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 <assert.h>
25 #include <inttypes.h>
26 #include <stdbool.h>
27 #include <stddef.h>
28 
29 #include "utf8.h"
30 
31 #define VALID(lit) assert(is_valid_utf8(lit, sizeof(lit)-1))
32 #define INVALID(lit) assert(!is_valid_utf8(lit, sizeof(lit)-1))
33 
34 static void
test_is_valid_utf8(void)35 test_is_valid_utf8(void)
36 {
37     /*
38      * Mostly taken from:
39      * http://www.cl.cam.ac.uk/~mgk25/ucs/examples/UTF-8-test.txt
40      */
41 
42     VALID("ascii");
43     VALID("\xCE\xBA\xE1\xBD\xB9\xCF\x83\xCE\xBC\xCE\xB5");
44 
45     VALID("");
46     VALID("\x00");
47     VALID("\x00\x00");
48 
49     VALID("\x50");
50     VALID("\xC2\x80");
51     VALID("\xE0\xA0\x80");
52     VALID("\xF0\x90\x80\x80");
53 
54     /* 5/6-byte continuations aren't allowed (unlike UTF-8-test). */
55     INVALID("\xF8\x88\x80\x80\x80");
56     INVALID("\xFC\x84\x80\x80\x80\x80");
57 
58     VALID("\x7F");
59     VALID("\xDF\xBF");
60     VALID("\xEF\xBF\xBF");
61     /* VALID("\xF7\xBF\xBF\xBF"); */
62 
63     /* 5/6-byte continuations aren't allowed (unlike UTF-8-test). */
64     INVALID("\xFB\xBF\xBF\xBF\xBF");
65     INVALID("\xFD\xBFxBF\xBF\xBF");
66 
67     VALID("\xED\x9F\xBF");
68     VALID("\xEE\x80\x80");
69     VALID("\xEF\xBF\xBD");
70     VALID("\xF4\x8F\xBF\xBF");
71     /* VALID("\xF4\x90\x80\x80"); */
72 
73     INVALID("\x80");
74     INVALID("\xBF");
75     INVALID("\x80\xBF");
76     INVALID("\x80\xBF\x80");
77     INVALID("\x80\xBF\x80\xBF");
78     INVALID("\x80\xBF\x80\xBF\x80");
79     INVALID("\x80\xBF\x80\xBF\x80\xBF");
80     INVALID("\x80\xBF\x80\xBF\x80\xBF\x80");
81     INVALID("\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8A\x8B\x8C\x8D\x8E\x8F"
82             "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9A\x9B\x9C\x9D\x9E\x9F"
83             "\xA0\xA1\xA2\xA3\xA4\xA5\xA6\xA7\xA8\xA9\xAA\xAB\xAC\xAD\xAE\xAF"
84             "\xB0\xB1\xB2\xB3\xB4\xB5\xB6\xB7\xB8\xB9\xBA\xBB\xBC\xBD\xBE\xBF");
85 
86     INVALID("\xC0 \xC1 \xC2 \xC3 \xC4 \xC5 \xC6 \xC7 \xC8 \xC9 \xCA \xCB \xCC "
87             "\xCD \xCE \xCF "
88             "\xD0 \xD1 \xD2 \xD3 \xD4 \xD5 \xD6 \xD7 \xD8 \xD9 \xDA \xDB \xDD "
89             "\xDD \xDE \xDF ");
90     INVALID("\xF0 \xF1 \xF2 \xF3 \xF4 \xF5 \xF6 \xF7 ");
91     INVALID("\xF8 \xF9 \xFA \xFB ");
92     INVALID("\xFC \xFD ");
93 
94     INVALID("\xC0");
95     INVALID("\xE0\x80");
96     INVALID("\xF0\x80\x80");
97     INVALID("\xF8\x80\x80\x80");
98     INVALID("\xFC\x80\x80\x80\x80");
99     INVALID("\xDF");
100     INVALID("\xEF\xBF");
101     INVALID("\xF7\xBF\xBF");
102     INVALID("\xFB\xBF\xBF\xBF");
103     INVALID("\xFD\xBF\xBF\xBF\xBF");
104 
105     INVALID("\xC0\xE0\x80\xF0\x80\x80\xF8\x80\x80\x80\xFC\x80\x80\x80\x80"
106             "\xDF\xEF\xBF\xF7\xBF\xBF\xFB\xBF\xBF\xBF\xFD\xBF\xBF\xBF\xBF");
107 
108     INVALID("\xFE");
109     INVALID("\xFF");
110     INVALID("\xFE\xFE\xFF\xFF");
111 
112     INVALID("\xC0\xAF");
113     INVALID("\xE0\x80\xAF");
114     INVALID("\xF0\x80\x80\xAF");
115     INVALID("\xF8\x80\x80\x80\xAF");
116     INVALID("\xFC\x80\x80\x80\x80\xAF");
117 
118     INVALID("\xC1\xBF");
119     INVALID("\xE0\x9F\xBF");
120     INVALID("\xF0\x8F\xBF\xBF");
121     INVALID("\xF8\x87\xBF\xBF\xBF");
122     INVALID("\xFC\x83\xBF\xBF\xBF\xBF");
123 
124     INVALID("\xC0\x80");
125     INVALID("\xE0\x80\x80");
126     INVALID("\xF0\x80\x80\x80");
127     INVALID("\xF8\x80\x80\x80\x80");
128     INVALID("\xFC\x80\x80\x80\x80\x80");
129 
130     INVALID("\xED\xA0\x80");
131     INVALID("\xED\xAD\xBF");
132     INVALID("\xED\xAE\x80");
133     INVALID("\xED\xAF\xBF");
134     INVALID("\xED\xB0\x80");
135     INVALID("\xED\xBE\x80");
136     INVALID("\xED\xBF\xBF");
137 
138     INVALID("\xED\xA0\x80\xED\xB0\x80");
139     INVALID("\xED\xA0\x80\xED\xBF\xBF");
140     INVALID("\xED\xAD\xBF\xED\xB0\x80");
141     INVALID("\xED\xAD\xBF\xED\xBF\xBF");
142     INVALID("\xED\xAE\x80\xED\xB0\x80");
143     INVALID("\xED\xAE\x80\xED\xBF\xBF");
144     INVALID("\xED\xAF\xBF\xED\xB0\x80");
145     INVALID("\xED\xAF\xBF\xED\xBF\xBF");
146 
147     /* INVALID("\xEF\xBF\xBE"); */
148     /* INVALID("\xEF\xBF\xBF"); */
149 }
150 
151 int
main(void)152 main(void)
153 {
154     test_is_valid_utf8();
155 
156     return 0;
157 }
158