a_utf8.c 7.69 KB
Newer Older
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
/* crypto/asn1/a_utf8.c */
/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
 * All rights reserved.
 *
 * This package is an SSL implementation written
 * by Eric Young (eay@cryptsoft.com).
 * The implementation was written so as to conform with Netscapes SSL.
 * 
 * This library is free for commercial and non-commercial use as long as
 * the following conditions are aheared to.  The following conditions
 * apply to all code found in this distribution, be it the RC4, RSA,
 * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
 * included with this distribution is covered by the same copyright terms
 * except that the holder is Tim Hudson (tjh@cryptsoft.com).
 * 
 * Copyright remains Eric Young's, and as such any Copyright notices in
 * the code are not to be removed.
 * If this package is used in a product, Eric Young should be given attribution
 * as the author of the parts of the library used.
 * This can be in the form of a textual message at program startup or
 * in documentation (online or textual) provided with the package.
 * 
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *    "This product includes cryptographic software written by
 *     Eric Young (eay@cryptsoft.com)"
 *    The word 'cryptographic' can be left out if the rouines from the library
 *    being used are not cryptographic related :-).
 * 4. If you include any Windows specific code (or a derivative thereof) from 
 *    the apps directory (application code) you must include an acknowledgement:
 *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
 * 
 * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``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 THE AUTHOR OR CONTRIBUTORS 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 DAMAGE.
 * 
 * The licence and distribution terms for any publically available version or
 * derivative of this code cannot be changed.  i.e. this code cannot simply be
 * copied and put under another distribution licence
 * [including the GNU Public Licence.]
 */

#include <stdio.h>
#include "cryptlib.h"
#include <openssl/asn1.h>


/* UTF8 utilities */

/* This parses a UTF8 string one character at a time. It is passed a pointer
 * to the string and the length of the string. It sets 'value' to the value of
 * the current character. It returns the number of characters read or a
 * negative error code:
 * -1 = string too short
 * -2 = illegal character
 * -3 = subsequent characters not of the form 10xxxxxx
 * -4 = character encoded incorrectly (not minimal length).
 */

int UTF8_getc(const unsigned char *str, int len, unsigned long *val)
{
	const unsigned char *p;
	unsigned long value;
	int ret;
	if(len <= 0) return 0;
	p = str;

	/* Check syntax and work out the encoded value (if correct) */
	if((*p & 0x80) == 0) {
		value = *p++ & 0x7f;
		ret = 1;
	} else if((*p & 0xe0) == 0xc0) {
		if(len < 2) return -1;
		if((p[1] & 0xc0) != 0x80) return -3;
		value = (*p++ & 0x1f) << 6;
		value |= *p++ & 0x3f;
		if(value < 0x80) return -4;
		ret = 2;
	} else if((*p & 0xf0) == 0xe0) {
		if(len < 3) return -1;
		if( ((p[1] & 0xc0) != 0x80)
		   || ((p[2] & 0xc0) != 0x80) ) return -3;
		value = (*p++ & 0xf) << 12;
		value |= (*p++ & 0x3f) << 6;
		value |= *p++ & 0x3f;
		if(value < 0x800) return -4;
		ret = 3;
	} else if((*p & 0xf8) == 0xf0) {
		if(len < 4) return -1;
		if( ((p[1] & 0xc0) != 0x80)
		   || ((p[2] & 0xc0) != 0x80) 
		   || ((p[3] & 0xc0) != 0x80) ) return -3;
		value = ((unsigned long)(*p++ & 0x7)) << 18;
		value |= (*p++ & 0x3f) << 12;
		value |= (*p++ & 0x3f) << 6;
		value |= *p++ & 0x3f;
		if(value < 0x10000) return -4;
		ret = 4;
	} else if((*p & 0xfc) == 0xf8) {
		if(len < 5) return -1;
		if( ((p[1] & 0xc0) != 0x80)
		   || ((p[2] & 0xc0) != 0x80) 
		   || ((p[3] & 0xc0) != 0x80) 
		   || ((p[4] & 0xc0) != 0x80) ) return -3;
		value = ((unsigned long)(*p++ & 0x3)) << 24;
		value |= ((unsigned long)(*p++ & 0x3f)) << 18;
		value |= ((unsigned long)(*p++ & 0x3f)) << 12;
		value |= (*p++ & 0x3f) << 6;
		value |= *p++ & 0x3f;
		if(value < 0x200000) return -4;
		ret = 5;
	} else if((*p & 0xfe) == 0xfc) {
		if(len < 6) return -1;
		if( ((p[1] & 0xc0) != 0x80)
		   || ((p[2] & 0xc0) != 0x80) 
		   || ((p[3] & 0xc0) != 0x80) 
		   || ((p[4] & 0xc0) != 0x80) 
		   || ((p[5] & 0xc0) != 0x80) ) return -3;
		value = ((unsigned long)(*p++ & 0x1)) << 30;
		value |= ((unsigned long)(*p++ & 0x3f)) << 24;
		value |= ((unsigned long)(*p++ & 0x3f)) << 18;
		value |= ((unsigned long)(*p++ & 0x3f)) << 12;
		value |= (*p++ & 0x3f) << 6;
		value |= *p++ & 0x3f;
		if(value < 0x4000000) return -4;
		ret = 6;
	} else return -2;
	*val = value;
	return ret;
}

/* This takes a character 'value' and writes the UTF8 encoded value in
 * 'str' where 'str' is a buffer containing 'len' characters. Returns
 * the number of characters written or -1 if 'len' is too small. 'str' can
 * be set to NULL in which case it just returns the number of characters.
 * It will need at most 6 characters.
 */

int UTF8_putc(unsigned char *str, int len, unsigned long value)
{
	if(!str) len = 6;	/* Maximum we will need */
	else if(len <= 0) return -1;
	if(value < 0x80) {
		if(str) *str = (unsigned char)value;
		return 1;
	}
	if(value < 0x800) {
		if(len < 2) return -1;
		if(str) {
			*str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0);
			*str = (unsigned char)((value & 0x3f) | 0x80);
		}
		return 2;
	}
	if(value < 0x10000) {
		if(len < 3) return -1;
		if(str) {
			*str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0);
			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
			*str = (unsigned char)((value & 0x3f) | 0x80);
		}
		return 3;
	}
	if(value < 0x200000) {
		if(len < 4) return -1;
		if(str) {
			*str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0);
			*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
			*str = (unsigned char)((value & 0x3f) | 0x80);
		}
		return 4;
	}
	if(value < 0x4000000) {
		if(len < 5) return -1;
		if(str) {
			*str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8);
			*str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
			*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
			*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
			*str = (unsigned char)((value & 0x3f) | 0x80);
		}
		return 5;
	}
	if(len < 6) return -1;
	if(str) {
		*str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc);
		*str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80);
		*str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80);
		*str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80);
		*str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80);
		*str = (unsigned char)((value & 0x3f) | 0x80);
	}
	return 6;
}