tests/uninorm/test-uninorm-filter-nfc.c

   1 /* Test of canonical normalization of streams.
   2    Copyright (C) 2009-2018 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>, 2009.  */
  18
  19 #include <config.h>
  20
  21 #include "uninorm.h"
  22
  23 #include <stdlib.h>
  24
  25 #include "unistr.h"
  26 #include "macros.h"
  27
  28 /* A stream of Unicode characters that simply accumulates the contents.  */
  29
  30 struct accumulator
  31 {
  32   uint32_t *result;
  33   size_t length;
  34   size_t allocated;
  35 };
  36
  37 static int
  38 write_to_accumulator (void *stream_data, ucs4_t uc)
  39 {
  40   struct accumulator *accu = (struct accumulator *) stream_data;
  41
  42   if (accu->length == accu->allocated)
  43     {
  44       accu->allocated = 2 * accu->allocated + 1;
  45       accu->result = (uint32_t *) realloc (accu->result, accu->allocated * sizeof (uint32_t));
  46     }
  47   accu->result[accu->length] = uc;
  48   accu->length++;
  49   return 0;
  50 }
  51
  52 static int
  53 check (const uint32_t *input, size_t input_length,
  54        const uint32_t *expected, size_t expected_length)
  55 {
  56   struct accumulator accu;
  57   struct uninorm_filter *filter;
  58   size_t i;
  59
  60   accu.result = NULL;
  61   accu.length = 0;
  62   accu.allocated = 0;
  63
  64   filter = uninorm_filter_create (UNINORM_NFC, write_to_accumulator, &accu);
  65   ASSERT (filter != NULL);
  66
  67   for (i = 0; i < input_length; i++)
  68     ASSERT (uninorm_filter_write (filter, input[i]) == 0);
  69
  70   ASSERT (uninorm_filter_free (filter) == 0);
  71
  72   if (!(accu.result != NULL))
  73     return 1;
  74   if (!(accu.length == expected_length))
  75     return 2;
  76   if (!(u32_cmp (accu.result, expected, expected_length) == 0))
  77     return 3;
  78   free (accu.result);
  79
  80   return 0;
  81 }
  82
  83 int
  84 main ()
  85 {
  86   { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a)  日本語,中文,한글" */
  87     static const uint32_t input[] =
  88       { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
  89         0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
  90         0x0439, 0x0442, 0x0435, '!', ' ',
  91         'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
  92         '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
  93         0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
  94       };
  95     static const uint32_t decomposed[] =
  96       { 'G', 'r', 0x0075, 0x0308, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
  97         0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
  98         0x0438, 0x0306, 0x0442, 0x0435, '!', ' ',
  99         'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
 100         '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
 101         0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',',
 102         0x1112, 0x1161, 0x11AB, 0x1100, 0x1173, 0x11AF, '\n'
 103       };
 104     ASSERT (check (input, SIZEOF (input),           input, SIZEOF (input)) == 0);
 105     ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
 106   }
 107
 108   return 0;
 109 }