1 /* Copyright (C) 1995-1998 Eric Young (eay (at) cryptsoft.com) 2 * All rights reserved. 3 * 4 * This package is an SSL implementation written 5 * by Eric Young (eay (at) 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 (at) 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 (at) 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 (at) 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 /* UTF8 utilities */ 63 64 /* 65 * This parses a UTF8 string one character at a time. It is passed a pointer 66 * to the string and the length of the string. It sets 'value' to the value 67 * of the current character. It returns the number of characters read or a 68 * negative error code: -1 = string too short -2 = illegal character -3 = 69 * subsequent characters not of the form 10xxxxxx -4 = character encoded 70 * incorrectly (not minimal length). 71 */ 72 73 int UTF8_getc(const unsigned char *str, int len, unsigned long *val) 74 { 75 const unsigned char *p; 76 unsigned long value; 77 int ret; 78 if (len <= 0) 79 return 0; 80 p = str; 81 82 /* Check syntax and work out the encoded value (if correct) */ 83 if ((*p & 0x80) == 0) { 84 value = *p++ & 0x7f; 85 ret = 1; 86 } else if ((*p & 0xe0) == 0xc0) { 87 if (len < 2) 88 return -1; 89 if ((p[1] & 0xc0) != 0x80) 90 return -3; 91 value = (*p++ & 0x1f) << 6; 92 value |= *p++ & 0x3f; 93 if (value < 0x80) 94 return -4; 95 ret = 2; 96 } else if ((*p & 0xf0) == 0xe0) { 97 if (len < 3) 98 return -1; 99 if (((p[1] & 0xc0) != 0x80) 100 || ((p[2] & 0xc0) != 0x80)) 101 return -3; 102 value = (*p++ & 0xf) << 12; 103 value |= (*p++ & 0x3f) << 6; 104 value |= *p++ & 0x3f; 105 if (value < 0x800) 106 return -4; 107 ret = 3; 108 } else if ((*p & 0xf8) == 0xf0) { 109 if (len < 4) 110 return -1; 111 if (((p[1] & 0xc0) != 0x80) 112 || ((p[2] & 0xc0) != 0x80) 113 || ((p[3] & 0xc0) != 0x80)) 114 return -3; 115 value = ((unsigned long)(*p++ & 0x7)) << 18; 116 value |= (*p++ & 0x3f) << 12; 117 value |= (*p++ & 0x3f) << 6; 118 value |= *p++ & 0x3f; 119 if (value < 0x10000) 120 return -4; 121 ret = 4; 122 } else if ((*p & 0xfc) == 0xf8) { 123 if (len < 5) 124 return -1; 125 if (((p[1] & 0xc0) != 0x80) 126 || ((p[2] & 0xc0) != 0x80) 127 || ((p[3] & 0xc0) != 0x80) 128 || ((p[4] & 0xc0) != 0x80)) 129 return -3; 130 value = ((unsigned long)(*p++ & 0x3)) << 24; 131 value |= ((unsigned long)(*p++ & 0x3f)) << 18; 132 value |= ((unsigned long)(*p++ & 0x3f)) << 12; 133 value |= (*p++ & 0x3f) << 6; 134 value |= *p++ & 0x3f; 135 if (value < 0x200000) 136 return -4; 137 ret = 5; 138 } else if ((*p & 0xfe) == 0xfc) { 139 if (len < 6) 140 return -1; 141 if (((p[1] & 0xc0) != 0x80) 142 || ((p[2] & 0xc0) != 0x80) 143 || ((p[3] & 0xc0) != 0x80) 144 || ((p[4] & 0xc0) != 0x80) 145 || ((p[5] & 0xc0) != 0x80)) 146 return -3; 147 value = ((unsigned long)(*p++ & 0x1)) << 30; 148 value |= ((unsigned long)(*p++ & 0x3f)) << 24; 149 value |= ((unsigned long)(*p++ & 0x3f)) << 18; 150 value |= ((unsigned long)(*p++ & 0x3f)) << 12; 151 value |= (*p++ & 0x3f) << 6; 152 value |= *p++ & 0x3f; 153 if (value < 0x4000000) 154 return -4; 155 ret = 6; 156 } else 157 return -2; 158 *val = value; 159 return ret; 160 } 161 162 /* 163 * This takes a character 'value' and writes the UTF8 encoded value in 'str' 164 * where 'str' is a buffer containing 'len' characters. Returns the number of 165 * characters written or -1 if 'len' is too small. 'str' can be set to NULL 166 * in which case it just returns the number of characters. It will need at 167 * most 6 characters. 168 */ 169 170 int UTF8_putc(unsigned char *str, int len, unsigned long value) 171 { 172 if (!str) 173 len = 6; /* Maximum we will need */ 174 else if (len <= 0) 175 return -1; 176 if (value < 0x80) { 177 if (str) 178 *str = (unsigned char)value; 179 return 1; 180 } 181 if (value < 0x800) { 182 if (len < 2) 183 return -1; 184 if (str) { 185 *str++ = (unsigned char)(((value >> 6) & 0x1f) | 0xc0); 186 *str = (unsigned char)((value & 0x3f) | 0x80); 187 } 188 return 2; 189 } 190 if (value < 0x10000) { 191 if (len < 3) 192 return -1; 193 if (str) { 194 *str++ = (unsigned char)(((value >> 12) & 0xf) | 0xe0); 195 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80); 196 *str = (unsigned char)((value & 0x3f) | 0x80); 197 } 198 return 3; 199 } 200 if (value < 0x200000) { 201 if (len < 4) 202 return -1; 203 if (str) { 204 *str++ = (unsigned char)(((value >> 18) & 0x7) | 0xf0); 205 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80); 206 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80); 207 *str = (unsigned char)((value & 0x3f) | 0x80); 208 } 209 return 4; 210 } 211 if (value < 0x4000000) { 212 if (len < 5) 213 return -1; 214 if (str) { 215 *str++ = (unsigned char)(((value >> 24) & 0x3) | 0xf8); 216 *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80); 217 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80); 218 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80); 219 *str = (unsigned char)((value & 0x3f) | 0x80); 220 } 221 return 5; 222 } 223 if (len < 6) 224 return -1; 225 if (str) { 226 *str++ = (unsigned char)(((value >> 30) & 0x1) | 0xfc); 227 *str++ = (unsigned char)(((value >> 24) & 0x3f) | 0x80); 228 *str++ = (unsigned char)(((value >> 18) & 0x3f) | 0x80); 229 *str++ = (unsigned char)(((value >> 12) & 0x3f) | 0x80); 230 *str++ = (unsigned char)(((value >> 6) & 0x3f) | 0x80); 231 *str = (unsigned char)((value & 0x3f) | 0x80); 232 } 233 return 6; 234 } 235
