summaryrefslogtreecommitdiffstats
path: root/contrib/idn/idnkit-1.0-src/lib/tests/ucs4.tsy
blob: 205edaeee7ef28b0438ab72719a9e5e472aa6033 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
#ifndef lint
static char *rcsid = "$Id: ucs4.tsy,v 1.1.1.1 2003/06/04 00:27:04 marka Exp $";
#endif

/*
 * Copyright (c) 2002 Japan Network Information Center.
 * All rights reserved.
 *  
 * By using this file, you agree to the terms and conditions set forth bellow.
 * 
 * 			LICENSE TERMS AND CONDITIONS 
 * 
 * The following License Terms and Conditions apply, unless a different
 * license is obtained from Japan Network Information Center ("JPNIC"),
 * a Japanese association, Kokusai-Kougyou-Kanda Bldg 6F, 2-3-4 Uchi-Kanda,
 * Chiyoda-ku, Tokyo 101-0047, Japan.
 * 
 * 1. Use, Modification and Redistribution (including distribution of any
 *    modified or derived work) in source and/or binary forms is permitted
 *    under this License Terms and Conditions.
 * 
 * 2. Redistribution of source code must retain the copyright notices as they
 *    appear in each source code file, this License Terms and Conditions.
 * 
 * 3. Redistribution in binary form must reproduce the Copyright Notice,
 *    this License Terms and Conditions, in the documentation and/or other
 *    materials provided with the distribution.  For the purposes of binary
 *    distribution the "Copyright Notice" refers to the following language:
 *    "Copyright (c) 2000-2002 Japan Network Information Center.  All rights reserved."
 * 
 * 4. The name of JPNIC may not be used to endorse or promote products
 *    derived from this Software without specific prior written approval of
 *    JPNIC.
 * 
 * 5. Disclaimer/Limitation of Liability: THIS SOFTWARE IS PROVIDED BY JPNIC
 *    "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *    LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A
 *    PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL JPNIC BE LIABLE
 *    FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
 *    CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
 *    SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
 *    BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
 *    WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
 *    OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
 *    ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
 */

#include <stddef.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <stdarg.h>
#include <idn/ucs4.h>
#include <idn/log.h>
#include "testutil.h"

/*
 * Sample UTF8 and UCS4 strings.
 */
static const char *utf8_string =
	"\x7f"				/* 0x0000007f */
	"\xdf\xbf"			/* 0x000007ff */
	"\xef\xbf\xbf"			/* 0x0000ffff */
	"\xf7\xbf\xbf\xbf"		/* 0x001fffff */
	"\xfb\xbf\xbf\xbf\xbf"		/* 0x03ffffff */
	"\xfd\xbf\xbf\xbf\xbf\xbf";	/* 0x7fffffff */

static const unsigned long ucs4_string[] = {
	0x0000007f,
	0x000007ff,
	0x0000ffff,
	0x001fffff,
	0x03ffffff,
	0x7fffffff,
	0x00000000
};

//--------------------------------------------------------------------
// Setups and Teardowns.
//--------------------------------------------------------------------

//# SETUP
//      group: utf8-init
{
	unsigned long to[256];
	size_t tolen = 256;
	idn_result_t r;
}

//# SETUP
//      group: ucs4-init
{
	char to[256];
	size_t tolen = 256;
	idn_result_t r;
}

//# SETUP
//	group: quiet
{
	int saved_log_level;

	saved_log_level = idn_log_getlevel();
	idn_log_setlevel(idn_log_level_fatal);
}

//# TEARDOWN
//	group: quiet
{
	idn_log_setlevel(saved_log_level);
}

//--------------------------------------------------------------------
// Testcases.
//--------------------------------------------------------------------

//# TESTCASE
//	title: call utf8toucs4()
//	group: utf8-init
{
	r = idn_ucs4_utf8toucs4(utf8_string, to, tolen);
	ASSERT_RESULT(r, idn_success);
	ASSERT_UCS4STRING(to, ucs4_string);
}

//# TESTCASE
//	title: call ucs4toutf8()
//	group: ucs4-init
{
	r = idn_ucs4_ucs4toutf8(ucs4_string, to, tolen);
	ASSERT_RESULT(r, idn_success);
	ASSERT_STRING(to, utf8_string);
}

//# TESTCASE
//	title: call utf8toucs4() with empty from
//	group: utf8-init
{
	static unsigned long empty_ucs4_string[] = {0};

	r = idn_ucs4_utf8toucs4("", to, tolen);
	ASSERT_RESULT(r, idn_success);
	ASSERT_UCS4STRING(to, empty_ucs4_string);
}

//# TESTCASE
//	title: call ucs4toutf8() with empty from
//	group: ucs4-init
{
	static unsigned long empty_ucs4_string[] = {0};

	r = idn_ucs4_ucs4toutf8(empty_ucs4_string, to, tolen);
	ASSERT_RESULT(r, idn_success);
	ASSERT_STRING(to, "");
}

//# TESTCASE
//	title: call utf8toucs4() with broken string
//	group: utf8-init quiet
{
	/* "\xfe" as the 1st byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xfe\xbf\xbf\xbf\xbf\xbf\xbf", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\x7f" as the 2nd byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xdf\x7f", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\xc0" as the 2nd byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xdf\xc0", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\x7f" as the 3rd byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xef\xbf\x7f", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\xc0" as the 3rd byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xef\xbf\xc0", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\x7f" as the 4th byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xf7\xbf\xbf\x7f", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\xc0" as the 4th byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xf7\xbf\xbf\xc0", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\x7f" as the 5th byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xfb\xbf\xbf\xbf\x7f", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\xc0" as the 5th byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xfb\xbf\xbf\xbf\xc0", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\x7f" as the 6th byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xfd\xbf\xbf\xbf\xbf\x7f", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* "\xc0" as the 6th byte is out of range. */
	r = idn_ucs4_utf8toucs4("\xfd\xbf\xbf\xbf\xbf\xc0", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* `from' contains surrogate pair */
	r = idn_ucs4_utf8toucs4("\xed\xa0\x80\xed\xbf\xbf", to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);
}

//# TESTCASE
//	title: call ucs4toutf8() with broken string
//	group: ucs4-init quiet
{
	static unsigned long invalid_ucs4_string0[] = {0x80000000, 0};
	static unsigned long invalid_ucs4_string1[] = {0xd800, 0xdfff, 0};

	/* 0x80000000 is out of range */
	r = idn_ucs4_ucs4toutf8(invalid_ucs4_string0, to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);

	/* `from' contains surrogate pair */
	r = idn_ucs4_ucs4toutf8(invalid_ucs4_string1, to, tolen);
	ASSERT_RESULT(r, idn_invalid_encoding);
}

//# TESTCASE
//	title: buffer overrun test for utf8toucs4()
//	group: utf8-init
{
	r = idn_ucs4_utf8toucs4(utf8_string, to,
				idn_ucs4_strlen(ucs4_string) + 1);
	ASSERT_RESULT(r, idn_success);
	ASSERT_UCS4STRING(to, ucs4_string);

	r = idn_ucs4_utf8toucs4(utf8_string, to,
				idn_ucs4_strlen(ucs4_string));
	ASSERT_RESULT(r, idn_buffer_overflow);

	r = idn_ucs4_utf8toucs4(utf8_string, to, 0);
	ASSERT_RESULT(r, idn_buffer_overflow);
}

//# TESTCASE
//	title: buffer overrun test for ucs4toutf8()
//	group: ucs4-init
{
	r = idn_ucs4_ucs4toutf8(ucs4_string, to, strlen(utf8_string) + 1);
	ASSERT_RESULT(r, idn_success);
	ASSERT_STRING(to, utf8_string);

	r = idn_ucs4_ucs4toutf8(ucs4_string, to, strlen(utf8_string));
	ASSERT_RESULT(r, idn_buffer_overflow);

	r = idn_ucs4_ucs4toutf8(ucs4_string, to, 0);
	ASSERT_RESULT(r, idn_buffer_overflow);
}