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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696
|
/*
* $Id: lregex.c,v 1.6 2003/07/11 01:21:53 darren Exp $
*
* Copyright (c) 2000-2003, Darren Hiebert
*
* This source code is released for free distribution under the terms of the
* GNU General Public License.
*
* This module contains functions for applying regular expression matching.
*
* The code for utlizing the Gnu regex package with regards to processing the
* regex option and checking for regex matches was adapted from routines in
* Gnu etags.
*/
/*
* INCLUDE FILES
*/
#include "general.h" /* must always come first */
#include <string.h>
#ifdef HAVE_REGCOMP
# include <ctype.h>
# include <stddef.h>
# ifdef HAVE_SYS_TYPES_H
# include <sys/types.h> /* declare off_t (not known to regex.h on FreeBSD) */
# endif
# include "regex.h"
#endif
#include "debug.h"
#include "entry.h"
#include "parse.h"
#include "read.h"
#include "routines.h"
#ifdef HAVE_REGEX
/*
* MACROS
*/
/* Back-references \0 through \9 */
#define BACK_REFERENCE_COUNT 10
#if defined (HAVE_REGCOMP) && !defined (REGCOMP_BROKEN)
# define POSIX_REGEX
#endif
#define REGEX_NAME "Regex"
/*
* DATA DECLARATIONS
*/
#if defined (POSIX_REGEX)
struct sKind {
boolean enabled;
char letter;
char* name;
char* description;
};
enum pType { PTRN_TAG, PTRN_CALLBACK };
typedef struct {
regex_t *pattern;
enum pType type;
union {
struct {
char *name_pattern;
struct sKind kind;
} tag;
struct {
regexCallback function;
} callback;
} u;
} regexPattern;
#endif
typedef struct {
regexPattern *patterns;
unsigned int count;
} patternSet;
/*
* DATA DEFINITIONS
*/
static boolean regexBroken = FALSE;
/* Array of pattern sets, indexed by language */
static patternSet* Sets = NULL;
static int SetUpper = -1; /* upper language index in list */
/*
* FUNCTION DEFINITIONS
*/
static void clearPatternSet (const langType language)
{
if (language < SetUpper)
{
patternSet* const set = Sets + language;
unsigned int i;
for (i = 0 ; i < set->count ; ++i)
{
#if defined (POSIX_REGEX)
regfree (set->patterns [i].pattern);
#endif
eFree (set->patterns [i].pattern);
set->patterns [i].pattern = NULL;
if (set->patterns [i].type == PTRN_TAG)
{
eFree (set->patterns [i].u.tag.name_pattern);
set->patterns [i].u.tag.name_pattern = NULL;
}
}
if (set->patterns != NULL)
eFree (set->patterns);
set->patterns = NULL;
set->count = 0;
}
}
/*
* Regex psuedo-parser
*/
static void makeRegexTag (
const vString* const name, const struct sKind* const kind)
{
if (kind->enabled)
{
tagEntryInfo e;
Assert (name != NULL && vStringLength (name) > 0);
Assert (kind != NULL);
initTagEntry (&e, vStringValue (name));
e.kind = kind->letter;
e.kindName = kind->name;
makeTagEntry (&e);
}
}
/*
* Regex pattern definition
*/
/* Take a string like "/blah/" and turn it into "blah", making sure
* that the first and last characters are the same, and handling
* quoted separator characters. Actually, stops on the occurrence of
* an unquoted separator. Also turns "\t" into a Tab character.
* Returns pointer to terminating separator. Works in place. Null
* terminates name string.
*/
static char* scanSeparators (char* name)
{
char sep = name [0];
char *copyto = name;
boolean quoted = FALSE;
for (++name ; *name != '\0' ; ++name)
{
if (quoted)
{
if (*name == sep)
*copyto++ = sep;
else if (*name == 't')
*copyto++ = '\t';
else
{
/* Something else is quoted, so preserve the quote. */
*copyto++ = '\\';
*copyto++ = *name;
}
quoted = FALSE;
}
else if (*name == '\\')
quoted = TRUE;
else if (*name == sep)
{
break;
}
else
*copyto++ = *name;
}
*copyto = '\0';
return name;
}
/* Parse `regexp', in form "/regex/name/[k,Kind/]flags" (where the separator
* character is whatever the first character of `regexp' is), by breaking it
* up into null terminated strings, removing the separators, and expanding
* '\t' into tabs. When complete, `regexp' points to the line matching
* pattern, a pointer to the name matching pattern is written to `name', a
* pointer to the kinds is written to `kinds' (possibly NULL), and a pointer
* to the trailing flags is written to `flags'. If the pattern is not in the
* correct format, a false value is returned.
*/
static boolean parseTagRegex (
char* const regexp, char** const name,
char** const kinds, char** const flags)
{
boolean result = FALSE;
const int separator = (unsigned char) regexp [0];
*name = scanSeparators (regexp);
if (*regexp == '\0')
error (WARNING, "empty regexp");
else if (**name != separator)
error (WARNING, "%s: incomplete regexp", regexp);
else
{
char* const third = scanSeparators (*name);
if (**name == '\0')
error (WARNING, "%s: regexp missing name pattern", regexp);
if ((*name) [strlen (*name) - 1] == '\\')
error (WARNING, "error in name pattern: \"%s\"", *name);
if (*third != separator)
error (WARNING, "%s: regexp missing final separator", regexp);
else
{
char* const fourth = scanSeparators (third);
if (*fourth == separator)
{
*kinds = third;
scanSeparators (fourth);
*flags = fourth;
}
else
{
*flags = third;
*kinds = NULL;
}
result = TRUE;
}
}
return result;
}
static void addCompiledTagPattern (
const langType language, regex_t* const pattern,
char* const name, const char kind, char* const kindName,
char *const description)
{
patternSet* set;
regexPattern *ptrn;
if (language > SetUpper)
{
int i;
Sets = xRealloc (Sets, (language + 1), patternSet);
for (i = SetUpper + 1 ; i <= language ; ++i)
{
Sets [i].patterns = NULL;
Sets [i].count = 0;
}
SetUpper = language;
}
set = Sets + language;
set->patterns = xRealloc (set->patterns, (set->count + 1), regexPattern);
ptrn = &set->patterns [set->count];
set->count += 1;
ptrn->pattern = pattern;
ptrn->type = PTRN_TAG;
ptrn->u.tag.name_pattern = name;
ptrn->u.tag.kind.enabled = TRUE;
ptrn->u.tag.kind.letter = kind;
ptrn->u.tag.kind.name = kindName;
ptrn->u.tag.kind.description = description;
}
static void addCompiledCallbackPattern (
const langType language, regex_t* const pattern,
const regexCallback callback)
{
patternSet* set;
regexPattern *ptrn;
if (language > SetUpper)
{
int i;
Sets = xRealloc (Sets, (language + 1), patternSet);
for (i = SetUpper + 1 ; i <= language ; ++i)
{
Sets [i].patterns = NULL;
Sets [i].count = 0;
}
SetUpper = language;
}
set = Sets + language;
set->patterns = xRealloc (set->patterns, (set->count + 1), regexPattern);
ptrn = &set->patterns [set->count];
set->count += 1;
ptrn->pattern = pattern;
ptrn->type = PTRN_CALLBACK;
ptrn->u.callback.function = callback;
}
#if defined (POSIX_REGEX)
static regex_t* compileRegex (const char* const regexp, const char* const flags)
{
int cflags = REG_EXTENDED | REG_NEWLINE;
regex_t *result = NULL;
int errcode;
int i;
for (i = 0 ; flags != NULL && flags [i] != '\0' ; ++i)
{
switch ((int) flags [i])
{
case 'b': cflags &= ~REG_EXTENDED; break;
case 'e': cflags |= REG_EXTENDED; break;
case 'i': cflags |= REG_ICASE; break;
default: error (WARNING, "unknown regex flag: '%c'", *flags); break;
}
}
result = xMalloc (1, regex_t);
errcode = regcomp (result, regexp, cflags);
if (errcode != 0)
{
char errmsg[256];
regerror (errcode, result, errmsg, 256);
error (WARNING, "%s", errmsg);
regfree (result);
eFree (result);
result = NULL;
}
return result;
}
#endif
static void parseKinds (
const char* const kinds, char* const kind, char** const kindName,
char **description)
{
*kind = '\0';
*kindName = NULL;
*description = NULL;
if (kinds == NULL || kinds [0] == '\0')
{
*kind = 'r';
*kindName = eStrdup ("regex");
}
else if (kinds [0] != '\0')
{
const char* k = kinds;
if (k [0] != ',' && (k [1] == ',' || k [1] == '\0'))
*kind = *k++;
else
*kind = 'r';
if (*k == ',')
++k;
if (k [0] == '\0')
*kindName = eStrdup ("regex");
else
{
const char *const comma = strchr (k, ',');
if (comma == NULL)
*kindName = eStrdup (k);
else
{
*kindName = (char*) eMalloc (comma - k + 1);
strncpy (*kindName, k, comma - k);
(*kindName) [comma - k] = '\0';
k = comma + 1;
if (k [0] != '\0')
*description = eStrdup (k);
}
}
}
}
static void printRegexKind (const regexPattern *pat, unsigned int i, boolean indent)
{
const struct sKind *const kind = &pat [i].u.tag.kind;
const char *const indentation = indent ? " " : "";
Assert (pat [i].type == PTRN_TAG);
printf ("%s%c %s %s\n", indentation,
kind->letter != '\0' ? kind->letter : '?',
kind->description != NULL ? kind->description : kind->name,
kind->enabled ? "" : " [off]");
}
static void processLanguageRegex (const langType language,
const char* const parameter)
{
if (parameter == NULL || parameter [0] == '\0')
clearPatternSet (language);
else if (parameter [0] != '@')
addLanguageRegex (language, parameter);
else if (! doesFileExist (parameter + 1))
error (WARNING, "cannot open regex file");
else
{
const char* regexfile = parameter + 1;
FILE* const fp = fopen (regexfile, "r");
if (fp == NULL)
error (WARNING | PERROR, regexfile);
else
{
vString* const regex = vStringNew ();
while (readLine (regex, fp))
addLanguageRegex (language, vStringValue (regex));
fclose (fp);
vStringDelete (regex);
}
}
}
/*
* Regex pattern matching
*/
#if defined (POSIX_REGEX)
static vString* substitute (
const char* const in, const char* out,
const int nmatch, const regmatch_t* const pmatch)
{
vString* result = vStringNew ();
const char* p;
for (p = out ; *p != '\0' ; p++)
{
if (*p == '\\' && isdigit ((int) *++p))
{
const int dig = *p - '0';
if (0 < dig && dig < nmatch && pmatch [dig].rm_so != -1)
{
const int diglen = pmatch [dig].rm_eo - pmatch [dig].rm_so;
vStringNCatS (result, in + pmatch [dig].rm_so, diglen);
}
}
else if (*p != '\n' && *p != '\r')
vStringPut (result, *p);
}
vStringTerminate (result);
return result;
}
static void matchTagPattern (const vString* const line,
const regexPattern* const patbuf,
const regmatch_t* const pmatch)
{
vString *const name = substitute (vStringValue (line),
patbuf->u.tag.name_pattern, BACK_REFERENCE_COUNT, pmatch);
vStringStripLeading (name);
vStringStripTrailing (name);
if (vStringLength (name) > 0)
makeRegexTag (name, &patbuf->u.tag.kind);
else
error (WARNING, "%s:%ld: null expansion of name pattern \"%s\"",
getInputFileName (), getInputLineNumber (),
patbuf->u.tag.name_pattern);
vStringDelete (name);
}
static void matchCallbackPattern (
const vString* const line, const regexPattern* const patbuf,
const regmatch_t* const pmatch)
{
regexMatch matches [BACK_REFERENCE_COUNT];
unsigned int count = 0;
int i;
for (i = 0 ; i < BACK_REFERENCE_COUNT && pmatch [i].rm_so != -1 ; ++i)
{
matches [i].start = pmatch [i].rm_so;
matches [i].length = pmatch [i].rm_eo - pmatch [i].rm_so;
++count;
}
patbuf->u.callback.function (vStringValue (line), matches, count);
}
static boolean matchRegexPattern (const vString* const line,
const regexPattern* const patbuf)
{
boolean result = FALSE;
regmatch_t pmatch [BACK_REFERENCE_COUNT];
const int match = regexec (patbuf->pattern, vStringValue (line),
BACK_REFERENCE_COUNT, pmatch, 0);
if (match == 0)
{
result = TRUE;
if (patbuf->type == PTRN_TAG)
matchTagPattern (line, patbuf, pmatch);
else if (patbuf->type == PTRN_CALLBACK)
matchCallbackPattern (line, patbuf, pmatch);
else
{
Assert ("invalid pattern type" == NULL);
result = FALSE;
}
}
return result;
}
#endif
/* PUBLIC INTERFACE */
/* Match against all patterns for specified language. Returns true if at least
* on pattern matched.
*/
extern boolean matchRegex (const vString* const line, const langType language)
{
boolean result = FALSE;
if (language != LANG_IGNORE && language <= SetUpper &&
Sets [language].count > 0)
{
const patternSet* const set = Sets + language;
unsigned int i;
for (i = 0 ; i < set->count ; ++i)
if (matchRegexPattern (line, set->patterns + i))
result = TRUE;
}
return result;
}
extern void findRegexTags (void)
{
/* merely read all lines of the file */
while (fileReadLine () != NULL)
;
}
#endif /* HAVE_REGEX */
extern void addTagRegex (
const langType language __unused__,
const char* const regex __unused__,
const char* const name __unused__,
const char* const kinds __unused__,
const char* const flags __unused__)
{
#ifdef HAVE_REGEX
Assert (regex != NULL);
Assert (name != NULL);
if (! regexBroken)
{
regex_t* const cp = compileRegex (regex, flags);
if (cp != NULL)
{
char kind;
char* kindName;
char* description;
parseKinds (kinds, &kind, &kindName, &description);
addCompiledTagPattern (language, cp, eStrdup (name),
kind, kindName, description);
}
}
#endif
}
extern void addCallbackRegex (
const langType language __unused__,
const char* const regex __unused__,
const char* const flags __unused__,
const regexCallback callback __unused__)
{
#ifdef HAVE_REGEX
Assert (regex != NULL);
if (! regexBroken)
{
regex_t* const cp = compileRegex (regex, flags);
if (cp != NULL)
addCompiledCallbackPattern (language, cp, callback);
}
#endif
}
extern void addLanguageRegex (
const langType language __unused__, const char* const regex __unused__)
{
#ifdef HAVE_REGEX
if (! regexBroken)
{
char *const regex_pat = eStrdup (regex);
char *name, *kinds, *flags;
if (parseTagRegex (regex_pat, &name, &kinds, &flags))
{
addTagRegex (language, regex_pat, name, kinds, flags);
eFree (regex_pat);
}
}
#endif
}
/*
* Regex option parsing
*/
extern boolean processRegexOption (const char *const option,
const char *const parameter __unused__)
{
boolean handled = FALSE;
const char* const dash = strchr (option, '-');
if (dash != NULL && strncmp (option, "regex", dash - option) == 0)
{
#ifdef HAVE_REGEX
langType language;
language = getNamedLanguage (dash + 1);
if (language == LANG_IGNORE)
error (WARNING, "unknown language in --%s option", option);
else
processLanguageRegex (language, parameter);
#else
error (WARNING, "regex support not available; required for --%s option",
option);
#endif
handled = TRUE;
}
return handled;
}
extern void disableRegexKinds (const langType language __unused__)
{
#ifdef HAVE_REGEX
if (language <= SetUpper && Sets [language].count > 0)
{
patternSet* const set = Sets + language;
unsigned int i;
for (i = 0 ; i < set->count ; ++i)
if (set->patterns [i].type == PTRN_TAG)
set->patterns [i].u.tag.kind.enabled = FALSE;
}
#endif
}
extern boolean enableRegexKind (
const langType language __unused__,
const int kind __unused__, const boolean mode __unused__)
{
boolean result = FALSE;
#ifdef HAVE_REGEX
if (language <= SetUpper && Sets [language].count > 0)
{
patternSet* const set = Sets + language;
unsigned int i;
for (i = 0 ; i < set->count ; ++i)
if (set->patterns [i].type == PTRN_TAG &&
set->patterns [i].u.tag.kind.letter == kind)
{
set->patterns [i].u.tag.kind.enabled = mode;
result = TRUE;
}
}
#endif
return result;
}
extern void printRegexKinds (const langType language __unused__, boolean indent)
{
#ifdef HAVE_REGEX
if (language <= SetUpper && Sets [language].count > 0)
{
patternSet* const set = Sets + language;
unsigned int i;
for (i = 0 ; i < set->count ; ++i)
if (set->patterns [i].type == PTRN_TAG)
printRegexKind (set->patterns, i, indent);
}
#endif
}
extern void freeRegexResources (void)
{
#ifdef HAVE_REGEX
int i;
for (i = 0 ; i <= SetUpper ; ++i)
clearPatternSet (i);
if (Sets != NULL)
eFree (Sets);
Sets = NULL;
SetUpper = -1;
#endif
}
/* Check for broken regcomp() on Cygwin */
extern void checkRegex (void)
{
#if defined (HAVE_REGEX) && defined (CHECK_REGCOMP)
regex_t patbuf;
int errcode;
if (regcomp (&patbuf, "/hello/", 0) != 0)
{
error (WARNING, "Disabling broken regex");
regexBroken = TRUE;
}
#endif
}
/* vi:set tabstop=8 shiftwidth=4: */
|