a_mbstr.c 11.2 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400
/* a_mbstr.c */
/* Written by Dr Stephen N Henson (steve@openssl.org) for the OpenSSL
 * project 1999.
 */
/* ====================================================================
 * Copyright (c) 1999 The OpenSSL Project.  All rights reserved.
 *
 * 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 above 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 acknowledgment:
 *    "This product includes software developed by the OpenSSL Project
 *    for use in the OpenSSL Toolkit. (http://www.OpenSSL.org/)"
 *
 * 4. The names "OpenSSL Toolkit" and "OpenSSL Project" must not be used to
 *    endorse or promote products derived from this software without
 *    prior written permission. For written permission, please contact
 *    licensing@OpenSSL.org.
 *
 * 5. Products derived from this software may not be called "OpenSSL"
 *    nor may "OpenSSL" appear in their names without prior written
 *    permission of the OpenSSL Project.
 *
 * 6. Redistributions of any form whatsoever must retain the following
 *    acknowledgment:
 *    "This product includes software developed by the OpenSSL Project
 *    for use in the OpenSSL Toolkit (http://www.OpenSSL.org/)"
 *
 * THIS SOFTWARE IS PROVIDED BY THE OpenSSL PROJECT ``AS IS'' AND ANY
 * EXPRESSED 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 OpenSSL PROJECT OR
 * ITS 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.
 * ====================================================================
 *
 * This product includes cryptographic software written by Eric Young
 * (eay@cryptsoft.com).  This product includes software written by Tim
 * Hudson (tjh@cryptsoft.com).
 *
 */

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

static int traverse_string(const unsigned char *p, int len, int inform,
		 int (*rfunc)(unsigned long value, void *in), void *arg);
static int in_utf8(unsigned long value, void *arg);
static int out_utf8(unsigned long value, void *arg);
static int type_str(unsigned long value, void *arg);
static int cpy_asc(unsigned long value, void *arg);
static int cpy_bmp(unsigned long value, void *arg);
static int cpy_univ(unsigned long value, void *arg);
static int cpy_utf8(unsigned long value, void *arg);
static int is_printable(unsigned long value);

/* These functions take a string in UTF8, ASCII or multibyte form and
 * a mask of permissible ASN1 string types. It then works out the minimal
 * type (using the order Printable < IA5 < T61 < BMP < Universal < UTF8)
 * and creates a string of the correct type with the supplied data.
 * Yes this is horrible: it has to be :-(
 * The 'ncopy' form checks minimum and maximum size limits too.
 */

int ASN1_mbstring_copy(ASN1_STRING **out, const unsigned char *in, int len,
					int inform, unsigned long mask)
{
	return ASN1_mbstring_ncopy(out, in, len, inform, mask, 0, 0);
}

int ASN1_mbstring_ncopy(ASN1_STRING **out, const unsigned char *in, int len,
					int inform, unsigned long mask, 
					long minsize, long maxsize)
{
	int str_type;
	int ret;
	char free_out;
	int outform, outlen = 0;
	ASN1_STRING *dest;
	unsigned char *p;
	int nchar;
	char strbuf[32];
	int (*cpyfunc)(unsigned long,void *) = NULL;
	if(len == -1) len = strlen((const char *)in);
	if(!mask) mask = DIRSTRING_TYPE;

	/* First do a string check and work out the number of characters */
	switch(inform) {

		case MBSTRING_BMP:
		if(len & 1) {
			ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY,
					 ASN1_R_INVALID_BMPSTRING_LENGTH);
			return -1;
		}
		nchar = len >> 1;
		break;

		case MBSTRING_UNIV:
		if(len & 3) {
			ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY,
					 ASN1_R_INVALID_UNIVERSALSTRING_LENGTH);
			return -1;
		}
		nchar = len >> 2;
		break;

		case MBSTRING_UTF8:
		nchar = 0;
		/* This counts the characters and does utf8 syntax checking */
		ret = traverse_string(in, len, MBSTRING_UTF8, in_utf8, &nchar);
		if(ret < 0) {
			ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY,
						 ASN1_R_INVALID_UTF8STRING);
			return -1;
		}
		break;

		case MBSTRING_ASC:
		nchar = len;
		break;

		default:
		ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY, ASN1_R_UNKNOWN_FORMAT);
		return -1;
	}

	if((minsize > 0) && (nchar < minsize)) {
		ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY, ASN1_R_STRING_TOO_SHORT);
		BIO_snprintf(strbuf, sizeof strbuf, "%ld", minsize);
		ERR_add_error_data(2, "minsize=", strbuf);
		return -1;
	}

	if((maxsize > 0) && (nchar > maxsize)) {
		ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY, ASN1_R_STRING_TOO_LONG);
		BIO_snprintf(strbuf, sizeof strbuf, "%ld", maxsize);
		ERR_add_error_data(2, "maxsize=", strbuf);
		return -1;
	}

	/* Now work out minimal type (if any) */
	if(traverse_string(in, len, inform, type_str, &mask) < 0) {
		ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY, ASN1_R_ILLEGAL_CHARACTERS);
		return -1;
	}


	/* Now work out output format and string type */
	outform = MBSTRING_ASC;
	if(mask & B_ASN1_PRINTABLESTRING) str_type = V_ASN1_PRINTABLESTRING;
	else if(mask & B_ASN1_IA5STRING) str_type = V_ASN1_IA5STRING;
	else if(mask & B_ASN1_T61STRING) str_type = V_ASN1_T61STRING;
	else if(mask & B_ASN1_BMPSTRING) {
		str_type = V_ASN1_BMPSTRING;
		outform = MBSTRING_BMP;
	} else if(mask & B_ASN1_UNIVERSALSTRING) {
		str_type = V_ASN1_UNIVERSALSTRING;
		outform = MBSTRING_UNIV;
	} else {
		str_type = V_ASN1_UTF8STRING;
		outform = MBSTRING_UTF8;
	}
	if(!out) return str_type;
	if(*out) {
		free_out = 0;
		dest = *out;
		if(dest->data) {
			dest->length = 0;
			OPENSSL_free(dest->data);
			dest->data = NULL;
		}
		dest->type = str_type;
	} else {
		free_out = 1;
		dest = ASN1_STRING_type_new(str_type);
		if(!dest) {
			ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY,
							ERR_R_MALLOC_FAILURE);
			return -1;
		}
		*out = dest;
	}
	/* If both the same type just copy across */
	if(inform == outform) {
		if(!ASN1_STRING_set(dest, in, len)) {
			ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY,ERR_R_MALLOC_FAILURE);
			return -1;
		}
		return str_type;
	} 

	/* Work out how much space the destination will need */
	switch(outform) {
		case MBSTRING_ASC:
		outlen = nchar;
		cpyfunc = cpy_asc;
		break;

		case MBSTRING_BMP:
		outlen = nchar << 1;
		cpyfunc = cpy_bmp;
		break;

		case MBSTRING_UNIV:
		outlen = nchar << 2;
		cpyfunc = cpy_univ;
		break;

		case MBSTRING_UTF8:
		outlen = 0;
		traverse_string(in, len, inform, out_utf8, &outlen);
		cpyfunc = cpy_utf8;
		break;
	}
	if(!(p = OPENSSL_malloc(outlen + 1))) {
		if(free_out) ASN1_STRING_free(dest);
		ASN1err(ASN1_F_ASN1_MBSTRING_NCOPY,ERR_R_MALLOC_FAILURE);
		return -1;
	}
	dest->length = outlen;
	dest->data = p;
	p[outlen] = 0;
	traverse_string(in, len, inform, cpyfunc, &p);
	return str_type;	
}

/* This function traverses a string and passes the value of each character
 * to an optional function along with a void * argument.
 */

static int traverse_string(const unsigned char *p, int len, int inform,
		 int (*rfunc)(unsigned long value, void *in), void *arg)
{
	unsigned long value;
	int ret;
	while(len) {
		if(inform == MBSTRING_ASC) {
			value = *p++;
			len--;
		} else if(inform == MBSTRING_BMP) {
			value = *p++ << 8;
			value |= *p++;
			len -= 2;
		} else if(inform == MBSTRING_UNIV) {
			value = ((unsigned long)*p++) << 24;
			value |= ((unsigned long)*p++) << 16;
			value |= *p++ << 8;
			value |= *p++;
			len -= 4;
		} else {
			ret = UTF8_getc(p, len, &value);
			if(ret < 0) return -1;
			len -= ret;
			p += ret;
		}
		if(rfunc) {
			ret = rfunc(value, arg);
			if(ret <= 0) return ret;
		}
	}
	return 1;
}

/* Various utility functions for traverse_string */

/* Just count number of characters */

static int in_utf8(unsigned long value, void *arg)
{
	int *nchar;
	nchar = arg;
	(*nchar)++;
	return 1;
}

/* Determine size of output as a UTF8 String */

static int out_utf8(unsigned long value, void *arg)
{
	int *outlen;
	outlen = arg;
	*outlen += UTF8_putc(NULL, -1, value);
	return 1;
}

/* Determine the "type" of a string: check each character against a
 * supplied "mask".
 */

static int type_str(unsigned long value, void *arg)
{
	unsigned long types;
	types = *((unsigned long *)arg);
	if((types & B_ASN1_PRINTABLESTRING) && !is_printable(value))
					types &= ~B_ASN1_PRINTABLESTRING;
	if((types & B_ASN1_IA5STRING) && (value > 127))
					types &= ~B_ASN1_IA5STRING;
	if((types & B_ASN1_T61STRING) && (value > 0xff))
					types &= ~B_ASN1_T61STRING;
	if((types & B_ASN1_BMPSTRING) && (value > 0xffff))
					types &= ~B_ASN1_BMPSTRING;
	if(!types) return -1;
	*((unsigned long *)arg) = types;
	return 1;
}

/* Copy one byte per character ASCII like strings */

static int cpy_asc(unsigned long value, void *arg)
{
	unsigned char **p, *q;
	p = arg;
	q = *p;
	*q = (unsigned char) value;
	(*p)++;
	return 1;
}

/* Copy two byte per character BMPStrings */

static int cpy_bmp(unsigned long value, void *arg)
{
	unsigned char **p, *q;
	p = arg;
	q = *p;
	*q++ = (unsigned char) ((value >> 8) & 0xff);
	*q = (unsigned char) (value & 0xff);
	*p += 2;
	return 1;
}

/* Copy four byte per character UniversalStrings */

static int cpy_univ(unsigned long value, void *arg)
{
	unsigned char **p, *q;
	p = arg;
	q = *p;
	*q++ = (unsigned char) ((value >> 24) & 0xff);
	*q++ = (unsigned char) ((value >> 16) & 0xff);
	*q++ = (unsigned char) ((value >> 8) & 0xff);
	*q = (unsigned char) (value & 0xff);
	*p += 4;
	return 1;
}

/* Copy to a UTF8String */

static int cpy_utf8(unsigned long value, void *arg)
{
	unsigned char **p;
	int ret;
	p = arg;
	/* We already know there is enough room so pass 0xff as the length */
	ret = UTF8_putc(*p, 0xff, value);
	*p += ret;
	return 1;
}

/* Return 1 if the character is permitted in a PrintableString */
static int is_printable(unsigned long value)
{
	int ch;
	if(value > 0x7f) return 0;
	ch = (int) value;
	/* Note: we can't use 'isalnum' because certain accented 
	 * characters may count as alphanumeric in some environments.
	 */
#ifndef CHARSET_EBCDIC
	if((ch >= 'a') && (ch <= 'z')) return 1;
	if((ch >= 'A') && (ch <= 'Z')) return 1;
	if((ch >= '0') && (ch <= '9')) return 1;
	if ((ch == ' ') || strchr("'()+,-./:=?", ch)) return 1;
#else /*CHARSET_EBCDIC*/
	if((ch >= os_toascii['a']) && (ch <= os_toascii['z'])) return 1;
	if((ch >= os_toascii['A']) && (ch <= os_toascii['Z'])) return 1;
	if((ch >= os_toascii['0']) && (ch <= os_toascii['9'])) return 1;
	if ((ch == os_toascii[' ']) || strchr("'()+,-./:=?", os_toebcdic[ch])) return 1;
#endif /*CHARSET_EBCDIC*/
	return 0;
}