1 /* Test of compatibility normalization of UTF-32 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. */
21 #if GNULIB_UNINORM_U32_NORMALIZE
32 #define SIZEOF(array) (sizeof (array) / sizeof (array[0]))
33 #define ASSERT(expr) \
38 fprintf (stderr, "%s:%d: assertion failed\n", __FILE__, __LINE__); \
46 check (const uint32_t *input, size_t input_length,
47 const uint32_t *expected, size_t expected_length)
52 /* Test return conventions with resultbuf == NULL. */
53 result = u32_normalize (UNINORM_NFKC, input, input_length, NULL, &length);
54 if (!(result != NULL))
56 if (!(length == expected_length))
58 if (!(u32_cmp (result, expected, expected_length) == 0))
62 /* Test return conventions with resultbuf too small. */
63 if (expected_length > 0)
65 uint32_t *preallocated;
67 length = expected_length - 1;
68 preallocated = (uint32_t *) malloc (length * sizeof (uint32_t));
69 result = u32_normalize (UNINORM_NFKC, input, input_length, preallocated, &length);
70 if (!(result != NULL))
72 if (!(result != preallocated))
74 if (!(length == expected_length))
76 if (!(u32_cmp (result, expected, expected_length) == 0))
82 /* Test return conventions with resultbuf large enough. */
84 uint32_t *preallocated;
86 length = expected_length;
87 preallocated = (uint32_t *) malloc (length * sizeof (uint32_t));
88 result = u32_normalize (UNINORM_NFKC, input, input_length, preallocated, &length);
89 if (!(result != NULL))
91 if (!(result == preallocated))
93 if (!(length == expected_length))
95 if (!(u32_cmp (result, expected, expected_length) == 0))
107 static const uint32_t input[] = { 0x0020 };
108 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
111 { /* LATIN CAPITAL LETTER A WITH DIAERESIS */
112 static const uint32_t input[] = { 0x00C4 };
113 static const uint32_t decomposed[] = { 0x0041, 0x0308 };
114 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
115 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
118 { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
119 static const uint32_t input[] = { 0x01DE };
120 static const uint32_t decomposed[] = { 0x0041, 0x0308, 0x0304 };
121 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
122 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
125 { /* ANGSTROM SIGN */
126 static const uint32_t input[] = { 0x212B };
127 static const uint32_t decomposed[] = { 0x0041, 0x030A };
128 static const uint32_t expected[] = { 0x00C5 };
129 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
130 ASSERT (check (decomposed, SIZEOF (decomposed), expected, SIZEOF (expected)) == 0);
131 ASSERT (check (expected, SIZEOF (expected), expected, SIZEOF (expected)) == 0);
134 { /* GREEK DIALYTIKA AND PERISPOMENI */
135 static const uint32_t input[] = { 0x1FC1 };
136 static const uint32_t decomposed[] = { 0x0020, 0x0308, 0x0342 };
137 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
138 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
141 { /* SCRIPT SMALL L */
142 static const uint32_t input[] = { 0x2113 };
143 static const uint32_t decomposed[] = { 0x006C };
144 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
145 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
148 { /* NO-BREAK SPACE */
149 static const uint32_t input[] = { 0x00A0 };
150 static const uint32_t decomposed[] = { 0x0020 };
151 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
152 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
155 { /* ARABIC LETTER VEH INITIAL FORM */
156 static const uint32_t input[] = { 0xFB6C };
157 static const uint32_t decomposed[] = { 0x06A4 };
158 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
159 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
162 { /* ARABIC LETTER VEH MEDIAL FORM */
163 static const uint32_t input[] = { 0xFB6D };
164 static const uint32_t decomposed[] = { 0x06A4 };
165 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
166 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
169 { /* ARABIC LETTER VEH FINAL FORM */
170 static const uint32_t input[] = { 0xFB6B };
171 static const uint32_t decomposed[] = { 0x06A4 };
172 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
173 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
176 { /* ARABIC LETTER VEH ISOLATED FORM */
177 static const uint32_t input[] = { 0xFB6A };
178 static const uint32_t decomposed[] = { 0x06A4 };
179 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
180 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
183 { /* CIRCLED NUMBER FIFTEEN */
184 static const uint32_t input[] = { 0x246E };
185 static const uint32_t decomposed[] = { 0x0031, 0x0035 };
186 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
187 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
190 { /* TRADE MARK SIGN */
191 static const uint32_t input[] = { 0x2122 };
192 static const uint32_t decomposed[] = { 0x0054, 0x004D };
193 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
194 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
197 { /* LATIN SUBSCRIPT SMALL LETTER I */
198 static const uint32_t input[] = { 0x1D62 };
199 static const uint32_t decomposed[] = { 0x0069 };
200 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
201 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
204 { /* PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS */
205 static const uint32_t input[] = { 0xFE35 };
206 static const uint32_t decomposed[] = { 0x0028 };
207 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
208 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
211 { /* FULLWIDTH LATIN CAPITAL LETTER A */
212 static const uint32_t input[] = { 0xFF21 };
213 static const uint32_t decomposed[] = { 0x0041 };
214 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
215 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
218 { /* HALFWIDTH IDEOGRAPHIC COMMA */
219 static const uint32_t input[] = { 0xFF64 };
220 static const uint32_t decomposed[] = { 0x3001 };
221 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
222 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
225 { /* SMALL IDEOGRAPHIC COMMA */
226 static const uint32_t input[] = { 0xFE51 };
227 static const uint32_t decomposed[] = { 0x3001 };
228 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
229 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
233 static const uint32_t input[] = { 0x3392 };
234 static const uint32_t decomposed[] = { 0x004D, 0x0048, 0x007A };
235 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
236 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
239 { /* VULGAR FRACTION THREE EIGHTHS */
240 static const uint32_t input[] = { 0x215C };
241 static const uint32_t decomposed[] = { 0x0033, 0x2044, 0x0038 };
242 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
243 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
247 static const uint32_t input[] = { 0x00B5 };
248 static const uint32_t decomposed[] = { 0x03BC };
249 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
250 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
253 { /* ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM */
254 static const uint32_t input[] = { 0xFDFA };
255 static const uint32_t decomposed[] =
256 { 0x0635, 0x0644, 0x0649, 0x0020, 0x0627, 0x0644, 0x0644, 0x0647, 0x0020,
257 0x0639, 0x0644, 0x064A, 0x0647, 0x0020, 0x0648, 0x0633, 0x0644, 0x0645
259 ASSERT (check (input, SIZEOF (input), decomposed, SIZEOF (decomposed)) == 0);
260 ASSERT (check (decomposed, SIZEOF (decomposed), decomposed, SIZEOF (decomposed)) == 0);
263 { /* HANGUL SYLLABLE GEUL */
264 static const uint32_t input[] = { 0xAE00 };
265 static const uint32_t decomposed[] = { 0x1100, 0x1173, 0x11AF };
266 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
267 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
270 { /* HANGUL SYLLABLE GEU */
271 static const uint32_t input[] = { 0xADF8 };
272 static const uint32_t decomposed[] = { 0x1100, 0x1173 };
273 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
274 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
277 { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
278 static const uint32_t input[] =
279 { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
280 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
281 0x0439, 0x0442, 0x0435, '!', ' ',
282 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
283 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
284 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
286 static const uint32_t decomposed[] =
287 { 'G', 'r', 0x0075, 0x0308, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
288 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
289 0x0438, 0x0306, 0x0442, 0x0435, '!', ' ',
290 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x0032,
291 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
292 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',',
293 0x1112, 0x1161, 0x11AB, 0x1100, 0x1173, 0x11AF, '\n'
295 static const uint32_t expected[] =
296 { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
297 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
298 0x0439, 0x0442, 0x0435, '!', ' ',
299 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x0032,
300 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
301 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
303 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
304 ASSERT (check (decomposed, SIZEOF (decomposed), expected, SIZEOF (expected)) == 0);
305 ASSERT (check (expected, SIZEOF (expected), expected, SIZEOF (expected)) == 0);
309 /* Declare failure if test takes too long, by using default abort
310 caused by SIGALRM. */
311 signal (SIGALRM, SIG_DFL);
315 /* Check that the sorting is not O(n²) but O(n log n). */
318 for (pass = 0; pass < 3; pass++)
322 uint32_t *input = (uint32_t *) malloc (2 * m * sizeof (uint32_t));
325 uint32_t *expected = input + m;
327 size_t m2 = (m - 1) / 2;
328 /* NB: m1 + m2 == m - 1. */
337 for (i = 0; i < m1; i++)
339 for (i = 0; i < m2; i++)
344 for (i = 0; i < m2; i++)
346 for (i = 0; i < m1; i++)
351 for (i = 0; i < m2; i++)
364 expected[0] = 0x00C0;
366 for (i = 0; i < m1; i++)
368 for (i = 0; i < m2 - 1; i++)
371 for (; repeat > 0; repeat--)
373 ASSERT (check (input, m, expected, m - 1) == 0);
374 ASSERT (check (expected, m - 1, expected, m - 1) == 0);