forked from github/codeql
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathregex.qll
More file actions
1006 lines (919 loc) · 32.1 KB
/
Copy pathregex.qll
File metadata and controls
1006 lines (919 loc) · 32.1 KB
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
import python
deprecated import semmle.python.objects.ObjectInternal as OI
private import semmle.python.ApiGraphs
/**
* Gets the positional argument index containing the regular expression flags for the member of the
* `re` module with the name `name`.
*/
private int re_member_flags_arg(string name) {
name = "compile" and result = 1
or
name = "search" and result = 2
or
name = "match" and result = 2
or
name = "split" and result = 3
or
name = "findall" and result = 2
or
name = "finditer" and result = 2
or
name = "sub" and result = 4
or
name = "subn" and result = 4
}
/**
* Gets the names and corresponding API nodes of members of the `re` module that are likely to be
* methods taking regular expressions as arguments.
*
* This is a helper predicate that fixes a bad join order, and should not be inlined without checking
* that this is safe.
*/
pragma[nomagic]
private API::Node relevant_re_member(string name) {
result = API::moduleImport("re").getMember(name) and
name != "escape"
}
/**
* Holds if `s` is used as a regex with the `re` module, with the regex-mode `mode` (if known).
* If regex mode is not known, `mode` will be `"None"`.
*/
predicate used_as_regex(Expr s, string mode) {
(s instanceof Bytes or s instanceof Unicode) and
/* Call to re.xxx(regex, ... [mode]) */
exists(DataFlow::CallCfgNode call, string name |
call.getArg(0).asExpr() = s and
call = relevant_re_member(name).getACall()
|
mode = "None"
or
mode = mode_from_node([call.getArg(re_member_flags_arg(name)), call.getArgByName("flags")])
)
}
/**
* Gets the canonical name for the API graph node corresponding to the `re` flag `flag`. For flags
* that have multiple names, we pick the long-form name as a canonical representative.
*/
private string canonical_name(API::Node flag) {
result in ["ASCII", "IGNORECASE", "LOCALE", "UNICODE", "MULTILINE", "TEMPLATE"] and
flag = API::moduleImport("re").getMember([result, result.prefix(1)])
or
flag = API::moduleImport("re").getMember(["DOTALL", "S"]) and result = "DOTALL"
or
flag = API::moduleImport("re").getMember(["VERBOSE", "X"]) and result = "VERBOSE"
}
/**
* A type tracker for regular expression flag names. Holds if the result is a node that may refer
* to the `re` flag with the canonical name `flag_name`
*/
private DataFlow::TypeTrackingNode re_flag_tracker(string flag_name, DataFlow::TypeTracker t) {
t.start() and
exists(API::Node flag | flag_name = canonical_name(flag) and result = flag.getAUse())
or
exists(BinaryExprNode binop, DataFlow::Node operand |
operand.getALocalSource() = re_flag_tracker(flag_name, t.continue()) and
operand.asCfgNode() = binop.getAnOperand() and
(binop.getOp() instanceof BitOr or binop.getOp() instanceof Add) and
result.asCfgNode() = binop
)
or
exists(DataFlow::TypeTracker t2 | result = re_flag_tracker(flag_name, t2).track(t2, t))
}
/**
* A type tracker for regular expression flag names. Holds if the result is a node that may refer
* to the `re` flag with the canonical name `flag_name`
*/
private DataFlow::Node re_flag_tracker(string flag_name) {
re_flag_tracker(flag_name, DataFlow::TypeTracker::end()).flowsTo(result)
}
/** Gets a regular expression mode flag associated with the given data flow node. */
string mode_from_node(DataFlow::Node node) { node = re_flag_tracker(result) }
/**
* DEPRECATED 2021-02-24 -- use `mode_from_node` instead.
*
* Gets a regular expression mode flag associated with the given value.
*/
deprecated string mode_from_mode_object(Value obj) {
result in ["DEBUG", "IGNORECASE", "LOCALE", "MULTILINE", "DOTALL", "UNICODE", "VERBOSE"] and
exists(int flag |
flag = Value::named("sre_constants.SRE_FLAG_" + result).(OI::ObjectInternal).intValue() and
obj.(OI::ObjectInternal).intValue().bitAnd(flag) = flag
)
}
/** A StrConst used as a regular expression */
abstract class RegexString extends Expr {
RegexString() { (this instanceof Bytes or this instanceof Unicode) }
/**
* Helper predicate for `char_set_start(int start, int end)`.
*
* In order to identify left brackets ('[') which actually start a character class,
* we perform a left to right scan of the string.
*
* To avoid negative recursion we return a boolean. See `escaping`,
* the helper for `escapingChar`, for a clean use of this pattern.
*
* result is true for those start chars that actually mark a start of a char set.
*/
boolean char_set_start(int pos) {
exists(int index |
// is opening bracket
this.char_set_delimiter(index, pos) = true and
(
// if this is the first bracket, `pos` starts a char set
index = 1 and result = true
or
// if the previous char set delimiter was not a closing bracket, `pos` does
// not start a char set. This is needed to handle cases such as `[[]` (a
// char set that matches the `[` char)
index > 1 and
not this.char_set_delimiter(index - 1, _) = false and
result = false
or
// special handling of cases such as `[][]` (the character-set of the characters `]` and `[`).
exists(int prev_closing_bracket_pos |
// previous bracket is a closing bracket
this.char_set_delimiter(index - 1, prev_closing_bracket_pos) = false and
if
// check if the character that comes before the previous closing bracket
// is an opening bracket (taking `^` into account)
exists(int pos_before_prev_closing_bracket |
if this.getChar(prev_closing_bracket_pos - 1) = "^"
then pos_before_prev_closing_bracket = prev_closing_bracket_pos - 2
else pos_before_prev_closing_bracket = prev_closing_bracket_pos - 1
|
this.char_set_delimiter(index - 2, pos_before_prev_closing_bracket) = true
)
then
// brackets without anything in between is not valid character ranges, so
// the first closing bracket in `[]]` and `[^]]` does not count,
//
// and we should _not_ mark the second opening bracket in `[][]` and `[^][]`
// as starting a new char set. ^ ^
exists(int pos_before_prev_closing_bracket |
this.char_set_delimiter(index - 2, pos_before_prev_closing_bracket) = true
|
result = this.char_set_start(pos_before_prev_closing_bracket).booleanNot()
)
else
// if not, `pos` does in fact mark a real start of a character range
result = true
)
)
)
}
/**
* Helper predicate for chars that could be character-set delimiters.
* Holds if the (non-escaped) char at `pos` in the string, is the (one-based) `index` occurrence of a bracket (`[` or `]`) in the string.
* Result if `true` is the char is `[`, and `false` if the char is `]`.
*/
boolean char_set_delimiter(int index, int pos) {
pos = rank[index](int p | this.nonEscapedCharAt(p) = "[" or this.nonEscapedCharAt(p) = "]") and
(
this.nonEscapedCharAt(pos) = "[" and result = true
or
this.nonEscapedCharAt(pos) = "]" and result = false
)
}
/** Hold is a character set starts between `start` and `end`. */
predicate char_set_start(int start, int end) {
this.char_set_start(start) = true and
(
this.getChar(start + 1) = "^" and end = start + 2
or
not this.getChar(start + 1) = "^" and end = start + 1
)
}
/** Whether there is a character class, between start (inclusive) and end (exclusive) */
predicate charSet(int start, int end) {
exists(int inner_start, int inner_end |
this.char_set_start(start, inner_start) and
not this.char_set_start(_, start)
|
end = inner_end + 1 and
inner_end > inner_start and
this.nonEscapedCharAt(inner_end) = "]" and
not exists(int mid | this.nonEscapedCharAt(mid) = "]" | mid > inner_start and mid < inner_end)
)
}
/** An indexed version of `char_set_token/3` */
private predicate char_set_token(int charset_start, int index, int token_start, int token_end) {
token_start =
rank[index](int start, int end | this.char_set_token(charset_start, start, end) | start) and
this.char_set_token(charset_start, token_start, token_end)
}
/** Either a char or a - */
private predicate char_set_token(int charset_start, int start, int end) {
this.char_set_start(charset_start, start) and
(
this.escapedCharacter(start, end)
or
exists(this.nonEscapedCharAt(start)) and end = start + 1
)
or
this.char_set_token(charset_start, _, start) and
(
this.escapedCharacter(start, end)
or
exists(this.nonEscapedCharAt(start)) and
end = start + 1 and
not this.getChar(start) = "]"
)
}
/**
* Holds if the character set starting at `charset_start` contains either
* a character or a range found between `start` and `end`.
*/
predicate char_set_child(int charset_start, int start, int end) {
this.char_set_token(charset_start, start, end) and
not exists(int range_start, int range_end |
this.charRange(charset_start, range_start, _, _, range_end) and
range_start <= start and
range_end >= end
)
or
this.charRange(charset_start, start, _, _, end)
}
/**
* Holds if the character set starting at `charset_start` contains a character range
* with lower bound found between `start` and `lower_end`
* and upper bound found between `upper_start` and `end`.
*/
predicate charRange(int charset_start, int start, int lower_end, int upper_start, int end) {
exists(int index |
this.charRangeEnd(charset_start, index) = true and
this.char_set_token(charset_start, index - 2, start, lower_end) and
this.char_set_token(charset_start, index, upper_start, end)
)
}
/**
* Helper predicate for `charRange`.
* We can determine where character ranges end by a left to right sweep.
*
* To avoid negative recursion we return a boolean. See `escaping`,
* the helper for `escapingChar`, for a clean use of this pattern.
*/
private boolean charRangeEnd(int charset_start, int index) {
this.char_set_token(charset_start, index, _, _) and
(
index in [1, 2] and result = false
or
index > 2 and
exists(int connector_start |
this.char_set_token(charset_start, index - 1, connector_start, _) and
this.nonEscapedCharAt(connector_start) = "-" and
result =
this.charRangeEnd(charset_start, index - 2)
.booleanNot()
.booleanAnd(this.charRangeEnd(charset_start, index - 1).booleanNot())
)
or
not exists(int connector_start |
this.char_set_token(charset_start, index - 1, connector_start, _) and
this.nonEscapedCharAt(connector_start) = "-"
) and
result = false
)
}
/** Holds if the character at `pos` is a "\" that is actually escaping what comes after. */
predicate escapingChar(int pos) { this.escaping(pos) = true }
/**
* Helper predicate for `escapingChar`.
* In order to avoid negative recusrion, we return a boolean.
* This way, we can refer to `escaping(pos - 1).booleanNot()`
* rather than to a negated version of `escaping(pos)`.
*/
private boolean escaping(int pos) {
pos = -1 and result = false
or
this.getChar(pos) = "\\" and result = this.escaping(pos - 1).booleanNot()
or
this.getChar(pos) != "\\" and result = false
}
/** Gets the text of this regex */
string getText() {
result = this.(Unicode).getS()
or
result = this.(Bytes).getS()
}
string getChar(int i) { result = this.getText().charAt(i) }
string nonEscapedCharAt(int i) {
result = this.getText().charAt(i) and
not exists(int x, int y | this.escapedCharacter(x, y) and i in [x .. y - 1])
}
private predicate isOptionDivider(int i) { this.nonEscapedCharAt(i) = "|" }
private predicate isGroupEnd(int i) { this.nonEscapedCharAt(i) = ")" and not this.inCharSet(i) }
private predicate isGroupStart(int i) { this.nonEscapedCharAt(i) = "(" and not this.inCharSet(i) }
predicate failedToParse(int i) {
exists(this.getChar(i)) and
not exists(int start, int end |
this.top_level(start, end) and
start <= i and
end > i
)
}
/** Named unicode characters, eg \N{degree sign} */
private predicate escapedName(int start, int end) {
this.escapingChar(start) and
this.getChar(start + 1) = "N" and
this.getChar(start + 2) = "{" and
this.getChar(end - 1) = "}" and
end > start and
not exists(int i | start + 2 < i and i < end - 1 | this.getChar(i) = "}")
}
/**
* Holds if an escaped character is found between `start` and `end`.
* Escaped characters include hex values, octal values and named escapes,
* but excludes backreferences.
*/
predicate escapedCharacter(int start, int end) {
this.escapingChar(start) and
not this.numbered_backreference(start, _, _) and
(
// hex value \xhh
this.getChar(start + 1) = "x" and end = start + 4
or
// octal value \o, \oo, or \ooo
end in [start + 2 .. start + 4] and
forall(int i | i in [start + 1 .. end - 1] | this.isOctal(i)) and
not (
end < start + 4 and
this.isOctal(end)
)
or
// 16-bit hex value \uhhhh
this.getChar(start + 1) = "u" and end = start + 6
or
// 32-bit hex value \Uhhhhhhhh
this.getChar(start + 1) = "U" and end = start + 10
or
this.escapedName(start, end)
or
// escape not handled above, update when adding a new case
not this.getChar(start + 1) in ["x", "u", "U", "N"] and
not exists(this.getChar(start + 1).toInt()) and
end = start + 2
)
}
pragma[inline]
private predicate isOctal(int index) { this.getChar(index) = [0 .. 7].toString() }
/** Holds if `index` is inside a character set. */
predicate inCharSet(int index) {
exists(int x, int y | this.charSet(x, y) and index in [x + 1 .. y - 2])
}
/**
* 'simple' characters are any that don't alter the parsing of the regex.
*/
private predicate simpleCharacter(int start, int end) {
end = start + 1 and
not this.charSet(start, _) and
not this.charSet(_, start + 1) and
exists(string c | c = this.getChar(start) |
exists(int x, int y, int z |
this.charSet(x, z) and
this.char_set_start(x, y)
|
start = y
or
start = z - 2
or
start > y and start < z - 2 and not this.charRange(_, _, start, end, _)
)
or
not this.inCharSet(start) and
not c = "(" and
not c = "[" and
not c = ")" and
not c = "|" and
not this.qualifier(start, _, _, _)
)
}
predicate character(int start, int end) {
(
this.simpleCharacter(start, end) and
not exists(int x, int y | this.escapedCharacter(x, y) and x <= start and y >= end)
or
this.escapedCharacter(start, end)
) and
not exists(int x, int y | this.group_start(x, y) and x <= start and y >= end) and
not exists(int x, int y | this.backreference(x, y) and x <= start and y >= end)
}
predicate normalCharacter(int start, int end) {
this.character(start, end) and
not this.specialCharacter(start, end, _)
}
predicate specialCharacter(int start, int end, string char) {
not this.inCharSet(start) and
this.character(start, end) and
(
end = start + 1 and
char = this.getChar(start) and
(char = "$" or char = "^" or char = ".")
or
end = start + 2 and
this.escapingChar(start) and
char = this.getText().substring(start, end) and
char = ["\\A", "\\Z", "\\b", "\\B"]
)
}
/** Whether the text in the range start,end is a group */
predicate group(int start, int end) {
this.groupContents(start, end, _, _)
or
this.emptyGroup(start, end)
}
/** Gets the number of the group in start,end */
int getGroupNumber(int start, int end) {
this.group(start, end) and
not this.non_capturing_group_start(start, _) and
result =
count(int i | this.group(i, _) and i < start and not this.non_capturing_group_start(i, _)) + 1
}
/** Gets the name, if it has one, of the group in start,end */
string getGroupName(int start, int end) {
this.group(start, end) and
exists(int name_end |
this.named_group_start(start, name_end) and
result = this.getText().substring(start + 4, name_end - 1)
)
}
/** Whether the text in the range start, end is a group and can match the empty string. */
predicate zeroWidthMatch(int start, int end) {
this.emptyGroup(start, end)
or
this.negativeAssertionGroup(start, end)
or
this.positiveLookaheadAssertionGroup(start, end)
or
this.positiveLookbehindAssertionGroup(start, end)
}
/** Holds if an empty group is found between `start` and `end`. */
predicate emptyGroup(int start, int end) {
exists(int endm1 | end = endm1 + 1 |
this.group_start(start, endm1) and
this.isGroupEnd(endm1)
)
}
private predicate emptyMatchAtStartGroup(int start, int end) {
this.emptyGroup(start, end)
or
this.negativeAssertionGroup(start, end)
or
this.positiveLookaheadAssertionGroup(start, end)
}
private predicate emptyMatchAtEndGroup(int start, int end) {
this.emptyGroup(start, end)
or
this.negativeAssertionGroup(start, end)
or
this.positiveLookbehindAssertionGroup(start, end)
}
private predicate negativeAssertionGroup(int start, int end) {
exists(int in_start |
this.negative_lookahead_assertion_start(start, in_start)
or
this.negative_lookbehind_assertion_start(start, in_start)
|
this.groupContents(start, end, in_start, _)
)
}
/** Holds if a negative lookahead is found between `start` and `end` */
predicate negativeLookaheadAssertionGroup(int start, int end) {
exists(int in_start | this.negative_lookahead_assertion_start(start, in_start) |
this.groupContents(start, end, in_start, _)
)
}
/** Holds if a negative lookbehind is found between `start` and `end` */
predicate negativeLookbehindAssertionGroup(int start, int end) {
exists(int in_start | this.negative_lookbehind_assertion_start(start, in_start) |
this.groupContents(start, end, in_start, _)
)
}
/** Holds if a positive lookahead is found between `start` and `end` */
predicate positiveLookaheadAssertionGroup(int start, int end) {
exists(int in_start | this.lookahead_assertion_start(start, in_start) |
this.groupContents(start, end, in_start, _)
)
}
/** Holds if a positive lookbehind is found between `start` and `end` */
predicate positiveLookbehindAssertionGroup(int start, int end) {
exists(int in_start | this.lookbehind_assertion_start(start, in_start) |
this.groupContents(start, end, in_start, _)
)
}
private predicate group_start(int start, int end) {
this.non_capturing_group_start(start, end)
or
this.flag_group_start(start, end, _)
or
this.named_group_start(start, end)
or
this.named_backreference_start(start, end)
or
this.lookahead_assertion_start(start, end)
or
this.negative_lookahead_assertion_start(start, end)
or
this.lookbehind_assertion_start(start, end)
or
this.negative_lookbehind_assertion_start(start, end)
or
this.comment_group_start(start, end)
or
this.simple_group_start(start, end)
}
private predicate non_capturing_group_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = ":" and
end = start + 3
}
private predicate simple_group_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) != "?" and
end = start + 1
}
private predicate named_group_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "P" and
this.getChar(start + 3) = "<" and
not this.getChar(start + 4) = "=" and
not this.getChar(start + 4) = "!" and
exists(int name_end |
name_end = min(int i | i > start + 4 and this.getChar(i) = ">") and
end = name_end + 1
)
}
private predicate named_backreference_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "P" and
this.getChar(start + 3) = "=" and
// Should this be looking for unescaped ")"?
// TODO: test this
end = min(int i | i > start + 4 and this.getChar(i) = "?")
}
private predicate flag_group_start(int start, int end, string c) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
end = start + 3 and
c = this.getChar(start + 2) and
c in ["i", "L", "m", "s", "u", "x"]
}
/**
* Gets the mode of this regular expression string if
* it is defined by a prefix.
*/
string getModeFromPrefix() {
exists(string c | this.flag_group_start(_, _, c) |
c = "i" and result = "IGNORECASE"
or
c = "L" and result = "LOCALE"
or
c = "m" and result = "MULTILINE"
or
c = "s" and result = "DOTALL"
or
c = "u" and result = "UNICODE"
or
c = "x" and result = "VERBOSE"
)
}
private predicate lookahead_assertion_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "=" and
end = start + 3
}
private predicate negative_lookahead_assertion_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "!" and
end = start + 3
}
private predicate lookbehind_assertion_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "<" and
this.getChar(start + 3) = "=" and
end = start + 4
}
private predicate negative_lookbehind_assertion_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "<" and
this.getChar(start + 3) = "!" and
end = start + 4
}
private predicate comment_group_start(int start, int end) {
this.isGroupStart(start) and
this.getChar(start + 1) = "?" and
this.getChar(start + 2) = "#" and
end = start + 3
}
predicate groupContents(int start, int end, int in_start, int in_end) {
this.group_start(start, in_start) and
end = in_end + 1 and
this.top_level(in_start, in_end) and
this.isGroupEnd(in_end)
}
private predicate named_backreference(int start, int end, string name) {
this.named_backreference_start(start, start + 4) and
end = min(int i | i > start + 4 and this.getChar(i) = ")") + 1 and
name = this.getText().substring(start + 4, end - 2)
}
private predicate numbered_backreference(int start, int end, int value) {
this.escapingChar(start) and
// starting with 0 makes it an octal escape
not this.getChar(start + 1) = "0" and
exists(string text, string svalue, int len |
end = start + len and
text = this.getText() and
len in [2 .. 3]
|
svalue = text.substring(start + 1, start + len) and
value = svalue.toInt() and
// value is composed of digits
forall(int i | i in [start + 1 .. start + len - 1] | this.getChar(i) = [0 .. 9].toString()) and
// a longer reference is not possible
not (
len = 2 and
exists(text.substring(start + 1, start + len + 1).toInt())
) and
// 3 octal digits makes it an octal escape
not forall(int i | i in [start + 1 .. start + 4] | this.isOctal(i))
// TODO: Inside a character set, all numeric escapes are treated as characters.
)
}
/** Whether the text in the range start,end is a back reference */
predicate backreference(int start, int end) {
this.numbered_backreference(start, end, _)
or
this.named_backreference(start, end, _)
}
/** Gets the number of the back reference in start,end */
int getBackrefNumber(int start, int end) { this.numbered_backreference(start, end, result) }
/** Gets the name, if it has one, of the back reference in start,end */
string getBackrefName(int start, int end) { this.named_backreference(start, end, result) }
private predicate baseItem(int start, int end) {
this.character(start, end) and
not exists(int x, int y | this.charSet(x, y) and x <= start and y >= end)
or
this.group(start, end)
or
this.charSet(start, end)
or
this.backreference(start, end)
}
private predicate qualifier(int start, int end, boolean maybe_empty, boolean may_repeat_forever) {
this.short_qualifier(start, end, maybe_empty, may_repeat_forever) and
not this.getChar(end) = "?"
or
exists(int short_end | this.short_qualifier(start, short_end, maybe_empty, may_repeat_forever) |
if this.getChar(short_end) = "?" then end = short_end + 1 else end = short_end
)
}
private predicate short_qualifier(
int start, int end, boolean maybe_empty, boolean may_repeat_forever
) {
(
this.getChar(start) = "+" and maybe_empty = false and may_repeat_forever = true
or
this.getChar(start) = "*" and maybe_empty = true and may_repeat_forever = true
or
this.getChar(start) = "?" and maybe_empty = true and may_repeat_forever = false
) and
end = start + 1
or
exists(string lower, string upper |
this.multiples(start, end, lower, upper) and
(if lower = "" or lower.toInt() = 0 then maybe_empty = true else maybe_empty = false) and
if upper = "" then may_repeat_forever = true else may_repeat_forever = false
)
}
/**
* Holds if a repetition quantifier is found between `start` and `end`,
* with the given lower and upper bounds. If a bound is omitted, the corresponding
* string is empty.
*/
predicate multiples(int start, int end, string lower, string upper) {
exists(string text, string match, string inner |
text = this.getText() and
end = start + match.length() and
inner = match.substring(1, match.length() - 1)
|
match = text.regexpFind("\\{[0-9]+\\}", _, start) and
lower = inner and
upper = lower
or
match = text.regexpFind("\\{[0-9]*,[0-9]*\\}", _, start) and
exists(int commaIndex |
commaIndex = inner.indexOf(",") and
lower = inner.prefix(commaIndex) and
upper = inner.suffix(commaIndex + 1)
)
)
}
/**
* Whether the text in the range start,end is a qualified item, where item is a character,
* a character set or a group.
*/
predicate qualifiedItem(int start, int end, boolean maybe_empty, boolean may_repeat_forever) {
this.qualifiedPart(start, _, end, maybe_empty, may_repeat_forever)
}
/**
* Holds if a qualified part is found between `start` and `part_end` and the qualifier is
* found between `part_end` and `end`.
*
* `maybe_empty` is true if the part is optional.
* `may_repeat_forever` is true if the part may be repeated unboundedly.
*/
predicate qualifiedPart(
int start, int part_end, int end, boolean maybe_empty, boolean may_repeat_forever
) {
this.baseItem(start, part_end) and
this.qualifier(part_end, end, maybe_empty, may_repeat_forever)
}
/** Holds if the range `start`, `end` contains a character, a quantifier, a character set or a group. */
predicate item(int start, int end) {
this.qualifiedItem(start, end, _, _)
or
this.baseItem(start, end) and not this.qualifier(end, _, _, _)
}
private predicate subsequence(int start, int end) {
(
start = 0 or
this.group_start(_, start) or
this.isOptionDivider(start - 1)
) and
this.item(start, end)
or
exists(int mid |
this.subsequence(start, mid) and
this.item(mid, end)
)
}
/**
* Whether the text in the range start,end is a sequence of 1 or more items, where an item is a character,
* a character set or a group.
*/
predicate sequence(int start, int end) {
this.sequenceOrQualified(start, end) and
not this.qualifiedItem(start, end, _, _)
}
private predicate sequenceOrQualified(int start, int end) {
this.subsequence(start, end) and
not this.item_start(end)
}
private predicate item_start(int start) {
this.character(start, _) or
this.isGroupStart(start) or
this.charSet(start, _) or
this.backreference(start, _)
}
private predicate item_end(int end) {
this.character(_, end)
or
exists(int endm1 | this.isGroupEnd(endm1) and end = endm1 + 1)
or
this.charSet(_, end)
or
this.qualifier(_, end, _, _)
}
private predicate top_level(int start, int end) {
this.subalternation(start, end, _) and
not this.isOptionDivider(end)
}
private predicate subalternation(int start, int end, int item_start) {
this.sequenceOrQualified(start, end) and
not this.isOptionDivider(start - 1) and
item_start = start
or
start = end and
not this.item_end(start) and
this.isOptionDivider(end) and
item_start = start
or
exists(int mid |
this.subalternation(start, mid, _) and
this.isOptionDivider(mid) and
item_start = mid + 1
|
this.sequenceOrQualified(item_start, end)
or
not this.item_start(end) and end = item_start
)
}
/**
* Whether the text in the range start,end is an alternation
*/
predicate alternation(int start, int end) {
this.top_level(start, end) and
exists(int less | this.subalternation(start, less, _) and less < end)
}
/**
* Whether the text in the range start,end is an alternation and the text in part_start, part_end is one of the
* options in that alternation.
*/
predicate alternationOption(int start, int end, int part_start, int part_end) {
this.alternation(start, end) and
this.subalternation(start, part_end, part_start)
}
/** A part of the regex that may match the start of the string. */
private predicate firstPart(int start, int end) {
start = 0 and end = this.getText().length()
or
exists(int x | this.firstPart(x, end) |
this.emptyMatchAtStartGroup(x, start) or
this.qualifiedItem(x, start, true, _) or
// ^ and \A match the start of the string
this.specialCharacter(x, start, ["^", "\\A"])
)
or
exists(int y | this.firstPart(start, y) |
this.item(start, end)
or
this.qualifiedPart(start, end, y, _, _)
)
or
exists(int x, int y | this.firstPart(x, y) |
this.groupContents(x, y, start, end)
or
this.alternationOption(x, y, start, end)
)
}
/** A part of the regex that may match the end of the string. */
private predicate lastPart(int start, int end) {
start = 0 and end = this.getText().length()
or
exists(int y | this.lastPart(start, y) |
this.emptyMatchAtEndGroup(end, y)
or
this.qualifiedItem(end, y, true, _)
or
// $ and \Z match the end of the string.
this.specialCharacter(end, y, ["$", "\\Z"])
)
or
exists(int x |
this.lastPart(x, end) and
this.item(start, end)
)
or
exists(int y | this.lastPart(start, y) | this.qualifiedPart(start, end, y, _, _))
or
exists(int x, int y | this.lastPart(x, y) |
this.groupContents(x, y, start, end)
or
this.alternationOption(x, y, start, end)
)
}
/**
* Whether the item at [start, end) is one of the first items
* to be matched.
*/
predicate firstItem(int start, int end) {
(
this.character(start, end)
or
this.qualifiedItem(start, end, _, _)
or
this.charSet(start, end)
) and
this.firstPart(start, end)
}
/**
* Whether the item at [start, end) is one of the last items
* to be matched.
*/
predicate lastItem(int start, int end) {
(
this.character(start, end)
or
this.qualifiedItem(start, end, _, _)
or
this.charSet(start, end)
) and
this.lastPart(start, end)
}
}
/** A StrConst used as a regular expression */
class Regex extends RegexString {
Regex() { used_as_regex(this, _) }
/**
* Gets a mode (if any) of this regular expression. Can be any of:
* DEBUG
* IGNORECASE
* LOCALE
* MULTILINE
* DOTALL
* UNICODE
* VERBOSE
*/
string getAMode() {