forked from php/php-src
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathpcre2_convert.c
1182 lines (951 loc) · 30.2 KB
/
pcre2_convert.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
/*************************************************
* Perl-Compatible Regular Expressions *
*************************************************/
/* PCRE is a library of functions to support regular expressions whose syntax
and semantics are as close as possible to those of the Perl 5 language.
Written by Philip Hazel
Original API code Copyright (c) 1997-2012 University of Cambridge
New API code Copyright (c) 2016-2018 University of Cambridge
-----------------------------------------------------------------------------
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the University of Cambridge nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
POSSIBILITY OF SUCH DAMAGE.
-----------------------------------------------------------------------------
*/
#ifdef HAVE_CONFIG_H
#include "config.h"
#endif
#include "pcre2_internal.h"
#define TYPE_OPTIONS (PCRE2_CONVERT_GLOB| \
PCRE2_CONVERT_POSIX_BASIC|PCRE2_CONVERT_POSIX_EXTENDED)
#define ALL_OPTIONS (PCRE2_CONVERT_UTF|PCRE2_CONVERT_NO_UTF_CHECK| \
PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR| \
PCRE2_CONVERT_GLOB_NO_STARSTAR| \
TYPE_OPTIONS)
#define DUMMY_BUFFER_SIZE 100
/* Generated pattern fragments */
#define STR_BACKSLASH_A STR_BACKSLASH STR_A
#define STR_BACKSLASH_z STR_BACKSLASH STR_z
#define STR_COLON_RIGHT_SQUARE_BRACKET STR_COLON STR_RIGHT_SQUARE_BRACKET
#define STR_DOT_STAR_LOOKBEHIND STR_DOT STR_ASTERISK STR_LEFT_PARENTHESIS STR_QUESTION_MARK STR_LESS_THAN_SIGN STR_EQUALS_SIGN
#define STR_LOOKAHEAD_NOT_DOT STR_LEFT_PARENTHESIS STR_QUESTION_MARK STR_EXCLAMATION_MARK STR_BACKSLASH STR_DOT STR_RIGHT_PARENTHESIS
#define STR_QUERY_s STR_LEFT_PARENTHESIS STR_QUESTION_MARK STR_s STR_RIGHT_PARENTHESIS
#define STR_STAR_NUL STR_LEFT_PARENTHESIS STR_ASTERISK STR_N STR_U STR_L STR_RIGHT_PARENTHESIS
/* States for range and POSIX processing */
enum { RANGE_NOT_STARTED, RANGE_STARTING, RANGE_STARTED };
enum { POSIX_START_REGEX, POSIX_ANCHORED, POSIX_NOT_BRACKET,
POSIX_CLASS_NOT_STARTED, POSIX_CLASS_STARTING, POSIX_CLASS_STARTED };
/* Macro to add a character string to the output buffer, checking for overflow. */
#define PUTCHARS(string) \
{ \
for (s = (char *)(string); *s != 0; s++) \
{ \
if (p >= endp) return PCRE2_ERROR_NOMEMORY; \
*p++ = *s; \
} \
}
/* Literals that must be escaped: \ ? * + | . ^ $ { } [ ] ( ) */
static const char *pcre2_escaped_literals =
STR_BACKSLASH STR_QUESTION_MARK STR_ASTERISK STR_PLUS
STR_VERTICAL_LINE STR_DOT STR_CIRCUMFLEX_ACCENT STR_DOLLAR_SIGN
STR_LEFT_CURLY_BRACKET STR_RIGHT_CURLY_BRACKET
STR_LEFT_SQUARE_BRACKET STR_RIGHT_SQUARE_BRACKET
STR_LEFT_PARENTHESIS STR_RIGHT_PARENTHESIS;
/* Recognized escaped metacharacters in POSIX basic patterns. */
static const char *posix_meta_escapes =
STR_LEFT_PARENTHESIS STR_RIGHT_PARENTHESIS
STR_LEFT_CURLY_BRACKET STR_RIGHT_CURLY_BRACKET
STR_1 STR_2 STR_3 STR_4 STR_5 STR_6 STR_7 STR_8 STR_9;
/*************************************************
* Convert a POSIX pattern *
*************************************************/
/* This function handles both basic and extended POSIX patterns.
Arguments:
pattype the pattern type
pattern the pattern
plength length in code units
utf TRUE if UTF
use_buffer where to put the output
use_length length of use_buffer
bufflenptr where to put the used length
dummyrun TRUE if a dummy run
ccontext the convert context
Returns: 0 => success
!0 => error code
*/
static int
convert_posix(uint32_t pattype, PCRE2_SPTR pattern, PCRE2_SIZE plength,
BOOL utf, PCRE2_UCHAR *use_buffer, PCRE2_SIZE use_length,
PCRE2_SIZE *bufflenptr, BOOL dummyrun, pcre2_convert_context *ccontext)
{
char *s;
PCRE2_SPTR posix = pattern;
PCRE2_UCHAR *p = use_buffer;
PCRE2_UCHAR *pp = p;
PCRE2_UCHAR *endp = p + use_length - 1; /* Allow for trailing zero */
PCRE2_SIZE convlength = 0;
uint32_t bracount = 0;
uint32_t posix_state = POSIX_START_REGEX;
uint32_t lastspecial = 0;
BOOL extended = (pattype & PCRE2_CONVERT_POSIX_EXTENDED) != 0;
BOOL nextisliteral = FALSE;
(void)utf; /* Not used when Unicode not supported */
(void)ccontext; /* Not currently used */
/* Initialize default for error offset as end of input. */
*bufflenptr = plength;
PUTCHARS(STR_STAR_NUL);
/* Now scan the input. */
while (plength > 0)
{
uint32_t c, sc;
int clength = 1;
/* Add in the length of the last item, then, if in the dummy run, pull the
pointer back to the start of the (temporary) buffer and then remember the
start of the next item. */
convlength += p - pp;
if (dummyrun) p = use_buffer;
pp = p;
/* Pick up the next character */
#ifndef SUPPORT_UNICODE
c = *posix;
#else
GETCHARLENTEST(c, posix, clength);
#endif
posix += clength;
plength -= clength;
sc = nextisliteral? 0 : c;
nextisliteral = FALSE;
/* Handle a character within a class. */
if (posix_state >= POSIX_CLASS_NOT_STARTED)
{
if (c == CHAR_RIGHT_SQUARE_BRACKET)
{
PUTCHARS(STR_RIGHT_SQUARE_BRACKET);
posix_state = POSIX_NOT_BRACKET;
}
/* Not the end of the class */
else
{
switch (posix_state)
{
case POSIX_CLASS_STARTED:
if (c <= 127 && islower(c)) break; /* Remain in started state */
posix_state = POSIX_CLASS_NOT_STARTED;
if (c == CHAR_COLON && plength > 0 &&
*posix == CHAR_RIGHT_SQUARE_BRACKET)
{
PUTCHARS(STR_COLON_RIGHT_SQUARE_BRACKET);
plength--;
posix++;
continue; /* With next character after :] */
}
/* Fall through */
case POSIX_CLASS_NOT_STARTED:
if (c == CHAR_LEFT_SQUARE_BRACKET)
posix_state = POSIX_CLASS_STARTING;
break;
case POSIX_CLASS_STARTING:
if (c == CHAR_COLON) posix_state = POSIX_CLASS_STARTED;
break;
}
if (c == CHAR_BACKSLASH) PUTCHARS(STR_BACKSLASH);
if (p + clength > endp) return PCRE2_ERROR_NOMEMORY;
memcpy(p, posix - clength, CU2BYTES(clength));
p += clength;
}
}
/* Handle a character not within a class. */
else switch(sc)
{
case CHAR_LEFT_SQUARE_BRACKET:
PUTCHARS(STR_LEFT_SQUARE_BRACKET);
#ifdef NEVER
/* We could handle special cases [[:<:]] and [[:>:]] (which PCRE does
support) but they are not part of POSIX 1003.1. */
if (plength >= 6)
{
if (posix[0] == CHAR_LEFT_SQUARE_BRACKET &&
posix[1] == CHAR_COLON &&
(posix[2] == CHAR_LESS_THAN_SIGN ||
posix[2] == CHAR_GREATER_THAN_SIGN) &&
posix[3] == CHAR_COLON &&
posix[4] == CHAR_RIGHT_SQUARE_BRACKET &&
posix[5] == CHAR_RIGHT_SQUARE_BRACKET)
{
if (p + 6 > endp) return PCRE2_ERROR_NOMEMORY;
memcpy(p, posix, CU2BYTES(6));
p += 6;
posix += 6;
plength -= 6;
continue; /* With next character */
}
}
#endif
/* Handle start of "normal" character classes */
posix_state = POSIX_CLASS_NOT_STARTED;
/* Handle ^ and ] as first characters */
if (plength > 0)
{
if (*posix == CHAR_CIRCUMFLEX_ACCENT)
{
posix++;
plength--;
PUTCHARS(STR_CIRCUMFLEX_ACCENT);
}
if (plength > 0 && *posix == CHAR_RIGHT_SQUARE_BRACKET)
{
posix++;
plength--;
PUTCHARS(STR_RIGHT_SQUARE_BRACKET);
}
}
break;
case CHAR_BACKSLASH:
if (plength == 0) return PCRE2_ERROR_END_BACKSLASH;
if (extended) nextisliteral = TRUE; else
{
if (*posix < 127 && strchr(posix_meta_escapes, *posix) != NULL)
{
if (isdigit(*posix)) PUTCHARS(STR_BACKSLASH);
if (p + 1 > endp) return PCRE2_ERROR_NOMEMORY;
lastspecial = *p++ = *posix++;
plength--;
}
else nextisliteral = TRUE;
}
break;
case CHAR_RIGHT_PARENTHESIS:
if (!extended || bracount == 0) goto ESCAPE_LITERAL;
bracount--;
goto COPY_SPECIAL;
case CHAR_LEFT_PARENTHESIS:
bracount++;
/* Fall through */
case CHAR_QUESTION_MARK:
case CHAR_PLUS:
case CHAR_LEFT_CURLY_BRACKET:
case CHAR_RIGHT_CURLY_BRACKET:
case CHAR_VERTICAL_LINE:
if (!extended) goto ESCAPE_LITERAL;
/* Fall through */
case CHAR_DOT:
case CHAR_DOLLAR_SIGN:
posix_state = POSIX_NOT_BRACKET;
COPY_SPECIAL:
lastspecial = c;
if (p + 1 > endp) return PCRE2_ERROR_NOMEMORY;
*p++ = c;
break;
case CHAR_ASTERISK:
if (lastspecial != CHAR_ASTERISK)
{
if (!extended && (posix_state < POSIX_NOT_BRACKET ||
lastspecial == CHAR_LEFT_PARENTHESIS))
goto ESCAPE_LITERAL;
goto COPY_SPECIAL;
}
break; /* Ignore second and subsequent asterisks */
case CHAR_CIRCUMFLEX_ACCENT:
if (extended) goto COPY_SPECIAL;
if (posix_state == POSIX_START_REGEX ||
lastspecial == CHAR_LEFT_PARENTHESIS)
{
posix_state = POSIX_ANCHORED;
goto COPY_SPECIAL;
}
/* Fall through */
default:
if (c < 128 && strchr(pcre2_escaped_literals, c) != NULL)
{
ESCAPE_LITERAL:
PUTCHARS(STR_BACKSLASH);
}
lastspecial = 0xff; /* Indicates nothing special */
if (p + clength > endp) return PCRE2_ERROR_NOMEMORY;
memcpy(p, posix - clength, CU2BYTES(clength));
p += clength;
posix_state = POSIX_NOT_BRACKET;
break;
}
}
if (posix_state >= POSIX_CLASS_NOT_STARTED)
return PCRE2_ERROR_MISSING_SQUARE_BRACKET;
convlength += p - pp; /* Final segment */
*bufflenptr = convlength;
*p++ = 0;
return 0;
}
/*************************************************
* Convert a glob pattern *
*************************************************/
/* Context for writing the output into a buffer. */
typedef struct pcre2_output_context {
PCRE2_UCHAR *output; /* current output position */
PCRE2_SPTR output_end; /* output end */
PCRE2_SIZE output_size; /* size of the output */
uint8_t out_str[8]; /* string copied to the output */
} pcre2_output_context;
/* Write a character into the output.
Arguments:
out output context
chr the next character
*/
static void
convert_glob_write(pcre2_output_context *out, PCRE2_UCHAR chr)
{
out->output_size++;
if (out->output < out->output_end)
*out->output++ = chr;
}
/* Write a string into the output.
Arguments:
out output context
length length of out->out_str
*/
static void
convert_glob_write_str(pcre2_output_context *out, PCRE2_SIZE length)
{
uint8_t *out_str = out->out_str;
PCRE2_UCHAR *output = out->output;
PCRE2_SPTR output_end = out->output_end;
PCRE2_SIZE output_size = out->output_size;
do
{
output_size++;
if (output < output_end)
*output++ = *out_str++;
}
while (--length != 0);
out->output = output;
out->output_size = output_size;
}
/* Prints the separator into the output.
Arguments:
out output context
separator glob separator
with_escape backslash is needed before separator
*/
static void
convert_glob_print_separator(pcre2_output_context *out,
PCRE2_UCHAR separator, BOOL with_escape)
{
if (with_escape)
convert_glob_write(out, CHAR_BACKSLASH);
convert_glob_write(out, separator);
}
/* Prints a wildcard into the output.
Arguments:
out output context
separator glob separator
with_escape backslash is needed before separator
*/
static void
convert_glob_print_wildcard(pcre2_output_context *out,
PCRE2_UCHAR separator, BOOL with_escape)
{
out->out_str[0] = CHAR_LEFT_SQUARE_BRACKET;
out->out_str[1] = CHAR_CIRCUMFLEX_ACCENT;
convert_glob_write_str(out, 2);
convert_glob_print_separator(out, separator, with_escape);
convert_glob_write(out, CHAR_RIGHT_SQUARE_BRACKET);
}
/* Parse a posix class.
Arguments:
from starting point of scanning the range
pattern_end end of pattern
out output context
Returns: >0 => class index
0 => malformed class
*/
static int
convert_glob_parse_class(PCRE2_SPTR *from, PCRE2_SPTR pattern_end,
pcre2_output_context *out)
{
static const char *posix_classes = "alnum:alpha:ascii:blank:cntrl:digit:"
"graph:lower:print:punct:space:upper:word:xdigit:";
PCRE2_SPTR start = *from + 1;
PCRE2_SPTR pattern = start;
const char *class_ptr;
PCRE2_UCHAR c;
int class_index;
while (TRUE)
{
if (pattern >= pattern_end) return 0;
c = *pattern++;
if (c < CHAR_a || c > CHAR_z) break;
}
if (c != CHAR_COLON || pattern >= pattern_end ||
*pattern != CHAR_RIGHT_SQUARE_BRACKET)
return 0;
class_ptr = posix_classes;
class_index = 1;
while (TRUE)
{
if (*class_ptr == CHAR_NUL) return 0;
pattern = start;
while (*pattern == (PCRE2_UCHAR) *class_ptr)
{
if (*pattern == CHAR_COLON)
{
pattern += 2;
start -= 2;
do convert_glob_write(out, *start++); while (start < pattern);
*from = pattern;
return class_index;
}
pattern++;
class_ptr++;
}
while (*class_ptr != CHAR_COLON) class_ptr++;
class_ptr++;
class_index++;
}
}
/* Checks whether the character is in the class.
Arguments:
class_index class index
c character
Returns: !0 => character is found in the class
0 => otherwise
*/
static BOOL
convert_glob_char_in_class(int class_index, PCRE2_UCHAR c)
{
switch (class_index)
{
case 1: return isalnum(c);
case 2: return isalpha(c);
case 3: return 1;
case 4: return c == CHAR_HT || c == CHAR_SPACE;
case 5: return iscntrl(c);
case 6: return isdigit(c);
case 7: return isgraph(c);
case 8: return islower(c);
case 9: return isprint(c);
case 10: return ispunct(c);
case 11: return isspace(c);
case 12: return isupper(c);
case 13: return isalnum(c) || c == CHAR_UNDERSCORE;
default: return isxdigit(c);
}
}
/* Parse a range of characters.
Arguments:
from starting point of scanning the range
pattern_end end of pattern
out output context
separator glob separator
with_escape backslash is needed before separator
Returns: 0 => success
!0 => error code
*/
static int
convert_glob_parse_range(PCRE2_SPTR *from, PCRE2_SPTR pattern_end,
pcre2_output_context *out, BOOL utf, PCRE2_UCHAR separator,
BOOL with_escape, PCRE2_UCHAR escape, BOOL no_wildsep)
{
BOOL is_negative = FALSE;
BOOL separator_seen = FALSE;
BOOL has_prev_c;
PCRE2_SPTR pattern = *from;
PCRE2_SPTR char_start = NULL;
uint32_t c, prev_c;
int len, class_index;
(void)utf; /* Avoid compiler warning. */
if (pattern >= pattern_end)
{
*from = pattern;
return PCRE2_ERROR_MISSING_SQUARE_BRACKET;
}
if (*pattern == CHAR_EXCLAMATION_MARK
|| *pattern == CHAR_CIRCUMFLEX_ACCENT)
{
pattern++;
if (pattern >= pattern_end)
{
*from = pattern;
return PCRE2_ERROR_MISSING_SQUARE_BRACKET;
}
is_negative = TRUE;
out->out_str[0] = CHAR_LEFT_SQUARE_BRACKET;
out->out_str[1] = CHAR_CIRCUMFLEX_ACCENT;
len = 2;
if (!no_wildsep)
{
if (with_escape)
{
out->out_str[len] = CHAR_BACKSLASH;
len++;
}
out->out_str[len] = (uint8_t) separator;
}
convert_glob_write_str(out, len + 1);
}
else
convert_glob_write(out, CHAR_LEFT_SQUARE_BRACKET);
has_prev_c = FALSE;
prev_c = 0;
if (*pattern == CHAR_RIGHT_SQUARE_BRACKET)
{
out->out_str[0] = CHAR_BACKSLASH;
out->out_str[1] = CHAR_RIGHT_SQUARE_BRACKET;
convert_glob_write_str(out, 2);
has_prev_c = TRUE;
prev_c = CHAR_RIGHT_SQUARE_BRACKET;
pattern++;
}
while (pattern < pattern_end)
{
char_start = pattern;
GETCHARINCTEST(c, pattern);
if (c == CHAR_RIGHT_SQUARE_BRACKET)
{
convert_glob_write(out, c);
if (!is_negative && !no_wildsep && separator_seen)
{
out->out_str[0] = CHAR_LEFT_PARENTHESIS;
out->out_str[1] = CHAR_QUESTION_MARK;
out->out_str[2] = CHAR_LESS_THAN_SIGN;
out->out_str[3] = CHAR_EXCLAMATION_MARK;
convert_glob_write_str(out, 4);
convert_glob_print_separator(out, separator, with_escape);
convert_glob_write(out, CHAR_RIGHT_PARENTHESIS);
}
*from = pattern;
return 0;
}
if (pattern >= pattern_end) break;
if (c == CHAR_LEFT_SQUARE_BRACKET && *pattern == CHAR_COLON)
{
*from = pattern;
class_index = convert_glob_parse_class(from, pattern_end, out);
if (class_index != 0)
{
pattern = *from;
has_prev_c = FALSE;
prev_c = 0;
if (!is_negative &&
convert_glob_char_in_class (class_index, separator))
separator_seen = TRUE;
continue;
}
}
else if (c == CHAR_MINUS && has_prev_c &&
*pattern != CHAR_RIGHT_SQUARE_BRACKET)
{
convert_glob_write(out, CHAR_MINUS);
char_start = pattern;
GETCHARINCTEST(c, pattern);
if (pattern >= pattern_end) break;
if (escape != 0 && c == escape)
{
char_start = pattern;
GETCHARINCTEST(c, pattern);
}
else if (c == CHAR_LEFT_SQUARE_BRACKET && *pattern == CHAR_COLON)
{
*from = pattern;
return PCRE2_ERROR_CONVERT_SYNTAX;
}
if (prev_c > c)
{
*from = pattern;
return PCRE2_ERROR_CONVERT_SYNTAX;
}
if (prev_c < separator && separator < c) separator_seen = TRUE;
has_prev_c = FALSE;
prev_c = 0;
}
else
{
if (escape != 0 && c == escape)
{
char_start = pattern;
GETCHARINCTEST(c, pattern);
if (pattern >= pattern_end) break;
}
has_prev_c = TRUE;
prev_c = c;
}
if (c == CHAR_LEFT_SQUARE_BRACKET || c == CHAR_RIGHT_SQUARE_BRACKET ||
c == CHAR_BACKSLASH || c == CHAR_MINUS)
convert_glob_write(out, CHAR_BACKSLASH);
if (c == separator) separator_seen = TRUE;
do convert_glob_write(out, *char_start++); while (char_start < pattern);
}
*from = pattern;
return PCRE2_ERROR_MISSING_SQUARE_BRACKET;
}
/* Prints a (*COMMIT) into the output.
Arguments:
out output context
*/
static void
convert_glob_print_commit(pcre2_output_context *out)
{
out->out_str[0] = CHAR_LEFT_PARENTHESIS;
out->out_str[1] = CHAR_ASTERISK;
out->out_str[2] = CHAR_C;
out->out_str[3] = CHAR_O;
out->out_str[4] = CHAR_M;
out->out_str[5] = CHAR_M;
out->out_str[6] = CHAR_I;
out->out_str[7] = CHAR_T;
convert_glob_write_str(out, 8);
convert_glob_write(out, CHAR_RIGHT_PARENTHESIS);
}
/* Bash glob converter.
Arguments:
pattype the pattern type
pattern the pattern
plength length in code units
utf TRUE if UTF
use_buffer where to put the output
use_length length of use_buffer
bufflenptr where to put the used length
dummyrun TRUE if a dummy run
ccontext the convert context
Returns: 0 => success
!0 => error code
*/
static int
convert_glob(uint32_t options, PCRE2_SPTR pattern, PCRE2_SIZE plength,
BOOL utf, PCRE2_UCHAR *use_buffer, PCRE2_SIZE use_length,
PCRE2_SIZE *bufflenptr, BOOL dummyrun, pcre2_convert_context *ccontext)
{
pcre2_output_context out;
PCRE2_SPTR pattern_start = pattern;
PCRE2_SPTR pattern_end = pattern + plength;
PCRE2_UCHAR separator = ccontext->glob_separator;
PCRE2_UCHAR escape = ccontext->glob_escape;
PCRE2_UCHAR c;
BOOL no_wildsep = (options & PCRE2_CONVERT_GLOB_NO_WILD_SEPARATOR) != 0;
BOOL no_starstar = (options & PCRE2_CONVERT_GLOB_NO_STARSTAR) != 0;
BOOL in_atomic = FALSE;
BOOL after_starstar = FALSE;
BOOL no_slash_z = FALSE;
BOOL with_escape, is_start, after_separator;
int result = 0;
(void)utf; /* Avoid compiler warning. */
#ifdef SUPPORT_UNICODE
if (utf && (separator >= 128 || escape >= 128))
{
/* Currently only ASCII characters are supported. */
*bufflenptr = 0;
return PCRE2_ERROR_CONVERT_SYNTAX;
}
#endif
with_escape = strchr(pcre2_escaped_literals, separator) != NULL;
/* Initialize default for error offset as end of input. */
out.output = use_buffer;
out.output_end = use_buffer + use_length;
out.output_size = 0;
out.out_str[0] = CHAR_LEFT_PARENTHESIS;
out.out_str[1] = CHAR_QUESTION_MARK;
out.out_str[2] = CHAR_s;
out.out_str[3] = CHAR_RIGHT_PARENTHESIS;
convert_glob_write_str(&out, 4);
is_start = TRUE;
if (pattern < pattern_end && pattern[0] == CHAR_ASTERISK)
{
if (no_wildsep)
is_start = FALSE;
else if (!no_starstar && pattern + 1 < pattern_end &&
pattern[1] == CHAR_ASTERISK)
is_start = FALSE;
}
if (is_start)
{
out.out_str[0] = CHAR_BACKSLASH;
out.out_str[1] = CHAR_A;
convert_glob_write_str(&out, 2);
}
while (pattern < pattern_end)
{
c = *pattern++;
if (c == CHAR_ASTERISK)
{
is_start = pattern == pattern_start + 1;
if (in_atomic)
{
convert_glob_write(&out, CHAR_RIGHT_PARENTHESIS);
in_atomic = FALSE;
}
if (!no_starstar && pattern < pattern_end && *pattern == CHAR_ASTERISK)
{
after_separator = is_start || (pattern[-2] == separator);
do pattern++; while (pattern < pattern_end &&
*pattern == CHAR_ASTERISK);
if (pattern >= pattern_end)
{
no_slash_z = TRUE;
break;
}
after_starstar = TRUE;
if (after_separator && escape != 0 && *pattern == escape &&
pattern + 1 < pattern_end && pattern[1] == separator)
pattern++;
if (is_start)
{
if (*pattern != separator) continue;
out.out_str[0] = CHAR_LEFT_PARENTHESIS;
out.out_str[1] = CHAR_QUESTION_MARK;
out.out_str[2] = CHAR_COLON;
out.out_str[3] = CHAR_BACKSLASH;
out.out_str[4] = CHAR_A;
out.out_str[5] = CHAR_VERTICAL_LINE;
convert_glob_write_str(&out, 6);
convert_glob_print_separator(&out, separator, with_escape);
convert_glob_write(&out, CHAR_RIGHT_PARENTHESIS);
pattern++;
continue;
}
convert_glob_print_commit(&out);
if (!after_separator || *pattern != separator)
{
out.out_str[0] = CHAR_DOT;
out.out_str[1] = CHAR_ASTERISK;
out.out_str[2] = CHAR_QUESTION_MARK;
convert_glob_write_str(&out, 3);
continue;
}
out.out_str[0] = CHAR_LEFT_PARENTHESIS;
out.out_str[1] = CHAR_QUESTION_MARK;
out.out_str[2] = CHAR_COLON;
out.out_str[3] = CHAR_DOT;
out.out_str[4] = CHAR_ASTERISK;
out.out_str[5] = CHAR_QUESTION_MARK;
convert_glob_write_str(&out, 6);
convert_glob_print_separator(&out, separator, with_escape);
out.out_str[0] = CHAR_RIGHT_PARENTHESIS;
out.out_str[1] = CHAR_QUESTION_MARK;
out.out_str[2] = CHAR_QUESTION_MARK;
convert_glob_write_str(&out, 3);
pattern++;
continue;
}
if (pattern < pattern_end && *pattern == CHAR_ASTERISK)
{
do pattern++; while (pattern < pattern_end &&
*pattern == CHAR_ASTERISK);
}
if (no_wildsep)
{
if (pattern >= pattern_end)
{
no_slash_z = TRUE;
break;
}
/* Start check must be after the end check. */
if (is_start) continue;
}
if (!is_start)
{
if (after_starstar)
{
out.out_str[0] = CHAR_LEFT_PARENTHESIS;
out.out_str[1] = CHAR_QUESTION_MARK;
out.out_str[2] = CHAR_GREATER_THAN_SIGN;
convert_glob_write_str(&out, 3);
in_atomic = TRUE;
}
else
convert_glob_print_commit(&out);
}
if (no_wildsep)
convert_glob_write(&out, CHAR_DOT);
else
convert_glob_print_wildcard(&out, separator, with_escape);
out.out_str[0] = CHAR_ASTERISK;
out.out_str[1] = CHAR_QUESTION_MARK;
if (pattern >= pattern_end)
out.out_str[1] = CHAR_PLUS;
convert_glob_write_str(&out, 2);
continue;
}
if (c == CHAR_QUESTION_MARK)
{
if (no_wildsep)
convert_glob_write(&out, CHAR_DOT);
else
convert_glob_print_wildcard(&out, separator, with_escape);
continue;
}
if (c == CHAR_LEFT_SQUARE_BRACKET)
{
result = convert_glob_parse_range(&pattern, pattern_end,
&out, utf, separator, with_escape, escape, no_wildsep);
if (result != 0) break;
continue;
}
if (escape != 0 && c == escape)
{
if (pattern >= pattern_end)
{
result = PCRE2_ERROR_CONVERT_SYNTAX;
break;
}
c = *pattern++;
}