xref: /freebsd/crypto/heimdal/lib/wind/test-utf8.c (revision 0b3105a37d7adcadcb720112fed4dc4e8040be99)
1 /*
2  * Copyright (c) 2004 Kungliga Tekniska Högskolan
3  * (Royal Institute of Technology, Stockholm, Sweden).
4  * All rights reserved.
5  *
6  * Redistribution and use in source and binary forms, with or without
7  * modification, are permitted provided that the following conditions
8  * are met:
9  *
10  * 1. Redistributions of source code must retain the above copyright
11  *    notice, this list of conditions and the following disclaimer.
12  *
13  * 2. Redistributions in binary form must reproduce the above copyright
14  *    notice, this list of conditions and the following disclaimer in the
15  *    documentation and/or other materials provided with the distribution.
16  *
17  * 3. Neither the name of the Institute nor the names of its contributors
18  *    may be used to endorse or promote products derived from this software
19  *    without specific prior written permission.
20  *
21  * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
22  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
23  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
24  * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
25  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
26  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
27  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
28  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
29  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
30  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
31  * SUCH DAMAGE.
32  */
33 
34 #ifdef HAVE_CONFIG_H
35 #include <config.h>
36 #endif
37 #include <stdio.h>
38 #include <string.h>
39 #include <err.h>
40 #include "windlocl.h"
41 
42 static const char *failing_testcases[] = {
43     "\x80",
44     "\xFF",
45     "\xC0",
46     "\xDF",
47     "\xE0",
48     "\xEF",
49     "\xF0",
50     "\xF7",
51     "\xC0\x01",
52     "\xC0\x7F",
53     "\xC0\xFF",
54     "\xC0\x80\x80",
55     "\xE0\x01",
56     "\xE0\x7F",
57     "\xE0\x80",
58     "\xE0\xFF",
59     "\xE0\x80\x20",
60     "\xE0\x80\xFF",
61     "\xE0\x80\x80\x80",
62     "\xF0\x01",
63     "\xF0\x80",
64     "\xF0\x80\x01",
65     "\xF0\x80\x80",
66     "\xF0\x80\x80\x01",
67     "\xF0\x80\x80\xFF",
68     NULL
69 };
70 
71 #define MAX_LENGTH 10
72 
73 struct testcase {
74     const char *utf8_str;
75     size_t len;
76     uint32_t u[MAX_LENGTH];
77     int invalid_ucs2;
78 };
79 
80 static const struct testcase testcases[] = {
81     {"", 0, {0}},
82     {"\x01", 1, {1}},
83     {"\x7F", 1, {0x7F}},
84     {"\x01\x7F", 2, {0x01, 0x7F}},
85     {"\xC0\x80", 1, {0}},
86     {"\xC0\x81", 1, {1}},
87     {"\xC1\x80", 1, {0x40}},
88     {"\xDF\xBF", 1, {0x7FF}},
89     {"\xE0\x80\x80", 1, {0}},
90     {"\xE0\x80\x81", 1, {1}},
91     {"\xE0\x81\x80", 1, {0x40}},
92     {"\xE1\x80\x80", 1, {0x1000}},
93     {"\xEF\xBF\xBF", 1, {0xFFFF}},
94     {"\xF0\x80\x80\x80", 1, {0}},
95     {"\xF0\x80\x80\x81", 1, {1}},
96     {"\xF0\x80\x81\x80", 1, {0x40}},
97     {"\xF0\x81\x80\x80", 1, {0x1000}},
98     {"\xF1\x80\x80\x80", 1, {0x40000}},
99     {"\xF7\xBF\xBF\xBF", 1, {0X1FFFFF}, 1},
100 };
101 
102 int
103 main(void)
104 {
105     unsigned failures = 0;
106     unsigned i;
107     const char **s;
108     int ret;
109     size_t len, len2;
110     uint32_t u[MAX_LENGTH];
111     char str[MAX_LENGTH * 4];
112 
113     for (s = failing_testcases; *s != NULL; ++s) {
114 	len = MAX_LENGTH;
115 	ret = wind_utf8ucs4(*s, u, &len);
116 	if (ret == 0) {
117 	    printf("utf8 decode of \"%s\" should have failed\n", *s);
118 	    ++failures;
119 	}
120     }
121 
122     for (i = 0; i < sizeof(testcases)/sizeof(testcases[0]); ++i) {
123 	const struct testcase *t = &testcases[i];
124 
125 	ret = wind_utf8ucs4_length(t->utf8_str, &len);
126 	if (ret) {
127 	    printf("utf8ucs4 length of \"%s\" should have succeeded\n",
128 		   t->utf8_str);
129 	    ++failures;
130 	    continue;
131 	}
132 	if (len != t->len) {
133 	    printf("utf8ucs4_length of \"%s\" has wrong length: "
134 		   "expected: %u, actual: %u\n",
135 		   t->utf8_str, (unsigned int)t->len, (unsigned int)len);
136 	    ++failures;
137 	    continue;
138 	}
139 
140 	len = MAX_LENGTH;
141 	ret = wind_utf8ucs4(t->utf8_str, u, &len);
142 	if (ret) {
143 	    printf("utf8 decode of \"%s\" should have succeeded\n",
144 		   t->utf8_str);
145 	    ++failures;
146 	    continue;
147 	}
148 	if (len != t->len) {
149 	    printf("utf8 decode of \"%s\" has wrong length: "
150 		   "expected: %u, actual: %u\n",
151 		   t->utf8_str, (unsigned int)t->len, (unsigned int)len);
152 	    ++failures;
153 	    continue;
154 	}
155 	if (memcmp(t->u, u, len * sizeof(uint32_t)) != 0) {
156 	    printf("utf8 decode of \"%s\" has wrong data\n",
157 		   t->utf8_str);
158 	    ++failures;
159 	    continue;
160 	}
161 	if (t->invalid_ucs2 == 0) {
162 	    len2 = sizeof(str);
163 	    ret = wind_ucs4utf8(u, len, str, &len2);
164 	    if (ret) {
165 		printf("ucs4 decode of \"%s\" should have succeeded\n",
166 		       t->utf8_str);
167 		++failures;
168 		continue;
169 	    }
170 	}
171     }
172 
173     return failures != 0;
174 }
175