1 /* Test of lowercase mapping for UTF-8 strings.
2 Copyright (C) 2009, 2010 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. */
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)
37 /* Test return conventions with resultbuf == NULL. */
38 result = u8_tolower (input, input_length, iso639_language, nf, NULL, &length);
39 if (!(result != NULL))
41 if (!(length == expected_length))
43 if (!(u8_cmp (result, expected, expected_length) == 0))
47 /* Test return conventions with resultbuf too small. */
48 if (expected_length > 0)
50 uint8_t *preallocated;
52 length = expected_length - 1;
53 preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
54 result = u8_tolower (input, input_length, iso639_language, nf, preallocated, &length);
55 if (!(result != NULL))
57 if (!(result != preallocated))
59 if (!(length == expected_length))
61 if (!(u8_cmp (result, expected, expected_length) == 0))
67 /* Test return conventions with resultbuf large enough. */
69 uint8_t *preallocated;
71 length = expected_length;
72 preallocated = (uint8_t *) malloc (length * sizeof (uint8_t));
73 result = u8_tolower (input, input_length, iso639_language, nf, preallocated, &length);
74 if (!(result != NULL))
76 if (!(preallocated == NULL || result == preallocated))
78 if (!(length == expected_length))
80 if (!(u8_cmp (result, expected, expected_length) == 0))
92 ASSERT (check (NULL, 0, NULL, NULL, NULL, 0) == 0);
93 ASSERT (check (NULL, 0, NULL, UNINORM_NFC, NULL, 0) == 0);
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, 0xBC, 0xC3, 0x9F, ' ', 'G', 'o', 't', 't', '.', ' ',
100 0xD0, 0x97, 0xD0, 0xB4, 0xD1, 0x80, 0xD0, 0xB0, 0xD0, 0xB2, 0xD1, 0x81,
101 0xD1, 0x82, 0xD0, 0xB2, 0xD1, 0x83, 0xD0, 0xB9, 0xD1, 0x82, 0xD0, 0xB5,
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'
108 static const uint8_t casemapped[] =
109 { 'g', 'r', 0xC3, 0xBC, 0xC3, 0x9F, ' ', 'g', 'o', 't', 't', '.', ' ',
110 0xD0, 0xB7, 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'
118 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
121 /* Turkish letters i İ ı I */
122 { /* LATIN CAPITAL LETTER I */
123 static const uint8_t input[] = { 0x49 };
124 static const uint8_t casemapped[] = { 0x69 };
125 static const uint8_t casemapped_tr[] = { 0xC4, 0xB1 };
126 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
127 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped_tr, SIZEOF (casemapped_tr)) == 0);
129 { /* LATIN SMALL LETTER I */
130 static const uint8_t input[] = { 0x69 };
131 static const uint8_t casemapped[] = { 0x69 };
132 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
133 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
135 { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
136 static const uint8_t input[] = { 0xC4, 0xB0 };
137 static const uint8_t casemapped[] = { 0x69, 0xCC, 0x87 };
138 static const uint8_t casemapped_tr[] = { 0x69 };
139 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
140 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped_tr, SIZEOF (casemapped_tr)) == 0);
142 { /* LATIN SMALL LETTER DOTLESS I */
143 static const uint8_t input[] = { 0xC4, 0xB1};
144 static const uint8_t casemapped[] = { 0xC4, 0xB1 };
145 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
146 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
149 static const uint8_t input[] =
150 { 0x54, 0x4F, 0x50, 0x4B, 0x41, 0x50, 0x49 };
151 static const uint8_t casemapped[] =
152 { 0x74, 0x6F, 0x70, 0x6B, 0x61, 0x70, 0xC4, 0xB1 };
153 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
156 /* Uppercasing can increase the number of Unicode characters. */
158 static const uint8_t input[] = { 0x48, 0x45, 0x49, 0xC3, 0x9F };
159 static const uint8_t casemapped[] = { 0x68, 0x65, 0x69, 0xC3, 0x9F };
160 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
163 /* Case mappings for some characters can depend on the surrounding characters. */
164 { /* "ΠΕΡΙΣΣΌΤΕΡΕΣ ΠΛΗΡΟΦΟΡΊΕΣ" */
165 static const uint8_t input[] =
167 0xCE, 0xA0, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x99, 0xCE, 0xA3, 0xCE, 0xA3,
168 0xCE, 0x8C, 0xCE, 0xA4, 0xCE, 0x95, 0xCE, 0xA1, 0xCE, 0x95, 0xCE, 0xA3,
169 ' ', 0xCE, 0xA0, 0xCE, 0x9B, 0xCE, 0x97, 0xCE, 0xA1, 0xCE, 0x9F,
170 0xCE, 0xA6, 0xCE, 0x9F, 0xCE, 0xA1, 0xCE, 0x8A, 0xCE, 0x95, 0xCE, 0xA3
172 static const uint8_t casemapped[] =
174 0xCF, 0x80, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB9, 0xCF, 0x83, 0xCF, 0x83,
175 0xCF, 0x8C, 0xCF, 0x84, 0xCE, 0xB5, 0xCF, 0x81, 0xCE, 0xB5, 0xCF, 0x82,
176 ' ', 0xCF, 0x80, 0xCE, 0xBB, 0xCE, 0xB7, 0xCF, 0x81, 0xCE, 0xBF,
177 0xCF, 0x86, 0xCE, 0xBF, 0xCF, 0x81, 0xCE, 0xAF, 0xCE, 0xB5, 0xCF, 0x82
179 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
182 static const uint8_t input[] = { 0xCE, 0xA3 };
183 static const uint8_t casemapped[] = { 0xCF, 0x83 };
184 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
187 static const uint8_t input[] = { 0xCE, 0x91, 0xCE, 0xA3 };
188 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0xCF, 0x82 };
189 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
191 /* It's a final sigma only if not followed by a case-ignorable sequence and
192 then a cased letter. Note that U+0345 and U+037A are simultaneously
193 case-ignorable and cased (which is a bit paradoxical). */
194 { /* "ΑΣΑ" -> "ασα" */
195 static const uint8_t input[] = { 0xCE, 0x91, 0xCE, 0xA3, 0xCE, 0x91 };
196 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0xCF, 0x83, 0xCE, 0xB1 };
197 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
199 { /* "ΑΣ:" -> "ας:" */
200 static const uint8_t input[] = { 0xCE, 0x91, 0xCE, 0xA3, 0x3A };
201 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0xCF, 0x82, 0x3A };
202 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
204 { /* "ΑΣ:Α" -> "ασ:α" */
205 static const uint8_t input[] = { 0xCE, 0x91, 0xCE, 0xA3, 0x3A, 0xCE, 0x91 };
206 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0xCF, 0x83, 0x3A, 0xCE, 0xB1 };
207 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
209 { /* "ΑΣ:ͺ" -> "ασ:ͺ" */
210 static const uint8_t input[] = { 0xCE, 0x91, 0xCE, 0xA3, 0x3A, 0xCD, 0xBA };
211 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0xCF, 0x83, 0x3A, 0xCD, 0xBA };
212 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
214 { /* "ΑΣ:ͺ " -> "ασ:ͺ " */
215 static const uint8_t input[] = { 0xCE, 0x91, 0xCE, 0xA3, 0x3A, 0xCD, 0xBA, 0x20 };
216 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0xCF, 0x83, 0x3A, 0xCD, 0xBA, 0x20 };
217 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
219 /* It's a final sigma only if preceded by a case-ignorable sequence and
220 a cased letter before it. Note that U+0345 and U+037A are simultaneously
221 case-ignorable and cased (which is a bit paradoxical). */
223 static const uint8_t input[] = { 0x3A, 0xCE, 0xA3 };
224 static const uint8_t casemapped[] = { 0x3A, 0xCF, 0x83 };
225 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
227 { /* "Α:Σ" -> "α:ς" */
228 static const uint8_t input[] = { 0xCE, 0x91, 0x3A, 0xCE, 0xA3 };
229 static const uint8_t casemapped[] = { 0xCE, 0xB1, 0x3A, 0xCF, 0x82 };
230 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
232 { /* "ͺ:Σ" -> "ͺ:ς" */
233 static const uint8_t input[] = { 0xCD, 0xBA, 0x3A, 0xCE, 0xA3 };
234 static const uint8_t casemapped[] = { 0xCD, 0xBA, 0x3A, 0xCF, 0x82 };
235 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
237 { /* " ͺ:Σ" -> " ͺ:ς" */
238 static const uint8_t input[] = { 0x20, 0xCD, 0xBA, 0x3A, 0xCE, 0xA3 };
239 static const uint8_t casemapped[] = { 0x20, 0xCD, 0xBA, 0x3A, 0xCF, 0x82 };
240 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);