE, GRAVE, -1);
 100   test_u32_grapheme_breaks ("#_#", 'e', ACUTE, 'x', -1);
 101   test_u32_grapheme_breaks ("#_#_", 'e', ACUTE, 'e', GRAVE, -1);
 102
 103   /* CR LF handling.  */
 104   test_u32_grapheme_breaks ("######_#",
 105                             'a', '\n', 'b', '\r', 'c', '\r', '\n', 'd',
 106                             -1);
 107
 108   /* Emoji modifier / ZWJ sequence. */
 109   test_u32_grapheme_breaks ("#____",
 110                             0x2605, 0x0305, 0x0347, 0x200D, 0x2600,
 111                             -1);
 112
 113   /* Regional indicators. */
 114   test_u32_grapheme_breaks ("##_#_#",
 115                             '.', 0x1F1E9, 0x1F1EA, 0x1F1EB, 0x1F1F7, '.',
 116                             -1);
 117
 118   return test_exit_status;
 119 }