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 #include "asn1_locl.h"
63
64 /* UTF8 utilities */
65
66 /*
67 * This parses a UTF8 string one character at a time. It is passed a pointer
68 * to the string and the length of the string. It sets 'value' to the value
69 * of the current character. It returns the number of characters read or a
70 * negative error code: -1 = string too short -2 = illegal character -3 =
71 * subsequent characters not of the form 10xxxxxx -4 = character encoded
72 * incorrectly (not minimal length).
73 */
74
UTF8_getc(const unsigned char * str,int len,uint32_t * val)75 int UTF8_getc(const unsigned char *str, int len, uint32_t *val)
76 {
77 const unsigned char *p;
78 uint32_t value;
79 int ret;
80 if (len <= 0)
81 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)
90 return -1;
91 if ((p[1] & 0xc0) != 0x80)
92 return -3;
93 value = (*p++ & 0x1f) << 6;
94 value |= *p++ & 0x3f;
95 if (value < 0x80)
96 return -4;
97 ret = 2;
98 } else if ((*p & 0xf0) == 0xe0) {
99 if (len < 3)
100 return -1;
101 if (((p[1] & 0xc0) != 0x80)
102 || ((p[2] & 0xc0) != 0x80))
103 return -3;
104 value = (*p++ & 0xf) << 12;
105 value |= (*p++ & 0x3f) << 6;
106 value |= *p++ & 0x3f;
107 if (value < 0x800)
108 return -4;
109 ret = 3;
110 } else if ((*p & 0xf8) == 0xf0) {
111 if (len < 4)
112 return -1;
113 if (((p[1] & 0xc0) != 0x80)
114 || ((p[2] & 0xc0) != 0x80)
115 || ((p[3] & 0xc0) != 0x80))
116 return -3;
117 value = ((uint32_t)(*p++ & 0x7)) << 18;
118 value |= (*p++ & 0x3f) << 12;
119 value |= (*p++ & 0x3f) << 6;
120 value |= *p++ & 0x3f;
121 if (value < 0x10000)
122 return -4;
123 ret = 4;
124 } else if ((*p & 0xfc) == 0xf8) {
125 if (len < 5)
126 return -1;
127 if (((p[1] & 0xc0) != 0x80)
128 || ((p[2] & 0xc0) != 0x80)
129 || ((p[3] & 0xc0) != 0x80)
130 || ((p[4] & 0xc0) != 0x80))
131 return -3;
132 value = ((uint32_t)(*p++ & 0x3)) << 24;
133 value |= ((uint32_t)(*p++ & 0x3f)) << 18;
134 value |= ((uint32_t)(*p++ & 0x3f)) << 12;
135 value |= (*p++ & 0x3f) << 6;
136 value |= *p++ & 0x3f;
137 if (value < 0x200000)
138 return -4;
139 ret = 5;
140 } else if ((*p & 0xfe) == 0xfc) {
141 if (len < 6)
142 return -1;
143 if (((p[1] & 0xc0) != 0x80)
144 || ((p[2] & 0xc0) != 0x80)
145 || ((p[3] & 0xc0) != 0x80)
146 || ((p[4] & 0xc0) != 0x80)
147 || ((p[5] & 0xc0) != 0x80))
148 return -3;
149 value = ((uint32_t)(*p++ & 0x1)) << 30;
150 value |= ((uint32_t)(*p++ & 0x3f)) << 24;
151 value |= ((uint32_t)(*p++ & 0x3f)) << 18;
152 value |= ((uint32_t)(*p++ & 0x3f)) << 12;
153 value |= (*p++ & 0x3f) << 6;
154 value |= *p++ & 0x3f;
155 if (value < 0x4000000)
156 return -4;
157 ret = 6;
158 } else
159 return -2;
160 *val = value;
161 return ret;
162 }
163
164 /*
165 * This takes a character 'value' and writes the UTF8 encoded value in 'str'
166 * where 'str' is a buffer containing 'len' characters. Returns the number of
167 * characters written or -1 if 'len' is too small. 'str' can be set to NULL
168 * in which case it just returns the number of characters. It will need at
169 * most 6 characters.
170 */
171
UTF8_putc(unsigned char * str,int len,uint32_t value)172 int UTF8_putc(unsigned char *str, int len, uint32_t value)
173 {
174 if (!str)
175 len = 6; /* Maximum we will need */
176 else if (len <= 0)
177 return -1;
178 if (value < 0x80) {
179 if (str)
180 *str = (unsigned char)value;
181 return 1;
182 }
183 if (value < 0x800) {
184 if (len < 2)
185 return -1;
186 if (str) {
187 *str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
188 *str = (unsigned char)((value & 0x3f) | 0x80);
189 }
190 return 2;
191 }
192 if (value < 0x10000) {
193 if (len < 3)
194 return -1;
195 if (str) {
196 *str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
197 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
198 *str = (unsigned char)((value & 0x3f) | 0x80);
199 }
200 return 3;
201 }
202 if (value < 0x200000) {
203 if (len < 4)
204 return -1;
205 if (str) {
206 *str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
207 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
208 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
209 *str = (unsigned char)((value & 0x3f) | 0x80);
210 }
211 return 4;
212 }
213 if (value < 0x4000000) {
214 if (len < 5)
215 return -1;
216 if (str) {
217 *str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
218 *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
219 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
220 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
221 *str = (unsigned char)((value & 0x3f) | 0x80);
222 }
223 return 5;
224 }
225 if (len < 6)
226 return -1;
227 if (str) {
228 *str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
229 *str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
230 *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
231 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
232 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
233 *str = (unsigned char)((value & 0x3f) | 0x80);
234 }
235 return 6;
236 }
237