1 /* -*- mode: c; c-basic-offset: 4; indent-tabs-mode: nil -*- */
2 /* util/support/t_utf16.c - test UTF-16 conversion functions */
3 /*
4 * Copyright (C) 2017 by the Massachusetts Institute of Technology.
5 * All rights reserved.
6 *
7 * Redistribution and use in source and binary forms, with or without
8 * modification, are permitted provided that the following conditions
9 * are met:
10 *
11 * * Redistributions of source code must retain the above copyright
12 * notice, this list of conditions and the following disclaimer.
13 *
14 * * Redistributions in binary form must reproduce the above copyright
15 * notice, this list of conditions and the following disclaimer in
16 * the documentation and/or other materials provided with the
17 * distribution.
18 *
19 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
20 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
21 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
22 * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
23 * COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT,
24 * INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
25 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
26 * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
27 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
28 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
29 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
30 * OF THE POSSIBILITY OF SUCH DAMAGE.
31 */
32
33 /*
34 * This program tests conversions between UTF-8 and little-endian UTF-16, with
35 * an eye mainly towards covering UTF-16 edge cases and UTF-8 decoding results
36 * which we detect as invalid in utf8_conv.c. t_utf8.c covers more UTF-8 edge
37 * cases.
38 */
39
40 #include <stdio.h>
41 #include <string.h>
42
43 #include "k5-platform.h"
44 #include "k5-utf8.h"
45
46 struct test {
47 const char *utf8;
48 const char *utf16;
49 size_t utf16len;
50 } tests[] = {
51 { "", "", 0 },
52 { "abcd", "a\0b\0c\0d\0", 8 },
53 /* From RFC 2781 (tests code point 0x12345 and some ASCII) */
54 { "\xF0\x92\x8D\x85=Ra", "\x08\xD8\x45\xDF=\0R\0a\0", 10 },
55 /* Lowest and highest Supplementary Plane code points */
56 { "\xF0\x90\x80\x80 \xF4\x8F\xBF\xBF",
57 "\x00\xD8\x00\xDC \0\xFF\xDB\xFF\xDF", 10 },
58 /* Basic Multilingual Plane code points near and above surrogate range */
59 { "\xED\x9F\xBF", "\xFF\xD7", 2 },
60 { "\xEE\x80\x80 \xEE\xBF\xBF", "\x00\xE0 \0\xFF\xEF", 6 },
61 /* Invalid UTF-8: decodes to value in surrogate pair range */
62 { "\xED\xA0\x80", NULL, 0 }, /* 0xD800 */
63 { "\xED\xAF\xBF", NULL, 0 }, /* 0xDBFF */
64 { "\xED\xB0\x80", NULL, 0 }, /* 0xDC00 */
65 { "\xED\xBF\xBF", NULL, 0 }, /* 0xDFFF */
66 /* Invalid UTF-8: decodes to value above Unicode range */
67 { "\xF4\x90\x80\x80", NULL, 0 },
68 { "\xF4\xBF\xBF\xBF", NULL, 0 },
69 { "\xF5\x80\x80\x80", NULL, 0 }, /* thrown out early due to first byte */
70 /* Invalid UTF-16: odd numbers of UTF-16 bytes */
71 { NULL, "\x00", 1 },
72 { NULL, "\x01\x00\x02", 3 },
73 /* Invalid UTF-16: high surrogate without a following low surrogate */
74 { NULL, "\x00\xD8\x00\x00", 4 },
75 { NULL, "\x00\xD8\xFF\xDB", 4 },
76 { NULL, "\xFF\xDB", 2 },
77 /* Invalid UTF-16: low surrogate without a preceding high surrogate */
78 { NULL, "\x61\x00\x00\xDC", 4 },
79 { NULL, "\xFF\xDF\xFF\xDB", 4 },
80 };
81
82 int
main(int argc,char ** argv)83 main(int argc, char **argv)
84 {
85 int ret;
86 struct test *t;
87 size_t i, utf16len;
88 uint8_t *utf16;
89 char *utf8;
90
91 for (i = 0; i < sizeof(tests) / sizeof(*tests); i++) {
92 t = &tests[i];
93 if (t->utf8 != NULL) {
94 ret = k5_utf8_to_utf16le(t->utf8, &utf16, &utf16len);
95 if (t->utf16 == NULL) {
96 assert(ret == EINVAL);
97 } else {
98 assert(ret == 0);
99 assert(t->utf16len == utf16len);
100 assert(memcmp(t->utf16, utf16, utf16len) == 0);
101 free(utf16);
102 }
103 }
104
105 if (t->utf16 != NULL) {
106 ret = k5_utf16le_to_utf8((uint8_t *)t->utf16, t->utf16len, &utf8);
107 if (t->utf8 == NULL) {
108 assert(ret == EINVAL);
109 } else {
110 assert(ret == 0);
111 assert(strcmp(t->utf8, utf8) == 0);
112 free(utf8);
113 }
114 }
115 }
116 return 0;
117 }
118