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
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
|
/* search.c - searching subroutines using dfa, kwset and regex for grep.
Copyright 1992, 1998, 2000 Free Software Foundation, Inc.
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, 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. */
/* Written August 1992 by Mike Haertel. */
/* $FreeBSD$ */
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <sys/types.h>
#if defined HAVE_WCTYPE_H && defined HAVE_WCHAR_H && defined HAVE_MBRTOWC
/* We can handle multibyte string. */
# define MBS_SUPPORT
# include <wchar.h>
# include <wctype.h>
#endif
#include "system.h"
#include "grep.h"
#include "regex.h"
#include "dfa.h"
#include "kwset.h"
#include "error.h"
#include "xalloc.h"
#ifdef HAVE_LIBPCRE
# include <pcre.h>
#endif
#define NCHAR (UCHAR_MAX + 1)
/* For -w, we also consider _ to be word constituent. */
#define WCHAR(C) (ISALNUM(C) || (C) == '_')
/* DFA compiled regexp. */
static struct dfa dfa;
/* The Regex compiled patterns. */
static struct patterns
{
/* Regex compiled regexp. */
struct re_pattern_buffer regexbuf;
struct re_registers regs; /* This is here on account of a BRAIN-DEAD
Q@#%!# library interface in regex.c. */
} patterns0;
struct patterns *patterns;
size_t pcount;
/* KWset compiled pattern. For Ecompile and Gcompile, we compile
a list of strings, at least one of which is known to occur in
any string matching the regexp. */
static kwset_t kwset;
/* Number of compiled fixed strings known to exactly match the regexp.
If kwsexec returns < kwset_exact_matches, then we don't need to
call the regexp matcher at all. */
static int kwset_exact_matches;
#if defined(MBS_SUPPORT)
static char* check_multibyte_string PARAMS ((char const *buf, size_t size));
#endif
static void kwsinit PARAMS ((void));
static void kwsmusts PARAMS ((void));
static void Gcompile PARAMS ((char const *, size_t));
static void Ecompile PARAMS ((char const *, size_t));
static size_t EGexecute PARAMS ((char const *, size_t, size_t *, int ));
static void Fcompile PARAMS ((char const *, size_t));
static size_t Fexecute PARAMS ((char const *, size_t, size_t *, int));
static void Pcompile PARAMS ((char const *, size_t ));
static size_t Pexecute PARAMS ((char const *, size_t, size_t *, int));
void
dfaerror (char const *mesg)
{
error (2, 0, mesg);
}
static void
kwsinit (void)
{
static char trans[NCHAR];
int i;
if (match_icase)
for (i = 0; i < NCHAR; ++i)
trans[i] = TOLOWER (i);
if (!(kwset = kwsalloc (match_icase ? trans : (char *) 0)))
error (2, 0, _("memory exhausted"));
}
/* If the DFA turns out to have some set of fixed strings one of
which must occur in the match, then we build a kwset matcher
to find those strings, and thus quickly filter out impossible
matches. */
static void
kwsmusts (void)
{
struct dfamust const *dm;
char const *err;
if (dfa.musts)
{
kwsinit ();
/* First, we compile in the substrings known to be exact
matches. The kwset matcher will return the index
of the matching string that it chooses. */
for (dm = dfa.musts; dm; dm = dm->next)
{
if (!dm->exact)
continue;
++kwset_exact_matches;
if ((err = kwsincr (kwset, dm->must, strlen (dm->must))) != 0)
error (2, 0, err);
}
/* Now, we compile the substrings that will require
the use of the regexp matcher. */
for (dm = dfa.musts; dm; dm = dm->next)
{
if (dm->exact)
continue;
if ((err = kwsincr (kwset, dm->must, strlen (dm->must))) != 0)
error (2, 0, err);
}
if ((err = kwsprep (kwset)) != 0)
error (2, 0, err);
}
}
#ifdef MBS_SUPPORT
/* This function allocate the array which correspond to "buf".
Then this check multibyte string and mark on the positions which
are not singlebyte character nor the first byte of a multibyte
character. Caller must free the array. */
static char*
check_multibyte_string(char const *buf, size_t size)
{
char *mb_properties = malloc(size);
mbstate_t cur_state;
int i;
memset(&cur_state, 0, sizeof(mbstate_t));
memset(mb_properties, 0, sizeof(char)*size);
for (i = 0; i < size ;)
{
size_t mbclen;
mbclen = mbrlen(buf + i, size - i, &cur_state);
if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0)
{
/* An invalid sequence, or a truncated multibyte character.
We treat it as a singlebyte character. */
mbclen = 1;
}
mb_properties[i] = mbclen;
i += mbclen;
}
return mb_properties;
}
#endif
static void
Gcompile (char const *pattern, size_t size)
{
const char *err;
char const *sep;
size_t total = size;
char const *motif = pattern;
re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE);
dfasyntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE, match_icase, eolbyte);
/* For GNU regex compiler we have to pass the patterns separately to detect
errors like "[\nallo\n]\n". The patterns here are "[", "allo" and "]"
GNU regex should have raise a syntax error. The same for backref, where
the backref should have been local to each pattern. */
do
{
size_t len;
sep = memchr (motif, '\n', total);
if (sep)
{
len = sep - motif;
sep++;
total -= (len + 1);
}
else
{
len = total;
total = 0;
}
patterns = realloc (patterns, (pcount + 1) * sizeof (*patterns));
if (patterns == NULL)
error (2, errno, _("memory exhausted"));
patterns[pcount] = patterns0;
if ((err = re_compile_pattern (motif, len,
&(patterns[pcount].regexbuf))) != 0)
error (2, 0, err);
pcount++;
motif = sep;
} while (sep && total != 0);
/* In the match_words and match_lines cases, we use a different pattern
for the DFA matcher that will quickly throw out cases that won't work.
Then if DFA succeeds we do some hairy stuff using the regex matcher
to decide whether the match should really count. */
if (match_words || match_lines)
{
/* In the whole-word case, we use the pattern:
\(^\|[^[:alnum:]_]\)\(userpattern\)\([^[:alnum:]_]|$\).
In the whole-line case, we use the pattern:
^\(userpattern\)$. */
static char const line_beg[] = "^\\(";
static char const line_end[] = "\\)$";
static char const word_beg[] = "\\(^\\|[^[:alnum:]_]\\)\\(";
static char const word_end[] = "\\)\\([^[:alnum:]_]\\|$\\)";
char *n = malloc (sizeof word_beg - 1 + size + sizeof word_end);
size_t i;
strcpy (n, match_lines ? line_beg : word_beg);
i = strlen (n);
memcpy (n + i, pattern, size);
i += size;
strcpy (n + i, match_lines ? line_end : word_end);
i += strlen (n + i);
pattern = n;
size = i;
}
dfacomp (pattern, size, &dfa, 1);
kwsmusts ();
}
static void
Ecompile (char const *pattern, size_t size)
{
const char *err;
const char *sep;
size_t total = size;
char const *motif = pattern;
if (strcmp (matcher, "awk") == 0)
{
re_set_syntax (RE_SYNTAX_AWK);
dfasyntax (RE_SYNTAX_AWK, match_icase, eolbyte);
}
else
{
re_set_syntax (RE_SYNTAX_POSIX_EGREP);
dfasyntax (RE_SYNTAX_POSIX_EGREP, match_icase, eolbyte);
}
/* For GNU regex compiler we have to pass the patterns separately to detect
errors like "[\nallo\n]\n". The patterns here are "[", "allo" and "]"
GNU regex should have raise a syntax error. The same for backref, where
the backref should have been local to each pattern. */
do
{
size_t len;
sep = memchr (motif, '\n', total);
if (sep)
{
len = sep - motif;
sep++;
total -= (len + 1);
}
else
{
len = total;
total = 0;
}
patterns = realloc (patterns, (pcount + 1) * sizeof (*patterns));
if (patterns == NULL)
error (2, errno, _("memory exhausted"));
patterns[pcount] = patterns0;
if ((err = re_compile_pattern (motif, len,
&(patterns[pcount].regexbuf))) != 0)
error (2, 0, err);
pcount++;
motif = sep;
} while (sep && total != 0);
/* In the match_words and match_lines cases, we use a different pattern
for the DFA matcher that will quickly throw out cases that won't work.
Then if DFA succeeds we do some hairy stuff using the regex matcher
to decide whether the match should really count. */
if (match_words || match_lines)
{
/* In the whole-word case, we use the pattern:
(^|[^[:alnum:]_])(userpattern)([^[:alnum:]_]|$).
In the whole-line case, we use the pattern:
^(userpattern)$. */
static char const line_beg[] = "^(";
static char const line_end[] = ")$";
static char const word_beg[] = "(^|[^[:alnum:]_])(";
static char const word_end[] = ")([^[:alnum:]_]|$)";
char *n = malloc (sizeof word_beg - 1 + size + sizeof word_end);
size_t i;
strcpy (n, match_lines ? line_beg : word_beg);
i = strlen(n);
memcpy (n + i, pattern, size);
i += size;
strcpy (n + i, match_lines ? line_end : word_end);
i += strlen (n + i);
pattern = n;
size = i;
}
dfacomp (pattern, size, &dfa, 1);
kwsmusts ();
}
static size_t
EGexecute (char const *buf, size_t size, size_t *match_size, int exact)
{
register char const *buflim, *beg, *end;
char eol = eolbyte;
int backref, start, len;
struct kwsmatch kwsm;
size_t i;
#ifdef MBS_SUPPORT
char *mb_properties = NULL;
#endif /* MBS_SUPPORT */
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1 && kwset)
mb_properties = check_multibyte_string(buf, size);
#endif /* MBS_SUPPORT */
buflim = buf + size;
for (beg = end = buf; end < buflim; beg = end)
{
if (!exact)
{
if (kwset)
{
/* Find a possible match using the KWset matcher. */
size_t offset = kwsexec (kwset, beg, buflim - beg, &kwsm);
if (offset == (size_t) -1)
{
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
free(mb_properties);
#endif
return (size_t)-1;
}
beg += offset;
/* Narrow down to the line containing the candidate, and
run it through DFA. */
end = memchr(beg, eol, buflim - beg);
end++;
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1 && mb_properties[beg - buf] == 0)
continue;
#endif
while (beg > buf && beg[-1] != eol)
--beg;
if (kwsm.index < kwset_exact_matches)
goto success;
if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1)
continue;
}
else
{
/* No good fixed strings; start with DFA. */
size_t offset = dfaexec (&dfa, beg, buflim - beg, &backref);
if (offset == (size_t) -1)
break;
/* Narrow down to the line we've found. */
beg += offset;
end = memchr (beg, eol, buflim - beg);
end++;
while (beg > buf && beg[-1] != eol)
--beg;
}
/* Successful, no backreferences encountered! */
if (!backref)
goto success;
}
else
end = beg + size;
/* If we've made it to this point, this means DFA has seen
a probable match, and we need to run it through Regex. */
for (i = 0; i < pcount; i++)
{
patterns[i].regexbuf.not_eol = 0;
if (0 <= (start = re_search (&(patterns[i].regexbuf), beg,
end - beg - 1, 0,
end - beg - 1, &(patterns[i].regs))))
{
len = patterns[i].regs.end[0] - start;
if (exact)
{
*match_size = len;
return start;
}
if ((!match_lines && !match_words)
|| (match_lines && len == end - beg - 1))
goto success;
/* If -w, check if the match aligns with word boundaries.
We do this iteratively because:
(a) the line may contain more than one occurence of the
pattern, and
(b) Several alternatives in the pattern might be valid at a
given point, and we may need to consider a shorter one to
find a word boundary. */
if (match_words)
while (start >= 0)
{
if ((start == 0 || !WCHAR ((unsigned char) beg[start - 1]))
&& (len == end - beg - 1
|| !WCHAR ((unsigned char) beg[start + len])))
goto success;
if (len > 0)
{
/* Try a shorter length anchored at the same place. */
--len;
patterns[i].regexbuf.not_eol = 1;
len = re_match (&(patterns[i].regexbuf), beg,
start + len, start,
&(patterns[i].regs));
}
if (len <= 0)
{
/* Try looking further on. */
if (start == end - beg - 1)
break;
++start;
patterns[i].regexbuf.not_eol = 0;
start = re_search (&(patterns[i].regexbuf), beg,
end - beg - 1,
start, end - beg - 1 - start,
&(patterns[i].regs));
len = patterns[i].regs.end[0] - start;
}
}
}
} /* for Regex patterns. */
} /* for (beg = end ..) */
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1 && mb_properties)
free (mb_properties);
#endif /* MBS_SUPPORT */
return (size_t) -1;
success:
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1 && mb_properties)
free (mb_properties);
#endif /* MBS_SUPPORT */
*match_size = end - beg;
return beg - buf;
}
static void
Fcompile (char const *pattern, size_t size)
{
char const *beg, *lim, *err;
kwsinit ();
beg = pattern;
do
{
for (lim = beg; lim < pattern + size && *lim != '\n'; ++lim)
;
if ((err = kwsincr (kwset, beg, lim - beg)) != 0)
error (2, 0, err);
if (lim < pattern + size)
++lim;
beg = lim;
}
while (beg < pattern + size);
if ((err = kwsprep (kwset)) != 0)
error (2, 0, err);
}
static size_t
Fexecute (char const *buf, size_t size, size_t *match_size, int exact)
{
register char const *beg, *try, *end;
register size_t len;
char eol = eolbyte;
struct kwsmatch kwsmatch;
#ifdef MBS_SUPPORT
char *mb_properties;
if (MB_CUR_MAX > 1)
mb_properties = check_multibyte_string (buf, size);
#endif /* MBS_SUPPORT */
for (beg = buf; beg <= buf + size; ++beg)
{
size_t offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch);
if (offset == (size_t) -1)
{
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
free(mb_properties);
#endif /* MBS_SUPPORT */
return offset;
}
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1 && mb_properties[offset+beg-buf] == 0)
continue; /* It is a part of multibyte character. */
#endif /* MBS_SUPPORT */
beg += offset;
len = kwsmatch.size[0];
if (exact)
{
*match_size = len;
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
free (mb_properties);
#endif /* MBS_SUPPORT */
return beg - buf;
}
if (match_lines)
{
if (beg > buf && beg[-1] != eol)
continue;
if (beg + len < buf + size && beg[len] != eol)
continue;
goto success;
}
else if (match_words)
for (try = beg; len; )
{
if (try > buf && WCHAR((unsigned char) try[-1]))
break;
if (try + len < buf + size && WCHAR((unsigned char) try[len]))
{
offset = kwsexec (kwset, beg, --len, &kwsmatch);
if (offset == (size_t) -1)
{
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
free (mb_properties);
#endif /* MBS_SUPPORT */
return offset;
}
try = beg + offset;
len = kwsmatch.size[0];
}
else
goto success;
}
else
goto success;
}
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
free (mb_properties);
#endif /* MBS_SUPPORT */
return -1;
success:
end = memchr (beg + len, eol, (buf + size) - (beg + len));
end++;
while (buf < beg && beg[-1] != eol)
--beg;
*match_size = end - beg;
#ifdef MBS_SUPPORT
if (MB_CUR_MAX > 1)
free (mb_properties);
#endif /* MBS_SUPPORT */
return beg - buf;
}
#if HAVE_LIBPCRE
/* Compiled internal form of a Perl regular expression. */
static pcre *cre;
/* Additional information about the pattern. */
static pcre_extra *extra;
#endif
static void
Pcompile (char const *pattern, size_t size)
{
#if !HAVE_LIBPCRE
error (2, 0, _("The -P option is not supported"));
#else
int e;
char const *ep;
char *re = xmalloc (4 * size + 7);
int flags = PCRE_MULTILINE | (match_icase ? PCRE_CASELESS : 0);
char const *patlim = pattern + size;
char *n = re;
char const *p;
char const *pnul;
/* FIXME: Remove this restriction. */
if (eolbyte != '\n')
error (2, 0, _("The -P and -z options cannot be combined"));
*n = '\0';
if (match_lines)
strcpy (n, "^(");
if (match_words)
strcpy (n, "\\b(");
n += strlen (n);
/* The PCRE interface doesn't allow NUL bytes in the pattern, so
replace each NUL byte in the pattern with the four characters
"\000", removing a preceding backslash if there are an odd
number of backslashes before the NUL.
FIXME: This method does not work with some multibyte character
encodings, notably Shift-JIS, where a multibyte character can end
in a backslash byte. */
for (p = pattern; (pnul = memchr (p, '\0', patlim - p)); p = pnul + 1)
{
memcpy (n, p, pnul - p);
n += pnul - p;
for (p = pnul; pattern < p && p[-1] == '\\'; p--)
continue;
n -= (pnul - p) & 1;
strcpy (n, "\\000");
n += 4;
}
memcpy (n, p, patlim - p);
n += patlim - p;
*n = '\0';
if (match_words)
strcpy (n, ")\\b");
if (match_lines)
strcpy (n, ")$");
cre = pcre_compile (re, flags, &ep, &e, pcre_maketables ());
if (!cre)
error (2, 0, ep);
extra = pcre_study (cre, 0, &ep);
if (ep)
error (2, 0, ep);
free (re);
#endif
}
static size_t
Pexecute (char const *buf, size_t size, size_t *match_size, int exact)
{
#if !HAVE_LIBPCRE
abort ();
return -1;
#else
/* This array must have at least two elements; everything after that
is just for performance improvement in pcre_exec. */
int sub[300];
int e = pcre_exec (cre, extra, buf, size, 0, 0,
sub, sizeof sub / sizeof *sub);
if (e <= 0)
{
switch (e)
{
case PCRE_ERROR_NOMATCH:
return -1;
case PCRE_ERROR_NOMEMORY:
error (2, 0, _("Memory exhausted"));
default:
abort ();
}
}
else
{
/* Narrow down to the line we've found. */
char const *beg = buf + sub[0];
char const *end = buf + sub[1];
char const *buflim = buf + size;
char eol = eolbyte;
if (!exact)
{
end = memchr (end, eol, buflim - end);
end++;
while (buf < beg && beg[-1] != eol)
--beg;
}
*match_size = end - beg;
return beg - buf;
}
#endif
}
struct matcher const matchers[] = {
{ "default", Gcompile, EGexecute },
{ "grep", Gcompile, EGexecute },
{ "egrep", Ecompile, EGexecute },
{ "awk", Ecompile, EGexecute },
{ "fgrep", Fcompile, Fexecute },
{ "perl", Pcompile, Pexecute },
{ "", 0, 0 },
};
|