1/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
2 * All rights reserved.
3 *
4 * This package is an SSL implementation written
5 * by Eric Young (eay@cryptsoft.com).
6 * The implementation was written so as to conform with Netscapes SSL.
7 *
8 * This library is free for commercial and non-commercial use as long as
9 * the following conditions are aheared to.  The following conditions
10 * apply to all code found in this distribution, be it the RC4, RSA,
11 * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
12 * included with this distribution is covered by the same copyright terms
13 * except that the holder is Tim Hudson (tjh@cryptsoft.com).
14 *
15 * Copyright remains Eric Young's, and as such any Copyright notices in
16 * the code are not to be removed.
17 * If this package is used in a product, Eric Young should be given attribution
18 * as the author of the parts of the library used.
19 * This can be in the form of a textual message at program startup or
20 * in documentation (online or textual) provided with the package.
21 *
22 * Redistribution and use in source and binary forms, with or without
23 * modification, are permitted provided that the following conditions
24 * are met:
25 * 1. Redistributions of source code must retain the copyright
26 *    notice, this list of conditions and the following disclaimer.
27 * 2. Redistributions in binary form must reproduce the above copyright
28 *    notice, this list of conditions and the following disclaimer in the
29 *    documentation and/or other materials provided with the distribution.
30 * 3. All advertising materials mentioning features or use of this software
31 *    must display the following acknowledgement:
32 *    "This product includes cryptographic software written by
33 *     Eric Young (eay@cryptsoft.com)"
34 *    The word 'cryptographic' can be left out if the rouines from the library
35 *    being used are not cryptographic related :-).
36 * 4. If you include any Windows specific code (or a derivative thereof) from
37 *    the apps directory (application code) you must include an acknowledgement:
38 *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
39 *
40 * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
41 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
42 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
43 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
44 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
45 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
46 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
47 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
48 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
49 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
50 * SUCH DAMAGE.
51 *
52 * The licence and distribution terms for any publically available version or
53 * derivative of this code cannot be changed.  i.e. this code cannot simply be
54 * copied and put under another distribution licence
55 * [including the GNU Public Licence.] */
56
57#include <openssl/asn1.h>
58
59#include <openssl/err.h>
60#include <openssl/mem.h>
61
62
63/* UTF8 utilities */
64
65/* This parses a UTF8 string one character at a time. It is passed a pointer
66 * to the string and the length of the string. It sets 'value' to the value of
67 * the current character. It returns the number of characters read or a
68 * negative error code:
69 * -1 = string too short
70 * -2 = illegal character
71 * -3 = subsequent characters not of the form 10xxxxxx
72 * -4 = character encoded incorrectly (not minimal length).
73 */
74
75int UTF8_getc(const unsigned char *str, int len, unsigned long *val)
76{
77	const unsigned char *p;
78	unsigned long value;
79	int ret;
80	if(len <= 0) return 0;
81	p = str;
82
83	/* Check syntax and work out the encoded value (if correct) */
84	if((*p & 0x80) == 0) {
85		value = *p++ & 0x7f;
86		ret = 1;
87	} else if((*p & 0xe0) == 0xc0) {
88		if(len < 2) return -1;
89		if((p[1] & 0xc0) != 0x80) return -3;
90		value = (*p++ & 0x1f) << 6;
91		value |= *p++ & 0x3f;
92		if(value < 0x80) return -4;
93		ret = 2;
94	} else if((*p & 0xf0) == 0xe0) {
95		if(len < 3) return -1;
96		if( ((p[1] & 0xc0) != 0x80)
97		   || ((p[2] & 0xc0) != 0x80) ) return -3;
98		value = (*p++ & 0xf) << 12;
99		value |= (*p++ & 0x3f) << 6;
100		value |= *p++ & 0x3f;
101		if(value < 0x800) return -4;
102		ret = 3;
103	} else if((*p & 0xf8) == 0xf0) {
104		if(len < 4) return -1;
105		if( ((p[1] & 0xc0) != 0x80)
106		   || ((p[2] & 0xc0) != 0x80)
107		   || ((p[3] & 0xc0) != 0x80) ) return -3;
108		value = ((unsigned long)(*p++ & 0x7)) << 18;
109		value |= (*p++ & 0x3f) << 12;
110		value |= (*p++ & 0x3f) << 6;
111		value |= *p++ & 0x3f;
112		if(value < 0x10000) return -4;
113		ret = 4;
114	} else if((*p & 0xfc) == 0xf8) {
115		if(len < 5) return -1;
116		if( ((p[1] & 0xc0) != 0x80)
117		   || ((p[2] & 0xc0) != 0x80)
118		   || ((p[3] & 0xc0) != 0x80)
119		   || ((p[4] & 0xc0) != 0x80) ) return -3;
120		value = ((unsigned long)(*p++ & 0x3)) << 24;
121		value |= ((unsigned long)(*p++ & 0x3f)) << 18;
122		value |= ((unsigned long)(*p++ & 0x3f)) << 12;
123		value |= (*p++ & 0x3f) << 6;
124		value |= *p++ & 0x3f;
125		if(value < 0x200000) return -4;
126		ret = 5;
127	} else if((*p & 0xfe) == 0xfc) {
128		if(len < 6) return -1;
129		if( ((p[1] & 0xc0) != 0x80)
130		   || ((p[2] & 0xc0) != 0x80)
131		   || ((p[3] & 0xc0) != 0x80)
132		   || ((p[4] & 0xc0) != 0x80)
133		   || ((p[5] & 0xc0) != 0x80) ) return -3;
134		value = ((unsigned long)(*p++ & 0x1)) << 30;
135		value |= ((unsigned long)(*p++ & 0x3f)) << 24;
136		value |= ((unsigned long)(*p++ & 0x3f)) << 18;
137		value |= ((unsigned long)(*p++ & 0x3f)) << 12;
138		value |= (*p++ & 0x3f) << 6;
139		value |= *p++ & 0x3f;
140		if(value < 0x4000000) return -4;
141		ret = 6;
142	} else return -2;
143	*val = value;
144	return ret;
145}
146
147/* This takes a character 'value' and writes the UTF8 encoded value in
148 * 'str' where 'str' is a buffer containing 'len' characters. Returns
149 * the number of characters written or -1 if 'len' is too small. 'str' can
150 * be set to NULL in which case it just returns the number of characters.
151 * It will need at most 6 characters.
152 */
153
154int UTF8_putc(unsigned char *str, int len, unsigned long value)
155{
156	if(!str) len = 6;	/* Maximum we will need */
157	else if(len <= 0) return -1;
158	if(value < 0x80) {
159		if(str) *str = (unsigned char)value;
160		return 1;
161	}
162	if(value < 0x800) {
163		if(len < 2) return -1;
164		if(str) {
165			*str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
166			*str = (unsigned char)((value & 0x3f) | 0x80);
167		}
168		return 2;
169	}
170	if(value < 0x10000) {
171		if(len < 3) return -1;
172		if(str) {
173			*str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
174			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
175			*str = (unsigned char)((value & 0x3f) | 0x80);
176		}
177		return 3;
178	}
179	if(value < 0x200000) {
180		if(len < 4) return -1;
181		if(str) {
182			*str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
183			*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
184			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
185			*str = (unsigned char)((value & 0x3f) | 0x80);
186		}
187		return 4;
188	}
189	if(value < 0x4000000) {
190		if(len < 5) return -1;
191		if(str) {
192			*str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
193			*str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
194			*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
195			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
196			*str = (unsigned char)((value & 0x3f) | 0x80);
197		}
198		return 5;
199	}
200	if(len < 6) return -1;
201	if(str) {
202		*str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
203		*str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
204		*str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
205		*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
206		*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
207		*str = (unsigned char)((value & 0x3f) | 0x80);
208	}
209	return 6;
210}
211