crypto/asn1/a_utf8.c

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