tests/unicase/test-u8-totitle.c

   1 /* Test of titlecase mapping for UTF-8 strings.
   2    Copyright (C) 2009-2020 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 "unicase.h"
  22
  23 #include <stdlib.h>
  24
  25 #include "unistr.h"
  26 #include "uninorm.h"
  27 #include "macros.h"
  28
  29 static int
  30 check (const uint8_t *input, size_t input_length,
  31        const char *iso639_language, uninorm_t nf,
  32        const uint8_t *expected, size_t expected_length)
  33 {
  34   size_t length;
  35   uint8_t *result;
  36
  37   /* Test return conventions with resultbuf == NULL.  */
  38   result = u8_totitle (input, input_length, iso639_language, nf, NULL, &length);
  39   if (!(result != NULL))
  40     return 1;
  41   if (!(length == expected_length))
  42     return 2;
  43   if (!(u8_cmp (result, expected, expected_length) == 0))
  44     return 3;
  45   free (result);
  46
  47   /* Test return conventions with resultbuf too small.  */
  48   if (expected_length > 0)
  49     {
  50       uint8_t *preallocated;
  51
  52       length = expected_length - 1;
  53       preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
  54       result = u8_totitle (input, input_length, iso639_language, nf, preallocated, &length);
  55       if (!(result != NULL))
  56         return 4;
  57       if (!(result != preallocated))
  58         return 5;
  59       if (!(length == expected_length))
  60         return 6;
  61       if (!(u8_cmp (result, expected, expected_length) == 0))
  62         return 7;
  63       free (result);
  64       free (preallocated);
  65     }
  66
  67   /* Test return conventions with resultbuf large enough.  */
  68   {
  69     uint8_t *preallocated;
  70
  71     length = expected_length;
  72     preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
  73     result = u8_totitle (input, input_length, iso639_language, nf, preallocated, &length);
  74     if (!(result != NULL))
  75       return 8;
  76     if (!(preallocated == NULL || result == preallocated))
  77       return 9;
  78     if (!(length == expected_length))
  79       return 10;
  80     if (!(u8_cmp (result, expected, expected_length) == 0))
  81       return 11;
  82     free (preallocated);
  83   }
  84
  85   return 0;
  86 }
  87
  88 int
  89 main ()
  90 {
  91   { /* Empty string.  */
  92     ASSERT (check (NULL, 0, NULL, NULL, NULL, 0) == 0);
  93     ASSERT (check (NULL, 0, NULL, UNINORM_NFC, NULL, 0) == 0);
  94   }
  95
  96   /* Simple string.  */
  97   { /* "GRÜß GOTT. ЗДРАВСТВУЙТЕ! X=(-B±SQRT(B²-4AC))/(2A)  日本語,中文,한글" */
  98     static const uint8_t input[] =
  99       { 'G', 'R', 0xC3, 0x9C, 0xC3, 0x9F, ' ', 'G', 'O', 'T', 'T', '.', ' ',
 100         0xD0, 0x97, 0xD0, 0x94, 0xD0, 0xA0, 0xD0, 0x90, 0xD0, 0x92, 0xD0, 0xA1,
 101         0xD0, 0xA2, 0xD0, 0x92, 0xD0, 0xA3, 0xD0, 0x99, 0xD0, 0xA2, 0xD0, 0x95,
 102         '!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'Q', 'R', 'T', '(',
 103         'B', 0xC2, 0xB2, '-', '4', 'A', 'C', ')', ')', '/', '(', '2', 'A', ')',
 104         ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
 105         0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
 106         0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
 107       };
 108     static const uint8_t casemapped[] =
 109       { 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
 110         0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
 111         0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
 112         '!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'q', 'r', 't', '(',
 113         'B', 0xC2, 0xB2, '-', '4', 'A', 'c', ')', ')', '/', '(', '2', 'A', ')',
 114         ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
 115         0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
 116         0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
 117       };
 118     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 119   }
 120
 121   /* Case mapping can increase the number of Unicode characters.  */
 122   { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
 123     static const uint8_t input[]      = { 0xC5, 0x89 };
 124     static const uint8_t casemapped[] = { 0xCA, 0xBC, 0x4E };
 125     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 126   }
 127   { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
 128     static const uint8_t input[]      = { 0xCE, 0x90 };
 129     static const uint8_t casemapped[] = { 0xCE, 0x99, 0xCC, 0x88, 0xCC, 0x81 };
 130     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 131   }
 132
 133   /* Turkish letters i İ ı I */
 134   { /* LATIN CAPITAL LETTER I */
 135     static const uint8_t input[]      = { 0x49 };
 136     static const uint8_t casemapped[] = { 0x49 };
 137     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 138     ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
 139   }
 140   { /* LATIN SMALL LETTER I */
 141     static const uint8_t input[]         = { 0x69 };
 142     static const uint8_t casemapped[]    = { 0x49 };
 143     static const uint8_t casemapped_tr[] = { 0xC4, 0xB0 };
 144     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 145     ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped_tr, SIZEOF (casemapped_tr)) == 0);
 146   }
 147   { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
 148     static const uint8_t input[]      = { 0xC4, 0xB0 };
 149     static const uint8_t casemapped[] = { 0xC4, 0xB0 };
 150     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 151     ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
 152   }
 153   { /* LATIN SMALL LETTER DOTLESS I */
 154     static const uint8_t input[]      = { 0xC4, 0xB1 };
 155     static const uint8_t casemapped[] = { 0x49 };
 156     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 157     ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
 158   }
 159   { /* "topkapı" */
 160     static const uint8_t input[] =
 161       { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
 162     static const uint8_t casemapped[] =
 163       { 0x54, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
 164     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 165     ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
 166   }
 167
 168   /* Uppercasing can increase the number of Unicode characters.  */
 169   { /* "heiß" */
 170     static const uint8_t input[]      = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
 171     static const uint8_t casemapped[] = { 0x48, 0x65, 0x69, 0xC3, 0x9F };
 172     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 173   }
 174
 175   /* Case mappings for some characters can depend on the surrounding characters.  */
 176   { /* "περισσότερες πληροφορίες" */
 177     static const uint8_t input[] =
 178       {
 179         0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
 180         0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
 181         ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
 182         0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
 183       };
 184     static const uint8_t casemapped[] =
 185       {
 186         0xCE, 0xA0, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
 187         0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
 188         ' ', 0xCE, 0xA0, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
 189         0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
 190       };
 191     ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
 192   }
 193
 194   /* Case mapping can require subsequent normalization.  */
 195   { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
 196     static const uint8_t input[]                 = { 0xC7, 0xB0, 0xCC, 0xA3 };
 197     static const uint8_t casemapped[]            = { 0x4A, 0xCC, 0x8C, 0xCC, 0xA3 };
 198     static const uint8_t casemapped_normalized[] = { 0x4A, 0xCC, 0xA3, 0xCC, 0x8C };
 199     ASSERT (check (input, SIZEOF (input), NULL, NULL,        casemapped, SIZEOF (casemapped)) == 0);
 200     ASSERT (check (input, SIZEOF (input), NULL, UNINORM_NFC, casemapped_normalized, SIZEOF (casemapped_normalized)) == 0);
 201   }
 202
 203   return 0;
 204 }