1 /*
2 * Copyright © 2014 Ran Benita <ran234@gmail.com>
3 *
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:
10 *
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
13 * Software.
14 *
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.
22 */
23
24 #include "config.h"
25
26 #include <assert.h>
27 #include <inttypes.h>
28 #include <stdbool.h>
29 #include <stddef.h>
30 #include <string.h>
31
32 #include "utf8.h"
33 #include "utils.h"
34
35 #define VALID(lit) assert(is_valid_utf8(lit, sizeof(lit)-1))
36 #define INVALID(lit) assert(!is_valid_utf8(lit, sizeof(lit)-1))
37
38 static void
test_is_valid_utf8(void)39 test_is_valid_utf8(void)
40 {
41 /*
42 * Mostly taken from:
43 * https://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
44 */
45
46 VALID("ascii");
47 VALID("\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5");
48
49 VALID("");
50 VALID("\x00");
51 VALID("\x00\x00");
52
53 VALID("\x50");
54 VALID("\xC2\x80");
55 VALID("\xE0\xA0\x80");
56 VALID("\xF0\x90\x80\x80");
57
58 /* 5/6-byte continuations aren't allowed (unlike UTF-8-test). */
59 INVALID("\xF8\x88\x80\x80\x80");
60 INVALID("\xFC\x84\x80\x80\x80\x80");
61
62 VALID("\x7F");
63 VALID("\xDF\xBF");
64 VALID("\xEF\xBF\xBF");
65 /* VALID("\xF7\xBF\xBF\xBF"); */
66
67 /* 5/6-byte continuations aren't allowed (unlike UTF-8-test). */
68 INVALID("\xFB\xBF\xBF\xBF\xBF");
69 INVALID("\xFD\xBFxBF\xBF\xBF");
70
71 VALID("\xED\x9F\xBF");
72 VALID("\xEE\x80\x80");
73 VALID("\xEF\xBF\xBD");
74 VALID("\xF4\x8F\xBF\xBF");
75 /* VALID("\xF4\x90\x80\x80"); */
76
77 INVALID("\x80");
78 INVALID("\xBF");
79 INVALID("\x80\xBF");
80 INVALID("\x80\xBF\x80");
81 INVALID("\x80\xBF\x80\xBF");
82 INVALID("\x80\xBF\x80\xBF\x80");
83 INVALID("\x80\xBF\x80\xBF\x80\xBF");
84 INVALID("\x80\xBF\x80\xBF\x80\xBF\x80");
85 INVALID("\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
86 "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
87 "\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
88 "\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF");
89
90 INVALID("\xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 \xC8 \xC9 \xCA \xCB \xCC "
91 "\xCD \xCE \xCF "
92 "\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 \xD8 \xD9 \xDA \xDB \xDD "
93 "\xDD \xDE \xDF ");
94 INVALID("\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ");
95 INVALID("\xF8 \xF9 \xFA \xFB ");
96 INVALID("\xFC \xFD ");
97
98 INVALID("\xC0");
99 INVALID("\xE0\x80");
100 INVALID("\xF0\x80\x80");
101 INVALID("\xF8\x80\x80\x80");
102 INVALID("\xFC\x80\x80\x80\x80");
103 INVALID("\xDF");
104 INVALID("\xEF\xBF");
105 INVALID("\xF7\xBF\xBF");
106 INVALID("\xFB\xBF\xBF\xBF");
107 INVALID("\xFD\xBF\xBF\xBF\xBF");
108
109 INVALID("\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
110 "\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF");
111
112 INVALID("\xFE");
113 INVALID("\xFF");
114 INVALID("\xFE\xFE\xFF\xFF");
115
116 INVALID("\xC0\xAF");
117 INVALID("\xE0\x80\xAF");
118 INVALID("\xF0\x80\x80\xAF");
119 INVALID("\xF8\x80\x80\x80\xAF");
120 INVALID("\xFC\x80\x80\x80\x80\xAF");
121
122 INVALID("\xC1\xBF");
123 INVALID("\xE0\x9F\xBF");
124 INVALID("\xF0\x8F\xBF\xBF");
125 INVALID("\xF8\x87\xBF\xBF\xBF");
126 INVALID("\xFC\x83\xBF\xBF\xBF\xBF");
127
128 INVALID("\xC0\x80");
129 INVALID("\xE0\x80\x80");
130 INVALID("\xF0\x80\x80\x80");
131 INVALID("\xF8\x80\x80\x80\x80");
132 INVALID("\xFC\x80\x80\x80\x80\x80");
133
134 INVALID("\xED\xA0\x80");
135 INVALID("\xED\xAD\xBF");
136 INVALID("\xED\xAE\x80");
137 INVALID("\xED\xAF\xBF");
138 INVALID("\xED\xB0\x80");
139 INVALID("\xED\xBE\x80");
140 INVALID("\xED\xBF\xBF");
141
142 INVALID("\xED\xA0\x80\xED\xB0\x80");
143 INVALID("\xED\xA0\x80\xED\xBF\xBF");
144 INVALID("\xED\xAD\xBF\xED\xB0\x80");
145 INVALID("\xED\xAD\xBF\xED\xBF\xBF");
146 INVALID("\xED\xAE\x80\xED\xB0\x80");
147 INVALID("\xED\xAE\x80\xED\xBF\xBF");
148 INVALID("\xED\xAF\xBF\xED\xB0\x80");
149 INVALID("\xED\xAF\xBF\xED\xBF\xBF");
150
151 /* INVALID("\xEF\xBF\xBE"); */
152 /* INVALID("\xEF\xBF\xBF"); */
153 }
154
155 static void
check_utf32_to_utf8(uint32_t unichar,int expected_length,const char * expected)156 check_utf32_to_utf8(uint32_t unichar, int expected_length, const char *expected) {
157 char buffer[7];
158 int length;
159
160 length = utf32_to_utf8(unichar, buffer);
161
162 assert(length == expected_length);
163 assert(streq(buffer, expected));
164 }
165
166 static void
test_utf32_to_utf8(void)167 test_utf32_to_utf8(void)
168 {
169 check_utf32_to_utf8(0x0, 2, "");
170 check_utf32_to_utf8(0x40, 2, "\x40");
171 check_utf32_to_utf8(0xA1, 3, "\xc2\xa1");
172 check_utf32_to_utf8(0x2701, 4, "\xe2\x9c\x81");
173 check_utf32_to_utf8(0x1f004, 5, "\xf0\x9f\x80\x84");
174 check_utf32_to_utf8(0x110000, 0, "");
175 check_utf32_to_utf8(0xffffffff, 0, "");
176 }
177
178 int
main(void)179 main(void)
180 {
181 test_is_valid_utf8();
182 test_utf32_to_utf8();
183
184 return 0;
185 }
186