1 /* Test of lowercase mapping for UTF-16 strings.
2 Copyright (C) 2009-2014 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 <http://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 <stdlib.h>
24
25 #include "unistr.h"
26 #include "uninorm.h"
27 #include "macros.h"
28
29 static int
check(const uint16_t * input,size_t input_length,const char * iso639_language,uninorm_t nf,const uint16_t * expected,size_t expected_length)30 check (const uint16_t *input, size_t input_length,
31 const char *iso639_language, uninorm_t nf,
32 const uint16_t *expected, size_t expected_length)
33 {
34 size_t length;
35 uint16_t *result;
36
37 /* Test return conventions with resultbuf == NULL. */
38 result = u16_tolower (input, input_length, iso639_language, nf, NULL, &length);
39 if (!(result != NULL))
40 return 1;
41 if (!(length == expected_length))
42 return 2;
43 if (!(u16_cmp (result, expected, expected_length) == 0))
44 return 3;
45 free (result);
46
47 /* Test return conventions with resultbuf too small. */
48 if (expected_length > 0)
49 {
50 uint16_t *preallocated;
51
52 length = expected_length - 1;
53 preallocated = (uint16_t *) malloc (length * sizeof (uint16_t));
54 result = u16_tolower (input, input_length, iso639_language, nf, preallocated, &length);
55 if (!(result != NULL))
56 return 4;
57 if (!(result != preallocated))
58 return 5;
59 if (!(length == expected_length))
60 return 6;
61 if (!(u16_cmp (result, expected, expected_length) == 0))
62 return 7;
63 free (result);
64 free (preallocated);
65 }
66
67 /* Test return conventions with resultbuf large enough. */
68 {
69 uint16_t *preallocated;
70
71 length = expected_length;
72 preallocated = (uint16_t *) malloc (length * sizeof (uint16_t));
73 result = u16_tolower (input, input_length, iso639_language, nf, preallocated, &length);
74 if (!(result != NULL))
75 return 8;
76 if (!(preallocated == NULL || result == preallocated))
77 return 9;
78 if (!(length == expected_length))
79 return 10;
80 if (!(u16_cmp (result, expected, expected_length) == 0))
81 return 11;
82 free (preallocated);
83 }
84
85 return 0;
86 }
87
88 int
main()89 main ()
90 {
91 { /* Empty string. */
92 ASSERT (check (NULL, 0, NULL, NULL, NULL, 0) == 0);
93 ASSERT (check (NULL, 0, NULL, UNINORM_NFC, NULL, 0) == 0);
94 }
95
96 /* Simple string. */
97 { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
98 static const uint16_t input[] =
99 { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
100 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
101 0x0439, 0x0442, 0x0435, '!', ' ',
102 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
103 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
104 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
105 };
106 static const uint16_t casemapped[] =
107 { 'g', 'r', 0x00FC, 0x00DF, ' ', 'g', 'o', 't', 't', '.', ' ',
108 0x0437, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
109 0x0439, 0x0442, 0x0435, '!', ' ',
110 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
111 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
112 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
113 };
114 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
115 }
116
117 /* Turkish letters i İ ı I */
118 { /* LATIN CAPITAL LETTER I */
119 static const uint16_t input[] = { 0x0049 };
120 static const uint16_t casemapped[] = { 0x0069 };
121 static const uint16_t casemapped_tr[] = { 0x0131 };
122 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
123 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped_tr, SIZEOF (casemapped_tr)) == 0);
124 }
125 { /* LATIN SMALL LETTER I */
126 static const uint16_t input[] = { 0x0069 };
127 static const uint16_t casemapped[] = { 0x0069 };
128 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
129 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
130 }
131 { /* LATIN CAPITAL LETTER I WITH DOT ABOVE */
132 static const uint16_t input[] = { 0x0130 };
133 static const uint16_t casemapped[] = { 0x0069, 0x0307 };
134 static const uint16_t casemapped_tr[] = { 0x0069 };
135 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
136 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped_tr, SIZEOF (casemapped_tr)) == 0);
137 }
138 { /* LATIN SMALL LETTER DOTLESS I */
139 static const uint16_t input[] = { 0x0131 };
140 static const uint16_t casemapped[] = { 0x0131 };
141 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
142 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
143 }
144 { /* "TOPKAPI" */
145 static const uint16_t input[] =
146 { 0x0054, 0x004F, 0x0050, 0x004B, 0x0041, 0x0050, 0x0049 };
147 static const uint16_t casemapped[] =
148 { 0x0074, 0x006F, 0x0070, 0x006B, 0x0061, 0x0070, 0x0131 };
149 ASSERT (check (input, SIZEOF (input), "tr", NULL, casemapped, SIZEOF (casemapped)) == 0);
150 }
151
152 /* Uppercasing can increase the number of Unicode characters. */
153 { /* "HEIß" */
154 static const uint16_t input[] = { 0x0048, 0x0045, 0x0049, 0x00DF };
155 static const uint16_t casemapped[] = { 0x0068, 0x0065, 0x0069, 0x00DF };
156 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
157 }
158
159 /* Case mappings for some characters can depend on the surrounding characters. */
160 { /* "ΠΕΡΙΣΣΌΤΕΡΕΣ ΠΛΗΡΟΦΟΡΊΕΣ" */
161 static const uint16_t input[] =
162 {
163 0x03A0, 0x0395, 0x03A1, 0x0399, 0x03A3, 0x03A3, 0x038C, 0x03A4,
164 0x0395, 0x03A1, 0x0395, 0x03A3, 0x0020, 0x03A0, 0x039B, 0x0397,
165 0x03A1, 0x039F, 0x03A6, 0x039F, 0x03A1, 0x038A, 0x0395, 0x03A3
166 };
167 static const uint16_t casemapped[] =
168 {
169 0x03C0, 0x03B5, 0x03C1, 0x03B9, 0x03C3, 0x03C3, 0x03CC, 0x03C4,
170 0x03B5, 0x03C1, 0x03B5, 0x03C2, 0x0020, 0x03C0, 0x03BB, 0x03B7,
171 0x03C1, 0x03BF, 0x03C6, 0x03BF, 0x03C1, 0x03AF, 0x03B5, 0x03C2
172 };
173 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
174 }
175 { /* "Σ" -> "σ" */
176 static const uint16_t input[] = { 0x03A3 };
177 static const uint16_t casemapped[] = { 0x03C3 };
178 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
179 }
180 { /* "ΑΣ" -> "ας" */
181 static const uint16_t input[] = { 0x0391, 0x03A3 };
182 static const uint16_t casemapped[] = { 0x03B1, 0x03C2 };
183 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
184 }
185 /* It's a final sigma only if not followed by a case-ignorable sequence and
186 then a cased letter. Note that U+0345 and U+037A are simultaneously
187 case-ignorable and cased (which is a bit paradoxical). */
188 { /* "ΑΣΑ" -> "ασα" */
189 static const uint16_t input[] = { 0x0391, 0x03A3, 0x0391 };
190 static const uint16_t casemapped[] = { 0x03B1, 0x03C3, 0x03B1 };
191 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
192 }
193 { /* "ΑΣ:" -> "ας:" */
194 static const uint16_t input[] = { 0x0391, 0x03A3, 0x003A };
195 static const uint16_t casemapped[] = { 0x03B1, 0x03C2, 0x003A };
196 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
197 }
198 { /* "ΑΣ:Α" -> "ασ:α" */
199 static const uint16_t input[] = { 0x0391, 0x03A3, 0x003A, 0x0391 };
200 static const uint16_t casemapped[] = { 0x03B1, 0x03C3, 0x003A, 0x03B1 };
201 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
202 }
203 { /* "ΑΣ:ͺ" -> "ασ:ͺ" */
204 static const uint16_t input[] = { 0x0391, 0x03A3, 0x003A, 0x037A };
205 static const uint16_t casemapped[] = { 0x03B1, 0x03C3, 0x003A, 0x037A };
206 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
207 }
208 { /* "ΑΣ:ͺ " -> "ασ:ͺ " */
209 static const uint16_t input[] = { 0x0391, 0x03A3, 0x003A, 0x037A, 0x0020 };
210 static const uint16_t casemapped[] = { 0x03B1, 0x03C3, 0x003A, 0x037A, 0x0020 };
211 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
212 }
213 /* It's a final sigma only if preceded by a case-ignorable sequence and
214 a cased letter before it. Note that U+0345 and U+037A are simultaneously
215 case-ignorable and cased (which is a bit paradoxical). */
216 { /* ":Σ" -> ":σ" */
217 static const uint16_t input[] = { 0x003A, 0x03A3 };
218 static const uint16_t casemapped[] = { 0x003A, 0x03C3 };
219 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
220 }
221 { /* "Α:Σ" -> "α:ς" */
222 static const uint16_t input[] = { 0x0391, 0x003A, 0x03A3 };
223 static const uint16_t casemapped[] = { 0x03B1, 0x003A, 0x03C2 };
224 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
225 }
226 { /* "ͺ:Σ" -> "ͺ:ς" */
227 static const uint16_t input[] = { 0x037A, 0x003A, 0x03A3 };
228 static const uint16_t casemapped[] = { 0x037A, 0x003A, 0x03C2 };
229 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
230 }
231 { /* " ͺ:Σ" -> " ͺ:ς" */
232 static const uint16_t input[] = { 0x0020, 0x037A, 0x003A, 0x03A3 };
233 static const uint16_t casemapped[] = { 0x0020, 0x037A, 0x003A, 0x03C2 };
234 ASSERT (check (input, SIZEOF (input), NULL, NULL, casemapped, SIZEOF (casemapped)) == 0);
235 }
236
237 return 0;
238 }
239