a_utf8.c revision 296465 
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/* UTF8 utilities */
64
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
76int 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)
82        return 0;
83    p = str;
84
85    /* Check syntax and work out the encoded value (if correct) */
86    if ((*p & 0x80) == 0) {
87        value = *p++ & 0x7f;
88        ret = 1;
89    } else if ((*p & 0xe0) == 0xc0) {
90        if (len < 2)
91            return -1;
92        if ((p[1] & 0xc0) != 0x80)
93            return -3;
94        value = (*p++ & 0x1f) << 6;
95        value |= *p++ & 0x3f;
96        if (value < 0x80)
97            return -4;
98        ret = 2;
99    } else if ((*p & 0xf0) == 0xe0) {
100        if (len < 3)
101            return -1;
102        if (((p[1] & 0xc0) != 0x80)
103            || ((p[2] & 0xc0) != 0x80))
104            return -3;
105        value = (*p++ & 0xf) << 12;
106        value |= (*p++ & 0x3f) << 6;
107        value |= *p++ & 0x3f;
108        if (value < 0x800)
109            return -4;
110        ret = 3;
111    } else if ((*p & 0xf8) == 0xf0) {
112        if (len < 4)
113            return -1;
114        if (((p[1] & 0xc0) != 0x80)
115            || ((p[2] & 0xc0) != 0x80)
116            || ((p[3] & 0xc0) != 0x80))
117            return -3;
118        value = ((unsigned long)(*p++ & 0x7)) << 18;
119        value |= (*p++ & 0x3f) << 12;
120        value |= (*p++ & 0x3f) << 6;
121        value |= *p++ & 0x3f;
122        if (value < 0x10000)
123            return -4;
124        ret = 4;
125    } else if ((*p & 0xfc) == 0xf8) {
126        if (len < 5)
127            return -1;
128        if (((p[1] & 0xc0) != 0x80)
129            || ((p[2] & 0xc0) != 0x80)
130            || ((p[3] & 0xc0) != 0x80)
131            || ((p[4] & 0xc0) != 0x80))
132            return -3;
133        value = ((unsigned long)(*p++ & 0x3)) << 24;
134        value |= ((unsigned long)(*p++ & 0x3f)) << 18;
135        value |= ((unsigned long)(*p++ & 0x3f)) << 12;
136        value |= (*p++ & 0x3f) << 6;
137        value |= *p++ & 0x3f;
138        if (value < 0x200000)
139            return -4;
140        ret = 5;
141    } else if ((*p & 0xfe) == 0xfc) {
142        if (len < 6)
143            return -1;
144        if (((p[1] & 0xc0) != 0x80)
145            || ((p[2] & 0xc0) != 0x80)
146            || ((p[3] & 0xc0) != 0x80)
147            || ((p[4] & 0xc0) != 0x80)
148            || ((p[5] & 0xc0) != 0x80))
149            return -3;
150        value = ((unsigned long)(*p++ & 0x1)) << 30;
151        value |= ((unsigned long)(*p++ & 0x3f)) << 24;
152        value |= ((unsigned long)(*p++ & 0x3f)) << 18;
153        value |= ((unsigned long)(*p++ & 0x3f)) << 12;
154        value |= (*p++ & 0x3f) << 6;
155        value |= *p++ & 0x3f;
156        if (value < 0x4000000)
157            return -4;
158        ret = 6;
159    } else
160        return -2;
161    *val = value;
162    return ret;
163}
164
165/*
166 * This takes a character 'value' and writes the UTF8 encoded value in 'str'
167 * where 'str' is a buffer containing 'len' characters. Returns the number of
168 * characters written or -1 if 'len' is too small. 'str' can be set to NULL
169 * in which case it just returns the number of characters. It will need at
170 * most 6 characters.
171 */
172
173int UTF8_putc(unsigned char *str, int len, unsigned long value)
174{
175    if (!str)
176        len = 6;                /* Maximum we will need */
177    else if (len <= 0)
178        return -1;
179    if (value < 0x80) {
180        if (str)
181            *str = (unsigned char)value;
182        return 1;
183    }
184    if (value < 0x800) {
185        if (len < 2)
186            return -1;
187        if (str) {
188            *str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
189            *str = (unsigned char)((value & 0x3f) | 0x80);
190        }
191        return 2;
192    }
193    if (value < 0x10000) {
194        if (len < 3)
195            return -1;
196        if (str) {
197            *str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
198            *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
199            *str = (unsigned char)((value & 0x3f) | 0x80);
200        }
201        return 3;
202    }
203    if (value < 0x200000) {
204        if (len < 4)
205            return -1;
206        if (str) {
207            *str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
208            *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
209            *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
210            *str = (unsigned char)((value & 0x3f) | 0x80);
211        }
212        return 4;
213    }
214    if (value < 0x4000000) {
215        if (len < 5)
216            return -1;
217        if (str) {
218            *str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
219            *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
220            *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
221            *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
222            *str = (unsigned char)((value & 0x3f) | 0x80);
223        }
224        return 5;
225    }
226    if (len < 6)
227        return -1;
228    if (str) {
229        *str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
230        *str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
231        *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
232        *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
233        *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
234        *str = (unsigned char)((value & 0x3f) | 0x80);
235    }
236    return 6;
237}
238