1 /* crypto/asn1/a_utf8.c */
2 /* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
3  * All rights reserved.
4  *
5  * This package is an SSL implementation written
6  * by Eric Young (eay@cryptsoft.com).
7  * The implementation was written so as to conform with Netscapes SSL.
8  *
9  * This library is free for commercial and non-commercial use as long as
10  * the following conditions are aheared to.  The following conditions
11  * apply to all code found in this distribution, be it the RC4, RSA,
12  * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
13  * included with this distribution is covered by the same copyright terms
14  * except that the holder is Tim Hudson (tjh@cryptsoft.com).
15  *
16  * Copyright remains Eric Young's, and as such any Copyright notices in
17  * the code are not to be removed.
18  * If this package is used in a product, Eric Young should be given attribution
19  * as the author of the parts of the library used.
20  * This can be in the form of a textual message at program startup or
21  * in documentation (online or textual) provided with the package.
22  *
23  * Redistribution and use in source and binary forms, with or without
24  * modification, are permitted provided that the following conditions
25  * are met:
26  * 1. Redistributions of source code must retain the copyright
27  *    notice, this list of conditions and the following disclaimer.
28  * 2. Redistributions in binary form must reproduce the above copyright
29  *    notice, this list of conditions and the following disclaimer in the
30  *    documentation and/or other materials provided with the distribution.
31  * 3. All advertising materials mentioning features or use of this software
32  *    must display the following acknowledgement:
33  *    "This product includes cryptographic software written by
34  *     Eric Young (eay@cryptsoft.com)"
35  *    The word 'cryptographic' can be left out if the rouines from the library
36  *    being used are not cryptographic related :-).
37  * 4. If you include any Windows specific code (or a derivative thereof) from
38  *    the apps directory (application code) you must include an acknowledgement:
39  *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
40  *
41  * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
42  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
43  * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
44  * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
45  * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
46  * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
47  * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
48  * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
49  * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
50  * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
51  * SUCH DAMAGE.
52  *
53  * The licence and distribution terms for any publically available version or
54  * derivative of this code cannot be changed.  i.e. this code cannot simply be
55  * copied and put under another distribution licence
56  * [including the GNU Public Licence.]
57  */
58 
59 #include <stdio.h>
60 #include "cryptlib.h"
61 #include <openssl/asn1.h>
62 
63 
64 /* UTF8 utilities */
65 
66 /* This parses a UTF8 string one character at a time. It is passed a pointer
67  * to the string and the length of the string. It sets 'value' to the value of
68  * the current character. It returns the number of characters read or a
69  * negative error code:
70  * -1 = string too short
71  * -2 = illegal character
72  * -3 = subsequent characters not of the form 10xxxxxx
73  * -4 = character encoded incorrectly (not minimal length).
74  */
75 
76 int UTF8_getc(const unsigned char *str, int len, unsigned long *val)
77 {
78 	const unsigned char *p;
79 	unsigned long value;
80 	int ret;
81 	if(len <= 0) return 0;
82 	p = str;
83 
84 	/* Check syntax and work out the encoded value (if correct) */
85 	if((*p & 0x80) == 0) {
86 		value = *p++ & 0x7f;
87 		ret = 1;
88 	} else if((*p & 0xe0) == 0xc0) {
89 		if(len < 2) return -1;
90 		if((p[1] & 0xc0) != 0x80) return -3;
91 		value = (*p++ & 0x1f) << 6;
92 		value |= *p++ & 0x3f;
93 		if(value < 0x80) return -4;
94 		ret = 2;
95 	} else if((*p & 0xf0) == 0xe0) {
96 		if(len < 3) return -1;
97 		if( ((p[1] & 0xc0) != 0x80)
98 		   || ((p[2] & 0xc0) != 0x80) ) return -3;
99 		value = (*p++ & 0xf) << 12;
100 		value |= (*p++ & 0x3f) << 6;
101 		value |= *p++ & 0x3f;
102 		if(value < 0x800) return -4;
103 		ret = 3;
104 	} else if((*p & 0xf8) == 0xf0) {
105 		if(len < 4) return -1;
106 		if( ((p[1] & 0xc0) != 0x80)
107 		   || ((p[2] & 0xc0) != 0x80)
108 		   || ((p[3] & 0xc0) != 0x80) ) return -3;
109 		value = ((unsigned long)(*p++ & 0x7)) << 18;
110 		value |= (*p++ & 0x3f) << 12;
111 		value |= (*p++ & 0x3f) << 6;
112 		value |= *p++ & 0x3f;
113 		if(value < 0x10000) return -4;
114 		ret = 4;
115 	} else if((*p & 0xfc) == 0xf8) {
116 		if(len < 5) return -1;
117 		if( ((p[1] & 0xc0) != 0x80)
118 		   || ((p[2] & 0xc0) != 0x80)
119 		   || ((p[3] & 0xc0) != 0x80)
120 		   || ((p[4] & 0xc0) != 0x80) ) return -3;
121 		value = ((unsigned long)(*p++ & 0x3)) << 24;
122 		value |= ((unsigned long)(*p++ & 0x3f)) << 18;
123 		value |= ((unsigned long)(*p++ & 0x3f)) << 12;
124 		value |= (*p++ & 0x3f) << 6;
125 		value |= *p++ & 0x3f;
126 		if(value < 0x200000) return -4;
127 		ret = 5;
128 	} else if((*p & 0xfe) == 0xfc) {
129 		if(len < 6) return -1;
130 		if( ((p[1] & 0xc0) != 0x80)
131 		   || ((p[2] & 0xc0) != 0x80)
132 		   || ((p[3] & 0xc0) != 0x80)
133 		   || ((p[4] & 0xc0) != 0x80)
134 		   || ((p[5] & 0xc0) != 0x80) ) return -3;
135 		value = ((unsigned long)(*p++ & 0x1)) << 30;
136 		value |= ((unsigned long)(*p++ & 0x3f)) << 24;
137 		value |= ((unsigned long)(*p++ & 0x3f)) << 18;
138 		value |= ((unsigned long)(*p++ & 0x3f)) << 12;
139 		value |= (*p++ & 0x3f) << 6;
140 		value |= *p++ & 0x3f;
141 		if(value < 0x4000000) return -4;
142 		ret = 6;
143 	} else return -2;
144 	*val = value;
145 	return ret;
146 }
147 
148 /* This takes a character 'value' and writes the UTF8 encoded value in
149  * 'str' where 'str' is a buffer containing 'len' characters. Returns
150  * the number of characters written or -1 if 'len' is too small. 'str' can
151  * be set to NULL in which case it just returns the number of characters.
152  * It will need at most 6 characters.
153  */
154 
155 int UTF8_putc(unsigned char *str, int len, unsigned long value)
156 {
157 	if(!str) len = 6;	/* Maximum we will need */
158 	else if(len <= 0) return -1;
159 	if(value < 0x80) {
160 		if(str) *str = (unsigned char)value;
161 		return 1;
162 	}
163 	if(value < 0x800) {
164 		if(len < 2) return -1;
165 		if(str) {
166 			*str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
167 			*str = (unsigned char)((value & 0x3f) | 0x80);
168 		}
169 		return 2;
170 	}
171 	if(value < 0x10000) {
172 		if(len < 3) return -1;
173 		if(str) {
174 			*str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
175 			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
176 			*str = (unsigned char)((value & 0x3f) | 0x80);
177 		}
178 		return 3;
179 	}
180 	if(value < 0x200000) {
181 		if(len < 4) return -1;
182 		if(str) {
183 			*str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
184 			*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
185 			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
186 			*str = (unsigned char)((value & 0x3f) | 0x80);
187 		}
188 		return 4;
189 	}
190 	if(value < 0x4000000) {
191 		if(len < 5) return -1;
192 		if(str) {
193 			*str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
194 			*str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
195 			*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
196 			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
197 			*str = (unsigned char)((value & 0x3f) | 0x80);
198 		}
199 		return 5;
200 	}
201 	if(len < 6) return -1;
202 	if(str) {
203 		*str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
204 		*str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
205 		*str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
206 		*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
207 		*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
208 		*str = (unsigned char)((value & 0x3f) | 0x80);
209 	}
210 	return 6;
211 }
212