tests/unicase/test-u8-casecmp.c

   1 /* Test of case and normalization insensitive comparison of 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 "uninorm.h"
  24 #include "macros.h"
  25
  26 #define UNIT uint8_t
  27 #include "test-casecmp.h"
  28 #undef UNIT
  29
  30 static void
  31 test_nonascii (int (*my_casecmp) (const uint8_t *, size_t, const uint8_t *, size_t, const char *, uninorm_t, int *))
  32 {
  33   /* Normalization effects.  */
  34   {
  35     static const uint8_t input1[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e' };
  36     static const uint8_t input2[] = { 'H', 'O', 0xCC, 0x88, 'h', 'L', 'e' };
  37     static const uint8_t input3[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e', 'n' };
  38     static const uint8_t input4[] = { 'H', 'O', 0xCC, 0x88, 'h', 'L', 'e', 'n' };
  39     static const uint8_t input5[] = { 'H', 'u', 'r', 'z' };
  40     int cmp;
  41
  42     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
  43     ASSERT (cmp == 0);
  44
  45     ASSERT (my_casecmp (input2, SIZEOF (input2), input1, SIZEOF (input1), NULL, UNINORM_NFD, &cmp) == 0);
  46     ASSERT (cmp == 0);
  47
  48     ASSERT (my_casecmp (input3, SIZEOF (input3), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
  49     ASSERT (cmp == 0);
  50
  51     ASSERT (my_casecmp (input4, SIZEOF (input4), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
  52     ASSERT (cmp == 0);
  53
  54     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
  55     ASSERT (cmp == -1);
  56
  57     ASSERT (my_casecmp (input1, SIZEOF (input1), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
  58     ASSERT (cmp == -1);
  59
  60     ASSERT (my_casecmp (input1, SIZEOF (input1), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
  61     ASSERT (cmp == -1);
  62
  63     ASSERT (my_casecmp (input2, SIZEOF (input2), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
  64     ASSERT (cmp == -1);
  65   }
  66   { /* LATIN CAPITAL LETTER A WITH DIAERESIS */
  67     static const uint8_t input1[] = { 0xC3, 0x84 };
  68     static const uint8_t input2[] = { 0x41, 0xCC, 0x88 };
  69     int cmp;
  70
  71     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
  72     ASSERT (cmp == 0);
  73   }
  74   { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
  75     static const uint8_t input1[] = { 0xC7, 0x9E };
  76     static const uint8_t input2[] = { 0x41, 0xCC, 0x88, 0xCC, 0x84 };
  77     int cmp;
  78
  79     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
  80     ASSERT (cmp == 0);
  81   }
  82   { /* GREEK DIALYTIKA AND PERISPOMENI */
  83     static const uint8_t input1[] = { 0xE1, 0xBF, 0x81 };
  84     static const uint8_t input2[] = { 0xC2, 0xA8, 0xCD, 0x82 };
  85     int cmp;
  86
  87     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
  88     ASSERT (cmp == 0);
  89   }
  90   { /* HANGUL SYLLABLE GEUL */
  91     static const uint8_t input1[] = { 0xEA, 0xB8, 0x80 };
  92     static const uint8_t input2[] = { 0xEA, 0xB7, 0xB8, 0xE1, 0x86, 0xAF };
  93     static const uint8_t input3[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3, 0xE1, 0x86, 0xAF };
  94     int cmp;
  95
  96     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
  97     ASSERT (cmp == 0);
  98
  99     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 100     ASSERT (cmp == 0);
 101   }
 102   { /* HANGUL SYLLABLE GEU */
 103     static const uint8_t input1[] = { 0xEA, 0xB7, 0xB8 };
 104     static const uint8_t input2[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3 };
 105     int cmp;
 106
 107     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 108     ASSERT (cmp == 0);
 109   }
 110
 111   /* Simple string.  */
 112   { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a)  日本語,中文,한글" */
 113     static const uint8_t input1[] =
 114       { 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
 115         0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
 116         0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
 117         '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
 118         'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
 119         ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
 120         0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
 121         0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
 122       };
 123     static const uint8_t input2[] =
 124       { 'g', 'r', 0xC3, 0xBC, 0x73, 0x73, ' ', 'g', 'o', 't', 't', '.', ' ',
 125         0xD0, 0xB7, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
 126         0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
 127         '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
 128         'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
 129         ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
 130         0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
 131         0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
 132       };
 133     static const uint8_t input3[] =
 134       { 'G', 'R', 0xC3, 0x9C, 0x53, 0x53, ' ', 'G', 'O', 'T', 'T', '.', ' ',
 135         0xD0, 0x97, 0xD0, 0x94, 0xD0, 0xA0, 0xD0, 0x90, 0xD0, 0x92, 0xD0, 0xA1,
 136         0xD0, 0xA2, 0xD0, 0x92, 0xD0, 0xA3, 0xD0, 0x99, 0xD0, 0xA2, 0xD0, 0x95,
 137         '!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'Q', 'R', 'T', '(',
 138         'B', 0xC2, 0xB2, '-', '4', 'A', 'C', ')', ')', '/', '(', '2', 'A', ')',
 139         ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
 140         0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
 141         0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
 142       };
 143     int cmp;
 144
 145     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 146     ASSERT (cmp == 0);
 147
 148     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 149     ASSERT (cmp == 0);
 150
 151     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 152     ASSERT (cmp == 0);
 153
 154     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 155     ASSERT (cmp == 0);
 156
 157     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 158     ASSERT (cmp == 0);
 159
 160     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 161     ASSERT (cmp == 0);
 162   }
 163
 164   /* Case mapping can increase the number of Unicode characters.  */
 165   { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
 166     static const uint8_t input1[] = { 0xC5, 0x89 };
 167     static const uint8_t input2[] = { 0xCA, 0xBC, 0x6E };
 168     static const uint8_t input3[] = { 0xCA, 0xBC, 0x4E };
 169     int cmp;
 170
 171     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 172     ASSERT (cmp == 0);
 173
 174     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 175     ASSERT (cmp == 0);
 176
 177     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 178     ASSERT (cmp == 0);
 179
 180     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 181     ASSERT (cmp == 0);
 182   }
 183   { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
 184     static const uint8_t input1[] = { 0xCE, 0x90 };
 185     static const uint8_t input2[] = { 0xCE, 0xB9, 0xCC, 0x88, 0xCC, 0x81 };
 186     int cmp;
 187
 188     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 189     ASSERT (cmp == 0);
 190
 191     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 192     ASSERT (cmp == 0);
 193   }
 194
 195   /* Turkish letters i İ ı I */
 196   { /* LATIN CAPITAL LETTER I */
 197     static const uint8_t input[]         = { 0x49 };
 198     static const uint8_t casefolded[]    = { 0x69 };
 199     static const uint8_t casefolded_tr[] = { 0xC4, 0xB1 };
 200     int cmp;
 201
 202     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 203     ASSERT (cmp == 0);
 204
 205     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
 206     ASSERT (cmp == 0);
 207   }
 208   { /* LATIN SMALL LETTER I */
 209     static const uint8_t input[]         = { 0x69 };
 210     static const uint8_t casefolded[]    = { 0x49 };
 211     static const uint8_t casefolded_tr[] = { 0xC4, 0xB0 };
 212     int cmp;
 213
 214     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 215     ASSERT (cmp == 0);
 216
 217     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
 218     ASSERT (cmp == 0);
 219   }
 220   { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
 221     static const uint8_t input[]         = { 0xC4, 0xB0 };
 222     static const uint8_t casefolded[]    = { 0x69, 0xCC, 0x87 };
 223     static const uint8_t casefolded_tr[] = { 0x69 };
 224     int cmp;
 225
 226     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 227     ASSERT (cmp == 0);
 228
 229     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
 230     ASSERT (cmp == 0);
 231   }
 232   { /* LATIN SMALL LETTER DOTLESS I */
 233     static const uint8_t input[]      = { 0xC4, 0xB1 };
 234     static const uint8_t casefolded[] = { 0x49 };
 235     int cmp;
 236
 237     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 238     ASSERT (cmp == 1);
 239
 240     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
 241     ASSERT (cmp == 0);
 242   }
 243   { /* "topkapı" */
 244     static const uint8_t input[] =
 245       { 0x54, 0x4F, 0x50, 0x4B, 0x41, 0x50, 0x49 };
 246     static const uint8_t casefolded[] =
 247       { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
 248     int cmp;
 249
 250     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 251     ASSERT (cmp == -1);
 252
 253     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
 254     ASSERT (cmp == 0);
 255   }
 256
 257   /* Uppercasing can increase the number of Unicode characters.  */
 258   { /* "heiß" */
 259     static const uint8_t input1[] = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
 260     static const uint8_t input2[] = { 0x68, 0x65, 0x69, 0x73, 0x73 };
 261     int cmp;
 262
 263     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 264     ASSERT (cmp == 0);
 265   }
 266
 267   /* Case mappings for some characters can depend on the surrounding characters.  */
 268   { /* "περισσότερες πληροφορίες" */
 269     static const uint8_t input1[] =
 270       {
 271         0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
 272         0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
 273         ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
 274         0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
 275       };
 276     static const uint8_t input2[] =
 277       {
 278         0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
 279         0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x83,
 280         ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
 281         0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x83
 282       };
 283     static const uint8_t input3[] =
 284       {
 285         0xCE, 0xA0, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x99, 0xCE, 0xA3, 0xCE, 0xA3,
 286         0xCE, 0x8C, 0xCE, 0xA4, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x95, 0xCE, 0xA3,
 287         ' ', 0xCE, 0xA0, 0xCE, 0x9B, 0xCE, 0x97, 0xCE, 0xA1, 0xCE, 0x9F,
 288         0xCE, 0xA6, 0xCE, 0x9F, 0xCE, 0xA1, 0xCE, 0x8A, 0xCE, 0x95, 0xCE, 0xA3
 289       };
 290     int cmp;
 291
 292     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 293     ASSERT (cmp == 0);
 294
 295     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 296     ASSERT (cmp == 0);
 297
 298     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 299     ASSERT (cmp == 0);
 300   }
 301
 302   /* Case mapping can require subsequent normalization.  */
 303   { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
 304     static const uint8_t input[]                 = { 0xC7, 0xB0, 0xCC, 0xA3 };
 305     static const uint8_t casefolded[]            = { 0x6A, 0xCC, 0x8C, 0xCC, 0xA3 };
 306     static const uint8_t casefolded_decomposed[] = { 0x6A, 0xCC, 0xA3, 0xCC, 0x8C };
 307     int cmp;
 308
 309     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 310     ASSERT (cmp == 0);
 311
 312     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, NULL, &cmp) == 0);
 313     ASSERT (cmp != 0);
 314
 315     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, UNINORM_NFD, &cmp) == 0);
 316     ASSERT (cmp == 0);
 317
 318     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, UNINORM_NFD, &cmp) == 0);
 319     ASSERT (cmp == 0);
 320   }
 321 }
 322
 323 int
 324 main ()
 325 {
 326   test_ascii (u8_casecmp, UNINORM_NFD);
 327   test_nonascii (u8_casecmp);
 328
 329   return 0;
 330 }