1 /* Test of canonical normalization of UTF-16 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_U16_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 uint16_t *input, size_t input_length,
47 const uint16_t *expected, size_t expected_length)
52 /* Test return conventions with resultbuf == NULL. */
53 result = u16_normalize (UNINORM_NFC, input, input_length, NULL, &length);
54 if (!(result != NULL))
56 if (!(length == expected_length))
58 if (!(u16_cmp (result, expected, expected_length) == 0))
62 /* Test return conventions with resultbuf too small. */
63 if (expected_length > 0)
65 uint16_t *preallocated;
67 length = expected_length - 1;
68 preallocated = (uint16_t *) malloc (length * sizeof (uint16_t));
69 result = u16_normalize (UNINORM_NFC, input, input_length, preallocated, &length);
70 if (!(result != NULL))
72 if (!(result != preallocated))
74 if (!(length == expected_length))
76 if (!(u16_cmp (result, expected, expected_length) == 0))
82 /* Test return conventions with resultbuf large enough. */
84 uint16_t *preallocated;
86 length = expected_length;
87 preallocated = (uint16_t *) malloc (length * sizeof (uint16_t));
88 result = u16_normalize (UNINORM_NFC, input, input_length, preallocated, &length);
89 if (!(result != NULL))
91 if (!(result == preallocated))
93 if (!(length == expected_length))
95 if (!(u16_cmp (result, expected, expected_length) == 0))
106 { /* Empty string. */
107 ASSERT (check (NULL, 0, NULL, 0) == 0);
110 static const uint16_t input[] = { 0x0020 };
111 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
114 { /* LATIN CAPITAL LETTER A WITH DIAERESIS */
115 static const uint16_t input[] = { 0x00C4 };
116 static const uint16_t decomposed[] = { 0x0041, 0x0308 };
117 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
118 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
121 { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
122 static const uint16_t input[] = { 0x01DE };
123 static const uint16_t decomposed[] = { 0x0041, 0x0308, 0x0304 };
124 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
125 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
128 { /* ANGSTROM SIGN */
129 static const uint16_t input[] = { 0x212B };
130 static const uint16_t decomposed[] = { 0x0041, 0x030A };
131 static const uint16_t expected[] = { 0x00C5 };
132 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
133 ASSERT (check (decomposed, SIZEOF (decomposed), expected, SIZEOF (expected)) == 0);
134 ASSERT (check (expected, SIZEOF (expected), expected, SIZEOF (expected)) == 0);
137 { /* GREEK DIALYTIKA AND PERISPOMENI */
138 static const uint16_t input[] = { 0x1FC1 };
139 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
142 { /* SCRIPT SMALL L */
143 static const uint16_t input[] = { 0x2113 };
144 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
147 { /* NO-BREAK SPACE */
148 static const uint16_t input[] = { 0x00A0 };
149 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
152 { /* ARABIC LETTER VEH INITIAL FORM */
153 static const uint16_t input[] = { 0xFB6C };
154 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
157 { /* ARABIC LETTER VEH MEDIAL FORM */
158 static const uint16_t input[] = { 0xFB6D };
159 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
162 { /* ARABIC LETTER VEH FINAL FORM */
163 static const uint16_t input[] = { 0xFB6B };
164 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
167 { /* ARABIC LETTER VEH ISOLATED FORM */
168 static const uint16_t input[] = { 0xFB6A };
169 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
172 { /* CIRCLED NUMBER FIFTEEN */
173 static const uint16_t input[] = { 0x246E };
174 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
177 { /* TRADE MARK SIGN */
178 static const uint16_t input[] = { 0x2122 };
179 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
182 { /* LATIN SUBSCRIPT SMALL LETTER I */
183 static const uint16_t input[] = { 0x1D62 };
184 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
187 { /* PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS */
188 static const uint16_t input[] = { 0xFE35 };
189 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
192 { /* FULLWIDTH LATIN CAPITAL LETTER A */
193 static const uint16_t input[] = { 0xFF21 };
194 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
197 { /* HALFWIDTH IDEOGRAPHIC COMMA */
198 static const uint16_t input[] = { 0xFF64 };
199 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
202 { /* SMALL IDEOGRAPHIC COMMA */
203 static const uint16_t input[] = { 0xFE51 };
204 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
208 static const uint16_t input[] = { 0x3392 };
209 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
212 { /* VULGAR FRACTION THREE EIGHTHS */
213 static const uint16_t input[] = { 0x215C };
214 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
218 static const uint16_t input[] = { 0x00B5 };
219 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
222 { /* ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM */
223 static const uint16_t input[] = { 0xFDFA };
224 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
227 { /* HANGUL SYLLABLE GEUL */
228 static const uint16_t input[] = { 0xAE00 };
229 static const uint16_t decomposed[] = { 0x1100, 0x1173, 0x11AF };
230 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
231 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
234 { /* HANGUL SYLLABLE GEU */
235 static const uint16_t input[] = { 0xADF8 };
236 static const uint16_t decomposed[] = { 0x1100, 0x1173 };
237 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
238 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
241 { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
242 static const uint16_t input[] =
243 { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
244 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
245 0x0439, 0x0442, 0x0435, '!', ' ',
246 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
247 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
248 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
250 static const uint16_t decomposed[] =
251 { 'G', 'r', 0x0075, 0x0308, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
252 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
253 0x0438, 0x0306, 0x0442, 0x0435, '!', ' ',
254 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
255 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
256 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',',
257 0x1112, 0x1161, 0x11AB, 0x1100, 0x1173, 0x11AF, '\n'
259 ASSERT (check (input, SIZEOF (input), input, SIZEOF (input)) == 0);
260 ASSERT (check (decomposed, SIZEOF (decomposed), input, SIZEOF (input)) == 0);
264 /* Declare failure if test takes too long, by using default abort
265 caused by SIGALRM. */
266 signal (SIGALRM, SIG_DFL);
270 /* Check that the sorting is not O(n²) but O(n log n). */
273 for (pass = 0; pass < 3; pass++)
277 uint16_t *input = (uint16_t *) malloc (2 * m * sizeof (uint16_t));
280 uint16_t *expected = input + m;
282 size_t m2 = (m - 1) / 2;
283 /* NB: m1 + m2 == m - 1. */
292 for (i = 0; i < m1; i++)
294 for (i = 0; i < m2; i++)
299 for (i = 0; i < m2; i++)
301 for (i = 0; i < m1; i++)
306 for (i = 0; i < m2; i++)
319 expected[0] = 0x00C0;
321 for (i = 0; i < m1; i++)
323 for (i = 0; i < m2 - 1; i++)
326 for (; repeat > 0; repeat--)
328 ASSERT (check (input, m, expected, m - 1) == 0);
329 ASSERT (check (expected, m - 1, expected, m - 1) == 0);