1 /* GLIB - Library of useful routines for C programming
2 * Copyright (C) 2001 Matthias Clasen <matthiasc@poet.de>
4 * SPDX-License-Identifier: LGPL-2.1-or-later
6 * This library is free software; you can redistribute it and/or
7 * modify it under the terms of the GNU Lesser General Public
8 * License as published by the Free Software Foundation; either
9 * version 2.1 of the License, or (at your option) any later version.
11 * This library is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 * Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public
17 * License along with this library; if not, see <http://www.gnu.org/licenses/>.
23 #define UNICODE_VALID(Char) \
24 ((Char) < 0x110000 && \
25 (((Char) & 0xFFFFF800) != 0xD800) && \
26 ((Char) < 0xFDD0 || (Char) > 0xFDEF) && \
27 ((Char) & 0xFFFE) != 0xFFFE)
37 static Test global_test[] = {
38 /* some tests to check max_len handling */
40 { "abcde", -1, 5, TRUE },
41 { "abcde", 3, 3, TRUE },
42 { "abcde", 5, 5, TRUE },
43 { "abcde", 7, 5, FALSE },
45 { "\xc2\xa9\xc2\xa9\xc2\xa9", -1, 6, TRUE },
46 { "\xc2\xa9\xc2\xa9\xc2\xa9", 1, 0, FALSE },
47 { "\xc2\xa9\xc2\xa9\xc2\xa9", 2, 2, TRUE },
48 { "\xc2\xa9\xc2\xa9\xc2\xa9", 3, 2, FALSE },
49 { "\xc2\xa9\xc2\xa9\xc2\xa9", 4, 4, TRUE },
50 { "\xc2\xa9\xc2\xa9\xc2\xa9", 5, 4, FALSE },
51 { "\xc2\xa9\xc2\xa9\xc2\xa9", 6, 6, TRUE },
52 { "\xc2\xa9\xc2\xa9\xc2\xa9", 7, 6, FALSE },
54 { "\xe2\x89\xa0\xe2\x89\xa0", -1, 6, TRUE },
55 { "\xe2\x89\xa0\xe2\x89\xa0", 1, 0, FALSE },
56 { "\xe2\x89\xa0\xe2\x89\xa0", 2, 0, FALSE },
57 { "\xe2\x89\xa0\xe2\x89\xa0", 3, 3, TRUE },
58 { "\xe2\x89\xa0\xe2\x89\xa0", 4, 3, FALSE },
59 { "\xe2\x89\xa0\xe2\x89\xa0", 5, 3, FALSE },
60 { "\xe2\x89\xa0\xe2\x89\xa0", 6, 6, TRUE },
61 { "\xe2\x89\xa0\xe2\x89\xa0", 7, 6, FALSE },
63 /* examples from http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt */
65 { "\xce\xba\xe1\xbd\xb9\xcf\x83\xce\xbc\xce\xb5", -1, 11, TRUE },
66 /* first sequence of each length */
67 { "\x00", -1, 0, TRUE },
68 { "\xc2\x80", -1, 2, TRUE },
69 { "\xe0\xa0\x80", -1, 3, TRUE },
70 { "\xf0\x90\x80\x80", -1, 4, TRUE },
71 { "\xf8\x88\x80\x80\x80", -1, 0, FALSE },
72 { "\xfc\x84\x80\x80\x80\x80", -1, 0, FALSE },
73 /* last sequence of each length */
74 { "\x7f", -1, 1, TRUE },
75 { "\xdf\xbf", -1, 2, TRUE },
76 { "\xef\xbf\xbf", -1, 3, TRUE },
77 { "\xf7\xbf\xbf\xbf", -1, 0, FALSE },
78 { "\xfb\xbf\xbf\xbf\xbf", -1, 0, FALSE },
79 { "\xfd\xbf\xbf\xbf\xbf\xbf", -1, 0, FALSE },
80 /* other boundary conditions */
81 { "\xed\x9f\xbf", -1, 3, TRUE },
82 { "\xee\x80\x80", -1, 3, TRUE },
83 { "\xef\xbf\xbd", -1, 3, TRUE },
84 { "\xf4\x8f\xbf\xbf", -1, 4, TRUE },
85 { "\xf4\x90\x80\x80", -1, 0, FALSE },
86 /* malformed sequences */
87 /* continuation bytes */
88 { "\x80", -1, 0, FALSE },
89 { "\xbf", -1, 0, FALSE },
90 { "\xbf\x80", -1, 0, FALSE },
91 { "\x80\xbf", -1, 0, FALSE },
92 { "\x80\xbf\x80", -1, 0, FALSE },
93 { "\x80\xbf\x80\xbf", -1, 0, FALSE },
94 { "\x80\xbf\x80\xbf\x80", -1, 0, FALSE },
95 { "\x80\xbf\x80\xbf\x80\xbf", -1, 0, FALSE },
96 { "\x80\xbf\x80\xbf\x80\xbf\x80", -1, 0, FALSE },
98 /* all possible continuation byte */
99 { "\x80", -1, 0, FALSE },
100 { "\x81", -1, 0, FALSE },
101 { "\x82", -1, 0, FALSE },
102 { "\x83", -1, 0, FALSE },
103 { "\x84", -1, 0, FALSE },
104 { "\x85", -1, 0, FALSE },
105 { "\x86", -1, 0, FALSE },
106 { "\x87", -1, 0, FALSE },
107 { "\x88", -1, 0, FALSE },
108 { "\x89", -1, 0, FALSE },
109 { "\x8a", -1, 0, FALSE },
110 { "\x8b", -1, 0, FALSE },
111 { "\x8c", -1, 0, FALSE },
112 { "\x8d", -1, 0, FALSE },
113 { "\x8e", -1, 0, FALSE },
114 { "\x8f", -1, 0, FALSE },
115 { "\x90", -1, 0, FALSE },
116 { "\x91", -1, 0, FALSE },
117 { "\x92", -1, 0, FALSE },
118 { "\x93", -1, 0, FALSE },
119 { "\x94", -1, 0, FALSE },
120 { "\x95", -1, 0, FALSE },
121 { "\x96", -1, 0, FALSE },
122 { "\x97", -1, 0, FALSE },
123 { "\x98", -1, 0, FALSE },
124 { "\x99", -1, 0, FALSE },
125 { "\x9a", -1, 0, FALSE },
126 { "\x9b", -1, 0, FALSE },
127 { "\x9c", -1, 0, FALSE },
128 { "\x9d", -1, 0, FALSE },
129 { "\x9e", -1, 0, FALSE },
130 { "\x9f", -1, 0, FALSE },
131 { "\xa0", -1, 0, FALSE },
132 { "\xa1", -1, 0, FALSE },
133 { "\xa2", -1, 0, FALSE },
134 { "\xa3", -1, 0, FALSE },
135 { "\xa4", -1, 0, FALSE },
136 { "\xa5", -1, 0, FALSE },
137 { "\xa6", -1, 0, FALSE },
138 { "\xa7", -1, 0, FALSE },
139 { "\xa8", -1, 0, FALSE },
140 { "\xa9", -1, 0, FALSE },
141 { "\xaa", -1, 0, FALSE },
142 { "\xab", -1, 0, FALSE },
143 { "\xac", -1, 0, FALSE },
144 { "\xad", -1, 0, FALSE },
145 { "\xae", -1, 0, FALSE },
146 { "\xaf", -1, 0, FALSE },
147 { "\xb0", -1, 0, FALSE },
148 { "\xb1", -1, 0, FALSE },
149 { "\xb2", -1, 0, FALSE },
150 { "\xb3", -1, 0, FALSE },
151 { "\xb4", -1, 0, FALSE },
152 { "\xb5", -1, 0, FALSE },
153 { "\xb6", -1, 0, FALSE },
154 { "\xb7", -1, 0, FALSE },
155 { "\xb8", -1, 0, FALSE },
156 { "\xb9", -1, 0, FALSE },
157 { "\xba", -1, 0, FALSE },
158 { "\xbb", -1, 0, FALSE },
159 { "\xbc", -1, 0, FALSE },
160 { "\xbd", -1, 0, FALSE },
161 { "\xbe", -1, 0, FALSE },
162 { "\xbf", -1, 0, FALSE },
163 /* lone start characters */
164 { "\xc0\x20", -1, 0, FALSE },
165 { "\xc1\x20", -1, 0, FALSE },
166 { "\xc2\x20", -1, 0, FALSE },
167 { "\xc3\x20", -1, 0, FALSE },
168 { "\xc4\x20", -1, 0, FALSE },
169 { "\xc5\x20", -1, 0, FALSE },
170 { "\xc6\x20", -1, 0, FALSE },
171 { "\xc7\x20", -1, 0, FALSE },
172 { "\xc8\x20", -1, 0, FALSE },
173 { "\xc9\x20", -1, 0, FALSE },
174 { "\xca\x20", -1, 0, FALSE },
175 { "\xcb\x20", -1, 0, FALSE },
176 { "\xcc\x20", -1, 0, FALSE },
177 { "\xcd\x20", -1, 0, FALSE },
178 { "\xce\x20", -1, 0, FALSE },
179 { "\xcf\x20", -1, 0, FALSE },
180 { "\xd0\x20", -1, 0, FALSE },
181 { "\xd1\x20", -1, 0, FALSE },
182 { "\xd2\x20", -1, 0, FALSE },
183 { "\xd3\x20", -1, 0, FALSE },
184 { "\xd4\x20", -1, 0, FALSE },
185 { "\xd5\x20", -1, 0, FALSE },
186 { "\xd6\x20", -1, 0, FALSE },
187 { "\xd7\x20", -1, 0, FALSE },
188 { "\xd8\x20", -1, 0, FALSE },
189 { "\xd9\x20", -1, 0, FALSE },
190 { "\xda\x20", -1, 0, FALSE },
191 { "\xdb\x20", -1, 0, FALSE },
192 { "\xdc\x20", -1, 0, FALSE },
193 { "\xdd\x20", -1, 0, FALSE },
194 { "\xde\x20", -1, 0, FALSE },
195 { "\xdf\x20", -1, 0, FALSE },
196 { "\xe0\x20", -1, 0, FALSE },
197 { "\xe1\x20", -1, 0, FALSE },
198 { "\xe2\x20", -1, 0, FALSE },
199 { "\xe3\x20", -1, 0, FALSE },
200 { "\xe4\x20", -1, 0, FALSE },
201 { "\xe5\x20", -1, 0, FALSE },
202 { "\xe6\x20", -1, 0, FALSE },
203 { "\xe7\x20", -1, 0, FALSE },
204 { "\xe8\x20", -1, 0, FALSE },
205 { "\xe9\x20", -1, 0, FALSE },
206 { "\xea\x20", -1, 0, FALSE },
207 { "\xeb\x20", -1, 0, FALSE },
208 { "\xec\x20", -1, 0, FALSE },
209 { "\xed\x20", -1, 0, FALSE },
210 { "\xee\x20", -1, 0, FALSE },
211 { "\xef\x20", -1, 0, FALSE },
212 { "\xf0\x20", -1, 0, FALSE },
213 { "\xf1\x20", -1, 0, FALSE },
214 { "\xf2\x20", -1, 0, FALSE },
215 { "\xf3\x20", -1, 0, FALSE },
216 { "\xf4\x20", -1, 0, FALSE },
217 { "\xf5\x20", -1, 0, FALSE },
218 { "\xf6\x20", -1, 0, FALSE },
219 { "\xf7\x20", -1, 0, FALSE },
220 { "\xf8\x20", -1, 0, FALSE },
221 { "\xf9\x20", -1, 0, FALSE },
222 { "\xfa\x20", -1, 0, FALSE },
223 { "\xfb\x20", -1, 0, FALSE },
224 { "\xfc\x20", -1, 0, FALSE },
225 { "\xfd\x20", -1, 0, FALSE },
226 /* missing continuation bytes */
227 { "\x20\xc0", -1, 1, FALSE },
228 { "\x20\xe0\x80", -1, 1, FALSE },
229 { "\x20\xf0\x80\x80", -1, 1, FALSE },
230 { "\x20\xf8\x80\x80\x80", -1, 1, FALSE },
231 { "\x20\xfc\x80\x80\x80\x80", -1, 1, FALSE },
232 { "\x20\xdf", -1, 1, FALSE },
233 { "\x20\xef\xbf", -1, 1, FALSE },
234 { "\x20\xf7\xbf\xbf", -1, 1, FALSE },
235 { "\x20\xfb\xbf\xbf\xbf", -1, 1, FALSE },
236 { "\x20\xfd\xbf\xbf\xbf\xbf", -1, 1, FALSE },
237 /* impossible bytes */
238 { "\x20\xfe\x20", -1, 1, FALSE },
239 { "\x20\xff\x20", -1, 1, FALSE },
240 /* overlong sequences */
241 { "\x20\xc0\xaf\x20", -1, 1, FALSE },
242 { "\x20\xe0\x80\xaf\x20", -1, 1, FALSE },
243 { "\x20\xf0\x80\x80\xaf\x20", -1, 1, FALSE },
244 { "\x20\xf8\x80\x80\x80\xaf\x20", -1, 1, FALSE },
245 { "\x20\xfc\x80\x80\x80\x80\xaf\x20", -1, 1, FALSE },
246 { "\x20\xc1\xbf\x20", -1, 1, FALSE },
247 { "\x20\xe0\x9f\xbf\x20", -1, 1, FALSE },
248 { "\x20\xf0\x8f\xbf\xbf\x20", -1, 1, FALSE },
249 { "\x20\xf8\x87\xbf\xbf\xbf\x20", -1, 1, FALSE },
250 { "\x20\xfc\x83\xbf\xbf\xbf\xbf\x20", -1, 1, FALSE },
251 { "\x20\xc0\x80\x20", -1, 1, FALSE },
252 { "\x20\xe0\x80\x80\x20", -1, 1, FALSE },
253 { "\x20\xf0\x80\x80\x80\x20", -1, 1, FALSE },
254 { "\x20\xf8\x80\x80\x80\x80\x20", -1, 1, FALSE },
255 { "\x20\xfc\x80\x80\x80\x80\x80\x20", -1, 1, FALSE },
256 /* illegal code positions */
257 { "\x20\xed\xa0\x80\x20", -1, 1, FALSE },
258 { "\x20\xed\xad\xbf\x20", -1, 1, FALSE },
259 { "\x20\xed\xae\x80\x20", -1, 1, FALSE },
260 { "\x20\xed\xaf\xbf\x20", -1, 1, FALSE },
261 { "\x20\xed\xb0\x80\x20", -1, 1, FALSE },
262 { "\x20\xed\xbe\x80\x20", -1, 1, FALSE },
263 { "\x20\xed\xbf\xbf\x20", -1, 1, FALSE },
264 { "\x20\xed\xa0\x80\xed\xb0\x80\x20", -1, 1, FALSE },
265 { "\x20\xed\xa0\x80\xed\xbf\xbf\x20", -1, 1, FALSE },
266 { "\x20\xed\xad\xbf\xed\xb0\x80\x20", -1, 1, FALSE },
267 { "\x20\xed\xad\xbf\xed\xbf\xbf\x20", -1, 1, FALSE },
268 { "\x20\xed\xae\x80\xed\xb0\x80\x20", -1, 1, FALSE },
269 { "\x20\xed\xae\x80\xed\xbf\xbf\x20", -1, 1, FALSE },
270 { "\x20\xed\xaf\xbf\xed\xb0\x80\x20", -1, 1, FALSE },
271 { "\x20\xed\xaf\xbf\xed\xbf\xbf\x20", -1, 1, FALSE },
277 do_test (gconstpointer d)
279 const Test *test = d;
283 result = g_utf8_validate (test->text, test->max_len, &end);
285 g_assert_true (result == test->valid);
286 g_assert_cmpint (end - test->text, ==, test->offset);
288 if (test->max_len < 0)
290 result = g_utf8_validate (test->text, strlen (test->text), &end);
292 g_assert_true (result == test->valid);
293 g_assert_cmpint (end - test->text, ==, test->offset);
297 result = g_utf8_validate_len (test->text, test->max_len, &end);
299 g_assert_true (result == test->valid);
300 g_assert_cmpint (end - test->text, ==, test->offset);
304 /* Test the behaviour of g_utf8_get_char_validated() with various inputs and
305 * length restrictions. */
307 test_utf8_get_char_validated (void)
312 gunichar expected_result;
315 { "\xC0\x00_45678", 8, (gunichar) -2 },
316 { "\xC0\x00_45678", -1, (gunichar) -2 },
317 /* It seems odd that the return value differs with the length input, but
318 * that’s how it’s documented: */
319 { "", 0, (gunichar) -2 },
320 { "", -1, (gunichar) 0 },
321 { "\0", 1, (gunichar) -2 },
324 { "\0AB", 3, (gunichar) -2 },
325 { "\xD8\0", 2, (gunichar) -2 },
327 { "hello", 5, (gunichar) 'h' },
328 { "hello", -1, (gunichar) 'h' },
329 { "\xD8\x9F", 2, 0x061F },
330 { "\xD8\x9F", -1, 0x061F },
331 { "\xD8\x9Fmore", 6, 0x061F },
332 { "\xD8\x9Fmore", -1, 0x061F },
333 { "\xD8\x9F\0", 3, 0x061F },
334 { "\xE2\x96\xB3", 3, 0x25B3 },
335 { "\xE2\x96\xB3", -1, 0x25B3 },
336 { "\xE2\x96\xB3more", 7, 0x25B3 },
337 { "\xE2\x96\xB3more", -1, 0x25B3 },
338 { "\xF0\x9F\x92\xA9", 4, 0x1F4A9 },
339 { "\xF0\x9F\x92\xA9", -1, 0x1F4A9 },
340 { "\xF0\x9F\x92\xA9more", 8, 0x1F4A9 },
341 { "\xF0\x9F\x92\xA9more", -1, 0x1F4A9 },
342 /* Partial unichars: */
343 { "\xD8", -1, (gunichar) -2 },
344 { "\xD8\x9F", 1, (gunichar) -2 },
345 { "\xCE", -1, (gunichar) -2 },
346 { "\xCE", 1, (gunichar) -2 },
350 for (i = 0; i < G_N_ELEMENTS (test_vectors); i++)
352 gunichar actual_result;
354 g_test_message ("Vector %" G_GSIZE_FORMAT, i);
355 actual_result = g_utf8_get_char_validated (test_vectors[i].buf,
356 test_vectors[i].max_len);
357 g_assert_cmpint (actual_result, ==, test_vectors[i].expected_result);
362 main (int argc, char *argv[])
367 g_test_init (&argc, &argv, NULL);
369 for (i = 0; global_test[i].text; i++)
371 path = g_strdup_printf ("/utf8/validate/%d", i);
372 g_test_add_data_func (path, &global_test[i], do_test);
376 g_test_add_func ("/utf8/get-char-validated", test_utf8_get_char_validated);
378 return g_test_run ();