2 * Copyright © 2014 Ran Benita <ran234@gmail.com>
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
21 * DEALINGS IN THE SOFTWARE.
33 #define VALID(lit) assert(is_valid_utf8(lit, sizeof(lit)-1))
34 #define INVALID(lit) assert(!is_valid_utf8(lit, sizeof(lit)-1))
37 test_is_valid_utf8(void)
41 * https://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
45 VALID("\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5");
53 VALID("\xE0\xA0\x80");
54 VALID("\xF0\x90\x80\x80");
56 /* 5/6-byte continuations aren't allowed (unlike UTF-8-test). */
57 INVALID("\xF8\x88\x80\x80\x80");
58 INVALID("\xFC\x84\x80\x80\x80\x80");
62 VALID("\xEF\xBF\xBF");
63 /* VALID("\xF7\xBF\xBF\xBF"); */
65 /* 5/6-byte continuations aren't allowed (unlike UTF-8-test). */
66 INVALID("\xFB\xBF\xBF\xBF\xBF");
67 INVALID("\xFD\xBFxBF\xBF\xBF");
69 VALID("\xED\x9F\xBF");
70 VALID("\xEE\x80\x80");
71 VALID("\xEF\xBF\xBD");
72 VALID("\xF4\x8F\xBF\xBF");
73 /* VALID("\xF4\x90\x80\x80"); */
78 INVALID("\x80\xBF\x80");
79 INVALID("\x80\xBF\x80\xBF");
80 INVALID("\x80\xBF\x80\xBF\x80");
81 INVALID("\x80\xBF\x80\xBF\x80\xBF");
82 INVALID("\x80\xBF\x80\xBF\x80\xBF\x80");
83 INVALID("\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
84 "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
85 "\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
86 "\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF");
88 INVALID("\xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 \xC8 \xC9 \xCA \xCB \xCC "
90 "\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 \xD8 \xD9 \xDA \xDB \xDD "
92 INVALID("\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ");
93 INVALID("\xF8 \xF9 \xFA \xFB ");
94 INVALID("\xFC \xFD ");
98 INVALID("\xF0\x80\x80");
99 INVALID("\xF8\x80\x80\x80");
100 INVALID("\xFC\x80\x80\x80\x80");
103 INVALID("\xF7\xBF\xBF");
104 INVALID("\xFB\xBF\xBF\xBF");
105 INVALID("\xFD\xBF\xBF\xBF\xBF");
107 INVALID("\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
108 "\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF");
112 INVALID("\xFE\xFE\xFF\xFF");
115 INVALID("\xE0\x80\xAF");
116 INVALID("\xF0\x80\x80\xAF");
117 INVALID("\xF8\x80\x80\x80\xAF");
118 INVALID("\xFC\x80\x80\x80\x80\xAF");
121 INVALID("\xE0\x9F\xBF");
122 INVALID("\xF0\x8F\xBF\xBF");
123 INVALID("\xF8\x87\xBF\xBF\xBF");
124 INVALID("\xFC\x83\xBF\xBF\xBF\xBF");
127 INVALID("\xE0\x80\x80");
128 INVALID("\xF0\x80\x80\x80");
129 INVALID("\xF8\x80\x80\x80\x80");
130 INVALID("\xFC\x80\x80\x80\x80\x80");
132 INVALID("\xED\xA0\x80");
133 INVALID("\xED\xAD\xBF");
134 INVALID("\xED\xAE\x80");
135 INVALID("\xED\xAF\xBF");
136 INVALID("\xED\xB0\x80");
137 INVALID("\xED\xBE\x80");
138 INVALID("\xED\xBF\xBF");
140 INVALID("\xED\xA0\x80\xED\xB0\x80");
141 INVALID("\xED\xA0\x80\xED\xBF\xBF");
142 INVALID("\xED\xAD\xBF\xED\xB0\x80");
143 INVALID("\xED\xAD\xBF\xED\xBF\xBF");
144 INVALID("\xED\xAE\x80\xED\xB0\x80");
145 INVALID("\xED\xAE\x80\xED\xBF\xBF");
146 INVALID("\xED\xAF\xBF\xED\xB0\x80");
147 INVALID("\xED\xAF\xBF\xED\xBF\xBF");
149 /* INVALID("\xEF\xBF\xBE"); */
150 /* INVALID("\xEF\xBF\xBF"); */
154 check_utf32_to_utf8(uint32_t unichar, int expected_length, const char *expected) {
158 length = utf32_to_utf8(unichar, buffer);
160 assert(length == expected_length);
161 assert(streq(buffer, expected));
165 test_utf32_to_utf8(void)
167 check_utf32_to_utf8(0x0, 2, "");
168 check_utf32_to_utf8(0x40, 2, "\x40");
169 check_utf32_to_utf8(0xA1, 3, "\xc2\xa1");
170 check_utf32_to_utf8(0x2701, 4, "\xe2\x9c\x81");
171 check_utf32_to_utf8(0x1f004, 5, "\xf0\x9f\x80\x84");
172 check_utf32_to_utf8(0x110000, 0, "");
173 check_utf32_to_utf8(0xffffffff, 0, "");
179 test_is_valid_utf8();
180 test_utf32_to_utf8();