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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660
|
/* $Id: mstring.c,v 1.15 2001/10/13 01:19:52 roesch Exp $ */
/*
** Copyright (C) 1998,1999,2000,2001 Martin Roesch <roesch@clark.net>
**
** This program is free software; you can redistribute it and/or modify
** it under the terms of the GNU General Public License as published by
** the Free Software Foundation; either version 2 of the License, or
** (at your option) any later version.
**
** This program is distributed in the hope that it will be useful,
** but WITHOUT ANY WARRANTY; without even the implied warranty of
** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
** GNU General Public License for more details.
**
** You should have received a copy of the GNU General Public License
** along with this program; if not, write to the Free Software
** Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
/***************************************************************************
*
* File: MSTRING.C
*
* Purpose: Provide a variety of string functions not included in libc. Makes
* up for the fact that the libstdc++ is hard to get reference
* material on and I don't want to write any more non-portable c++
* code until I have solid references and libraries to use.
*
* History:
*
* Date: Author: Notes:
* ---------- ------- ----------------------------------------------
* 08/19/98 MFR Initial coding begun
* 03/06/99 MFR Added Boyer-Moore pattern match routine, don't use
* mContainsSubstr() any more if you don't have to
* 12/31/99 JGW Added a full Boyer-Moore implementation to increase
* performance. Added a case insensitive version of mSearch
* 07/24/01 MFR Fixed Regex pattern matcher introduced by Fyodor
*
**************************************************************************/
#include "mstring.h"
#include "debug.h"
#ifdef TEST_MSTRING
#define FatalPrintError perror
#else
void FatalPrintError(char *);
#endif
#ifdef TEST_MSTRING
int main()
{
char test[] = "\0\0\0\0\0\0\0\0\0CKAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\0\0";
char find[] = "CKAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA\0\0";
/* char test[] = "\x90\x90\x90\x90\x90\x90\xe8\xc0\xff\xff\xff/bin/sh\x90\x90\x90\x90\x90\x90\x90\x90\x90\x90";
char find[] = "\xe8\xc0\xff\xff\xff/bin/sh"; */
int i;
int toks;
int *shift;
int *skip;
/* shift=make_shift(find,sizeof(find)-1);
skip=make_skip(find,sizeof(find)-1); */
DebugMessage(DEBUG_PATTERN_MATCH,"%d\n",
mSarch(test, sizeof(test) - 1, find, sizeof(find) - 1, shift, skip));
return 0;
}
#endif
/****************************************************************
*
* Function: mSplit()
*
* Purpose: Splits a string into tokens non-destructively.
*
* Parameters:
* char *str => the string to be split
* char *sep => a string of token seperaters
* int max_strs => how many tokens should be returned
* int *toks => place to store the number of tokens found in str
* char meta => the "escape metacharacter", treat the character
* after this character as a literal and "escape" a
* seperator
*
* Returns:
* 2D char array with one token per "row" of the returned
* array.
*
****************************************************************/
char **mSplit(char *str, char *sep, int max_strs, int *toks, char meta)
{
char **retstr; /* 2D array which is returned to caller */
char *idx; /* index pointer into str */
char *end; /* ptr to end of str */
char *sep_end; /* ptr to end of seperator string */
char *sep_idx; /* index ptr into seperator string */
int len = 0; /* length of current token string */
int curr_str = 0; /* current index into the 2D return array */
char last_char = (char) 0xFF;
if (!str) return NULL;
*toks = 0;
DebugMessage(DEBUG_PATTERN_MATCH, "[*] Splitting string: %s\n", str);
DebugMessage(DEBUG_PATTERN_MATCH, "curr_str = %d\n", curr_str);
/*
* find the ends of the respective passed strings so our while() loops
* know where to stop
*/
sep_end = sep + strlen(sep);
end = str + strlen(str);
/* remove trailing whitespace */
while(isspace((int) *(end - 1)) && ((end - 1) >= str))
*(--end) = '\0'; /* -1 because of NULL */
/* set our indexing pointers */
sep_idx = sep;
idx = str;
/*
* alloc space for the return string, this is where the pointers to the
* tokens will be stored
*/
if((retstr = (char **) malloc((sizeof(char **) * max_strs))) == NULL)
FatalPrintError("malloc");
max_strs--;
DebugMessage(DEBUG_PATTERN_MATCH, "max_strs = %d curr_str = %d\n",
max_strs, curr_str);
/* loop thru each letter in the string being tokenized */
while(idx < end)
{
/* loop thru each seperator string char */
while(sep_idx < sep_end)
{
/*
* if the current string-indexed char matches the current
* seperator char...
*/
if((*idx == *sep_idx) && (last_char != meta))
{
/* if there's something to store... */
if(len > 0)
{
DebugMessage(DEBUG_PATTERN_MATCH, "Allocating %d bytes "
"for token ", len + 1);
if(curr_str <= max_strs)
{
/* allocate space for the new token */
if((retstr[curr_str] = (char *)
malloc((sizeof(char) * len) + 1)) == NULL)
{
FatalPrintError("malloc");
}
/* copy the token into the return string array */
memcpy(retstr[curr_str], (idx - len), len);
retstr[curr_str][len] = 0;
DebugMessage(DEBUG_PATTERN_MATCH, "tok[%d]: %s\n",
curr_str, retstr[curr_str]);
/* twiddle the necessary pointers and vars */
len = 0;
curr_str++;
DebugMessage(DEBUG_PATTERN_MATCH, "curr_str = %d\n",
curr_str);
DebugMessage(DEBUG_PATTERN_MATCH, "max_strs = %d "
"curr_str = %d\n", max_strs, curr_str);
last_char = *idx;
idx++;
}
DebugMessage(DEBUG_PATTERN_MATCH, "Checking if curr_str "
"(%d) >= max_strs (%d)\n", curr_str, max_strs);
/*
* if we've gotten all the tokens requested, return the
* list
*/
if(curr_str >= max_strs)
{
while(isspace((int) *idx))
idx++;
len = end - idx;
DebugMessage(DEBUG_PATTERN_MATCH, "Finishing up...\n");
DebugMessage(DEBUG_PATTERN_MATCH, "Allocating %d bytes "
"for last token ", len + 1);
fflush(stdout);
if((retstr[curr_str] = (char *)
malloc((sizeof(char) * len) + 1)) == NULL)
FatalPrintError("malloc");
memcpy(retstr[curr_str], idx, len);
retstr[curr_str][len] = 0;
DebugMessage(DEBUG_PATTERN_MATCH, "tok[%d]: %s\n",
curr_str, retstr[curr_str]);
*toks = curr_str + 1;
DebugMessage(DEBUG_PATTERN_MATCH, "max_strs = %d "
"curr_str = %d\n", max_strs, curr_str);
DebugMessage(DEBUG_PATTERN_MATCH, "mSplit got %d "
"tokens!\n", *toks);
return retstr;
}
}
else
/*
* otherwise, the previous char was a seperator as well,
* and we should just continue
*/
{
last_char = *idx;
idx++;
/* make sure to reset this so we test all the sep. chars */
sep_idx = sep;
len = 0;
}
}
else
{
/* go to the next seperator */
sep_idx++;
}
}
sep_idx = sep;
len++;
last_char = *idx;
idx++;
}
/* put the last string into the list */
if(len > 0)
{
DebugMessage(DEBUG_PATTERN_MATCH, "Allocating %d bytes for last token ",
len + 1);
if((retstr[curr_str] = (char *)
malloc((sizeof(char) * len) + 1)) == NULL)
FatalPrintError("malloc");
memcpy(retstr[curr_str], (idx - len), len);
retstr[curr_str][len] = 0;
DebugMessage(DEBUG_PATTERN_MATCH,"tok[%d]: %s\n", curr_str,
retstr[curr_str]);
*toks = curr_str + 1;
}
DebugMessage(DEBUG_PATTERN_MATCH, "mSplit got %d tokens!\n", *toks);
/* return the token list */
return retstr;
}
/****************************************************************
*
* Function: mContainsSubstr(char *, int, char *, int)
*
* Purpose: Determines if a string contains a (non-regex)
* substring.
*
* Parameters:
* buf => data buffer we want to find the data in
* b_len => data buffer length
* pat => pattern to find
* p_len => length of the data in the pattern buffer
*
* Returns:
* Integer value, 1 on success (str constains substr), 0 on
* failure (substr not in str)
*
****************************************************************/
int mContainsSubstr(char *buf, int b_len, char *pat, int p_len)
{
char *b_idx; /* index ptr into the data buffer */
char *p_idx; /* index ptr into the pattern buffer */
char *b_end; /* ptr to the end of the data buffer */
int m_cnt = 0; /* number of pattern matches so far... */
unsigned long loopcnt = 0;
/* mark the end of the strs */
b_end = (char *) (buf + b_len);
/* init the index ptrs */
b_idx = buf;
p_idx = pat;
do
{
#ifdef DEBUG
loopcnt++;
#endif
if(*p_idx == *b_idx)
{
if(m_cnt == (p_len - 1))
{
DebugMessage(DEBUG_PATTERN_MATCH,
"\n%ld compares for match\n", loopcnt);
return 1;
}
m_cnt++;
b_idx++;
p_idx++;
}
else
{
if(m_cnt == 0)
{
b_idx++;
}
else
{
b_idx = b_idx - (m_cnt - 1);
}
p_idx = pat;
m_cnt = 0;
}
} while(b_idx < b_end);
/* if we make it here we didn't find what we were looking for */
return 0;
}
/****************************************************************
*
* Function: make_skip(char *, int)
*
* Purpose: Create a Boyer-Moore skip table for a given pattern
*
* Parameters:
* ptrn => pattern
* plen => length of the data in the pattern buffer
*
* Returns:
* int * - the skip table
*
****************************************************************/
int *make_skip(char *ptrn, int plen)
{
int *skip = (int *) malloc(256 * sizeof(int));
int *sptr = &skip[256];
if (skip == NULL)
FatalPrintError("malloc");
while(sptr-- != skip)
*sptr = plen + 1;
while(plen != 0)
skip[(unsigned char) *ptrn++] = plen--;
return skip;
}
/****************************************************************
*
* Function: make_shift(char *, int)
*
* Purpose: Create a Boyer-Moore shift table for a given pattern
*
* Parameters:
* ptrn => pattern
* plen => length of the data in the pattern buffer
*
* Returns:
* int * - the shift table
*
****************************************************************/
int *make_shift(char *ptrn, int plen)
{
int *shift = (int *) malloc(plen * sizeof(int));
int *sptr = shift + plen - 1;
char *pptr = ptrn + plen - 1;
char c;
if (shift == NULL)
FatalPrintError("malloc");
c = ptrn[plen - 1];
*sptr = 1;
while(sptr-- != shift)
{
char *p1 = ptrn + plen - 2, *p2, *p3;
do
{
while(p1 >= ptrn && *p1-- != c);
p2 = ptrn + plen - 2;
p3 = p1;
while(p3 >= ptrn && *p3-- == *p2-- && p2 >= pptr);
}
while(p3 >= ptrn && p2 >= pptr);
*sptr = shift + plen - sptr + p2 - p3;
pptr--;
}
return shift;
}
/****************************************************************
*
* Function: mSearch(char *, int, char *, int)
*
* Purpose: Determines if a string contains a (non-regex)
* substring.
*
* Parameters:
* buf => data buffer we want to find the data in
* blen => data buffer length
* ptrn => pattern to find
* plen => length of the data in the pattern buffer
* skip => the B-M skip array
* shift => the B-M shift array
*
* Returns:
* Integer value, 1 on success (str constains substr), 0 on
* failure (substr not in str)
*
****************************************************************/
int mSearch(char *buf, int blen, char *ptrn, int plen, int *skip, int *shift)
{
int b_idx = plen;
int cmpcnt = 0;
DebugMessage(DEBUG_PATTERN_MATCH,"buf: %p blen: %d ptrn: %p "
"plen: %d\n", buf, blen, ptrn, plen);
if(plen == 0)
return 1;
while(b_idx <= blen)
{
int p_idx = plen, skip_stride, shift_stride;
while(buf[--b_idx] == ptrn[--p_idx])
{
#ifdef DEBUG
cmpcnt++;
#endif
if(b_idx < 0)
return 0;
if(p_idx == 0)
{
DebugMessage(DEBUG_PATTERN_MATCH, "match: compares = %d.\n",
cmpcnt);
return 1;
}
}
skip_stride = skip[(unsigned char) buf[b_idx]];
shift_stride = shift[p_idx];
b_idx += (skip_stride > shift_stride) ? skip_stride : shift_stride;
}
DebugMessage(DEBUG_PATTERN_MATCH, "no match: compares = %d.\n", cmpcnt);
return 0;
}
/****************************************************************
*
* Function: mSearchCI(char *, int, char *, int)
*
* Purpose: Determines if a string contains a (non-regex)
* substring matching is case insensitive
*
* Parameters:
* buf => data buffer we want to find the data in
* blen => data buffer length
* ptrn => pattern to find
* plen => length of the data in the pattern buffer
* skip => the B-M skip array
* shift => the B-M shift array
*
* Returns:
* Integer value, 1 on success (str constains substr), 0 on
* failure (substr not in str)
*
****************************************************************/
int mSearchCI(char *buf, int blen, char *ptrn, int plen, int *skip, int *shift)
{
int b_idx = plen;
int cmpcnt = 0;
if(plen == 0)
return 1;
while(b_idx <= blen)
{
int p_idx = plen, skip_stride, shift_stride;
while((unsigned char) ptrn[--p_idx] ==
toupper((unsigned char) buf[--b_idx]))
{
#ifdef DEBUG
cmpcnt++;
#endif
if(p_idx == 0)
{
DebugMessage(DEBUG_PATTERN_MATCH, "match: compares = %d.\n",
cmpcnt);
return 1;
}
}
skip_stride = skip[toupper((unsigned char) buf[b_idx])];
shift_stride = shift[p_idx];
b_idx += (skip_stride > shift_stride) ? skip_stride : shift_stride;
}
DebugMessage(DEBUG_PATTERN_MATCH, "no match: compares = %d.\n", cmpcnt);
return 0;
}
/****************************************************************
*
* Function: mSearchREG(char *, int, char *, int)
*
* Purpose: Determines if a string contains a (regex)
* substring.
*
* Parameters:
* buf => data buffer we want to find the data in
* blen => data buffer length
* ptrn => pattern to find
* plen => length of the data in the pattern buffer
* skip => the B-M skip array
* shift => the B-M shift array
*
* Returns:
* Integer value, 1 on success (str constains substr), 0 on
* failure (substr not in str)
*
****************************************************************/
int mSearchREG(char *buf, int blen, char *ptrn, int plen, int *skip, int *shift)
{
int b_idx = plen;
int literal = 0;
int cmpcnt = 0;
DebugMessage(DEBUG_PATTERN_MATCH, "buf: %p blen: %d ptrn: %p "
" plen: %d b_idx: %d\n", buf, blen, ptrn, plen, b_idx);
DebugMessage(DEBUG_PATTERN_MATCH, "packet data: \"%s\"\n", buf);
DebugMessage(DEBUG_PATTERN_MATCH, "matching for \"%s\"\n", ptrn);
if(plen == 0)
return 1;
while(b_idx <= blen)
{
int p_idx = plen, skip_stride, shift_stride;
DebugMessage(DEBUG_PATTERN_MATCH, "Looping... "
"([%d]0x%X (%c) -> [%d]0x%X(%c))\n", b_idx, buf[b_idx-1],
buf[b_idx-1],
p_idx, ptrn[p_idx-1], ptrn[p_idx-1]);
while(buf[--b_idx] == ptrn[--p_idx]
|| (ptrn[p_idx] == '?' && !literal)
|| (ptrn[p_idx] == '*' && !literal)
|| (ptrn[p_idx] == '\\' && !literal))
{
DebugMessage(DEBUG_PATTERN_MATCH, "comparing: b:%c -> p:%c\n",
buf[b_idx], ptrn[p_idx]);
#ifdef DEBUG
cmpcnt++;
#endif
if(literal)
literal = 0;
if(!literal && ptrn[p_idx] == '\\')
literal = 1;
if(ptrn[p_idx] == '*')
{
DebugMessage(DEBUG_PATTERN_MATCH,"Checking wildcard matching...\n");
while(p_idx != 0 && ptrn[--p_idx] == '*'); /* fool-proof */
while(buf[--b_idx] != ptrn[p_idx])
{
DebugMessage(DEBUG_PATTERN_MATCH, "comparing: b[%d]:%c -> p[%d]:%c\n",
b_idx, buf[b_idx], p_idx, ptrn[p_idx]);
if(b_idx == 0)
{
DebugMessage(DEBUG_PATTERN_MATCH, "b_idx went to 0, returning 0\n");
return 0;
}
}
DebugMessage(DEBUG_PATTERN_MATCH, "got wildcard final char match! (b[%d]: %c -> p[%d]: %c\n", b_idx, buf[b_idx], p_idx, ptrn[p_idx]);
}
if(p_idx == 0)
{
DebugMessage(DEBUG_PATTERN_MATCH, "match: compares = %d.\n",
cmpcnt);
return 1;
}
if(b_idx == 0)
break;
}
DebugMessage(DEBUG_PATTERN_MATCH, "skip-shifting...\n");
skip_stride = skip[(unsigned char) buf[b_idx]];
shift_stride = shift[p_idx];
b_idx += (skip_stride > shift_stride) ? skip_stride : shift_stride;
DebugMessage(DEBUG_PATTERN_MATCH, "b_idx skip-shifted to %d\n", b_idx);
}
DebugMessage(DEBUG_PATTERN_MATCH, "no match: compares = %d, b_idx = %d, "
"blen = %d\n", cmpcnt, b_idx, blen);
return 0;
}
|