1 /* Test of compatibility decomposition 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_NFKD, 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_NFKD, 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_NFKD, input, input_length, preallocated, &length);
89 if (!(result != NULL))
91 if (!(preallocated == NULL || 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 expected[] = { 0x0041, 0x0308 };
117 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
120 { /* LATIN CAPITAL LETTER A WITH DIAERESIS AND MACRON */
121 static const uint16_t input[] = { 0x01DE };
122 static const uint16_t expected[] = { 0x0041, 0x0308, 0x0304 };
123 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
126 { /* GREEK DIALYTIKA AND PERISPOMENI */
127 static const uint16_t input[] = { 0x1FC1 };
128 static const uint16_t expected[] = { 0x0020, 0x0308, 0x0342 };
129 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
132 { /* SCRIPT SMALL L */
133 static const uint16_t input[] = { 0x2113 };
134 static const uint16_t expected[] = { 0x006C };
135 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
138 { /* NO-BREAK SPACE */
139 static const uint16_t input[] = { 0x00A0 };
140 static const uint16_t expected[] = { 0x0020 };
141 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
144 { /* ARABIC LETTER VEH INITIAL FORM */
145 static const uint16_t input[] = { 0xFB6C };
146 static const uint16_t expected[] = { 0x06A4 };
147 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
150 { /* ARABIC LETTER VEH MEDIAL FORM */
151 static const uint16_t input[] = { 0xFB6D };
152 static const uint16_t expected[] = { 0x06A4 };
153 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
156 { /* ARABIC LETTER VEH FINAL FORM */
157 static const uint16_t input[] = { 0xFB6B };
158 static const uint16_t expected[] = { 0x06A4 };
159 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
162 { /* ARABIC LETTER VEH ISOLATED FORM */
163 static const uint16_t input[] = { 0xFB6A };
164 static const uint16_t expected[] = { 0x06A4 };
165 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
168 { /* CIRCLED NUMBER FIFTEEN */
169 static const uint16_t input[] = { 0x246E };
170 static const uint16_t expected[] = { 0x0031, 0x0035 };
171 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
174 { /* TRADE MARK SIGN */
175 static const uint16_t input[] = { 0x2122 };
176 static const uint16_t expected[] = { 0x0054, 0x004D };
177 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
180 { /* LATIN SUBSCRIPT SMALL LETTER I */
181 static const uint16_t input[] = { 0x1D62 };
182 static const uint16_t expected[] = { 0x0069 };
183 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
186 { /* PRESENTATION FORM FOR VERTICAL LEFT PARENTHESIS */
187 static const uint16_t input[] = { 0xFE35 };
188 static const uint16_t expected[] = { 0x0028 };
189 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
192 { /* FULLWIDTH LATIN CAPITAL LETTER A */
193 static const uint16_t input[] = { 0xFF21 };
194 static const uint16_t expected[] = { 0x0041 };
195 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
198 { /* HALFWIDTH IDEOGRAPHIC COMMA */
199 static const uint16_t input[] = { 0xFF64 };
200 static const uint16_t expected[] = { 0x3001 };
201 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
204 { /* SMALL IDEOGRAPHIC COMMA */
205 static const uint16_t input[] = { 0xFE51 };
206 static const uint16_t expected[] = { 0x3001 };
207 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
211 static const uint16_t input[] = { 0x3392 };
212 static const uint16_t expected[] = { 0x004D, 0x0048, 0x007A };
213 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
216 { /* VULGAR FRACTION THREE EIGHTHS */
217 static const uint16_t input[] = { 0x215C };
218 static const uint16_t expected[] = { 0x0033, 0x2044, 0x0038 };
219 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
223 static const uint16_t input[] = { 0x00B5 };
224 static const uint16_t expected[] = { 0x03BC };
225 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
228 { /* ARABIC LIGATURE SALLALLAHOU ALAYHE WASALLAM */
229 static const uint16_t input[] = { 0xFDFA };
230 static const uint16_t expected[] =
231 { 0x0635, 0x0644, 0x0649, 0x0020, 0x0627, 0x0644, 0x0644, 0x0647, 0x0020,
232 0x0639, 0x0644, 0x064A, 0x0647, 0x0020, 0x0648, 0x0633, 0x0644, 0x0645
234 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
237 { /* HANGUL SYLLABLE GEUL */
238 static const uint16_t input[] = { 0xAE00 };
239 static const uint16_t expected[] = { 0x1100, 0x1173, 0x11AF };
240 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
243 { /* HANGUL SYLLABLE GEU */
244 static const uint16_t input[] = { 0xADF8 };
245 static const uint16_t expected[] = { 0x1100, 0x1173 };
246 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
249 { /* "Grüß Gott. Здравствуйте! x=(-b±sqrt(b²-4ac))/(2a) 日本語,中文,한글" */
250 static const uint16_t input[] =
251 { 'G', 'r', 0x00FC, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
252 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
253 0x0439, 0x0442, 0x0435, '!', ' ',
254 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x00B2,
255 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
256 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',', 0xD55C, 0xAE00, '\n'
258 static const uint16_t expected[] =
259 { 'G', 'r', 0x0075, 0x0308, 0x00DF, ' ', 'G', 'o', 't', 't', '.', ' ',
260 0x0417, 0x0434, 0x0440, 0x0430, 0x0432, 0x0441, 0x0442, 0x0432, 0x0443,
261 0x0438, 0x0306, 0x0442, 0x0435, '!', ' ',
262 'x', '=', '(', '-', 'b', 0x00B1, 's', 'q', 'r', 't', '(', 'b', 0x0032,
263 '-', '4', 'a', 'c', ')', ')', '/', '(', '2', 'a', ')', ' ', ' ',
264 0x65E5, 0x672C, 0x8A9E, ',', 0x4E2D, 0x6587, ',',
265 0x1112, 0x1161, 0x11AB, 0x1100, 0x1173, 0x11AF, '\n'
267 ASSERT (check (input, SIZEOF (input), expected, SIZEOF (expected)) == 0);
271 /* Declare failure if test takes too long, by using default abort
272 caused by SIGALRM. */
273 signal (SIGALRM, SIG_DFL);
277 /* Check that the sorting is not O(n²) but O(n log n). */
280 for (pass = 0; pass < 3; pass++)
284 uint16_t *input = (uint16_t *) malloc (2 * m * sizeof (uint16_t));
287 uint16_t *expected = input + m;
289 size_t m2 = (m - 1) / 2;
290 /* NB: m1 + m2 == m - 1. */
299 for (i = 0; i < m1; i++)
301 for (i = 0; i < m2; i++)
306 for (i = 0; i < m2; i++)
308 for (i = 0; i < m1; i++)
313 for (i = 0; i < m2; i++)
326 expected[0] = 0x0041;
328 for (i = 0; i < m1; i++)
330 for (i = 0; i < m2; i++)
333 for (; repeat > 0; repeat--)
334 ASSERT (check (input, m, expected, m) == 0);