tests/unigbrk/test-u8-grapheme-next.c

   1 /* Next grapheme cluster length test.
   2    Copyright (C) 2010-2024 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 <stdio.h>
  25 #include <stdlib.h>
  26
  27 #include "macros.h"
  28
  29 static void
  30 test_u8_grapheme_next (const char *input, size_t n, size_t len)
  31 {
  32   const uint8_t *s = (const uint8_t *) input;
  33   const uint8_t *next = u8_grapheme_next (s, s + n);
  34   if (next != s + len)
  35     {
  36       size_t i;
  37
  38       if (next == NULL)
  39         fputs ("u8_grapheme_next returned NULL", stderr);
  40       else
  41         fprintf (stderr, "u8_grapheme_next skipped %tu bytes", next - s);
  42       fprintf (stderr, ", expected %zu:\n", len);
  43       for (i = 0; i < n; i++)
  44         fprintf (stderr, " %02x", s[i]);
  45       putc ('\n', stderr);
  46       fflush (stderr);
  47       abort ();
  48     }
  49 }
  50
  51 int
  52 main (void)
  53 {
  54   static const uint8_t s[] = "abc";
  55
  56   /* Empty string. */
  57   ASSERT (u8_grapheme_next (NULL, NULL) == NULL);
  58   ASSERT (u8_grapheme_next (s, s) == NULL);
  59
  60   /* Standalone 1-unit graphemes.  */
  61   test_u8_grapheme_next ("a", 1, 1);
  62   test_u8_grapheme_next ("ab", 2, 1);
  63   test_u8_grapheme_next ("abc", 3, 1);
  64
  65   /* Multi-unit, single code point graphemes. */
  66 #define HIRAGANA_A "\343\201\202" /* あ: Hiragana letter 'a'. */
  67   test_u8_grapheme_next (HIRAGANA_A, 3, 3);
  68   test_u8_grapheme_next (HIRAGANA_A"x", 4, 3);
  69   test_u8_grapheme_next (HIRAGANA_A HIRAGANA_A, 6, 3);
  70
  71   /* Combining accents. */
  72 #define GRAVE "\314\200"        /* Combining grave accent. */
  73 #define ACUTE "\314\201"        /* Combining acute accent. */
  74   test_u8_grapheme_next ("e"ACUTE, 3, 3);
  75   test_u8_grapheme_next ("e"ACUTE GRAVE, 5, 5);
  76   test_u8_grapheme_next ("e"ACUTE"x", 4, 3);
  77   test_u8_grapheme_next ("e"ACUTE "e"ACUTE, 6, 3);
  78
  79   return test_exit_status;
  80 }