1 /* Test of casefolding mapping for 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. */
29 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
30 #define ASSERT(expr) \
35 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
43 check (const uint8_t *input, size_t input_length,
44 const char *iso639_language, uninorm_t nf,
45 const uint8_t *expected, size_t expected_length)
50 /* Test return conventions with resultbuf == NULL. */
51 result = u8_casefold (input, input_length, iso639_language, nf, NULL, &length);
52 if (!(result != NULL))
54 if (!(length == expected_length))
56 if (!(u8_cmp (result, expected, expected_length) == 0))
60 /* Test return conventions with resultbuf too small. */
61 if (expected_length > 0)
63 uint8_t *preallocated;
65 length = expected_length - 1;
66 preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
67 result = u8_casefold (input, input_length, iso639_language, nf, preallocated, &length);
68 if (!(result != NULL))
70 if (!(result != preallocated))
72 if (!(length == expected_length))
74 if (!(u8_cmp (result, expected, expected_length) == 0))
80 /* Test return conventions with resultbuf large enough. */
82 uint8_t *preallocated;
84 length = expected_length;
85 preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
86 result = u8_casefold (input, input_length, iso639_language, nf, preallocated, &length);
87 if (!(result != NULL))
89 if (!(preallocated == NULL || result == preallocated))
91 if (!(length == expected_length))
93 if (!(u8_cmp (result, expected, expected_length) == 0))
104 { /* Empty string. */
105 ASSERT (check (NULL, 0, NULL, NULL, NULL, 0) == 0);
106 ASSERT (check (NULL, 0, NULL, UNINORM_NFC, NULL, 0) == 0);
110 { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
111 static const uint8_t input[] =
112 { 'G', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
113 0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
114 0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
115 '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
116 'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
117 ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
118 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
119 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
121 static const uint8_t casefolded[] =
122 { 'g', 'r', 0xC3, 0xBC, 0x73, 0x73, ' ', 'g', 'o', 't', 't', '.', ' ',
123 0xD0, 0xB7, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
124 0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
125 '!', ' ', 'x', '=', '(', '-', 'b', 0xC2, 0xB1, 's', 'q', 'r', 't', '(',
126 'b', 0xC2, 0xB2, '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')',
127 ' ', ' ', 0xE6, 0x97, 0xA5, 0xE6, 0x9C, 0xAC, 0xE8, 0xAA, 0x9E, ',',
128 0xE4, 0xB8, 0xAD, 0xE6, 0x96, 0x87, ',',
129 0xED, 0x95, 0x9C, 0xEA, 0xB8, 0x80, '\n'
131 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
134 /* Case mapping can increase the number of Unicode characters. */
135 { /* LATIN SMALL LETTER N PRECEDED BY APOSTROPHE */
136 static const uint8_t input[] = { 0xC5, 0x89 };
137 static const uint8_t casefolded[] = { 0xCA, 0xBC, 0x6E };
138 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
140 { /* GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS */
141 static const uint8_t input[] = { 0xCE, 0x90 };
142 static const uint8_t casefolded[] = { 0xCE, 0xB9, 0xCC, 0x88, 0xCC, 0x81 };
143 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
146 /* Turkish letters i İ ı I */
147 { /* LATIN CAPITAL LETTER I */
148 static const uint8_t input[] = { 0x49 };
149 static const uint8_t casefolded[] = { 0x69 };
150 static const uint8_t casefolded_tr[] = { 0xC4, 0xB1 };
151 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
152 ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded_tr, SIZEOF (casefolded_tr)) == 0);
154 { /* LATIN SMALL LETTER I */
155 static const uint8_t input[] = { 0x69 };
156 static const uint8_t casefolded[] = { 0x69 };
157 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
158 ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded, SIZEOF (casefolded)) == 0);
160 { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
161 static const uint8_t input[] = { 0xC4, 0xB0 };
162 static const uint8_t casefolded[] = { 0x69, 0xCC, 0x87 };
163 static const uint8_t casefolded_tr[] = { 0x69 };
164 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
165 ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded_tr, SIZEOF (casefolded_tr)) == 0);
167 { /* LATIN SMALL LETTER DOTLESS I */
168 static const uint8_t input[] = { 0xC4, 0xB1 };
169 static const uint8_t casefolded[] = { 0xC4, 0xB1 };
170 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
171 ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded, SIZEOF (casefolded)) == 0);
174 static const uint8_t input[] =
175 { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
176 static const uint8_t casefolded[] =
177 { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
178 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
179 ASSERT (check (input, SIZEOF (input), "tr", NULL, casefolded, SIZEOF (casefolded)) == 0);
182 /* Uppercasing can increase the number of Unicode characters. */
184 static const uint8_t input[] = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
185 static const uint8_t casefolded[] = { 0x68, 0x65, 0x69, 0x73, 0x73 };
186 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
189 /* Case mappings for some characters can depend on the surrounding characters. */
190 { /* "περισσότερες πληροφορίες" */
191 static const uint8_t input[] =
193 0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
194 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
195 ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
196 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
198 static const uint8_t casefolded[] =
200 0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
201 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x83,
202 ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
203 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x83
205 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
208 /* Case mapping can require subsequent normalization. */
209 { /* LATIN SMALL LETTER J WITH CARON, COMBINING DOT BELOW */
210 static const uint8_t input[] = { 0xC7, 0xB0, 0xCC, 0xA3 };
211 static const uint8_t casefolded[] = { 0x6A, 0xCC, 0x8C, 0xCC, 0xA3 };
212 static const uint8_t casefolded_decomposed[] = { 0x6A, 0xCC, 0xA3, 0xCC, 0x8C };
213 static const uint8_t casefolded_normalized[] = { 0xC7, 0xB0, 0xCC, 0xA3 };
214 ASSERT (check (input, SIZEOF (input), NULL, NULL, casefolded, SIZEOF (casefolded)) == 0);
215 ASSERT (check (input, SIZEOF (input), NULL, UNINORM_NFD, casefolded_decomposed, SIZEOF (casefolded_decomposed)) == 0);
216 ASSERT (check (input, SIZEOF (input), NULL, UNINORM_NFC, casefolded_normalized, SIZEOF (casefolded_normalized)) == 0);