1 /* Test of case and normalization insensitive comparison of UTF-8 strings.
2 Copyright (C) 2009 Free Software Foundation, Inc.
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.
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.
14 You should have received a copy of the GNU General Public License
15 along with this program. If not, see <http://www.gnu.org/licenses/>. */
17 /* Written by Bruno Haible <bruno@clisp.org>, 2009. */
28 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
29 #define ASSERT(expr) \
34 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
42 #include "test-casecmp.h"
46 test_nonascii (int (*my_casecmp) (const uint8_t *, size_t, const uint8_t *, size_t, const char *, uninorm_t, int *))
48 /* Normalization effects. */
50 static const uint8_t input1[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e' };
51 static const uint8_t input2[] = { 'H', 'O', 0xCC, 0x88, 'h', 'L', 'e' };
52 static const uint8_t input3[] = { 'H', 0xC3, 0xB6, 'h', 'l', 'e', 'n' };
53 static const uint8_t input4[] = { 'H', 'O', 0xCC, 0x88, 'h', 'L', 'e', 'n' };
54 static const uint8_t input5[] = { 'H', 'u', 'r', 'z' };
57 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
60 ASSERT (my_casecmp (input2, SIZEOF (input2), input1, SIZEOF (input1), NULL, UNINORM_NFD, &cmp) == 0);
63 ASSERT (my_casecmp (input3, SIZEOF (input3), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
66 ASSERT (my_casecmp (input4, SIZEOF (input4), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
69 ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
72 ASSERT (my_casecmp (input1, SIZEOF (input1), input4, SIZEOF (input4), NULL, UNINORM_NFD, &cmp) == 0);
75 ASSERT (my_casecmp (input1, SIZEOF (input1), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
78 ASSERT (my_casecmp (input2, SIZEOF (input2), input5, SIZEOF (input5), NULL, UNINORM_NFD, &cmp) == 0);
81 { /* LATIN CAPITAL LETTER A WITH DIAERESIS */
82 static const uint8_t input1[] = { 0xC3, 0x84 };
83 static const uint8_t input2[] = { 0x41, 0xCC, 0x88 };
86 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
89 { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
90 static const uint8_t input1[] = { 0xC7, 0x9E };
91 static const uint8_t input2[] = { 0x41, 0xCC, 0x88, 0xCC, 0x84 };
94 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
97 { /* GREEK DIALYTIKA AND PERISPOMENI */
98 static const uint8_t input1[] = { 0xE1, 0xBF, 0x81 };
99 static const uint8_t input2[] = { 0xC2, 0xA8, 0xCD, 0x82 };
102 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
105 { /* HANGUL SYLLABLE GEUL */
106 static const uint8_t input1[] = { 0xEA, 0xB8, 0x80 };
107 static const uint8_t input2[] = { 0xEA, 0xB7, 0xB8, 0xE1, 0x86, 0xAF };
108 static const uint8_t input3[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3, 0xE1, 0x86, 0xAF };
111 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
114 ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
117 { /* HANGUL SYLLABLE GEU */
118 static const uint8_t input1[] = { 0xEA, 0xB7, 0xB8 };
119 static const uint8_t input2[] = { 0xE1, 0x84, 0x80, 0xE1, 0x85, 0xB3 };
122 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
127 { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
128 static const uint8_t input1[] =
129 { 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
130 0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
131 0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
132 '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
133 'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
134 ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
135 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
136 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
138 static const uint8_t input2[] =
139 { 'g', 'r', 0xC3, 0xBC, 0x73, 0x73, ' ', 'g', 'o', 't', 't', '.', ' ',
140 0xD0, 0xB7, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
141 0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
142 '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
143 'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
144 ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
145 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
146 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
148 static const uint8_t input3[] =
149 { 'G', 'R', 0xC3, 0x9C, 0x53, 0x53, ' ', 'G', 'O', 'T', 'T', '.', ' ',
150 0xD0, 0x97, 0xD0, 0x94, 0xD0, 0xA0, 0xD0, 0x90, 0xD0, 0x92, 0xD0, 0xA1,
151 0xD0, 0xA2, 0xD0, 0x92, 0xD0, 0xA3, 0xD0, 0x99, 0xD0, 0xA2, 0xD0, 0x95,
152 '!', ' ', 'X', '=', '(', '-', 'B', 0xC2, 0xB1, 'S', 'Q', 'R', 'T', '(',
153 'B', 0xC2, 0xB2, '-', '4', 'A', 'C', ')', ')', '/', '(', '2', 'A', ')',
154 ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
155 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
156 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
160 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
163 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
166 ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
169 ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
172 ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
175 ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
179 /* Case mapping can increase the number of Unicode characters. */
180 { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
181 static const uint8_t input1[] = { 0xC5, 0x89 };
182 static const uint8_t input2[] = { 0xCA, 0xBC, 0x6E };
183 static const uint8_t input3[] = { 0xCA, 0xBC, 0x4E };
186 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
189 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
192 ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
195 ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, UNINORM_NFD, &cmp) == 0);
198 { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
199 static const uint8_t input1[] = { 0xCE, 0x90 };
200 static const uint8_t input2[] = { 0xCE, 0xB9, 0xCC, 0x88, 0xCC, 0x81 };
203 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
206 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, UNINORM_NFD, &cmp) == 0);
210 /* Turkish letters i İ ı I */
211 { /* LATIN CAPITAL LETTER I */
212 static const uint8_t input[] = { 0x49 };
213 static const uint8_t casefolded[] = { 0x69 };
214 static const uint8_t casefolded_tr[] = { 0xC4, 0xB1 };
217 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
220 ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
223 { /* LATIN SMALL LETTER I */
224 static const uint8_t input[] = { 0x69 };
225 static const uint8_t casefolded[] = { 0x49 };
226 static const uint8_t casefolded_tr[] = { 0xC4, 0xB0 };
229 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
232 ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
235 { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
236 static const uint8_t input[] = { 0xC4, 0xB0 };
237 static const uint8_t casefolded[] = { 0x69, 0xCC, 0x87 };
238 static const uint8_t casefolded_tr[] = { 0x69 };
241 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
244 ASSERT (my_casecmp (input, SIZEOF (input), casefolded_tr, SIZEOF (casefolded_tr), "tr", NULL, &cmp) == 0);
247 { /* LATIN SMALL LETTER DOTLESS I */
248 static const uint8_t input[] = { 0xC4, 0xB1 };
249 static const uint8_t casefolded[] = { 0x49 };
252 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
255 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
259 static const uint8_t input[] =
260 { 0x54, 0x4F, 0x50, 0x4B, 0x41, 0x50, 0x49 };
261 static const uint8_t casefolded[] =
262 { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
265 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
268 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), "tr", NULL, &cmp) == 0);
272 /* Uppercasing can increase the number of Unicode characters. */
274 static const uint8_t input1[] = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
275 static const uint8_t input2[] = { 0x68, 0x65, 0x69, 0x73, 0x73 };
278 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
282 /* Case mappings for some characters can depend on the surrounding characters. */
283 { /* "περισσότερες πληροφορίες" */
284 static const uint8_t input1[] =
286 0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
287 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
288 ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
289 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
291 static const uint8_t input2[] =
293 0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
294 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x83,
295 ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
296 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x83
298 static const uint8_t input3[] =
300 0xCE, 0xA0, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x99, 0xCE, 0xA3, 0xCE, 0xA3,
301 0xCE, 0x8C, 0xCE, 0xA4, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x95, 0xCE, 0xA3,
302 ' ', 0xCE, 0xA0, 0xCE, 0x9B, 0xCE, 0x97, 0xCE, 0xA1, 0xCE, 0x9F,
303 0xCE, 0xA6, 0xCE, 0x9F, 0xCE, 0xA1, 0xCE, 0x8A, 0xCE, 0x95, 0xCE, 0xA3
307 ASSERT (my_casecmp (input1, SIZEOF (input1), input2, SIZEOF (input2), NULL, NULL, &cmp) == 0);
310 ASSERT (my_casecmp (input1, SIZEOF (input1), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
313 ASSERT (my_casecmp (input2, SIZEOF (input2), input3, SIZEOF (input3), NULL, NULL, &cmp) == 0);
317 /* Case mapping can require subsequent normalization. */
318 { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
319 static const uint8_t input[] = { 0xC7, 0xB0, 0xCC, 0xA3 };
320 static const uint8_t casefolded[] = { 0x6A, 0xCC, 0x8C, 0xCC, 0xA3 };
321 static const uint8_t casefolded_decomposed[] = { 0x6A, 0xCC, 0xA3, 0xCC, 0x8C };
324 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, NULL, &cmp) == 0);
327 ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, NULL, &cmp) == 0);
330 ASSERT (my_casecmp (input, SIZEOF (input), casefolded, SIZEOF (casefolded), NULL, UNINORM_NFD, &cmp) == 0);
333 ASSERT (my_casecmp (input, SIZEOF (input), casefolded_decomposed, SIZEOF (casefolded_decomposed), NULL, UNINORM_NFD, &cmp) == 0);
341 test_ascii (u8_casecmp, UNINORM_NFD);
342 test_nonascii (u8_casecmp);