1 /* $OpenBSD: a_mbstr.c,v 1.24 2021/12/25 13:17:48 jsing Exp $ */ 2 /* Written by Dr Stephen N Henson (steve@openssl.org) for the OpenSSL 3 * project 1999. 4 */ 5 /* ==================================================================== 6 * Copyright (c) 1999 The OpenSSL Project. All rights reserved. 7 * 8 * Redistribution and use in source and binary forms, with or without 9 * modification, are permitted provided that the following conditions 10 * are met: 11 * 12 * 1. Redistributions of source code must retain the above copyright 13 * notice, this list of conditions and the following disclaimer. 14 * 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in 17 * the documentation and/or other materials provided with the 18 * distribution. 19 * 20 * 3. All advertising materials mentioning features or use of this 21 * software must display the following acknowledgment: 22 * "This product includes software developed by the OpenSSL Project 23 * for use in the OpenSSL Toolkit. (http://www.OpenSSL.org/)" 24 * 25 * 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to 26 * endorse or promote products derived from this software without 27 * prior written permission. For written permission, please contact 28 * licensing@OpenSSL.org. 29 * 30 * 5. Products derived from this software may not be called "OpenSSL" 31 * nor may "OpenSSL" appear in their names without prior written 32 * permission of the OpenSSL Project. 33 * 34 * 6. Redistributions of any form whatsoever must retain the following 35 * acknowledgment: 36 * "This product includes software developed by the OpenSSL Project 37 * for use in the OpenSSL Toolkit (http://www.OpenSSL.org/)" 38 * 39 * THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY 40 * EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 41 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR 42 * PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OpenSSL PROJECT OR 43 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, 44 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT 45 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; 46 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 47 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, 48 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) 49 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED 50 * OF THE POSSIBILITY OF SUCH DAMAGE. 51 * ==================================================================== 52 * 53 * This product includes cryptographic software written by Eric Young 54 * (eay@cryptsoft.com). This product includes software written by Tim 55 * Hudson (tjh@cryptsoft.com). 56 * 57 */ 58 59 #include <ctype.h> 60 #include <stdio.h> 61 #include <string.h> 62 63 #include <openssl/asn1.h> 64 #include <openssl/err.h> 65 66 #include "asn1_locl.h" 67 68 static int traverse_string(const unsigned char *p, int len, int inform, 69 int (*rfunc)(unsigned long value, void *in), void *arg); 70 static int in_utf8(unsigned long value, void *arg); 71 static int out_utf8(unsigned long value, void *arg); 72 static int type_str(unsigned long value, void *arg); 73 static int cpy_asc(unsigned long value, void *arg); 74 static int cpy_bmp(unsigned long value, void *arg); 75 static int cpy_univ(unsigned long value, void *arg); 76 static int cpy_utf8(unsigned long value, void *arg); 77 static int is_printable(unsigned long value); 78 79 /* These functions take a string in UTF8, ASCII or multibyte form and 80 * a mask of permissible ASN1 string types. It then works out the minimal 81 * type (using the order Printable < IA5 < T61 < BMP < Universal < UTF8) 82 * and creates a string of the correct type with the supplied data. 83 * Yes this is horrible: it has to be :-( 84 * The 'ncopy' form checks minimum and maximum size limits too. 85 */ 86 87 int 88 ASN1_mbstring_copy(ASN1_STRING **out, const unsigned char *in, int len, 89 int inform, unsigned long mask) 90 { 91 return ASN1_mbstring_ncopy(out, in, len, inform, mask, 0, 0); 92 } 93 94 int 95 ASN1_mbstring_ncopy(ASN1_STRING **out, const unsigned char *in, int len, 96 int inform, unsigned long mask, long minsize, long maxsize) 97 { 98 int str_type; 99 int ret; 100 char free_out; 101 int outform, outlen = 0; 102 ASN1_STRING *dest; 103 unsigned char *p; 104 int nchar; 105 int (*cpyfunc)(unsigned long, void *) = NULL; 106 107 if (len < 0) 108 len = strlen((const char *)in); 109 if (!mask) 110 mask = DIRSTRING_TYPE; 111 112 /* First do a string check and work out the number of characters */ 113 switch (inform) { 114 case MBSTRING_BMP: 115 if (len & 1) { 116 ASN1error(ASN1_R_INVALID_BMPSTRING_LENGTH); 117 return -1; 118 } 119 nchar = len >> 1; 120 break; 121 122 case MBSTRING_UNIV: 123 if (len & 3) { 124 ASN1error(ASN1_R_INVALID_UNIVERSALSTRING_LENGTH); 125 return -1; 126 } 127 nchar = len >> 2; 128 break; 129 130 case MBSTRING_UTF8: 131 nchar = 0; 132 /* This counts the characters and does utf8 syntax checking */ 133 ret = traverse_string(in, len, MBSTRING_UTF8, in_utf8, &nchar); 134 if (ret < 0) { 135 ASN1error(ASN1_R_INVALID_UTF8STRING); 136 return -1; 137 } 138 break; 139 140 case MBSTRING_ASC: 141 nchar = len; 142 break; 143 144 default: 145 ASN1error(ASN1_R_UNKNOWN_FORMAT); 146 return -1; 147 } 148 149 if ((minsize > 0) && (nchar < minsize)) { 150 ASN1error(ASN1_R_STRING_TOO_SHORT); 151 ERR_asprintf_error_data("minsize=%ld", minsize); 152 return -1; 153 } 154 155 if ((maxsize > 0) && (nchar > maxsize)) { 156 ASN1error(ASN1_R_STRING_TOO_LONG); 157 ERR_asprintf_error_data("maxsize=%ld", maxsize); 158 return -1; 159 } 160 161 /* Now work out minimal type (if any) */ 162 if (traverse_string(in, len, inform, type_str, &mask) < 0) { 163 ASN1error(ASN1_R_ILLEGAL_CHARACTERS); 164 return -1; 165 } 166 167 168 /* Now work out output format and string type */ 169 outform = MBSTRING_ASC; 170 if (mask & B_ASN1_PRINTABLESTRING) 171 str_type = V_ASN1_PRINTABLESTRING; 172 else if (mask & B_ASN1_IA5STRING) 173 str_type = V_ASN1_IA5STRING; 174 else if (mask & B_ASN1_T61STRING) 175 str_type = V_ASN1_T61STRING; 176 else if (mask & B_ASN1_BMPSTRING) { 177 str_type = V_ASN1_BMPSTRING; 178 outform = MBSTRING_BMP; 179 } else if (mask & B_ASN1_UNIVERSALSTRING) { 180 str_type = V_ASN1_UNIVERSALSTRING; 181 outform = MBSTRING_UNIV; 182 } else { 183 str_type = V_ASN1_UTF8STRING; 184 outform = MBSTRING_UTF8; 185 } 186 if (!out) 187 return str_type; 188 if (*out) { 189 free_out = 0; 190 dest = *out; 191 if (dest->data) { 192 dest->length = 0; 193 free(dest->data); 194 dest->data = NULL; 195 } 196 dest->type = str_type; 197 } else { 198 free_out = 1; 199 dest = ASN1_STRING_type_new(str_type); 200 if (!dest) { 201 ASN1error(ERR_R_MALLOC_FAILURE); 202 return -1; 203 } 204 *out = dest; 205 } 206 /* If both the same type just copy across */ 207 if (inform == outform) { 208 if (!ASN1_STRING_set(dest, in, len)) { 209 ASN1error(ERR_R_MALLOC_FAILURE); 210 goto err; 211 } 212 return str_type; 213 } 214 215 /* Work out how much space the destination will need */ 216 switch (outform) { 217 case MBSTRING_ASC: 218 outlen = nchar; 219 cpyfunc = cpy_asc; 220 break; 221 222 case MBSTRING_BMP: 223 outlen = nchar << 1; 224 cpyfunc = cpy_bmp; 225 break; 226 227 case MBSTRING_UNIV: 228 outlen = nchar << 2; 229 cpyfunc = cpy_univ; 230 break; 231 232 case MBSTRING_UTF8: 233 outlen = 0; 234 if (traverse_string(in, len, inform, out_utf8, &outlen) < 0) { 235 ASN1error(ASN1_R_ILLEGAL_CHARACTERS); 236 goto err; 237 } 238 cpyfunc = cpy_utf8; 239 break; 240 } 241 if (!(p = malloc(outlen + 1))) { 242 ASN1error(ERR_R_MALLOC_FAILURE); 243 goto err; 244 } 245 dest->length = outlen; 246 dest->data = p; 247 p[outlen] = 0; 248 traverse_string(in, len, inform, cpyfunc, &p); 249 return str_type; 250 251 err: 252 if (free_out) { 253 ASN1_STRING_free(dest); 254 *out = NULL; 255 } 256 return -1; 257 } 258 259 /* This function traverses a string and passes the value of each character 260 * to an optional function along with a void * argument. 261 */ 262 263 static int 264 traverse_string(const unsigned char *p, int len, int inform, 265 int (*rfunc)(unsigned long value, void *in), void *arg) 266 { 267 unsigned long value; 268 int ret; 269 270 while (len) { 271 switch (inform) { 272 case MBSTRING_ASC: 273 value = *p++; 274 len--; 275 break; 276 case MBSTRING_BMP: 277 value = *p++ << 8; 278 value |= *p++; 279 /* BMP is explictly defined to not support surrogates */ 280 if (UNICODE_IS_SURROGATE(value)) 281 return -1; 282 len -= 2; 283 break; 284 case MBSTRING_UNIV: 285 value = (unsigned long)*p++ << 24; 286 value |= *p++ << 16; 287 value |= *p++ << 8; 288 value |= *p++; 289 if (value > UNICODE_MAX || UNICODE_IS_SURROGATE(value)) 290 return -1; 291 len -= 4; 292 break; 293 default: 294 ret = UTF8_getc(p, len, &value); 295 if (ret < 0) 296 return -1; 297 len -= ret; 298 p += ret; 299 break; 300 } 301 if (rfunc) { 302 ret = rfunc(value, arg); 303 if (ret <= 0) 304 return ret; 305 } 306 } 307 return 1; 308 } 309 310 /* Various utility functions for traverse_string */ 311 312 /* Just count number of characters */ 313 314 static int 315 in_utf8(unsigned long value, void *arg) 316 { 317 int *nchar; 318 319 nchar = arg; 320 (*nchar)++; 321 return 1; 322 } 323 324 /* Determine size of output as a UTF8 String */ 325 326 static int 327 out_utf8(unsigned long value, void *arg) 328 { 329 int *outlen; 330 int ret; 331 332 outlen = arg; 333 ret = UTF8_putc(NULL, -1, value); 334 if (ret < 0) 335 return ret; 336 *outlen += ret; 337 return 1; 338 } 339 340 /* Determine the "type" of a string: check each character against a 341 * supplied "mask". 342 */ 343 344 static int 345 type_str(unsigned long value, void *arg) 346 { 347 unsigned long types; 348 349 types = *((unsigned long *)arg); 350 if ((types & B_ASN1_PRINTABLESTRING) && !is_printable(value)) 351 types &= ~B_ASN1_PRINTABLESTRING; 352 if ((types & B_ASN1_IA5STRING) && (value > 127)) 353 types &= ~B_ASN1_IA5STRING; 354 if ((types & B_ASN1_T61STRING) && (value > 0xff)) 355 types &= ~B_ASN1_T61STRING; 356 if ((types & B_ASN1_BMPSTRING) && (value > 0xffff)) 357 types &= ~B_ASN1_BMPSTRING; 358 if (!types) 359 return -1; 360 *((unsigned long *)arg) = types; 361 return 1; 362 } 363 364 /* Copy one byte per character ASCII like strings */ 365 366 static int 367 cpy_asc(unsigned long value, void *arg) 368 { 369 unsigned char **p, *q; 370 371 p = arg; 372 q = *p; 373 *q = value; 374 (*p)++; 375 return 1; 376 } 377 378 /* Copy two byte per character BMPStrings */ 379 380 static int 381 cpy_bmp(unsigned long value, void *arg) 382 { 383 unsigned char **p, *q; 384 385 p = arg; 386 q = *p; 387 *q++ = (value >> 8) & 0xff; 388 *q = value & 0xff; 389 *p += 2; 390 return 1; 391 } 392 393 /* Copy four byte per character UniversalStrings */ 394 395 static int 396 cpy_univ(unsigned long value, void *arg) 397 { 398 unsigned char **p, *q; 399 400 p = arg; 401 q = *p; 402 *q++ = (value >> 24) & 0xff; 403 *q++ = (value >> 16) & 0xff; 404 *q++ = (value >> 8) & 0xff; 405 *q = value & 0xff; 406 *p += 4; 407 return 1; 408 } 409 410 /* Copy to a UTF8String */ 411 412 static int 413 cpy_utf8(unsigned long value, void *arg) 414 { 415 unsigned char **p; 416 417 int ret; 418 p = arg; 419 /* We already know there is enough room so pass 0xff as the length */ 420 ret = UTF8_putc(*p, 0xff, value); 421 *p += ret; 422 return 1; 423 } 424 425 /* Return 1 if the character is permitted in a PrintableString */ 426 static int 427 is_printable(unsigned long value) 428 { 429 int ch; 430 431 if (value > 0x7f) 432 return 0; 433 ch = (int)value; 434 435 /* Note: we can't use 'isalnum' because certain accented 436 * characters may count as alphanumeric in some environments. 437 */ 438 if ((ch >= 'a') && (ch <= 'z')) 439 return 1; 440 if ((ch >= 'A') && (ch <= 'Z')) 441 return 1; 442 if ((ch >= '0') && (ch <= '9')) 443 return 1; 444 if ((ch == ' ') || strchr("'()+,-./:=?", ch)) 445 return 1; 446 return 0; 447 } 448