forked from golang/go
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathregexp.go
More file actions
1285 lines (1177 loc) · 37.7 KB
/
regexp.go
File metadata and controls
1285 lines (1177 loc) · 37.7 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
// Copyright 2009 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Package regexp implements regular expression search.
//
// The syntax of the regular expressions accepted is the same
// general syntax used by Perl, Python, and other languages.
// More precisely, it is the syntax accepted by RE2 and described at
// https://golang.org/s/re2syntax, except for \C.
// For an overview of the syntax, run
//
// go doc regexp/syntax
//
// The regexp implementation provided by this package is
// guaranteed to run in time linear in the size of the input.
// (This is a property not guaranteed by most open source
// implementations of regular expressions.) For more information
// about this property, see
//
// https://swtch.com/~rsc/regexp/regexp1.html
//
// or any book about automata theory.
//
// All characters are UTF-8-encoded code points.
// Following utf8.DecodeRune, each byte of an invalid UTF-8 sequence
// is treated as if it encoded utf8.RuneError (U+FFFD).
//
// There are 16 methods of Regexp that match a regular expression and identify
// the matched text. Their names are matched by this regular expression:
//
// Find(All)?(String)?(Submatch)?(Index)?
//
// If 'All' is present, the routine matches successive non-overlapping
// matches of the entire expression. Empty matches abutting a preceding
// match are ignored. The return value is a slice containing the successive
// return values of the corresponding non-'All' routine. These routines take
// an extra integer argument, n. If n >= 0, the function returns at most n
// matches/submatches; otherwise, it returns all of them.
//
// If 'String' is present, the argument is a string; otherwise it is a slice
// of bytes; return values are adjusted as appropriate.
//
// If 'Submatch' is present, the return value is a slice identifying the
// successive submatches of the expression. Submatches are matches of
// parenthesized subexpressions (also known as capturing groups) within the
// regular expression, numbered from left to right in order of opening
// parenthesis. Submatch 0 is the match of the entire expression, submatch 1 is
// the match of the first parenthesized subexpression, and so on.
//
// If 'Index' is present, matches and submatches are identified by byte index
// pairs within the input string: result[2*n:2*n+2] identifies the indexes of
// the nth submatch. The pair for n==0 identifies the match of the entire
// expression. If 'Index' is not present, the match is identified by the text
// of the match/submatch. If an index is negative or text is nil, it means that
// subexpression did not match any string in the input. For 'String' versions
// an empty string means either no match or an empty match.
//
// There is also a subset of the methods that can be applied to text read
// from a RuneReader:
//
// MatchReader, FindReaderIndex, FindReaderSubmatchIndex
//
// This set may grow. Note that regular expression matches may need to
// examine text beyond the text returned by a match, so the methods that
// match text from a RuneReader may read arbitrarily far into the input
// before returning.
//
// (There are a few other methods that do not match this pattern.)
package regexp
import (
"bytes"
"io"
"regexp/syntax"
"strconv"
"strings"
"sync"
"unicode"
"unicode/utf8"
)
// Regexp is the representation of a compiled regular expression.
// A Regexp is safe for concurrent use by multiple goroutines,
// except for configuration methods, such as Longest.
type Regexp struct {
expr string // as passed to Compile
prog *syntax.Prog // compiled program
onepass *onePassProg // onepass program or nil
numSubexp int
maxBitStateLen int
subexpNames []string
prefix string // required prefix in unanchored matches
prefixBytes []byte // prefix, as a []byte
prefixRune rune // first rune in prefix
prefixEnd uint32 // pc for last rune in prefix
mpool int // pool for machines
matchcap int // size of recorded match lengths
prefixComplete bool // prefix is the entire regexp
cond syntax.EmptyOp // empty-width conditions required at start of match
minInputLen int // minimum length of the input in bytes
// This field can be modified by the Longest method,
// but it is otherwise read-only.
longest bool // whether regexp prefers leftmost-longest match
}
// String returns the source text used to compile the regular expression.
func (re *Regexp) String() string {
return re.expr
}
// Copy returns a new Regexp object copied from re.
// Calling Longest on one copy does not affect another.
//
// Deprecated: In earlier releases, when using a Regexp in multiple goroutines,
// giving each goroutine its own copy helped to avoid lock contention.
// As of Go 1.12, using Copy is no longer necessary to avoid lock contention.
// Copy may still be appropriate if the reason for its use is to make
// two copies with different Longest settings.
func (re *Regexp) Copy() *Regexp {
re2 := *re
return &re2
}
// Compile parses a regular expression and returns, if successful,
// a Regexp object that can be used to match against text.
//
// When matching against text, the regexp returns a match that
// begins as early as possible in the input (leftmost), and among those
// it chooses the one that a backtracking search would have found first.
// This so-called leftmost-first matching is the same semantics
// that Perl, Python, and other implementations use, although this
// package implements it without the expense of backtracking.
// For POSIX leftmost-longest matching, see CompilePOSIX.
func Compile(expr string) (*Regexp, error) {
return compile(expr, syntax.Perl, false)
}
// CompilePOSIX is like Compile but restricts the regular expression
// to POSIX ERE (egrep) syntax and changes the match semantics to
// leftmost-longest.
//
// That is, when matching against text, the regexp returns a match that
// begins as early as possible in the input (leftmost), and among those
// it chooses a match that is as long as possible.
// This so-called leftmost-longest matching is the same semantics
// that early regular expression implementations used and that POSIX
// specifies.
//
// However, there can be multiple leftmost-longest matches, with different
// submatch choices, and here this package diverges from POSIX.
// Among the possible leftmost-longest matches, this package chooses
// the one that a backtracking search would have found first, while POSIX
// specifies that the match be chosen to maximize the length of the first
// subexpression, then the second, and so on from left to right.
// The POSIX rule is computationally prohibitive and not even well-defined.
// See https://swtch.com/~rsc/regexp/regexp2.html#posix for details.
func CompilePOSIX(expr string) (*Regexp, error) {
return compile(expr, syntax.POSIX, true)
}
// Longest makes future searches prefer the leftmost-longest match.
// That is, when matching against text, the regexp returns a match that
// begins as early as possible in the input (leftmost), and among those
// it chooses a match that is as long as possible.
// This method modifies the Regexp and may not be called concurrently
// with any other methods.
func (re *Regexp) Longest() {
re.longest = true
}
func compile(expr string, mode syntax.Flags, longest bool) (*Regexp, error) {
re, err := syntax.Parse(expr, mode)
if err != nil {
return nil, err
}
maxCap := re.MaxCap()
capNames := re.CapNames()
re = re.Simplify()
prog, err := syntax.Compile(re)
if err != nil {
return nil, err
}
matchcap := prog.NumCap
if matchcap < 2 {
matchcap = 2
}
regexp := &Regexp{
expr: expr,
prog: prog,
onepass: compileOnePass(prog),
numSubexp: maxCap,
subexpNames: capNames,
cond: prog.StartCond(),
longest: longest,
matchcap: matchcap,
minInputLen: minInputLen(re),
}
if regexp.onepass == nil {
regexp.prefix, regexp.prefixComplete = prog.Prefix()
regexp.maxBitStateLen = maxBitStateLen(prog)
} else {
regexp.prefix, regexp.prefixComplete, regexp.prefixEnd = onePassPrefix(prog)
}
if regexp.prefix != "" {
// TODO(rsc): Remove this allocation by adding
// IndexString to package bytes.
regexp.prefixBytes = []byte(regexp.prefix)
regexp.prefixRune, _ = utf8.DecodeRuneInString(regexp.prefix)
}
n := len(prog.Inst)
i := 0
for matchSize[i] != 0 && matchSize[i] < n {
i++
}
regexp.mpool = i
return regexp, nil
}
// Pools of *machine for use during (*Regexp).doExecute,
// split up by the size of the execution queues.
// matchPool[i] machines have queue size matchSize[i].
// On a 64-bit system each queue entry is 16 bytes,
// so matchPool[0] has 16*2*128 = 4kB queues, etc.
// The final matchPool is a catch-all for very large queues.
var (
matchSize = [...]int{128, 512, 2048, 16384, 0}
matchPool [len(matchSize)]sync.Pool
)
// get returns a machine to use for matching re.
// It uses the re's machine cache if possible, to avoid
// unnecessary allocation.
func (re *Regexp) get() *machine {
m, ok := matchPool[re.mpool].Get().(*machine)
if !ok {
m = new(machine)
}
m.re = re
m.p = re.prog
if cap(m.matchcap) < re.matchcap {
m.matchcap = make([]int, re.matchcap)
for _, t := range m.pool {
t.cap = make([]int, re.matchcap)
}
}
// Allocate queues if needed.
// Or reallocate, for "large" match pool.
n := matchSize[re.mpool]
if n == 0 { // large pool
n = len(re.prog.Inst)
}
if len(m.q0.sparse) < n {
m.q0 = queue{make([]uint32, n), make([]entry, 0, n)}
m.q1 = queue{make([]uint32, n), make([]entry, 0, n)}
}
return m
}
// put returns a machine to the correct machine pool.
func (re *Regexp) put(m *machine) {
m.re = nil
m.p = nil
m.inputs.clear()
matchPool[re.mpool].Put(m)
}
// minInputLen walks the regexp to find the minimum length of any matchable input
func minInputLen(re *syntax.Regexp) int {
switch re.Op {
default:
return 0
case syntax.OpAnyChar, syntax.OpAnyCharNotNL, syntax.OpCharClass:
return 1
case syntax.OpLiteral:
l := 0
for _, r := range re.Rune {
if r == utf8.RuneError {
l++
} else {
l += utf8.RuneLen(r)
}
}
return l
case syntax.OpCapture, syntax.OpPlus:
return minInputLen(re.Sub[0])
case syntax.OpRepeat:
return re.Min * minInputLen(re.Sub[0])
case syntax.OpConcat:
l := 0
for _, sub := range re.Sub {
l += minInputLen(sub)
}
return l
case syntax.OpAlternate:
l := minInputLen(re.Sub[0])
var lnext int
for _, sub := range re.Sub[1:] {
lnext = minInputLen(sub)
if lnext < l {
l = lnext
}
}
return l
}
}
// MustCompile is like Compile but panics if the expression cannot be parsed.
// It simplifies safe initialization of global variables holding compiled regular
// expressions.
func MustCompile(str string) *Regexp {
regexp, err := Compile(str)
if err != nil {
panic(`regexp: Compile(` + quote(str) + `): ` + err.Error())
}
return regexp
}
// MustCompilePOSIX is like CompilePOSIX but panics if the expression cannot be parsed.
// It simplifies safe initialization of global variables holding compiled regular
// expressions.
func MustCompilePOSIX(str string) *Regexp {
regexp, err := CompilePOSIX(str)
if err != nil {
panic(`regexp: CompilePOSIX(` + quote(str) + `): ` + err.Error())
}
return regexp
}
func quote(s string) string {
if strconv.CanBackquote(s) {
return "`" + s + "`"
}
return strconv.Quote(s)
}
// NumSubexp returns the number of parenthesized subexpressions in this Regexp.
func (re *Regexp) NumSubexp() int {
return re.numSubexp
}
// SubexpNames returns the names of the parenthesized subexpressions
// in this Regexp. The name for the first sub-expression is names[1],
// so that if m is a match slice, the name for m[i] is SubexpNames()[i].
// Since the Regexp as a whole cannot be named, names[0] is always
// the empty string. The slice should not be modified.
func (re *Regexp) SubexpNames() []string {
return re.subexpNames
}
// SubexpIndex returns the index of the first subexpression with the given name,
// or -1 if there is no subexpression with that name.
//
// Note that multiple subexpressions can be written using the same name, as in
// (?P<bob>a+)(?P<bob>b+), which declares two subexpressions named "bob".
// In this case, SubexpIndex returns the index of the leftmost such subexpression
// in the regular expression.
func (re *Regexp) SubexpIndex(name string) int {
if name != "" {
for i, s := range re.subexpNames {
if name == s {
return i
}
}
}
return -1
}
const endOfText rune = -1
// input abstracts different representations of the input text. It provides
// one-character lookahead.
type input interface {
step(pos int) (r rune, width int) // advance one rune
canCheckPrefix() bool // can we look ahead without losing info?
hasPrefix(re *Regexp) bool
index(re *Regexp, pos int) int
context(pos int) lazyFlag
}
// inputString scans a string.
type inputString struct {
str string
}
func (i *inputString) step(pos int) (rune, int) {
if pos < len(i.str) {
c := i.str[pos]
if c < utf8.RuneSelf {
return rune(c), 1
}
return utf8.DecodeRuneInString(i.str[pos:])
}
return endOfText, 0
}
func (i *inputString) canCheckPrefix() bool {
return true
}
func (i *inputString) hasPrefix(re *Regexp) bool {
return strings.HasPrefix(i.str, re.prefix)
}
func (i *inputString) index(re *Regexp, pos int) int {
return strings.Index(i.str[pos:], re.prefix)
}
func (i *inputString) context(pos int) lazyFlag {
r1, r2 := endOfText, endOfText
// 0 < pos && pos <= len(i.str)
if uint(pos-1) < uint(len(i.str)) {
r1 = rune(i.str[pos-1])
if r1 >= utf8.RuneSelf {
r1, _ = utf8.DecodeLastRuneInString(i.str[:pos])
}
}
// 0 <= pos && pos < len(i.str)
if uint(pos) < uint(len(i.str)) {
r2 = rune(i.str[pos])
if r2 >= utf8.RuneSelf {
r2, _ = utf8.DecodeRuneInString(i.str[pos:])
}
}
return newLazyFlag(r1, r2)
}
// inputBytes scans a byte slice.
type inputBytes struct {
str []byte
}
func (i *inputBytes) step(pos int) (rune, int) {
if pos < len(i.str) {
c := i.str[pos]
if c < utf8.RuneSelf {
return rune(c), 1
}
return utf8.DecodeRune(i.str[pos:])
}
return endOfText, 0
}
func (i *inputBytes) canCheckPrefix() bool {
return true
}
func (i *inputBytes) hasPrefix(re *Regexp) bool {
return bytes.HasPrefix(i.str, re.prefixBytes)
}
func (i *inputBytes) index(re *Regexp, pos int) int {
return bytes.Index(i.str[pos:], re.prefixBytes)
}
func (i *inputBytes) context(pos int) lazyFlag {
r1, r2 := endOfText, endOfText
// 0 < pos && pos <= len(i.str)
if uint(pos-1) < uint(len(i.str)) {
r1 = rune(i.str[pos-1])
if r1 >= utf8.RuneSelf {
r1, _ = utf8.DecodeLastRune(i.str[:pos])
}
}
// 0 <= pos && pos < len(i.str)
if uint(pos) < uint(len(i.str)) {
r2 = rune(i.str[pos])
if r2 >= utf8.RuneSelf {
r2, _ = utf8.DecodeRune(i.str[pos:])
}
}
return newLazyFlag(r1, r2)
}
// inputReader scans a RuneReader.
type inputReader struct {
r io.RuneReader
atEOT bool
pos int
}
func (i *inputReader) step(pos int) (rune, int) {
if !i.atEOT && pos != i.pos {
return endOfText, 0
}
r, w, err := i.r.ReadRune()
if err != nil {
i.atEOT = true
return endOfText, 0
}
i.pos += w
return r, w
}
func (i *inputReader) canCheckPrefix() bool {
return false
}
func (i *inputReader) hasPrefix(re *Regexp) bool {
return false
}
func (i *inputReader) index(re *Regexp, pos int) int {
return -1
}
func (i *inputReader) context(pos int) lazyFlag {
return 0 // not used
}
// LiteralPrefix returns a literal string that must begin any match
// of the regular expression re. It returns the boolean true if the
// literal string comprises the entire regular expression.
func (re *Regexp) LiteralPrefix() (prefix string, complete bool) {
return re.prefix, re.prefixComplete
}
// MatchReader reports whether the text returned by the RuneReader
// contains any match of the regular expression re.
func (re *Regexp) MatchReader(r io.RuneReader) bool {
return re.doMatch(r, nil, "")
}
// MatchString reports whether the string s
// contains any match of the regular expression re.
func (re *Regexp) MatchString(s string) bool {
return re.doMatch(nil, nil, s)
}
// Match reports whether the byte slice b
// contains any match of the regular expression re.
func (re *Regexp) Match(b []byte) bool {
return re.doMatch(nil, b, "")
}
// MatchReader reports whether the text returned by the RuneReader
// contains any match of the regular expression pattern.
// More complicated queries need to use Compile and the full Regexp interface.
func MatchReader(pattern string, r io.RuneReader) (matched bool, err error) {
re, err := Compile(pattern)
if err != nil {
return false, err
}
return re.MatchReader(r), nil
}
// MatchString reports whether the string s
// contains any match of the regular expression pattern.
// More complicated queries need to use Compile and the full Regexp interface.
func MatchString(pattern string, s string) (matched bool, err error) {
re, err := Compile(pattern)
if err != nil {
return false, err
}
return re.MatchString(s), nil
}
// Match reports whether the byte slice b
// contains any match of the regular expression pattern.
// More complicated queries need to use Compile and the full Regexp interface.
func Match(pattern string, b []byte) (matched bool, err error) {
re, err := Compile(pattern)
if err != nil {
return false, err
}
return re.Match(b), nil
}
// ReplaceAllString returns a copy of src, replacing matches of the Regexp
// with the replacement string repl. Inside repl, $ signs are interpreted as
// in Expand, so for instance $1 represents the text of the first submatch.
func (re *Regexp) ReplaceAllString(src, repl string) string {
n := 2
if strings.Contains(repl, "$") {
n = 2 * (re.numSubexp + 1)
}
b := re.replaceAll(nil, src, n, func(dst []byte, match []int) []byte {
return re.expand(dst, repl, nil, src, match)
})
return string(b)
}
// ReplaceAllLiteralString returns a copy of src, replacing matches of the Regexp
// with the replacement string repl. The replacement repl is substituted directly,
// without using Expand.
func (re *Regexp) ReplaceAllLiteralString(src, repl string) string {
return string(re.replaceAll(nil, src, 2, func(dst []byte, match []int) []byte {
return append(dst, repl...)
}))
}
// ReplaceAllStringFunc returns a copy of src in which all matches of the
// Regexp have been replaced by the return value of function repl applied
// to the matched substring. The replacement returned by repl is substituted
// directly, without using Expand.
func (re *Regexp) ReplaceAllStringFunc(src string, repl func(string) string) string {
b := re.replaceAll(nil, src, 2, func(dst []byte, match []int) []byte {
return append(dst, repl(src[match[0]:match[1]])...)
})
return string(b)
}
func (re *Regexp) replaceAll(bsrc []byte, src string, nmatch int, repl func(dst []byte, m []int) []byte) []byte {
lastMatchEnd := 0 // end position of the most recent match
searchPos := 0 // position where we next look for a match
var buf []byte
var endPos int
if bsrc != nil {
endPos = len(bsrc)
} else {
endPos = len(src)
}
if nmatch > re.prog.NumCap {
nmatch = re.prog.NumCap
}
var dstCap [2]int
for searchPos <= endPos {
a := re.doExecute(nil, bsrc, src, searchPos, nmatch, dstCap[:0])
if len(a) == 0 {
break // no more matches
}
// Copy the unmatched characters before this match.
if bsrc != nil {
buf = append(buf, bsrc[lastMatchEnd:a[0]]...)
} else {
buf = append(buf, src[lastMatchEnd:a[0]]...)
}
// Now insert a copy of the replacement string, but not for a
// match of the empty string immediately after another match.
// (Otherwise, we get double replacement for patterns that
// match both empty and nonempty strings.)
if a[1] > lastMatchEnd || a[0] == 0 {
buf = repl(buf, a)
}
lastMatchEnd = a[1]
// Advance past this match; always advance at least one character.
var width int
if bsrc != nil {
_, width = utf8.DecodeRune(bsrc[searchPos:])
} else {
_, width = utf8.DecodeRuneInString(src[searchPos:])
}
if searchPos+width > a[1] {
searchPos += width
} else if searchPos+1 > a[1] {
// This clause is only needed at the end of the input
// string. In that case, DecodeRuneInString returns width=0.
searchPos++
} else {
searchPos = a[1]
}
}
// Copy the unmatched characters after the last match.
if bsrc != nil {
buf = append(buf, bsrc[lastMatchEnd:]...)
} else {
buf = append(buf, src[lastMatchEnd:]...)
}
return buf
}
// ReplaceAll returns a copy of src, replacing matches of the Regexp
// with the replacement text repl. Inside repl, $ signs are interpreted as
// in Expand, so for instance $1 represents the text of the first submatch.
func (re *Regexp) ReplaceAll(src, repl []byte) []byte {
n := 2
if bytes.IndexByte(repl, '$') >= 0 {
n = 2 * (re.numSubexp + 1)
}
srepl := ""
b := re.replaceAll(src, "", n, func(dst []byte, match []int) []byte {
if len(srepl) != len(repl) {
srepl = string(repl)
}
return re.expand(dst, srepl, src, "", match)
})
return b
}
// ReplaceAllLiteral returns a copy of src, replacing matches of the Regexp
// with the replacement bytes repl. The replacement repl is substituted directly,
// without using Expand.
func (re *Regexp) ReplaceAllLiteral(src, repl []byte) []byte {
return re.replaceAll(src, "", 2, func(dst []byte, match []int) []byte {
return append(dst, repl...)
})
}
// ReplaceAllFunc returns a copy of src in which all matches of the
// Regexp have been replaced by the return value of function repl applied
// to the matched byte slice. The replacement returned by repl is substituted
// directly, without using Expand.
func (re *Regexp) ReplaceAllFunc(src []byte, repl func([]byte) []byte) []byte {
return re.replaceAll(src, "", 2, func(dst []byte, match []int) []byte {
return append(dst, repl(src[match[0]:match[1]])...)
})
}
// Bitmap used by func special to check whether a character needs to be escaped.
var specialBytes [16]byte
// special reports whether byte b needs to be escaped by QuoteMeta.
func special(b byte) bool {
return b < utf8.RuneSelf && specialBytes[b%16]&(1<<(b/16)) != 0
}
func init() {
for _, b := range []byte(`\.+*?()|[]{}^$`) {
specialBytes[b%16] |= 1 << (b / 16)
}
}
// QuoteMeta returns a string that escapes all regular expression metacharacters
// inside the argument text; the returned string is a regular expression matching
// the literal text.
func QuoteMeta(s string) string {
// A byte loop is correct because all metacharacters are ASCII.
var i int
for i = 0; i < len(s); i++ {
if special(s[i]) {
break
}
}
// No meta characters found, so return original string.
if i >= len(s) {
return s
}
b := make([]byte, 2*len(s)-i)
copy(b, s[:i])
j := i
for ; i < len(s); i++ {
if special(s[i]) {
b[j] = '\\'
j++
}
b[j] = s[i]
j++
}
return string(b[:j])
}
// The number of capture values in the program may correspond
// to fewer capturing expressions than are in the regexp.
// For example, "(a){0}" turns into an empty program, so the
// maximum capture in the program is 0 but we need to return
// an expression for \1. Pad appends -1s to the slice a as needed.
func (re *Regexp) pad(a []int) []int {
if a == nil {
// No match.
return nil
}
n := (1 + re.numSubexp) * 2
for len(a) < n {
a = append(a, -1)
}
return a
}
// allMatches calls deliver at most n times
// with the location of successive matches in the input text.
// The input text is b if non-nil, otherwise s.
func (re *Regexp) allMatches(s string, b []byte, n int, deliver func([]int)) {
var end int
if b == nil {
end = len(s)
} else {
end = len(b)
}
for pos, i, prevMatchEnd := 0, 0, -1; i < n && pos <= end; {
matches := re.doExecute(nil, b, s, pos, re.prog.NumCap, nil)
if len(matches) == 0 {
break
}
accept := true
if matches[1] == pos {
// We've found an empty match.
if matches[0] == prevMatchEnd {
// We don't allow an empty match right
// after a previous match, so ignore it.
accept = false
}
var width int
if b == nil {
is := inputString{str: s}
_, width = is.step(pos)
} else {
ib := inputBytes{str: b}
_, width = ib.step(pos)
}
if width > 0 {
pos += width
} else {
pos = end + 1
}
} else {
pos = matches[1]
}
prevMatchEnd = matches[1]
if accept {
deliver(re.pad(matches))
i++
}
}
}
// Find returns a slice holding the text of the leftmost match in b of the regular expression.
// A return value of nil indicates no match.
func (re *Regexp) Find(b []byte) []byte {
var dstCap [2]int
a := re.doExecute(nil, b, "", 0, 2, dstCap[:0])
if a == nil {
return nil
}
return b[a[0]:a[1]:a[1]]
}
// FindIndex returns a two-element slice of integers defining the location of
// the leftmost match in b of the regular expression. The match itself is at
// b[loc[0]:loc[1]].
// A return value of nil indicates no match.
func (re *Regexp) FindIndex(b []byte) (loc []int) {
a := re.doExecute(nil, b, "", 0, 2, nil)
if a == nil {
return nil
}
return a[0:2]
}
// FindString returns a string holding the text of the leftmost match in s of the regular
// expression. If there is no match, the return value is an empty string,
// but it will also be empty if the regular expression successfully matches
// an empty string. Use FindStringIndex or FindStringSubmatch if it is
// necessary to distinguish these cases.
func (re *Regexp) FindString(s string) string {
var dstCap [2]int
a := re.doExecute(nil, nil, s, 0, 2, dstCap[:0])
if a == nil {
return ""
}
return s[a[0]:a[1]]
}
// FindStringIndex returns a two-element slice of integers defining the
// location of the leftmost match in s of the regular expression. The match
// itself is at s[loc[0]:loc[1]].
// A return value of nil indicates no match.
func (re *Regexp) FindStringIndex(s string) (loc []int) {
a := re.doExecute(nil, nil, s, 0, 2, nil)
if a == nil {
return nil
}
return a[0:2]
}
// FindReaderIndex returns a two-element slice of integers defining the
// location of the leftmost match of the regular expression in text read from
// the RuneReader. The match text was found in the input stream at
// byte offset loc[0] through loc[1]-1.
// A return value of nil indicates no match.
func (re *Regexp) FindReaderIndex(r io.RuneReader) (loc []int) {
a := re.doExecute(r, nil, "", 0, 2, nil)
if a == nil {
return nil
}
return a[0:2]
}
// FindSubmatch returns a slice of slices holding the text of the leftmost
// match of the regular expression in b and the matches, if any, of its
// subexpressions, as defined by the 'Submatch' descriptions in the package
// comment.
// A return value of nil indicates no match.
func (re *Regexp) FindSubmatch(b []byte) [][]byte {
var dstCap [4]int
a := re.doExecute(nil, b, "", 0, re.prog.NumCap, dstCap[:0])
if a == nil {
return nil
}
ret := make([][]byte, 1+re.numSubexp)
for i := range ret {
if 2*i < len(a) && a[2*i] >= 0 {
ret[i] = b[a[2*i]:a[2*i+1]:a[2*i+1]]
}
}
return ret
}
// Expand appends template to dst and returns the result; during the
// append, Expand replaces variables in the template with corresponding
// matches drawn from src. The match slice should have been returned by
// FindSubmatchIndex.
//
// In the template, a variable is denoted by a substring of the form
// $name or ${name}, where name is a non-empty sequence of letters,
// digits, and underscores. A purely numeric name like $1 refers to
// the submatch with the corresponding index; other names refer to
// capturing parentheses named with the (?P<name>...) syntax. A
// reference to an out of range or unmatched index or a name that is not
// present in the regular expression is replaced with an empty slice.
//
// In the $name form, name is taken to be as long as possible: $1x is
// equivalent to ${1x}, not ${1}x, and, $10 is equivalent to ${10}, not ${1}0.
//
// To insert a literal $ in the output, use $$ in the template.
func (re *Regexp) Expand(dst []byte, template []byte, src []byte, match []int) []byte {
return re.expand(dst, string(template), src, "", match)
}
// ExpandString is like Expand but the template and source are strings.
// It appends to and returns a byte slice in order to give the calling
// code control over allocation.
func (re *Regexp) ExpandString(dst []byte, template string, src string, match []int) []byte {
return re.expand(dst, template, nil, src, match)
}
func (re *Regexp) expand(dst []byte, template string, bsrc []byte, src string, match []int) []byte {
for len(template) > 0 {
before, after, ok := strings.Cut(template, "$")
if !ok {
break
}
dst = append(dst, before...)
template = after
if template != "" && template[0] == '$' {
// Treat $$ as $.
dst = append(dst, '$')
template = template[1:]
continue
}
name, num, rest, ok := extract(template)
if !ok {
// Malformed; treat $ as raw text.
dst = append(dst, '$')
continue
}
template = rest
if num >= 0 {
if 2*num+1 < len(match) && match[2*num] >= 0 {
if bsrc != nil {
dst = append(dst, bsrc[match[2*num]:match[2*num+1]]...)
} else {
dst = append(dst, src[match[2*num]:match[2*num+1]]...)
}
}
} else {
for i, namei := range re.subexpNames {
if name == namei && 2*i+1 < len(match) && match[2*i] >= 0 {
if bsrc != nil {
dst = append(dst, bsrc[match[2*i]:match[2*i+1]]...)
} else {
dst = append(dst, src[match[2*i]:match[2*i+1]]...)
}
break
}
}
}
}
dst = append(dst, template...)
return dst
}
// extract returns the name from a leading "name" or "{name}" in str.
// (The $ has already been removed by the caller.)
// If it is a number, extract returns num set to that number; otherwise num = -1.
func extract(str string) (name string, num int, rest string, ok bool) {
if str == "" {
return
}
brace := false
if str[0] == '{' {
brace = true
str = str[1:]
}
i := 0
for i < len(str) {
rune, size := utf8.DecodeRuneInString(str[i:])
if !unicode.IsLetter(rune) && !unicode.IsDigit(rune) && rune != '_' {
break
}
i += size
}
if i == 0 {
// empty name is not okay
return