tests/unicase/test-u16-casecmp.c

   1 /* Test of case and normalization insensitive comparison of UTF-16 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 uint16_t
  27 #include "test-casecmp.h"
  28 #undef UNIT
  29
  30 static void
  31 test_nonascii (int (*my_casecmp) (const uint16_t *, size_t, const uint16_t *, size_t, const char *, uninorm_t, int *))
  32 {
  33   /* Normalization effects.  */
  34   {
  35     static const uint16_t input1[] = { 'H', 0x00F6, 'h', 'l', 'e' };
  36     static const uint16_t input2[] = { 'H', 'O', 0x0308, 'h', 'L', 'e' };
  37     static const uint16_t input3[] = { 'H', 0x00F6, 'h', 'l', 'e', 'n' };
  38     static const uint16_t input4[] = { 'H', 'O', 0x0308, 'h', 'L', 'e', 'n' };
  39     static const uint16_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 uint16_t input1[] = { 0x00C4 };
  68     static const uint16_t input2[] = { 0x0041, 0x0308 };
  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 uint16_t input1[] = { 0x01DE };
  76     static const uint16_t input2[] = { 0x0041, 0x0308, 0x0304 };
  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 uint16_t input1[] = { 0x1FC1 };
  84     static const uint16_t input2[] = { 0x00A8, 0x0342 };
  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 uint16_t input1[] = { 0xAE00 };
  92     static const uint16_t input2[] = { 0xADF8, 0x11AF };
  93     static const uint16_t input3[] = { 0x1100, 0x1173, 0x11AF };
  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 uint16_t input1[] = { 0xADF8 };
 104     static const uint16_t input2[] = { 0x1100, 0x1173 };
 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 uint16_t input1[] =
 114       { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
 115         0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
 116         0x0439, 0x0442, 0x0435, '!', ' ',
 117         'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
 118         '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
 119         0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
 120       };
 121     static const uint16_t input2[] =
 122       { 'g', 'r', 0x00FC, 0x0073, 0x0073, ' ', 'g', 'o', 't', 't', '.', ' ',
 123         0x0437, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
 124         0x0439, 0x0442, 0x0435, '!', ' ',
 125         'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
 126         '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
 127         0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
 128       };
 129     static const uint16_t input3[] =
 130       { 'G', 'R', 0x00DC, 0x0053, 0x0053, ' ', 'G', 'O', 'T', 'T', '.', ' ',
 131         0x0417, 0x0414, 0x0420, 0x0410, 0x0412, 0x0421, 0x0422, 0x0412, 0x0423,
 132         0x0419, 0x0422, 0x0415, '!', ' ',
 133         'X', '=', '(', '-', 'B', 0x00B1, 'S', 'Q', 'R', 'T', '(', 'B', 0x00B2,
 134         '-', '4', 'A', 'C', ')', ')', '/', '(', '2', 'A', ')', ' ', ' ',
 135         0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
 136       };
 137     int cmp;
 138
 139     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 140     ASSERT (cmp == 0);
 141
 142     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 143     ASSERT (cmp == 0);
 144
 145     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 146     ASSERT (cmp == 0);
 147
 148     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 149     ASSERT (cmp == 0);
 150
 151     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 152     ASSERT (cmp == 0);
 153
 154     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 155     ASSERT (cmp == 0);
 156   }
 157
 158   /* Case mapping can increase the number of Unicode characters.  */
 159   { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
 160     static const uint16_t input1[] = { 0x0149 };
 161     static const uint16_t input2[] = { 0x02BC, 0x006E };
 162     static const uint16_t input3[] = { 0x02BC, 0x004E };
 163     int cmp;
 164
 165     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 166     ASSERT (cmp == 0);
 167
 168     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 169     ASSERT (cmp == 0);
 170
 171     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 172     ASSERT (cmp == 0);
 173
 174     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
 175     ASSERT (cmp == 0);
 176   }
 177   { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
 178     static const uint16_t input1[] = { 0x0390 };
 179     static const uint16_t input2[] = { 0x03B9, 0x0308, 0x0301 };
 180     int cmp;
 181
 182     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 183     ASSERT (cmp == 0);
 184
 185     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
 186     ASSERT (cmp == 0);
 187   }
 188
 189   /* Turkish letters i İ ı I */
 190   { /* LATIN CAPITAL LETTER I */
 191     static const uint16_t input[]         = { 0x0049 };
 192     static const uint16_t casefolded[]    = { 0x0069 };
 193     static const uint16_t casefolded_tr[] = { 0x0131 };
 194     int cmp;
 195
 196     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 197     ASSERT (cmp == 0);
 198
 199     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
 200     ASSERT (cmp == 0);
 201   }
 202   { /* LATIN SMALL LETTER I */
 203     static const uint16_t input[]         = { 0x0069 };
 204     static const uint16_t casefolded[]    = { 0x0049 };
 205     static const uint16_t casefolded_tr[] = { 0x0130 };
 206     int cmp;
 207
 208     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 209     ASSERT (cmp == 0);
 210
 211     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
 212     ASSERT (cmp == 0);
 213   }
 214   { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
 215     static const uint16_t input[]         = { 0x0130 };
 216     static const uint16_t casefolded[]    = { 0x0069, 0x0307 };
 217     static const uint16_t casefolded_tr[] = { 0x0069 };
 218     int cmp;
 219
 220     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 221     ASSERT (cmp == 0);
 222
 223     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
 224     ASSERT (cmp == 0);
 225   }
 226   { /* LATIN SMALL LETTER DOTLESS I */
 227     static const uint16_t input[]      = { 0x0131 };
 228     static const uint16_t casefolded[] = { 0x0049 };
 229     int cmp;
 230
 231     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 232     ASSERT (cmp == 1);
 233
 234     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
 235     ASSERT (cmp == 0);
 236   }
 237   { /* "topkapı" */
 238     static const uint16_t input[] =
 239       { 0x0054, 0x004F, 0x0050, 0x004B, 0x0041, 0x0050, 0x0049 };
 240     static const uint16_t casefolded[] =
 241       { 0x0074, 0x006F, 0x0070, 0x006B, 0x0061, 0x0070, 0x0131 };
 242     int cmp;
 243
 244     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 245     ASSERT (cmp == -1);
 246
 247     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
 248     ASSERT (cmp == 0);
 249   }
 250
 251   /* Uppercasing can increase the number of Unicode characters.  */
 252   { /* "heiß" */
 253     static const uint16_t input1[] = { 0x0068, 0x0065, 0x0069, 0x00DF };
 254     static const uint16_t input2[] = { 0x0068, 0x0065, 0x0069, 0x0073, 0x0073 };
 255     int cmp;
 256
 257     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 258     ASSERT (cmp == 0);
 259   }
 260
 261   /* Case mappings for some characters can depend on the surrounding characters.  */
 262   { /* "περισσότερες πληροφορίες" */
 263     static const uint16_t input1[] =
 264       {
 265         0x03C0, 0x03B5, 0x03C1, 0x03B9, 0x03C3, 0x03C3, 0x03CC, 0x03C4,
 266         0x03B5, 0x03C1, 0x03B5, 0x03C2, 0x0020, 0x03C0, 0x03BB, 0x03B7,
 267         0x03C1, 0x03BF, 0x03C6, 0x03BF, 0x03C1, 0x03AF, 0x03B5, 0x03C2
 268       };
 269     static const uint16_t input2[] =
 270       {
 271         0x03C0, 0x03B5, 0x03C1, 0x03B9, 0x03C3, 0x03C3, 0x03CC, 0x03C4,
 272         0x03B5, 0x03C1, 0x03B5, 0x03C3, 0x0020, 0x03C0, 0x03BB, 0x03B7,
 273         0x03C1, 0x03BF, 0x03C6, 0x03BF, 0x03C1, 0x03AF, 0x03B5, 0x03C3
 274       };
 275     static const uint16_t input3[] =
 276       {
 277         0x03A0, 0x0395, 0x03A1, 0x0399, 0x03A3, 0x03A3, 0x038C, 0x03A4,
 278         0x0395, 0x03A1, 0x0395, 0x03A3, 0x0020, 0x03A0, 0x039B, 0x0397,
 279         0x03A1, 0x039F, 0x03A6, 0x039F, 0x03A1, 0x038A, 0x0395, 0x03A3
 280       };
 281     int cmp;
 282
 283     ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
 284     ASSERT (cmp == 0);
 285
 286     ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 287     ASSERT (cmp == 0);
 288
 289     ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
 290     ASSERT (cmp == 0);
 291   }
 292
 293   /* Case mapping can require subsequent normalization.  */
 294   { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
 295     static const uint16_t input[]                 = { 0x01F0, 0x0323 };
 296     static const uint16_t casefolded[]            = { 0x006A, 0x030C, 0x0323 };
 297     static const uint16_t casefolded_decomposed[] = { 0x006A, 0x0323, 0x030C };
 298     int cmp;
 299
 300     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
 301     ASSERT (cmp == 0);
 302
 303     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, NULL, &cmp) == 0);
 304     ASSERT (cmp != 0);
 305
 306     ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, UNINORM_NFD, &cmp) == 0);
 307     ASSERT (cmp == 0);
 308
 309     ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, UNINORM_NFD, &cmp) == 0);
 310     ASSERT (cmp == 0);
 311   }
 312 }
 313
 314 int
 315 main ()
 316 {
 317   test_ascii (u16_casecmp, UNINORM_NFD);
 318   test_nonascii (u16_casecmp);
 319
 320   return 0;
 321 }