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
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
|
/* 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. */
/* $FreeBSD$ */
#ifndef _GNU_SOURCE
# define _GNU_SOURCE 1
#endif
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#include <assert.h>
#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
#ifdef HAVE_LANGINFO_CODESET
# include <langinfo.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;
/* UTF-8 encoding allows some optimizations that we can't otherwise
assume in a multibyte encoding. */
static int using_utf8;
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
check_utf8 (void)
{
#ifdef HAVE_LANGINFO_CODESET
if (strcmp (nl_langinfo (CODESET), "UTF-8") == 0)
using_utf8 = 1;
#endif
}
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);
}
}
static void
Gcompile (char const *pattern, size_t size)
{
const char *err;
char const *sep;
size_t total = size;
char const *motif = pattern;
check_utf8 ();
re_set_syntax (RE_SYNTAX_GREP | RE_HAT_LISTS_NOT_NEWLINE | (match_icase ? RE_ICASE : 0));
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:]_]\\|$\\)";
char *n = xmalloc (sizeof word_beg - 1 + size + sizeof word_end);
size_t i;
strcpy (n, match_lines ? line_beg : word_beg);
i = strlen (n);
memcpy (n + i, pattern, size);
i += size;
strcpy (n + i, match_lines ? line_end : word_end);
i += strlen (n + i);
pattern = n;
size = i;
}
dfacomp (pattern, size, &dfa, 1);
kwsmusts ();
}
static void
Ecompile (char const *pattern, size_t size)
{
const char *err;
const char *sep;
size_t total = size;
char const *motif = pattern;
check_utf8 ();
if (strcmp (matcher, "awk") == 0)
{
re_set_syntax (RE_SYNTAX_AWK | (match_icase ? RE_ICASE : 0));
dfasyntax (RE_SYNTAX_AWK, match_icase, eolbyte);
}
else
{
re_set_syntax (RE_SYNTAX_POSIX_EGREP | (match_icase ? RE_ICASE : 0));
dfasyntax (RE_SYNTAX_POSIX_EGREP, match_icase, eolbyte);
}
/* For GNU regex compiler we have to pass the patterns separately to detect
errors like "[\nallo\n]\n". The patterns here are "[", "allo" and "]"
GNU regex should have raise a syntax error. The same for backref, where
the backref should have been local to each pattern. */
do
{
size_t len;
sep = memchr (motif, '\n', total);
if (sep)
{
len = sep - motif;
sep++;
total -= (len + 1);
}
else
{
len = total;
total = 0;
}
patterns = realloc (patterns, (pcount + 1) * sizeof (*patterns));
if (patterns == NULL)
error (2, errno, _("memory exhausted"));
patterns[pcount] = patterns0;
if ((err = re_compile_pattern (motif, len,
&(patterns[pcount].regexbuf))) != 0)
error (2, 0, err);
pcount++;
motif = sep;
} while (sep && total != 0);
/* In the match_words and match_lines cases, we use a different pattern
for the DFA matcher that will quickly throw out cases that won't work.
Then if DFA succeeds we do some hairy stuff using the regex matcher
to decide whether the match should really count. */
if (match_words || match_lines)
{
/* In the whole-word case, we use the pattern:
(^|[^[:alnum:]_])(userpattern)([^[:alnum:]_]|$).
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 = xmalloc (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, ret_val;
static int use_dfa;
static int use_dfa_checked = 0;
#ifdef MBS_SUPPORT
const char *last_char = NULL;
int mb_cur_max = MB_CUR_MAX;
mbstate_t mbs;
memset (&mbs, '\0', sizeof (mbstate_t));
#endif /* MBS_SUPPORT */
if (!use_dfa_checked)
{
char *grep_use_dfa = getenv ("GREP_USE_DFA");
if (!grep_use_dfa)
{
#ifdef MBS_SUPPORT
/* Turn off DFA when processing multibyte input. */
use_dfa = (MB_CUR_MAX == 1);
#else
use_dfa = 1;
#endif /* MBS_SUPPORT */
}
else
{
use_dfa = atoi (grep_use_dfa);
}
use_dfa_checked = 1;
}
buflim = buf + size;
for (beg = end = buf; end < buflim; beg = end)
{
if (!exact)
{
if (kwset)
{
/* Find a possible match using the KWset matcher. */
#ifdef MBS_SUPPORT
size_t bytes_left = 0;
#endif /* MBS_SUPPORT */
size_t offset;
#ifdef MBS_SUPPORT
/* kwsexec doesn't work with match_icase and multibyte input. */
if (match_icase && mb_cur_max > 1)
/* Avoid kwset */
offset = 0;
else
#endif /* MBS_SUPPORT */
offset = kwsexec (kwset, beg, buflim - beg, &kwsm);
if (offset == (size_t) -1)
goto failure;
#ifdef MBS_SUPPORT
if (mb_cur_max > 1 && !using_utf8)
{
bytes_left = offset;
while (bytes_left)
{
size_t mlen = mbrlen (beg, bytes_left, &mbs);
last_char = beg;
if (mlen == (size_t) -1 || mlen == 0)
{
/* Incomplete character: treat as single-byte. */
memset (&mbs, '\0', sizeof (mbstate_t));
beg++;
bytes_left--;
continue;
}
if (mlen == (size_t) -2)
/* Offset points inside multibyte character:
* no good. */
break;
beg += mlen;
bytes_left -= mlen;
}
}
else
#endif /* MBS_SUPPORT */
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 && bytes_left)
continue;
#endif /* MBS_SUPPORT */
while (beg > buf && beg[-1] != eol)
--beg;
if (
#ifdef MBS_SUPPORT
!(match_icase && mb_cur_max > 1) &&
#endif /* MBS_SUPPORT */
(kwsm.index < kwset_exact_matches))
goto success_in_beg_and_end;
if (use_dfa &&
dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1)
continue;
}
else
{
/* No good fixed strings; start with DFA. */
#ifdef MBS_SUPPORT
size_t bytes_left = 0;
#endif /* MBS_SUPPORT */
size_t offset = 0;
if (use_dfa)
offset = dfaexec (&dfa, beg, buflim - beg, &backref);
if (offset == (size_t) -1)
break;
/* Narrow down to the line we've found. */
#ifdef MBS_SUPPORT
if (mb_cur_max > 1 && !using_utf8)
{
bytes_left = offset;
while (bytes_left)
{
size_t mlen = mbrlen (beg, bytes_left, &mbs);
last_char = beg;
if (mlen == (size_t) -1 || mlen == 0)
{
/* Incomplete character: treat as single-byte. */
memset (&mbs, '\0', sizeof (mbstate_t));
beg++;
bytes_left--;
continue;
}
if (mlen == (size_t) -2)
/* Offset points inside multibyte character:
* no good. */
break;
beg += mlen;
bytes_left -= mlen;
}
}
else
#endif /* MBS_SUPPORT */
beg += offset;
end = memchr (beg, eol, buflim - beg);
end++;
#ifdef MBS_SUPPORT
if (mb_cur_max > 1 && bytes_left)
continue;
#endif /* MBS_SUPPORT */
while (beg > buf && beg[-1] != eol)
--beg;
}
/* Successful, no backreferences encountered! */
if (use_dfa && !backref)
goto success_in_beg_and_end;
}
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_words)
goto success_in_start_and_len;
if ((!match_lines && !match_words)
|| (match_lines && len == end - beg - 1))
goto success_in_beg_and_end;
/* 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)
{
int lword_match = 0;
if (start == 0)
lword_match = 1;
else
{
assert (start > 0);
#ifdef MBS_SUPPORT
if (mb_cur_max > 1)
{
const char *s;
int mr;
wchar_t pwc;
if (using_utf8)
{
s = beg + start - 1;
while (s > buf
&& (unsigned char) *s >= 0x80
&& (unsigned char) *s <= 0xbf)
--s;
}
else
s = last_char;
mr = mbtowc (&pwc, s, beg + start - s);
if (mr <= 0)
{
memset (&mbs, '\0', sizeof (mbstate_t));
lword_match = 1;
}
else if (!(iswalnum (pwc) || pwc == L'_')
&& mr == (int) (beg + start - s))
lword_match = 1;
}
else
#endif /* MBS_SUPPORT */
if (!WCHAR ((unsigned char) beg[start - 1]))
lword_match = 1;
}
if (lword_match)
{
int rword_match = 0;
if (start + len == end - beg - 1)
rword_match = 1;
else
{
#ifdef MBS_SUPPORT
if (mb_cur_max > 1)
{
wchar_t nwc;
int mr;
mr = mbtowc (&nwc, beg + start + len,
end - beg - start - len - 1);
if (mr <= 0)
{
memset (&mbs, '\0', sizeof (mbstate_t));
rword_match = 1;
}
else if (!iswalnum (nwc) && nwc != L'_')
rword_match = 1;
}
else
#endif /* MBS_SUPPORT */
if (!WCHAR ((unsigned char) beg[start + len]))
rword_match = 1;
}
if (rword_match)
{
if (!exact)
/* Returns the whole line. */
goto success_in_beg_and_end;
else
/* Returns just this word match. */
goto success_in_start_and_len;
}
}
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 ..) */
failure:
return (size_t) -1;
success_in_beg_and_end:
len = end - beg;
start = beg - buf;
/* FALLTHROUGH */
success_in_start_and_len:
*match_size = len;
return start;
}
#ifdef MBS_SUPPORT
static int f_i_multibyte; /* whether we're using the new -Fi MB method */
static struct
{
wchar_t **patterns;
size_t count, maxlen;
unsigned char *match;
} Fimb;
#endif
static void
Fcompile (char const *pattern, size_t size)
{
int mb_cur_max = MB_CUR_MAX;
char const *beg, *lim, *err;
check_utf8 ();
#ifdef MBS_SUPPORT
/* Support -F -i for UTF-8 input. */
if (match_icase && mb_cur_max > 1)
{
mbstate_t mbs;
wchar_t *wcpattern = xmalloc ((size + 1) * sizeof (wchar_t));
const char *patternend = pattern;
size_t wcsize;
kwset_t fimb_kwset = NULL;
char *starts = NULL;
wchar_t *wcbeg, *wclim;
size_t allocated = 0;
memset (&mbs, '\0', sizeof (mbs));
# ifdef __GNU_LIBRARY__
wcsize = mbsnrtowcs (wcpattern, &patternend, size, size, &mbs);
if (patternend != pattern + size)
wcsize = (size_t) -1;
# else
{
char *patterncopy = xmalloc (size + 1);
memcpy (patterncopy, pattern, size);
patterncopy[size] = '\0';
patternend = patterncopy;
wcsize = mbsrtowcs (wcpattern, &patternend, size, &mbs);
if (patternend != patterncopy + size)
wcsize = (size_t) -1;
free (patterncopy);
}
# endif
if (wcsize + 2 <= 2)
{
fimb_fail:
free (wcpattern);
free (starts);
if (fimb_kwset)
kwsfree (fimb_kwset);
free (Fimb.patterns);
Fimb.patterns = NULL;
}
else
{
if (!(fimb_kwset = kwsalloc (NULL)))
error (2, 0, _("memory exhausted"));
starts = xmalloc (mb_cur_max * 3);
wcbeg = wcpattern;
do
{
int i;
size_t wclen;
if (Fimb.count >= allocated)
{
if (allocated == 0)
allocated = 128;
else
allocated *= 2;
Fimb.patterns = xrealloc (Fimb.patterns,
sizeof (wchar_t *) * allocated);
}
Fimb.patterns[Fimb.count++] = wcbeg;
for (wclim = wcbeg;
wclim < wcpattern + wcsize && *wclim != L'\n'; ++wclim)
*wclim = towlower (*wclim);
*wclim = L'\0';
wclen = wclim - wcbeg;
if (wclen > Fimb.maxlen)
Fimb.maxlen = wclen;
if (wclen > 3)
wclen = 3;
if (wclen == 0)
{
if ((err = kwsincr (fimb_kwset, "", 0)) != 0)
error (2, 0, err);
}
else
for (i = 0; i < (1 << wclen); i++)
{
char *p = starts;
int j, k;
for (j = 0; j < wclen; ++j)
{
wchar_t wc = wcbeg[j];
if (i & (1 << j))
{
wc = towupper (wc);
if (wc == wcbeg[j])
continue;
}
k = wctomb (p, wc);
if (k <= 0)
goto fimb_fail;
p += k;
}
if ((err = kwsincr (fimb_kwset, starts, p - starts)) != 0)
error (2, 0, err);
}
if (wclim < wcpattern + wcsize)
++wclim;
wcbeg = wclim;
}
while (wcbeg < wcpattern + wcsize);
f_i_multibyte = 1;
kwset = fimb_kwset;
free (starts);
Fimb.match = xmalloc (Fimb.count);
if ((err = kwsprep (kwset)) != 0)
error (2, 0, err);
return;
}
}
#endif /* MBS_SUPPORT */
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);
}
#ifdef MBS_SUPPORT
static int
Fimbexec (const char *buf, size_t size, size_t *plen, int exact)
{
size_t len, letter, i;
int ret = -1;
mbstate_t mbs;
wchar_t wc;
int patterns_left;
assert (match_icase && f_i_multibyte == 1);
assert (MB_CUR_MAX > 1);
memset (&mbs, '\0', sizeof (mbs));
memset (Fimb.match, '\1', Fimb.count);
letter = len = 0;
patterns_left = 1;
while (patterns_left && len <= size)
{
size_t c;
patterns_left = 0;
if (len < size)
{
c = mbrtowc (&wc, buf + len, size - len, &mbs);
if (c + 2 <= 2)
return ret;
wc = towlower (wc);
}
else
{
c = 1;
wc = L'\0';
}
for (i = 0; i < Fimb.count; i++)
{
if (Fimb.match[i])
{
if (Fimb.patterns[i][letter] == L'\0')
{
/* Found a match. */
*plen = len;
if (!exact && !match_words)
return 0;
else
{
/* For -w or exact look for longest match. */
ret = 0;
Fimb.match[i] = '\0';
continue;
}
}
if (Fimb.patterns[i][letter] == wc)
patterns_left = 1;
else
Fimb.match[i] = '\0';
}
}
len += c;
letter++;
}
return ret;
}
#endif /* MBS_SUPPORT */
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;
size_t ret_val;
#ifdef MBS_SUPPORT
int mb_cur_max = MB_CUR_MAX;
mbstate_t mbs;
memset (&mbs, '\0', sizeof (mbstate_t));
const char *last_char = NULL;
#endif /* MBS_SUPPORT */
for (beg = buf; beg <= buf + size; ++beg)
{
size_t offset;
offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch);
if (offset == (size_t) -1)
goto failure;
#ifdef MBS_SUPPORT
if (mb_cur_max > 1 && !using_utf8)
{
size_t bytes_left = offset;
while (bytes_left)
{
size_t mlen = mbrlen (beg, bytes_left, &mbs);
last_char = beg;
if (mlen == (size_t) -1 || mlen == 0)
{
/* Incomplete character: treat as single-byte. */
memset (&mbs, '\0', sizeof (mbstate_t));
beg++;
bytes_left--;
continue;
}
if (mlen == (size_t) -2)
/* Offset points inside multibyte character: no good. */
break;
beg += mlen;
bytes_left -= mlen;
}
if (bytes_left)
continue;
}
else
#endif /* MBS_SUPPORT */
beg += offset;
#ifdef MBS_SUPPORT
/* For f_i_multibyte, the string at beg now matches first 3 chars of
one of the search strings (less if there are shorter search strings).
See if this is a real match. */
if (f_i_multibyte
&& Fimbexec (beg, buf + size - beg, &kwsmatch.size[0], exact))
goto next_char;
#endif /* MBS_SUPPORT */
len = kwsmatch.size[0];
if (exact && !match_words)
goto success_in_beg_and_len;
if (match_lines)
{
if (beg > buf && beg[-1] != eol)
goto next_char;
if (beg + len < buf + size && beg[len] != eol)
goto next_char;
goto success;
}
else if (match_words)
{
while (1)
{
int word_match = 0;
if (beg > buf)
{
#ifdef MBS_SUPPORT
if (mb_cur_max > 1)
{
const char *s;
int mr;
wchar_t pwc;
if (using_utf8)
{
s = beg - 1;
while (s > buf
&& (unsigned char) *s >= 0x80
&& (unsigned char) *s <= 0xbf)
--s;
}
else
s = last_char;
mr = mbtowc (&pwc, s, beg - s);
if (mr <= 0)
memset (&mbs, '\0', sizeof (mbstate_t));
else if ((iswalnum (pwc) || pwc == L'_')
&& mr == (int) (beg - s))
goto next_char;
}
else
#endif /* MBS_SUPPORT */
if (!WCHAR ((unsigned char) beg[-1]))
goto next_char;
}
#ifdef MBS_SUPPORT
if (mb_cur_max > 1)
{
wchar_t nwc;
int mr;
mr = mbtowc (&nwc, beg + len, buf + size - beg - len);
if (mr <= 0)
{
memset (&mbs, '\0', sizeof (mbstate_t));
word_match = 1;
}
else if (!iswalnum (nwc) && nwc != L'_')
word_match = 1;
}
else
#endif /* MBS_SUPPORT */
if (beg + len >= buf + size && !WCHAR ((unsigned char) beg[len]))
word_match = 1;
if (word_match)
{
if (!exact)
/* Returns the whole line now we know there's a word match. */
goto success;
else
/* Returns just this word match. */
goto success_in_beg_and_len;
}
if (len > 0)
{
/* Try a shorter length anchored at the same place. */
--len;
offset = kwsexec (kwset, beg, len, &kwsmatch);
if (offset == -1)
goto next_char; /* Try a different anchor. */
#ifdef MBS_SUPPORT
if (mb_cur_max > 1 && !using_utf8)
{
size_t bytes_left = offset;
while (bytes_left)
{
size_t mlen = mbrlen (beg, bytes_left, &mbs);
last_char = beg;
if (mlen == (size_t) -1 || mlen == 0)
{
/* Incomplete character: treat as single-byte. */
memset (&mbs, '\0', sizeof (mbstate_t));
beg++;
bytes_left--;
continue;
}
if (mlen == (size_t) -2)
{
/* Offset points inside multibyte character:
* no good. */
break;
}
beg += mlen;
bytes_left -= mlen;
}
if (bytes_left)
{
memset (&mbs, '\0', sizeof (mbstate_t));
goto next_char; /* Try a different anchor. */
}
}
else
#endif /* MBS_SUPPORT */
beg += offset;
#ifdef MBS_SUPPORT
/* The string at beg now matches first 3 chars of one of
the search strings (less if there are shorter search
strings). See if this is a real match. */
if (f_i_multibyte
&& Fimbexec (beg, len - offset, &kwsmatch.size[0],
exact))
goto next_char;
#endif /* MBS_SUPPORT */
len = kwsmatch.size[0];
}
}
}
else
goto success;
next_char:;
#ifdef MBS_SUPPORT
/* Advance to next character. For MB_CUR_MAX == 1 case this is handled
by ++beg above. */
if (mb_cur_max > 1)
{
if (using_utf8)
{
unsigned char c = *beg;
if (c >= 0xc2)
{
if (c < 0xe0)
++beg;
else if (c < 0xf0)
beg += 2;
else if (c < 0xf8)
beg += 3;
else if (c < 0xfc)
beg += 4;
else if (c < 0xfe)
beg += 5;
}
}
else
{
size_t l = mbrlen (beg, buf + size - beg, &mbs);
last_char = beg;
if (l + 2 >= 2)
beg += l - 1;
else
memset (&mbs, '\0', sizeof (mbstate_t));
}
}
#endif /* MBS_SUPPORT */
}
failure:
return -1;
success:
#ifdef MBS_SUPPORT
if (mb_cur_max > 1 && !using_utf8)
{
end = beg + len;
while (end < buf + size)
{
size_t mlen = mbrlen (end, buf + size - end, &mbs);
if (mlen == (size_t) -1 || mlen == (size_t) -2 || mlen == 0)
{
memset (&mbs, '\0', sizeof (mbstate_t));
mlen = 1;
}
if (mlen == 1 && *end == eol)
break;
end += mlen;
}
}
else
#endif /* MBS_SUPPORT */
end = memchr (beg + len, eol, (buf + size) - (beg + len));
end++;
while (buf < beg && beg[-1] != eol)
--beg;
len = end - beg;
/* FALLTHROUGH */
success_in_beg_and_len:
*match_size = len;
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 },
};
|