-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathregex_internal.c
1744 lines (1583 loc) · 46.5 KB
/
regex_internal.c
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
/* Extended regular expression matching and search library.
Copyright (C) 2002-2006, 2010 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <[email protected]>.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, write to the Free
Software Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
02110-1301 USA. */
static void re_string_construct_common (const char *str, int len,
re_string_t *pstr,
RE_TRANSLATE_TYPE trans, int icase,
const re_dfa_t *dfa) internal_function;
static re_dfastate_t *create_ci_newstate (const re_dfa_t *dfa,
const re_node_set *nodes,
unsigned int hash) internal_function;
static re_dfastate_t *create_cd_newstate (const re_dfa_t *dfa,
const re_node_set *nodes,
unsigned int context,
unsigned int hash) internal_function;
#ifdef GAWK
#undef MAX /* safety */
static int
MAX(size_t a, size_t b)
{
return (a > b ? a : b);
}
#endif
/* Functions for string operation. */
/* This function allocate the buffers. It is necessary to call
re_string_reconstruct before using the object. */
static reg_errcode_t
internal_function
re_string_allocate (re_string_t *pstr, const char *str, int len, int init_len,
RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa)
{
reg_errcode_t ret;
int init_buf_len;
/* Ensure at least one character fits into the buffers. */
if (init_len < dfa->mb_cur_max)
init_len = dfa->mb_cur_max;
init_buf_len = (len + 1 < init_len) ? len + 1: init_len;
re_string_construct_common (str, len, pstr, trans, icase, dfa);
ret = re_string_realloc_buffers (pstr, init_buf_len);
if (BE (ret != REG_NOERROR, 0))
return ret;
pstr->word_char = dfa->word_char;
pstr->word_ops_used = dfa->word_ops_used;
pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str;
pstr->valid_len = (pstr->mbs_allocated || dfa->mb_cur_max > 1) ? 0 : len;
pstr->valid_raw_len = pstr->valid_len;
return REG_NOERROR;
}
/* This function allocate the buffers, and initialize them. */
static reg_errcode_t
internal_function
re_string_construct (re_string_t *pstr, const char *str, int len,
RE_TRANSLATE_TYPE trans, int icase, const re_dfa_t *dfa)
{
reg_errcode_t ret;
memset (pstr, '\0', sizeof (re_string_t));
re_string_construct_common (str, len, pstr, trans, icase, dfa);
if (len > 0)
{
ret = re_string_realloc_buffers (pstr, len + 1);
if (BE (ret != REG_NOERROR, 0))
return ret;
}
pstr->mbs = pstr->mbs_allocated ? pstr->mbs : (unsigned char *) str;
if (icase)
{
#ifdef RE_ENABLE_I18N
if (dfa->mb_cur_max > 1)
{
while (1)
{
ret = build_wcs_upper_buffer (pstr);
if (BE (ret != REG_NOERROR, 0))
return ret;
if (pstr->valid_raw_len >= len)
break;
if (pstr->bufs_len > pstr->valid_len + dfa->mb_cur_max)
break;
ret = re_string_realloc_buffers (pstr, pstr->bufs_len * 2);
if (BE (ret != REG_NOERROR, 0))
return ret;
}
}
else
#endif /* RE_ENABLE_I18N */
build_upper_buffer (pstr);
}
else
{
#ifdef RE_ENABLE_I18N
if (dfa->mb_cur_max > 1)
build_wcs_buffer (pstr);
else
#endif /* RE_ENABLE_I18N */
{
if (trans != NULL)
re_string_translate_buffer (pstr);
else
{
pstr->valid_len = pstr->bufs_len;
pstr->valid_raw_len = pstr->bufs_len;
}
}
}
return REG_NOERROR;
}
/* Helper functions for re_string_allocate, and re_string_construct. */
static reg_errcode_t
internal_function
re_string_realloc_buffers (re_string_t *pstr, int new_buf_len)
{
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1)
{
wint_t *new_wcs;
/* Avoid overflow in realloc. */
const size_t max_object_size = MAX (sizeof (wint_t), sizeof (int));
if (BE (SIZE_MAX / max_object_size < new_buf_len, 0))
return REG_ESPACE;
new_wcs = re_realloc (pstr->wcs, wint_t, new_buf_len);
if (BE (new_wcs == NULL, 0))
return REG_ESPACE;
pstr->wcs = new_wcs;
if (pstr->offsets != NULL)
{
int *new_offsets = re_realloc (pstr->offsets, int, new_buf_len);
if (BE (new_offsets == NULL, 0))
return REG_ESPACE;
pstr->offsets = new_offsets;
}
}
#endif /* RE_ENABLE_I18N */
if (pstr->mbs_allocated)
{
unsigned char *new_mbs = re_realloc (pstr->mbs, unsigned char,
new_buf_len);
if (BE (new_mbs == NULL, 0))
return REG_ESPACE;
pstr->mbs = new_mbs;
}
pstr->bufs_len = new_buf_len;
return REG_NOERROR;
}
static void
internal_function
re_string_construct_common (const char *str, int len, re_string_t *pstr,
RE_TRANSLATE_TYPE trans, int icase,
const re_dfa_t *dfa)
{
pstr->raw_mbs = (const unsigned char *) str;
pstr->len = len;
pstr->raw_len = len;
pstr->trans = trans;
pstr->icase = icase ? 1 : 0;
pstr->mbs_allocated = (trans != NULL || icase);
pstr->mb_cur_max = dfa->mb_cur_max;
pstr->is_utf8 = dfa->is_utf8;
pstr->map_notascii = dfa->map_notascii;
pstr->stop = pstr->len;
pstr->raw_stop = pstr->stop;
}
#ifdef RE_ENABLE_I18N
/* Build wide character buffer PSTR->WCS.
If the byte sequence of the string are:
<mb1>(0), <mb1>(1), <mb2>(0), <mb2>(1), <sb3>
Then wide character buffer will be:
<wc1> , WEOF , <wc2> , WEOF , <wc3>
We use WEOF for padding, they indicate that the position isn't
a first byte of a multibyte character.
Note that this function assumes PSTR->VALID_LEN elements are already
built and starts from PSTR->VALID_LEN. */
static void
internal_function
build_wcs_buffer (re_string_t *pstr)
{
#ifdef _LIBC
unsigned char buf[MB_LEN_MAX];
assert (MB_LEN_MAX >= pstr->mb_cur_max);
#else
unsigned char buf[64];
#endif
mbstate_t prev_st;
int byte_idx, end_idx, remain_len;
size_t mbclen;
/* Build the buffers from pstr->valid_len to either pstr->len or
pstr->bufs_len. */
end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len;
for (byte_idx = pstr->valid_len; byte_idx < end_idx;)
{
wchar_t wc;
const char *p;
remain_len = end_idx - byte_idx;
prev_st = pstr->cur_state;
/* Apply the translation if we need. */
if (BE (pstr->trans != NULL, 0))
{
int i, ch;
for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i)
{
ch = pstr->raw_mbs [pstr->raw_mbs_idx + byte_idx + i];
buf[i] = pstr->mbs[byte_idx + i] = pstr->trans[ch];
}
p = (const char *) buf;
}
else
p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx;
mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state);
if (BE (mbclen == (size_t) -2, 0))
{
/* The buffer doesn't have enough space, finish to build. */
pstr->cur_state = prev_st;
break;
}
else if (BE (mbclen == (size_t) -1 || mbclen == 0, 0))
{
/* We treat these cases as a singlebyte character. */
mbclen = 1;
wc = (wchar_t) pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx];
if (BE (pstr->trans != NULL, 0))
wc = pstr->trans[wc];
pstr->cur_state = prev_st;
}
/* Write wide character and padding. */
pstr->wcs[byte_idx++] = wc;
/* Write paddings. */
for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;)
pstr->wcs[byte_idx++] = WEOF;
}
pstr->valid_len = byte_idx;
pstr->valid_raw_len = byte_idx;
}
/* Build wide character buffer PSTR->WCS like build_wcs_buffer,
but for REG_ICASE. */
static reg_errcode_t
internal_function
build_wcs_upper_buffer (re_string_t *pstr)
{
mbstate_t prev_st;
int src_idx, byte_idx, end_idx, remain_len;
size_t mbclen;
#ifdef _LIBC
char buf[MB_LEN_MAX];
assert (MB_LEN_MAX >= pstr->mb_cur_max);
#else
char buf[64];
#endif
byte_idx = pstr->valid_len;
end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len;
/* The following optimization assumes that ASCII characters can be
mapped to wide characters with a simple cast. */
if (! pstr->map_notascii && pstr->trans == NULL && !pstr->offsets_needed)
{
while (byte_idx < end_idx)
{
wchar_t wc;
if (isascii (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx])
&& mbsinit (&pstr->cur_state))
{
/* In case of a singlebyte character. */
pstr->mbs[byte_idx]
= toupper (pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]);
/* The next step uses the assumption that wchar_t is encoded
ASCII-safe: all ASCII values can be converted like this. */
pstr->wcs[byte_idx] = (wchar_t) pstr->mbs[byte_idx];
++byte_idx;
continue;
}
remain_len = end_idx - byte_idx;
prev_st = pstr->cur_state;
mbclen = __mbrtowc (&wc,
((const char *) pstr->raw_mbs + pstr->raw_mbs_idx
+ byte_idx), remain_len, &pstr->cur_state);
if (BE (mbclen + 2 > 2, 1))
{
wchar_t wcu = wc;
if (iswlower (wc))
{
size_t mbcdlen;
wcu = towupper (wc);
mbcdlen = wcrtomb (buf, wcu, &prev_st);
if (BE (mbclen == mbcdlen, 1))
memcpy (pstr->mbs + byte_idx, buf, mbclen);
else
{
src_idx = byte_idx;
goto offsets_needed;
}
}
else
memcpy (pstr->mbs + byte_idx,
pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx, mbclen);
pstr->wcs[byte_idx++] = wcu;
/* Write paddings. */
for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;)
pstr->wcs[byte_idx++] = WEOF;
}
else if (mbclen == (size_t) -1 || mbclen == 0)
{
/* It is an invalid character or '\0'. Just use the byte. */
int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx];
pstr->mbs[byte_idx] = ch;
/* And also cast it to wide char. */
pstr->wcs[byte_idx++] = (wchar_t) ch;
if (BE (mbclen == (size_t) -1, 0))
pstr->cur_state = prev_st;
}
else
{
/* The buffer doesn't have enough space, finish to build. */
pstr->cur_state = prev_st;
break;
}
}
pstr->valid_len = byte_idx;
pstr->valid_raw_len = byte_idx;
return REG_NOERROR;
}
else
for (src_idx = pstr->valid_raw_len; byte_idx < end_idx;)
{
wchar_t wc;
const char *p;
offsets_needed:
remain_len = end_idx - byte_idx;
prev_st = pstr->cur_state;
if (BE (pstr->trans != NULL, 0))
{
int i, ch;
for (i = 0; i < pstr->mb_cur_max && i < remain_len; ++i)
{
ch = pstr->raw_mbs [pstr->raw_mbs_idx + src_idx + i];
buf[i] = pstr->trans[ch];
}
p = (const char *) buf;
}
else
p = (const char *) pstr->raw_mbs + pstr->raw_mbs_idx + src_idx;
mbclen = __mbrtowc (&wc, p, remain_len, &pstr->cur_state);
if (BE (mbclen + 2 > 2, 1))
{
wchar_t wcu = wc;
if (iswlower (wc))
{
size_t mbcdlen;
wcu = towupper (wc);
mbcdlen = wcrtomb ((char *) buf, wcu, &prev_st);
if (BE (mbclen == mbcdlen, 1))
memcpy (pstr->mbs + byte_idx, buf, mbclen);
else if (mbcdlen != (size_t) -1)
{
size_t i;
if (byte_idx + mbcdlen > pstr->bufs_len)
{
pstr->cur_state = prev_st;
break;
}
if (pstr->offsets == NULL)
{
pstr->offsets = re_malloc (int, pstr->bufs_len);
if (pstr->offsets == NULL)
return REG_ESPACE;
}
if (!pstr->offsets_needed)
{
for (i = 0; i < (size_t) byte_idx; ++i)
pstr->offsets[i] = i;
pstr->offsets_needed = 1;
}
memcpy (pstr->mbs + byte_idx, buf, mbcdlen);
pstr->wcs[byte_idx] = wcu;
pstr->offsets[byte_idx] = src_idx;
for (i = 1; i < mbcdlen; ++i)
{
pstr->offsets[byte_idx + i]
= src_idx + (i < mbclen ? i : mbclen - 1);
pstr->wcs[byte_idx + i] = WEOF;
}
pstr->len += mbcdlen - mbclen;
if (pstr->raw_stop > src_idx)
pstr->stop += mbcdlen - mbclen;
end_idx = (pstr->bufs_len > pstr->len)
? pstr->len : pstr->bufs_len;
byte_idx += mbcdlen;
src_idx += mbclen;
continue;
}
else
memcpy (pstr->mbs + byte_idx, p, mbclen);
}
else
memcpy (pstr->mbs + byte_idx, p, mbclen);
if (BE (pstr->offsets_needed != 0, 0))
{
size_t i;
for (i = 0; i < mbclen; ++i)
pstr->offsets[byte_idx + i] = src_idx + i;
}
src_idx += mbclen;
pstr->wcs[byte_idx++] = wcu;
/* Write paddings. */
for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;)
pstr->wcs[byte_idx++] = WEOF;
}
else if (mbclen == (size_t) -1 || mbclen == 0)
{
/* It is an invalid character or '\0'. Just use the byte. */
int ch = pstr->raw_mbs[pstr->raw_mbs_idx + src_idx];
if (BE (pstr->trans != NULL, 0))
ch = pstr->trans [ch];
pstr->mbs[byte_idx] = ch;
if (BE (pstr->offsets_needed != 0, 0))
pstr->offsets[byte_idx] = src_idx;
++src_idx;
/* And also cast it to wide char. */
pstr->wcs[byte_idx++] = (wchar_t) ch;
if (BE (mbclen == (size_t) -1, 0))
pstr->cur_state = prev_st;
}
else
{
/* The buffer doesn't have enough space, finish to build. */
pstr->cur_state = prev_st;
break;
}
}
pstr->valid_len = byte_idx;
pstr->valid_raw_len = src_idx;
return REG_NOERROR;
}
/* Skip characters until the index becomes greater than NEW_RAW_IDX.
Return the index. */
static int
internal_function
re_string_skip_chars (re_string_t *pstr, int new_raw_idx, wint_t *last_wc)
{
mbstate_t prev_st;
int rawbuf_idx;
size_t mbclen;
wint_t wc = WEOF;
/* Skip the characters which are not necessary to check. */
for (rawbuf_idx = pstr->raw_mbs_idx + pstr->valid_raw_len;
rawbuf_idx < new_raw_idx;)
{
wchar_t wc2;
int remain_len = pstr->len - rawbuf_idx;
prev_st = pstr->cur_state;
mbclen = __mbrtowc (&wc2, (const char *) pstr->raw_mbs + rawbuf_idx,
remain_len, &pstr->cur_state);
if (BE (mbclen == (size_t) -2 || mbclen == (size_t) -1 || mbclen == 0, 0))
{
/* We treat these cases as a single byte character. */
if (mbclen == 0 || remain_len == 0)
wc = L'\0';
else
wc = *(unsigned char *) (pstr->raw_mbs + rawbuf_idx);
mbclen = 1;
pstr->cur_state = prev_st;
}
else
wc = (wint_t) wc2;
/* Then proceed the next character. */
rawbuf_idx += mbclen;
}
*last_wc = (wint_t) wc;
return rawbuf_idx;
}
#endif /* RE_ENABLE_I18N */
/* Build the buffer PSTR->MBS, and apply the translation if we need.
This function is used in case of REG_ICASE. */
static void
internal_function
build_upper_buffer (re_string_t *pstr)
{
int char_idx, end_idx;
end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len;
for (char_idx = pstr->valid_len; char_idx < end_idx; ++char_idx)
{
int ch = pstr->raw_mbs[pstr->raw_mbs_idx + char_idx];
if (BE (pstr->trans != NULL, 0))
ch = pstr->trans[ch];
if (islower (ch))
pstr->mbs[char_idx] = toupper (ch);
else
pstr->mbs[char_idx] = ch;
}
pstr->valid_len = char_idx;
pstr->valid_raw_len = char_idx;
}
/* Apply TRANS to the buffer in PSTR. */
static void
internal_function
re_string_translate_buffer (re_string_t *pstr)
{
int buf_idx, end_idx;
end_idx = (pstr->bufs_len > pstr->len) ? pstr->len : pstr->bufs_len;
for (buf_idx = pstr->valid_len; buf_idx < end_idx; ++buf_idx)
{
int ch = pstr->raw_mbs[pstr->raw_mbs_idx + buf_idx];
pstr->mbs[buf_idx] = pstr->trans[ch];
}
pstr->valid_len = buf_idx;
pstr->valid_raw_len = buf_idx;
}
/* This function re-construct the buffers.
Concretely, convert to wide character in case of pstr->mb_cur_max > 1,
convert to upper case in case of REG_ICASE, apply translation. */
static reg_errcode_t
internal_function
re_string_reconstruct (re_string_t *pstr, int idx, int eflags)
{
int offset = idx - pstr->raw_mbs_idx;
if (BE (offset < 0, 0))
{
/* Reset buffer. */
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1)
memset (&pstr->cur_state, '\0', sizeof (mbstate_t));
#endif /* RE_ENABLE_I18N */
pstr->len = pstr->raw_len;
pstr->stop = pstr->raw_stop;
pstr->valid_len = 0;
pstr->raw_mbs_idx = 0;
pstr->valid_raw_len = 0;
pstr->offsets_needed = 0;
pstr->tip_context = ((eflags & REG_NOTBOL) ? CONTEXT_BEGBUF
: CONTEXT_NEWLINE | CONTEXT_BEGBUF);
if (!pstr->mbs_allocated)
pstr->mbs = (unsigned char *) pstr->raw_mbs;
offset = idx;
}
if (BE (offset != 0, 1))
{
/* Should the already checked characters be kept? */
if (BE (offset < pstr->valid_raw_len, 1))
{
/* Yes, move them to the front of the buffer. */
#ifdef RE_ENABLE_I18N
if (BE (pstr->offsets_needed, 0))
{
int low = 0, high = pstr->valid_len, mid;
do
{
mid = (high + low) / 2;
if (pstr->offsets[mid] > offset)
high = mid;
else if (pstr->offsets[mid] < offset)
low = mid + 1;
else
break;
}
while (low < high);
if (pstr->offsets[mid] < offset)
++mid;
pstr->tip_context = re_string_context_at (pstr, mid - 1,
eflags);
/* This can be quite complicated, so handle specially
only the common and easy case where the character with
different length representation of lower and upper
case is present at or after offset. */
if (pstr->valid_len > offset
&& mid == offset && pstr->offsets[mid] == offset)
{
memmove (pstr->wcs, pstr->wcs + offset,
(pstr->valid_len - offset) * sizeof (wint_t));
memmove (pstr->mbs, pstr->mbs + offset, pstr->valid_len - offset);
pstr->valid_len -= offset;
pstr->valid_raw_len -= offset;
for (low = 0; low < pstr->valid_len; low++)
pstr->offsets[low] = pstr->offsets[low + offset] - offset;
}
else
{
/* Otherwise, just find out how long the partial multibyte
character at offset is and fill it with WEOF/255. */
pstr->len = pstr->raw_len - idx + offset;
pstr->stop = pstr->raw_stop - idx + offset;
pstr->offsets_needed = 0;
while (mid > 0 && pstr->offsets[mid - 1] == offset)
--mid;
while (mid < pstr->valid_len)
if (pstr->wcs[mid] != WEOF)
break;
else
++mid;
if (mid == pstr->valid_len)
pstr->valid_len = 0;
else
{
pstr->valid_len = pstr->offsets[mid] - offset;
if (pstr->valid_len)
{
for (low = 0; low < pstr->valid_len; ++low)
pstr->wcs[low] = WEOF;
memset (pstr->mbs, 255, pstr->valid_len);
}
}
pstr->valid_raw_len = pstr->valid_len;
}
}
else
#endif
{
pstr->tip_context = re_string_context_at (pstr, offset - 1,
eflags);
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1)
memmove (pstr->wcs, pstr->wcs + offset,
(pstr->valid_len - offset) * sizeof (wint_t));
#endif /* RE_ENABLE_I18N */
if (BE (pstr->mbs_allocated, 0))
memmove (pstr->mbs, pstr->mbs + offset,
pstr->valid_len - offset);
pstr->valid_len -= offset;
pstr->valid_raw_len -= offset;
#if DEBUG
assert (pstr->valid_len > 0);
#endif
}
}
else
{
#ifdef RE_ENABLE_I18N
/* No, skip all characters until IDX. */
int prev_valid_len = pstr->valid_len;
if (BE (pstr->offsets_needed, 0))
{
pstr->len = pstr->raw_len - idx + offset;
pstr->stop = pstr->raw_stop - idx + offset;
pstr->offsets_needed = 0;
}
#endif
pstr->valid_len = 0;
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1)
{
int wcs_idx;
wint_t wc = WEOF;
if (pstr->is_utf8)
{
const unsigned char *raw, *p, *end;
/* Special case UTF-8. Multi-byte chars start with any
byte other than 0x80 - 0xbf. */
raw = pstr->raw_mbs + pstr->raw_mbs_idx;
end = raw + (offset - pstr->mb_cur_max);
if (end < pstr->raw_mbs)
end = pstr->raw_mbs;
p = raw + offset - 1;
#ifdef _LIBC
/* We know the wchar_t encoding is UCS4, so for the simple
case, ASCII characters, skip the conversion step. */
if (isascii (*p) && BE (pstr->trans == NULL, 1))
{
memset (&pstr->cur_state, '\0', sizeof (mbstate_t));
/* pstr->valid_len = 0; */
wc = (wchar_t) *p;
}
else
#endif
for (; p >= end; --p)
if ((*p & 0xc0) != 0x80)
{
mbstate_t cur_state;
wchar_t wc2;
int mlen = raw + pstr->len - p;
unsigned char buf[6];
size_t mbclen;
if (BE (pstr->trans != NULL, 0))
{
int i = mlen < 6 ? mlen : 6;
while (--i >= 0)
buf[i] = pstr->trans[p[i]];
}
/* XXX Don't use mbrtowc, we know which conversion
to use (UTF-8 -> UCS4). */
memset (&cur_state, 0, sizeof (cur_state));
mbclen = __mbrtowc (&wc2, (const char *) p, mlen,
&cur_state);
if (raw + offset - p <= mbclen
&& mbclen < (size_t) -2)
{
memset (&pstr->cur_state, '\0',
sizeof (mbstate_t));
pstr->valid_len = mbclen - (raw + offset - p);
wc = wc2;
}
break;
}
}
if (wc == WEOF)
pstr->valid_len = re_string_skip_chars (pstr, idx, &wc) - idx;
if (wc == WEOF)
pstr->tip_context
= re_string_context_at (pstr, prev_valid_len - 1, eflags);
else
pstr->tip_context = ((BE (pstr->word_ops_used != 0, 0)
&& IS_WIDE_WORD_CHAR (wc))
? CONTEXT_WORD
: ((IS_WIDE_NEWLINE (wc)
&& pstr->newline_anchor)
? CONTEXT_NEWLINE : 0));
if (BE (pstr->valid_len, 0))
{
for (wcs_idx = 0; wcs_idx < pstr->valid_len; ++wcs_idx)
pstr->wcs[wcs_idx] = WEOF;
if (pstr->mbs_allocated)
memset (pstr->mbs, 255, pstr->valid_len);
}
pstr->valid_raw_len = pstr->valid_len;
}
else
#endif /* RE_ENABLE_I18N */
{
int c = pstr->raw_mbs[pstr->raw_mbs_idx + offset - 1];
pstr->valid_raw_len = 0;
if (pstr->trans)
c = pstr->trans[c];
pstr->tip_context = (bitset_contain (pstr->word_char, c)
? CONTEXT_WORD
: ((IS_NEWLINE (c) && pstr->newline_anchor)
? CONTEXT_NEWLINE : 0));
}
}
if (!BE (pstr->mbs_allocated, 0))
pstr->mbs += offset;
}
pstr->raw_mbs_idx = idx;
pstr->len -= offset;
pstr->stop -= offset;
/* Then build the buffers. */
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1)
{
if (pstr->icase)
{
reg_errcode_t ret = build_wcs_upper_buffer (pstr);
if (BE (ret != REG_NOERROR, 0))
return ret;
}
else
build_wcs_buffer (pstr);
}
else
#endif /* RE_ENABLE_I18N */
if (BE (pstr->mbs_allocated, 0))
{
if (pstr->icase)
build_upper_buffer (pstr);
else if (pstr->trans != NULL)
re_string_translate_buffer (pstr);
}
else
pstr->valid_len = pstr->len;
pstr->cur_idx = 0;
return REG_NOERROR;
}
static unsigned char
internal_function __attribute ((pure))
re_string_peek_byte_case (const re_string_t *pstr, int idx)
{
int ch, off;
/* Handle the common (easiest) cases first. */
if (BE (!pstr->mbs_allocated, 1))
return re_string_peek_byte (pstr, idx);
#ifdef RE_ENABLE_I18N
if (pstr->mb_cur_max > 1
&& ! re_string_is_single_byte_char (pstr, pstr->cur_idx + idx))
return re_string_peek_byte (pstr, idx);
#endif
off = pstr->cur_idx + idx;
#ifdef RE_ENABLE_I18N
if (pstr->offsets_needed)
off = pstr->offsets[off];
#endif
ch = pstr->raw_mbs[pstr->raw_mbs_idx + off];
#ifdef RE_ENABLE_I18N
/* Ensure that e.g. for tr_TR.UTF-8 BACKSLASH DOTLESS SMALL LETTER I
this function returns CAPITAL LETTER I instead of first byte of
DOTLESS SMALL LETTER I. The latter would confuse the parser,
since peek_byte_case doesn't advance cur_idx in any way. */
if (pstr->offsets_needed && !isascii (ch))
return re_string_peek_byte (pstr, idx);
#endif
return ch;
}
static unsigned char
internal_function __attribute ((pure))
re_string_fetch_byte_case (re_string_t *pstr)
{
if (BE (!pstr->mbs_allocated, 1))
return re_string_fetch_byte (pstr);
#ifdef RE_ENABLE_I18N
if (pstr->offsets_needed)
{
int off, ch;
/* For tr_TR.UTF-8 [[:islower:]] there is
[[: CAPITAL LETTER I WITH DOT lower:]] in mbs. Skip
in that case the whole multi-byte character and return
the original letter. On the other side, with
[[: DOTLESS SMALL LETTER I return [[:I, as doing
anything else would complicate things too much. */
if (!re_string_first_byte (pstr, pstr->cur_idx))
return re_string_fetch_byte (pstr);
off = pstr->offsets[pstr->cur_idx];
ch = pstr->raw_mbs[pstr->raw_mbs_idx + off];
if (! isascii (ch))
return re_string_fetch_byte (pstr);
re_string_skip_bytes (pstr,
re_string_char_size_at (pstr, pstr->cur_idx));
return ch;
}
#endif
return pstr->raw_mbs[pstr->raw_mbs_idx + pstr->cur_idx++];
}
static void
internal_function
re_string_destruct (re_string_t *pstr)
{
#ifdef RE_ENABLE_I18N
re_free (pstr->wcs);
re_free (pstr->offsets);
#endif /* RE_ENABLE_I18N */
if (pstr->mbs_allocated)
re_free (pstr->mbs);
}
/* Return the context at IDX in INPUT. */
static unsigned int
internal_function
re_string_context_at (const re_string_t *input, int idx, int eflags)
{
int c;
if (BE (idx < 0, 0))
/* In this case, we use the value stored in input->tip_context,
since we can't know the character in input->mbs[-1] here. */
return input->tip_context;
if (BE (idx == input->len, 0))
return ((eflags & REG_NOTEOL) ? CONTEXT_ENDBUF
: CONTEXT_NEWLINE | CONTEXT_ENDBUF);
#ifdef RE_ENABLE_I18N
if (input->mb_cur_max > 1)
{
wint_t wc;
int wc_idx = idx;
while(input->wcs[wc_idx] == WEOF)
{
#ifdef DEBUG
/* It must not happen. */
assert (wc_idx >= 0);
#endif
--wc_idx;
if (wc_idx < 0)
return input->tip_context;
}
wc = input->wcs[wc_idx];
if (BE (input->word_ops_used != 0, 0) && IS_WIDE_WORD_CHAR (wc))
return CONTEXT_WORD;
return (IS_WIDE_NEWLINE (wc) && input->newline_anchor
? CONTEXT_NEWLINE : 0);
}
else
#endif
{
c = re_string_byte_at (input, idx);
if (bitset_contain (input->word_char, c))
return CONTEXT_WORD;
return IS_NEWLINE (c) && input->newline_anchor ? CONTEXT_NEWLINE : 0;
}
}
/* Functions for set operation. */
static reg_errcode_t
internal_function
re_node_set_alloc (re_node_set *set, int size)
{
/*
* ADR: valgrind says size can be 0, which then doesn't
* free the block of size 0. Harumph. This seems
* to work ok, though.
*/
if (size == 0)
{
memset(set, 0, sizeof(*set));
return REG_NOERROR;
}
set->alloc = size;
set->nelem = 0;
set->elems = re_malloc (int, size);
if (BE (set->elems == NULL, 0))
return REG_ESPACE;
return REG_NOERROR;
}
static reg_errcode_t
internal_function
re_node_set_init_1 (re_node_set *set, int elem)
{
set->alloc = 1;
set->nelem = 1;
set->elems = re_malloc (int, 1);
if (BE (set->elems == NULL, 0))
{
set->alloc = set->nelem = 0;