forked from XWxiaowei/JavaCode
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathMatcher.java
More file actions
1319 lines (1250 loc) · 48.8 KB
/
Matcher.java
File metadata and controls
1319 lines (1250 loc) · 48.8 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 (c) 1999, 2013, Oracle and/or its affiliates. All rights reserved.
* ORACLE PROPRIETARY/CONFIDENTIAL. Use is subject to license terms.
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*
*/
package java.util.regex;
import java.util.Objects;
/**
* An engine that performs match operations on a {@linkplain java.lang.CharSequence
* character sequence} by interpreting a {@link Pattern}.
*
* <p> A matcher is created from a pattern by invoking the pattern's {@link
* Pattern#matcher matcher} method. Once created, a matcher can be used to
* perform three different kinds of match operations:
*
* <ul>
*
* <li><p> The {@link #matches matches} method attempts to match the entire
* input sequence against the pattern. </p></li>
*
* <li><p> The {@link #lookingAt lookingAt} method attempts to match the
* input sequence, starting at the beginning, against the pattern. </p></li>
*
* <li><p> The {@link #find find} method scans the input sequence looking for
* the next subsequence that matches the pattern. </p></li>
*
* </ul>
*
* <p> Each of these methods returns a boolean indicating success or failure.
* More information about a successful match can be obtained by querying the
* state of the matcher.
*
* <p> A matcher finds matches in a subset of its input called the
* <i>region</i>. By default, the region contains all of the matcher's input.
* The region can be modified via the{@link #region region} method and queried
* via the {@link #regionStart regionStart} and {@link #regionEnd regionEnd}
* methods. The way that the region boundaries interact with some pattern
* constructs can be changed. See {@link #useAnchoringBounds
* useAnchoringBounds} and {@link #useTransparentBounds useTransparentBounds}
* for more details.
*
* <p> This class also defines methods for replacing matched subsequences with
* new strings whose contents can, if desired, be computed from the match
* result. The {@link #appendReplacement appendReplacement} and {@link
* #appendTail appendTail} methods can be used in tandem in order to collect
* the result into an existing string buffer, or the more convenient {@link
* #replaceAll replaceAll} method can be used to create a string in which every
* matching subsequence in the input sequence is replaced.
*
* <p> The explicit state of a matcher includes the start and end indices of
* the most recent successful match. It also includes the start and end
* indices of the input subsequence captured by each <a
* href="Pattern.html#cg">capturing group</a> in the pattern as well as a total
* count of such subsequences. As a convenience, methods are also provided for
* returning these captured subsequences in string form.
*
* <p> The explicit state of a matcher is initially undefined; attempting to
* query any part of it before a successful match will cause an {@link
* IllegalStateException} to be thrown. The explicit state of a matcher is
* recomputed by every match operation.
*
* <p> The implicit state of a matcher includes the input character sequence as
* well as the <i>append position</i>, which is initially zero and is updated
* by the {@link #appendReplacement appendReplacement} method.
*
* <p> A matcher may be reset explicitly by invoking its {@link #reset()}
* method or, if a new input sequence is desired, its {@link
* #reset(java.lang.CharSequence) reset(CharSequence)} method. Resetting a
* matcher discards its explicit state information and sets the append position
* to zero.
*
* <p> Instances of this class are not safe for use by multiple concurrent
* threads. </p>
*
*
* @author Mike McCloskey
* @author Mark Reinhold
* @author JSR-51 Expert Group
* @since 1.4
* @spec JSR-51
*/
public final class Matcher implements MatchResult {
/**
* The Pattern object that created this Matcher.
*/
Pattern parentPattern;
/**
* The storage used by groups. They may contain invalid values if
* a group was skipped during the matching.
*/
int[] groups;
/**
* The range within the sequence that is to be matched. Anchors
* will match at these "hard" boundaries. Changing the region
* changes these values.
*/
int from, to;
/**
* Lookbehind uses this value to ensure that the subexpression
* match ends at the point where the lookbehind was encountered.
*/
int lookbehindTo;
/**
* The original string being matched.
*/
CharSequence text;
/**
* Matcher state used by the last node. NOANCHOR is used when a
* match does not have to consume all of the input. ENDANCHOR is
* the mode used for matching all the input.
*/
static final int ENDANCHOR = 1;
static final int NOANCHOR = 0;
int acceptMode = NOANCHOR;
/**
* The range of string that last matched the pattern. If the last
* match failed then first is -1; last initially holds 0 then it
* holds the index of the end of the last match (which is where the
* next search starts).
*/
int first = -1, last = 0;
/**
* The end index of what matched in the last match operation.
*/
int oldLast = -1;
/**
* The index of the last position appended in a substitution.
*/
int lastAppendPosition = 0;
/**
* Storage used by nodes to tell what repetition they are on in
* a pattern, and where groups begin. The nodes themselves are stateless,
* so they rely on this field to hold state during a match.
*/
int[] locals;
/**
* Boolean indicating whether or not more input could change
* the results of the last match.
*
* If hitEnd is true, and a match was found, then more input
* might cause a different match to be found.
* If hitEnd is true and a match was not found, then more
* input could cause a match to be found.
* If hitEnd is false and a match was found, then more input
* will not change the match.
* If hitEnd is false and a match was not found, then more
* input will not cause a match to be found.
*/
boolean hitEnd;
/**
* Boolean indicating whether or not more input could change
* a positive match into a negative one.
*
* If requireEnd is true, and a match was found, then more
* input could cause the match to be lost.
* If requireEnd is false and a match was found, then more
* input might change the match but the match won't be lost.
* If a match was not found, then requireEnd has no meaning.
*/
boolean requireEnd;
/**
* If transparentBounds is true then the boundaries of this
* matcher's region are transparent to lookahead, lookbehind,
* and boundary matching constructs that try to see beyond them.
*/
boolean transparentBounds = false;
/**
* If anchoringBounds is true then the boundaries of this
* matcher's region match anchors such as ^ and $.
*/
boolean anchoringBounds = true;
/**
* No default constructor.
*/
Matcher() {
}
/**
* All matchers have the state used by Pattern during a match.
*/
Matcher(Pattern parent, CharSequence text) {
this.parentPattern = parent;
this.text = text;
// Allocate state storage
int parentGroupCount = Math.max(parent.capturingGroupCount, 10);
groups = new int[parentGroupCount * 2];
locals = new int[parent.localCount];
// Put fields into initial states
reset();
}
/**
* Returns the pattern that is interpreted by this matcher.
*
* @return The pattern for which this matcher was created
*/
public Pattern pattern() {
return parentPattern;
}
/**
* Returns the match state of this matcher as a {@link MatchResult}.
* The result is unaffected by subsequent operations performed upon this
* matcher.
*
* @return a <code>MatchResult</code> with the state of this matcher
* @since 1.5
*/
public MatchResult toMatchResult() {
Matcher result = new Matcher(this.parentPattern, text.toString());
result.first = this.first;
result.last = this.last;
result.groups = this.groups.clone();
return result;
}
/**
* Changes the <tt>Pattern</tt> that this <tt>Matcher</tt> uses to
* find matches with.
*
* <p> This method causes this matcher to lose information
* about the groups of the last match that occurred. The
* matcher's position in the input is maintained and its
* last append position is unaffected.</p>
*
* @param newPattern
* The new pattern used by this matcher
* @return This matcher
* @throws IllegalArgumentException
* If newPattern is <tt>null</tt>
* @since 1.5
*/
public Matcher usePattern(Pattern newPattern) {
if (newPattern == null)
throw new IllegalArgumentException("Pattern cannot be null");
parentPattern = newPattern;
// Reallocate state storage
int parentGroupCount = Math.max(newPattern.capturingGroupCount, 10);
groups = new int[parentGroupCount * 2];
locals = new int[newPattern.localCount];
for (int i = 0; i < groups.length; i++)
groups[i] = -1;
for (int i = 0; i < locals.length; i++)
locals[i] = -1;
return this;
}
/**
* Resets this matcher.
*
* <p> Resetting a matcher discards all of its explicit state information
* and sets its append position to zero. The matcher's region is set to the
* default region, which is its entire character sequence. The anchoring
* and transparency of this matcher's region boundaries are unaffected.
*
* @return This matcher
*/
public Matcher reset() {
first = -1;
last = 0;
oldLast = -1;
for(int i=0; i<groups.length; i++)
groups[i] = -1;
for(int i=0; i<locals.length; i++)
locals[i] = -1;
lastAppendPosition = 0;
from = 0;
to = getTextLength();
return this;
}
/**
* Resets this matcher with a new input sequence.
*
* <p> Resetting a matcher discards all of its explicit state information
* and sets its append position to zero. The matcher's region is set to
* the default region, which is its entire character sequence. The
* anchoring and transparency of this matcher's region boundaries are
* unaffected.
*
* @param input
* The new input character sequence
*
* @return This matcher
*/
public Matcher reset(CharSequence input) {
text = input;
return reset();
}
/**
* Returns the start index of the previous match.
*
* @return The index of the first character matched
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*/
public int start() {
if (first < 0)
throw new IllegalStateException("No match available");
return first;
}
/**
* Returns the start index of the subsequence captured by the given group
* during the previous match operation.
*
* <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
* to right, starting at one. Group zero denotes the entire pattern, so
* the expression <i>m.</i><tt>start(0)</tt> is equivalent to
* <i>m.</i><tt>start()</tt>. </p>
*
* @param group
* The index of a capturing group in this matcher's pattern
*
* @return The index of the first character captured by the group,
* or <tt>-1</tt> if the match was successful but the group
* itself did not match anything
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IndexOutOfBoundsException
* If there is no capturing group in the pattern
* with the given index
*/
public int start(int group) {
if (first < 0)
throw new IllegalStateException("No match available");
if (group < 0 || group > groupCount())
throw new IndexOutOfBoundsException("No group " + group);
return groups[group * 2];
}
/**
* Returns the start index of the subsequence captured by the given
* <a href="Pattern.html#groupname">named-capturing group</a> during the
* previous match operation.
*
* @param name
* The name of a named-capturing group in this matcher's pattern
*
* @return The index of the first character captured by the group,
* or {@code -1} if the match was successful but the group
* itself did not match anything
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IllegalArgumentException
* If there is no capturing group in the pattern
* with the given name
* @since 1.8
*/
public int start(String name) {
return groups[getMatchedGroupIndex(name) * 2];
}
/**
* Returns the offset after the last character matched.
*
* @return The offset after the last character matched
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*/
public int end() {
if (first < 0)
throw new IllegalStateException("No match available");
return last;
}
/**
* Returns the offset after the last character of the subsequence
* captured by the given group during the previous match operation.
*
* <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
* to right, starting at one. Group zero denotes the entire pattern, so
* the expression <i>m.</i><tt>end(0)</tt> is equivalent to
* <i>m.</i><tt>end()</tt>. </p>
*
* @param group
* The index of a capturing group in this matcher's pattern
*
* @return The offset after the last character captured by the group,
* or <tt>-1</tt> if the match was successful
* but the group itself did not match anything
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IndexOutOfBoundsException
* If there is no capturing group in the pattern
* with the given index
*/
public int end(int group) {
if (first < 0)
throw new IllegalStateException("No match available");
if (group < 0 || group > groupCount())
throw new IndexOutOfBoundsException("No group " + group);
return groups[group * 2 + 1];
}
/**
* Returns the offset after the last character of the subsequence
* captured by the given <a href="Pattern.html#groupname">named-capturing
* group</a> during the previous match operation.
*
* @param name
* The name of a named-capturing group in this matcher's pattern
*
* @return The offset after the last character captured by the group,
* or {@code -1} if the match was successful
* but the group itself did not match anything
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IllegalArgumentException
* If there is no capturing group in the pattern
* with the given name
* @since 1.8
*/
public int end(String name) {
return groups[getMatchedGroupIndex(name) * 2 + 1];
}
/**
* Returns the input subsequence matched by the previous match.
*
* <p> For a matcher <i>m</i> with input sequence <i>s</i>,
* the expressions <i>m.</i><tt>group()</tt> and
* <i>s.</i><tt>substring(</tt><i>m.</i><tt>start(),</tt> <i>m.</i><tt>end())</tt>
* are equivalent. </p>
*
* <p> Note that some patterns, for example <tt>a*</tt>, match the empty
* string. This method will return the empty string when the pattern
* successfully matches the empty string in the input. </p>
*
* @return The (possibly empty) subsequence matched by the previous match,
* in string form
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*/
public String group() {
return group(0);
}
/**
* Returns the input subsequence captured by the given group during the
* previous match operation.
*
* <p> For a matcher <i>m</i>, input sequence <i>s</i>, and group index
* <i>g</i>, the expressions <i>m.</i><tt>group(</tt><i>g</i><tt>)</tt> and
* <i>s.</i><tt>substring(</tt><i>m.</i><tt>start(</tt><i>g</i><tt>),</tt> <i>m.</i><tt>end(</tt><i>g</i><tt>))</tt>
* are equivalent. </p>
*
* <p> <a href="Pattern.html#cg">Capturing groups</a> are indexed from left
* to right, starting at one. Group zero denotes the entire pattern, so
* the expression <tt>m.group(0)</tt> is equivalent to <tt>m.group()</tt>.
* </p>
*
* <p> If the match was successful but the group specified failed to match
* any part of the input sequence, then <tt>null</tt> is returned. Note
* that some groups, for example <tt>(a*)</tt>, match the empty string.
* This method will return the empty string when such a group successfully
* matches the empty string in the input. </p>
*
* @param group
* The index of a capturing group in this matcher's pattern
*
* @return The (possibly empty) subsequence captured by the group
* during the previous match, or <tt>null</tt> if the group
* failed to match part of the input
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IndexOutOfBoundsException
* If there is no capturing group in the pattern
* with the given index
*/
public String group(int group) {
if (first < 0)
throw new IllegalStateException("No match found");
if (group < 0 || group > groupCount())
throw new IndexOutOfBoundsException("No group " + group);
if ((groups[group*2] == -1) || (groups[group*2+1] == -1))
return null;
return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString();
}
/**
* Returns the input subsequence captured by the given
* <a href="Pattern.html#groupname">named-capturing group</a> during the previous
* match operation.
*
* <p> If the match was successful but the group specified failed to match
* any part of the input sequence, then <tt>null</tt> is returned. Note
* that some groups, for example <tt>(a*)</tt>, match the empty string.
* This method will return the empty string when such a group successfully
* matches the empty string in the input. </p>
*
* @param name
* The name of a named-capturing group in this matcher's pattern
*
* @return The (possibly empty) subsequence captured by the named group
* during the previous match, or <tt>null</tt> if the group
* failed to match part of the input
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IllegalArgumentException
* If there is no capturing group in the pattern
* with the given name
* @since 1.7
*/
public String group(String name) {
int group = getMatchedGroupIndex(name);
if ((groups[group*2] == -1) || (groups[group*2+1] == -1))
return null;
return getSubSequence(groups[group * 2], groups[group * 2 + 1]).toString();
}
/**
* Returns the number of capturing groups in this matcher's pattern.
*
* <p> Group zero denotes the entire pattern by convention. It is not
* included in this count.
*
* <p> Any non-negative integer smaller than or equal to the value
* returned by this method is guaranteed to be a valid group index for
* this matcher. </p>
*
* @return The number of capturing groups in this matcher's pattern
*/
public int groupCount() {
return parentPattern.capturingGroupCount - 1;
}
/**
* Attempts to match the entire region against the pattern.
*
* <p> If the match succeeds then more information can be obtained via the
* <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p>
*
* @return <tt>true</tt> if, and only if, the entire region sequence
* matches this matcher's pattern
*/
public boolean matches() {
return match(from, ENDANCHOR);
}
/**
* Attempts to find the next subsequence of the input sequence that matches
* the pattern.
*
* <p> This method starts at the beginning of this matcher's region, or, if
* a previous invocation of the method was successful and the matcher has
* not since been reset, at the first character not matched by the previous
* match.
*
* <p> If the match succeeds then more information can be obtained via the
* <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p>
*
* @return <tt>true</tt> if, and only if, a subsequence of the input
* sequence matches this matcher's pattern
*/
public boolean find() {
int nextSearchIndex = last;
if (nextSearchIndex == first)
nextSearchIndex++;
// If next search starts before region, start it at region
if (nextSearchIndex < from)
nextSearchIndex = from;
// If next search starts beyond region then it fails
if (nextSearchIndex > to) {
for (int i = 0; i < groups.length; i++)
groups[i] = -1;
return false;
}
return search(nextSearchIndex);
}
/**
* Resets this matcher and then attempts to find the next subsequence of
* the input sequence that matches the pattern, starting at the specified
* index.
*
* <p> If the match succeeds then more information can be obtained via the
* <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods, and subsequent
* invocations of the {@link #find()} method will start at the first
* character not matched by this match. </p>
*
* @param start the index to start searching for a match
* @throws IndexOutOfBoundsException
* If start is less than zero or if start is greater than the
* length of the input sequence.
*
* @return <tt>true</tt> if, and only if, a subsequence of the input
* sequence starting at the given index matches this matcher's
* pattern
*/
public boolean find(int start) {
int limit = getTextLength();
if ((start < 0) || (start > limit))
throw new IndexOutOfBoundsException("Illegal start index");
reset();
return search(start);
}
/**
* Attempts to match the input sequence, starting at the beginning of the
* region, against the pattern.
*
* <p> Like the {@link #matches matches} method, this method always starts
* at the beginning of the region; unlike that method, it does not
* require that the entire region be matched.
*
* <p> If the match succeeds then more information can be obtained via the
* <tt>start</tt>, <tt>end</tt>, and <tt>group</tt> methods. </p>
*
* @return <tt>true</tt> if, and only if, a prefix of the input
* sequence matches this matcher's pattern
*/
public boolean lookingAt() {
return match(from, NOANCHOR);
}
/**
* Returns a literal replacement <code>String</code> for the specified
* <code>String</code>.
*
* This method produces a <code>String</code> that will work
* as a literal replacement <code>s</code> in the
* <code>appendReplacement</code> method of the {@link Matcher} class.
* The <code>String</code> produced will match the sequence of characters
* in <code>s</code> treated as a literal sequence. Slashes ('\') and
* dollar signs ('$') will be given no special meaning.
*
* @param s The string to be literalized
* @return A literal string replacement
* @since 1.5
*/
public static String quoteReplacement(String s) {
if ((s.indexOf('\\') == -1) && (s.indexOf('$') == -1))
return s;
StringBuilder sb = new StringBuilder();
for (int i=0; i<s.length(); i++) {
char c = s.charAt(i);
if (c == '\\' || c == '$') {
sb.append('\\');
}
sb.append(c);
}
return sb.toString();
}
/**
* Implements a non-terminal append-and-replace step.
*
* <p> This method performs the following actions: </p>
*
* <ol>
*
* <li><p> It reads characters from the input sequence, starting at the
* append position, and appends them to the given string buffer. It
* stops after reading the last character preceding the previous match,
* that is, the character at index {@link
* #start()} <tt>-</tt> <tt>1</tt>. </p></li>
*
* <li><p> It appends the given replacement string to the string buffer.
* </p></li>
*
* <li><p> It sets the append position of this matcher to the index of
* the last character matched, plus one, that is, to {@link #end()}.
* </p></li>
*
* </ol>
*
* <p> The replacement string may contain references to subsequences
* captured during the previous match: Each occurrence of
* <tt>${</tt><i>name</i><tt>}</tt> or <tt>$</tt><i>g</i>
* will be replaced by the result of evaluating the corresponding
* {@link #group(String) group(name)} or {@link #group(int) group(g)}
* respectively. For <tt>$</tt><i>g</i>,
* the first number after the <tt>$</tt> is always treated as part of
* the group reference. Subsequent numbers are incorporated into g if
* they would form a legal group reference. Only the numerals '0'
* through '9' are considered as potential components of the group
* reference. If the second group matched the string <tt>"foo"</tt>, for
* example, then passing the replacement string <tt>"$2bar"</tt> would
* cause <tt>"foobar"</tt> to be appended to the string buffer. A dollar
* sign (<tt>$</tt>) may be included as a literal in the replacement
* string by preceding it with a backslash (<tt>\$</tt>).
*
* <p> Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in
* the replacement string may cause the results to be different than if it
* were being treated as a literal replacement string. Dollar signs may be
* treated as references to captured subsequences as described above, and
* backslashes are used to escape literal characters in the replacement
* string.
*
* <p> This method is intended to be used in a loop together with the
* {@link #appendTail appendTail} and {@link #find find} methods. The
* following code, for example, writes <tt>one dog two dogs in the
* yard</tt> to the standard-output stream: </p>
*
* <blockquote><pre>
* Pattern p = Pattern.compile("cat");
* Matcher m = p.matcher("one cat two cats in the yard");
* StringBuffer sb = new StringBuffer();
* while (m.find()) {
* m.appendReplacement(sb, "dog");
* }
* m.appendTail(sb);
* System.out.println(sb.toString());</pre></blockquote>
*
* @param sb
* The target string buffer
*
* @param replacement
* The replacement string
*
* @return This matcher
*
* @throws IllegalStateException
* If no match has yet been attempted,
* or if the previous match operation failed
*
* @throws IllegalArgumentException
* If the replacement string refers to a named-capturing
* group that does not exist in the pattern
*
* @throws IndexOutOfBoundsException
* If the replacement string refers to a capturing group
* that does not exist in the pattern
*/
public Matcher appendReplacement(StringBuffer sb, String replacement) {
// If no match, return error
if (first < 0)
throw new IllegalStateException("No match available");
// Process substitution string to replace group references with groups
int cursor = 0;
StringBuilder result = new StringBuilder();
while (cursor < replacement.length()) {
char nextChar = replacement.charAt(cursor);
if (nextChar == '\\') {
cursor++;
if (cursor == replacement.length())
throw new IllegalArgumentException(
"character to be escaped is missing");
nextChar = replacement.charAt(cursor);
result.append(nextChar);
cursor++;
} else if (nextChar == '$') {
// Skip past $
cursor++;
// Throw IAE if this "$" is the last character in replacement
if (cursor == replacement.length())
throw new IllegalArgumentException(
"Illegal group reference: group index is missing");
nextChar = replacement.charAt(cursor);
int refNum = -1;
if (nextChar == '{') {
cursor++;
StringBuilder gsb = new StringBuilder();
while (cursor < replacement.length()) {
nextChar = replacement.charAt(cursor);
if (ASCII.isLower(nextChar) ||
ASCII.isUpper(nextChar) ||
ASCII.isDigit(nextChar)) {
gsb.append(nextChar);
cursor++;
} else {
break;
}
}
if (gsb.length() == 0)
throw new IllegalArgumentException(
"named capturing group has 0 length name");
if (nextChar != '}')
throw new IllegalArgumentException(
"named capturing group is missing trailing '}'");
String gname = gsb.toString();
if (ASCII.isDigit(gname.charAt(0)))
throw new IllegalArgumentException(
"capturing group name {" + gname +
"} starts with digit character");
if (!parentPattern.namedGroups().containsKey(gname))
throw new IllegalArgumentException(
"No group with name {" + gname + "}");
refNum = parentPattern.namedGroups().get(gname);
cursor++;
} else {
// The first number is always a group
refNum = (int)nextChar - '0';
if ((refNum < 0)||(refNum > 9))
throw new IllegalArgumentException(
"Illegal group reference");
cursor++;
// Capture the largest legal group string
boolean done = false;
while (!done) {
if (cursor >= replacement.length()) {
break;
}
int nextDigit = replacement.charAt(cursor) - '0';
if ((nextDigit < 0)||(nextDigit > 9)) { // not a number
break;
}
int newRefNum = (refNum * 10) + nextDigit;
if (groupCount() < newRefNum) {
done = true;
} else {
refNum = newRefNum;
cursor++;
}
}
}
// Append group
if (start(refNum) != -1 && end(refNum) != -1)
result.append(text, start(refNum), end(refNum));
} else {
result.append(nextChar);
cursor++;
}
}
// Append the intervening text
sb.append(text, lastAppendPosition, first);
// Append the match substitution
sb.append(result);
lastAppendPosition = last;
return this;
}
/**
* Implements a terminal append-and-replace step.
*
* <p> This method reads characters from the input sequence, starting at
* the append position, and appends them to the given string buffer. It is
* intended to be invoked after one or more invocations of the {@link
* #appendReplacement appendReplacement} method in order to copy the
* remainder of the input sequence. </p>
*
* @param sb
* The target string buffer
*
* @return The target string buffer
*/
public StringBuffer appendTail(StringBuffer sb) {
sb.append(text, lastAppendPosition, getTextLength());
return sb;
}
/**
* Replaces every subsequence of the input sequence that matches the
* pattern with the given replacement string.
*
* <p> This method first resets this matcher. It then scans the input
* sequence looking for matches of the pattern. Characters that are not
* part of any match are appended directly to the result string; each match
* is replaced in the result by the replacement string. The replacement
* string may contain references to captured subsequences as in the {@link
* #appendReplacement appendReplacement} method.
*
* <p> Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in
* the replacement string may cause the results to be different than if it
* were being treated as a literal replacement string. Dollar signs may be
* treated as references to captured subsequences as described above, and
* backslashes are used to escape literal characters in the replacement
* string.
*
* <p> Given the regular expression <tt>a*b</tt>, the input
* <tt>"aabfooaabfooabfoob"</tt>, and the replacement string
* <tt>"-"</tt>, an invocation of this method on a matcher for that
* expression would yield the string <tt>"-foo-foo-foo-"</tt>.
*
* <p> Invoking this method changes this matcher's state. If the matcher
* is to be used in further matching operations then it should first be
* reset. </p>
*
* @param replacement
* The replacement string
*
* @return The string constructed by replacing each matching subsequence
* by the replacement string, substituting captured subsequences
* as needed
*/
public String replaceAll(String replacement) {
reset();
boolean result = find();
if (result) {
StringBuffer sb = new StringBuffer();
do {
appendReplacement(sb, replacement);
result = find();
} while (result);
appendTail(sb);
return sb.toString();
}
return text.toString();
}
/**
* Replaces the first subsequence of the input sequence that matches the
* pattern with the given replacement string.
*
* <p> This method first resets this matcher. It then scans the input
* sequence looking for a match of the pattern. Characters that are not
* part of the match are appended directly to the result string; the match
* is replaced in the result by the replacement string. The replacement
* string may contain references to captured subsequences as in the {@link
* #appendReplacement appendReplacement} method.
*
* <p>Note that backslashes (<tt>\</tt>) and dollar signs (<tt>$</tt>) in
* the replacement string may cause the results to be different than if it
* were being treated as a literal replacement string. Dollar signs may be
* treated as references to captured subsequences as described above, and
* backslashes are used to escape literal characters in the replacement
* string.
*
* <p> Given the regular expression <tt>dog</tt>, the input
* <tt>"zzzdogzzzdogzzz"</tt>, and the replacement string
* <tt>"cat"</tt>, an invocation of this method on a matcher for that
* expression would yield the string <tt>"zzzcatzzzdogzzz"</tt>. </p>
*
* <p> Invoking this method changes this matcher's state. If the matcher
* is to be used in further matching operations then it should first be
* reset. </p>
*
* @param replacement
* The replacement string
* @return The string constructed by replacing the first matching
* subsequence by the replacement string, substituting captured
* subsequences as needed
*/
public String replaceFirst(String replacement) {
if (replacement == null)
throw new NullPointerException("replacement");
reset();