forked from jruby/jruby
-
Notifications
You must be signed in to change notification settings - Fork 0
/
RubyRegexp.java
2104 lines (1858 loc) · 80.2 KB
/
RubyRegexp.java
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
/***** BEGIN LICENSE BLOCK *****
* Version: CPL 1.0/GPL 2.0/LGPL 2.1
*
* The contents of this file are subject to the Common Public
* License Version 1.0 (the "License"); you may not use this file
* except in compliance with the License. You may obtain a copy of
* the License at http://www.eclipse.org/legal/cpl-v10.html
*
* Software distributed under the License is distributed on an "AS
* IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
* implied. See the License for the specific language governing
* rights and limitations under the License.
*
* Copyright (C) 2001 Alan Moore <alan_moore@gmx.net>
* Copyright (C) 2001-2002 Benoit Cerrina <b.cerrina@wanadoo.fr>
* Copyright (C) 2001-2004 Jan Arne Petersen <jpetersen@uni-bonn.de>
* Copyright (C) 2002-2004 Anders Bengtsson <ndrsbngtssn@yahoo.se>
* Copyright (C) 2004-2005 Thomas E Enebo <enebo@acm.org>
* Copyright (C) 2004 Stefan Matthias Aust <sma@3plus4.de>
* Copyright (C) 2005 David Corbin <dcorbin@users.sourceforge.net>
* Copyright (C) 2006 Nick Sieger <nicksieger@gmail.com>
* Copyright (C) 2006 Miguel Covarrubias <mlcovarrubias@gmail.com>
*
* Alternatively, the contents of this file may be used under the terms of
* either of the GNU General Public License Version 2 or later (the "GPL"),
* or the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
* in which case the provisions of the GPL or the LGPL are applicable instead
* of those above. If you wish to allow use of your version of this file only
* under the terms of either the GPL or the LGPL, and not to allow others to
* use your version of this file under the terms of the CPL, indicate your
* decision by deleting the provisions above and replace them with the notice
* and other provisions required by the GPL or the LGPL. If you do not delete
* the provisions above, a recipient may use your version of this file under
* the terms of any one of the CPL, the GPL or the LGPL.
***** END LICENSE BLOCK *****/
package org.jruby;
import static org.jruby.anno.FrameField.BACKREF;
import static org.jruby.anno.FrameField.LASTLINE;
import java.lang.ref.SoftReference;
import java.util.Iterator;
import java.util.Map;
import java.util.concurrent.ConcurrentHashMap;
import org.jcodings.Encoding;
import org.jcodings.specific.ASCIIEncoding;
import org.jcodings.specific.USASCIIEncoding;
import org.jcodings.specific.UTF8Encoding;
import org.joni.Matcher;
import org.joni.NameEntry;
import org.joni.Option;
import org.joni.Regex;
import org.joni.Region;
import org.joni.Syntax;
import org.joni.exception.JOniException;
import org.jruby.anno.JRubyClass;
import org.jruby.anno.JRubyMethod;
import org.jruby.common.IRubyWarnings.ID;
import org.jruby.exceptions.RaiseException;
import org.jruby.parser.ReOptions;
import org.jruby.runtime.Arity;
import org.jruby.runtime.Block;
import org.jruby.runtime.ClassIndex;
import org.jruby.runtime.DynamicScope;
import org.jruby.runtime.ObjectAllocator;
import org.jruby.runtime.ThreadContext;
import org.jruby.runtime.Visibility;
import org.jruby.runtime.builtin.IRubyObject;
import org.jruby.runtime.encoding.EncodingCapable;
import org.jruby.runtime.marshal.MarshalStream;
import org.jruby.runtime.marshal.UnmarshalStream;
import org.jruby.util.ByteList;
import org.jruby.util.KCode;
import org.jruby.util.Pack;
import org.jruby.util.Sprintf;
import org.jruby.util.StringSupport;
import org.jruby.util.TypeConverter;
@JRubyClass(name="Regexp")
public class RubyRegexp extends RubyObject implements ReOptions, EncodingCapable {
private KCode kcode;
private Regex pattern;
private ByteList str = ByteList.EMPTY_BYTELIST;
private static final int REGEXP_LITERAL_F = USER1_F;
private static final int REGEXP_KCODE_DEFAULT = USER2_F;
private static final int REGEXP_ENCODING_NONE = USER3_F;
private static final int ARG_OPTION_MASK = RE_OPTION_IGNORECASE | RE_OPTION_EXTENDED | RE_OPTION_MULTILINE;
private static final int ARG_ENCODING_FIXED = 16;
private static final int ARG_ENCODING_NONE = 32;
public void setLiteral() {
flags |= REGEXP_LITERAL_F;
}
public void clearLiteral() {
flags &= ~REGEXP_LITERAL_F;
}
public boolean isLiteral() {
return (flags & REGEXP_LITERAL_F) != 0;
}
public void setKCodeDefault() {
flags |= REGEXP_KCODE_DEFAULT;
}
public void clearKCodeDefault() {
flags &= ~REGEXP_KCODE_DEFAULT;
}
public boolean isKCodeDefault() {
return (flags & REGEXP_KCODE_DEFAULT) != 0;
}
public void setEncodingNone() {
flags |= REGEXP_ENCODING_NONE;
}
public void clearEncodingNone() {
flags &= ~REGEXP_ENCODING_NONE;
}
public boolean isEncodingNone() {
return (flags & REGEXP_ENCODING_NONE) != 0;
}
public KCode getKCode() {
return kcode;
}
public Encoding getEncoding() {
return pattern.getEncoding();
}
private static final class RegexpCache {
private volatile SoftReference<Map<ByteList, Regex>> cache = new SoftReference<Map<ByteList, Regex>>(null);
private Map<ByteList, Regex> get() {
Map<ByteList, Regex> patternCache = cache.get();
if (patternCache == null) {
patternCache = new ConcurrentHashMap<ByteList, Regex>(5);
cache = new SoftReference<Map<ByteList, Regex>>(patternCache);
}
return patternCache;
}
}
private static final RegexpCache patternCache = new RegexpCache();
private static final RegexpCache quotedPatternCache = new RegexpCache();
private static final RegexpCache preprocessedPatternCache = new RegexpCache();
private static Regex makeRegexp(Ruby runtime, ByteList bytes, int flags, Encoding enc) {
try {
int p = bytes.begin;
return new Regex(bytes.bytes, p, p + bytes.realSize, flags, enc, Syntax.DEFAULT, runtime.getWarnings());
} catch (Exception e) {
if (runtime.is1_9()) {
raiseRegexpError19(runtime, bytes, enc, flags, e.getMessage());
} else {
raiseRegexpError(runtime, bytes, enc, flags, e.getMessage());
}
return null; // not reached
}
}
static Regex getRegexpFromCache(Ruby runtime, ByteList bytes, Encoding enc, int options) {
Map<ByteList, Regex> cache = patternCache.get();
Regex regex = cache.get(bytes);
if (regex != null && regex.getEncoding() == enc && regex.getOptions() == options) return regex;
regex = makeRegexp(runtime, bytes, options, enc);
cache.put(bytes, regex);
return regex;
}
static Regex getQuotedRegexpFromCache(Ruby runtime, ByteList bytes, Encoding enc, int options) {
Map<ByteList, Regex> cache = quotedPatternCache.get();
Regex regex = cache.get(bytes);
if (regex != null && regex.getEncoding() == enc && regex.getOptions() == options) return regex;
regex = makeRegexp(runtime, quote(bytes, enc), options, enc);
cache.put(bytes, regex);
return regex;
}
static Regex getQuotedRegexpFromCache19(Ruby runtime, ByteList bytes, int options, boolean asciiOnly) {
Map<ByteList, Regex> cache = quotedPatternCache.get();
Regex regex = cache.get(bytes);
Encoding enc = asciiOnly ? USASCIIEncoding.INSTANCE : bytes.encoding;
if (regex != null && regex.getEncoding() == enc && regex.getOptions() == options) return regex;
ByteList quoted = quote19(bytes, asciiOnly);
regex = makeRegexp(runtime, quoted, options, quoted.encoding);
regex.setUserObject(quoted);
cache.put(bytes, regex);
return regex;
}
private static Regex getPreprocessedRegexpFromCache(Ruby runtime, ByteList bytes, Encoding enc, int options, ErrorMode mode) {
Map<ByteList, Regex> cache = preprocessedPatternCache.get();
Regex regex = cache.get(bytes);
if (regex != null && regex.getEncoding() == enc && regex.getOptions() == options) return regex;
ByteList preprocessed = preprocess(runtime, bytes, enc, new Encoding[]{null}, ErrorMode.RAISE);
regex = makeRegexp(runtime, preprocessed, options, enc);
regex.setUserObject(preprocessed);
cache.put(bytes, regex);
return regex;
}
public static RubyClass createRegexpClass(Ruby runtime) {
RubyClass regexpClass = runtime.defineClass("Regexp", runtime.getObject(), REGEXP_ALLOCATOR);
runtime.setRegexp(regexpClass);
regexpClass.index = ClassIndex.REGEXP;
regexpClass.setReifiedClass(RubyRegexp.class);
regexpClass.kindOf = new RubyModule.KindOf() {
@Override
public boolean isKindOf(IRubyObject obj, RubyModule type) {
return obj instanceof RubyRegexp;
}
};
regexpClass.defineConstant("IGNORECASE", runtime.newFixnum(RE_OPTION_IGNORECASE));
regexpClass.defineConstant("EXTENDED", runtime.newFixnum(RE_OPTION_EXTENDED));
regexpClass.defineConstant("MULTILINE", runtime.newFixnum(RE_OPTION_MULTILINE));
if (runtime.is1_9()) regexpClass.defineConstant("FIXEDENCODING", runtime.newFixnum(ARG_ENCODING_FIXED));
regexpClass.defineAnnotatedMethods(RubyRegexp.class);
return regexpClass;
}
private static ObjectAllocator REGEXP_ALLOCATOR = new ObjectAllocator() {
public IRubyObject allocate(Ruby runtime, RubyClass klass) {
return new RubyRegexp(runtime, klass);
}
};
@Override
public int getNativeTypeIndex() {
return ClassIndex.REGEXP;
}
/** used by allocator
*/
private RubyRegexp(Ruby runtime, RubyClass klass) {
super(runtime, klass);
}
/** default constructor
*/
private RubyRegexp(Ruby runtime) {
super(runtime, runtime.getRegexp());
}
private RubyRegexp(Ruby runtime, ByteList str) {
this(runtime);
setKCodeDefault();
this.kcode = runtime.getKCode();
this.str = str;
this.pattern = getRegexpFromCache(runtime, str, kcode.getEncoding(), 0);
}
private RubyRegexp(Ruby runtime, ByteList str, int options) {
this(runtime);
setKCode(runtime, options & 0x7f); // mask off "once" flag
this.str = str;
this.pattern = getRegexpFromCache(runtime, str, kcode.getEncoding(), options & 0xf);
}
// used only by the compiler/interpreter (will set the literal flag)
public static RubyRegexp newRegexp(Ruby runtime, String pattern, int options) {
return newRegexp(runtime, ByteList.create(pattern), options);
}
// used only by the compiler/interpreter (will set the literal flag)
public static RubyRegexp newRegexp(Ruby runtime, ByteList pattern, int options) {
try {
return new RubyRegexp(runtime, pattern, options);
} catch (RaiseException re) {
throw runtime.newSyntaxError(re.getMessage());
}
}
// used only by the compiler/interpreter (will set the literal flag)
public static RubyRegexp newDRegexp(Ruby runtime, RubyString pattern, int options) {
try {
return new RubyRegexp(runtime, pattern.getByteList(), options);
} catch (RaiseException re) {
throw runtime.newRegexpError(re.getMessage());
}
}
public static RubyRegexp newRegexp(Ruby runtime, ByteList pattern) {
return new RubyRegexp(runtime, pattern);
}
static RubyRegexp newRegexp(Ruby runtime, ByteList str, Regex pattern) {
RubyRegexp regexp = new RubyRegexp(runtime);
regexp.str = str;
regexp.setKCode(runtime, pattern.getOptions());
regexp.pattern = pattern;
return regexp;
}
// internal usage (Complex/Rational)
static RubyRegexp newDummyRegexp(Ruby runtime, Regex regex) {
RubyRegexp regexp = new RubyRegexp(runtime);
regexp.pattern = regex;
regexp.str = ByteList.EMPTY_BYTELIST;
regexp.kcode = KCode.NONE;
return regexp;
}
/** rb_get_kcode
*/
private int getKcode() {
if (kcode == KCode.NONE) {
return 16;
} else if (kcode == KCode.EUC) {
return 32;
} else if (kcode == KCode.SJIS) {
return 48;
} else if (kcode == KCode.UTF8) {
return 64;
}
return 0;
}
/** rb_set_kcode
*/
private void setKCode(Ruby runtime, int options) {
clearKCodeDefault();
switch (options & ~0xf) {
case 0:
default:
setKCodeDefault();
kcode = runtime.getKCode();
break;
case 16:
kcode = KCode.NONE;
break;
case 32:
kcode = KCode.EUC;
break;
case 48:
kcode = KCode.SJIS;
break;
case 64:
kcode = KCode.UTF8;
break;
}
}
/** rb_reg_options
*/
private int getOptions() {
check();
int options = (pattern.getOptions() & (RE_OPTION_IGNORECASE|RE_OPTION_MULTILINE|RE_OPTION_EXTENDED));
if (!isKCodeDefault()) options |= getKcode();
return options;
}
final Regex getPattern() {
check();
return pattern;
}
private static void encodingMatchError(Ruby runtime, Regex pattern, Encoding strEnc) {
throw runtime.newEncodingCompatibilityError("incompatible encoding regexp match (" +
pattern.getEncoding() + " regexp with " + strEnc + " string)");
}
private Encoding checkEncoding(RubyString str, boolean warn) {
if (str.scanForCodeRange() == StringSupport.CR_BROKEN) {
throw getRuntime().newArgumentError("invalid byte sequence in " + str.getEncoding());
}
check();
Encoding enc = str.getEncoding();
if (!enc.isAsciiCompatible()) {
if (enc != pattern.getEncoding()) encodingMatchError(getRuntime(), pattern, enc);
} else if (!isKCodeDefault()) {
if (enc != pattern.getEncoding() &&
(!pattern.getEncoding().isAsciiCompatible() ||
str.scanForCodeRange() != StringSupport.CR_7BIT)) encodingMatchError(getRuntime(), pattern, enc);
enc = pattern.getEncoding();
}
if (warn && isEncodingNone() && enc != ASCIIEncoding.INSTANCE && str.scanForCodeRange() != StringSupport.CR_7BIT) {
getRuntime().getWarnings().warn(ID.REGEXP_MATCH_AGAINST_STRING, "regexp match /.../n against to " + enc + " string");
}
return enc;
}
final Regex preparePattern(RubyString str) {
check();
Encoding enc = checkEncoding(str, true);
if (enc == pattern.getEncoding()) return pattern;
return getPreprocessedRegexpFromCache(getRuntime(), this.str, enc, pattern.getOptions(), ErrorMode.PREPROCESS);
}
static Regex preparePattern(Ruby runtime, Regex pattern, RubyString str) {
if (str.scanForCodeRange() == StringSupport.CR_BROKEN) {
throw runtime.newArgumentError("invalid byte sequence in " + str.getEncoding());
}
Encoding enc = str.getEncoding();
if (!enc.isAsciiCompatible()) {
if (enc != pattern.getEncoding()) encodingMatchError(runtime, pattern, enc);
}
// TODO: check for isKCodeDefault() somehow
// if (warn && isEncodingNone() && enc != ASCIIEncoding.INSTANCE && str.scanForCodeRange() != StringSupport.CR_7BIT) {
// getRuntime().getWarnings().warn(ID.REGEXP_MATCH_AGAINST_STRING, "regexp match /.../n against to " + enc + " string");
// }
if (enc == pattern.getEncoding()) return pattern;
return getPreprocessedRegexpFromCache(runtime, (ByteList)pattern.getUserObject(), enc, pattern.getOptions(), ErrorMode.PREPROCESS);
}
private static enum ErrorMode {RAISE, PREPROCESS, DESC}
private static int raisePreprocessError(Ruby runtime, ByteList str, String err, ErrorMode mode) {
switch (mode) {
case RAISE:
raiseRegexpError19(runtime, str, str.encoding, 0, err);
case PREPROCESS:
throw runtime.newArgumentError("regexp preprocess failed: " + err);
case DESC:
// silent ?
}
return 0;
}
private static int readEscapedByte(Ruby runtime, byte[]to, int toP, byte[]bytes, int p, int end, ByteList str, ErrorMode mode) {
if (p == end || bytes[p++] != (byte)'\\') raisePreprocessError(runtime, str, "too short escaped multibyte character", mode);
boolean metaPrefix = false, ctrlPrefix = false;
int code = 0;
while (true) {
if (p == end) raisePreprocessError(runtime, str, "too short escape sequence", mode);
switch (bytes[p++]) {
case '\\': code = '\\'; break;
case 'n': code = '\n'; break;
case 't': code = '\t'; break;
case 'r': code = '\r'; break;
case 'f': code = '\f'; break;
case 'v': code = '\013'; break;
case 'a': code = '\007'; break;
case 'e': code = '\033'; break;
/* \OOO */
case '0': case '1': case '2': case '3':
case '4': case '5': case '6': case '7':
p--;
int olen = end < p + 3 ? end - p : 3;
code = StringSupport.scanOct(bytes, p, olen);
p += StringSupport.octLength(bytes, p, olen);
break;
case 'x': /* \xHH */
int hlen = end < p + 2 ? end - p : 2;
code = StringSupport.scanHex(bytes, p, hlen);
int len = StringSupport.hexLength(bytes, p, hlen);
if (len < 1) raisePreprocessError(runtime, str, "invalid hex escape", mode);
p += len;
break;
case 'M': /* \M-X, \M-\C-X, \M-\cX */
if (metaPrefix) raisePreprocessError(runtime, str, "duplicate meta escape", mode);
metaPrefix = true;
if (p + 1 < end && bytes[p++] == (byte)'-' && (bytes[p] & 0x80) == 0) {
if (bytes[p] == (byte)'\\') {
p++;
continue;
} else {
code = bytes[p++] & 0xff;
break;
}
}
raisePreprocessError(runtime, str, "too short meta escape", mode);
case 'C': /* \C-X, \C-\M-X */
if (p == end || bytes[p++] != (byte)'-') raisePreprocessError(runtime, str, "too short control escape", mode);
case 'c': /* \cX, \c\M-X */
if (ctrlPrefix) raisePreprocessError(runtime, str, "duplicate control escape", mode);
ctrlPrefix = true;
if (p < end && (bytes[p] & 0x80) == 0) {
if (bytes[p] == (byte)'\\') {
p++;
continue;
} else {
code = bytes[p++] & 0xff;
break;
}
}
raisePreprocessError(runtime, str, "too short control escape", mode);
default:
raisePreprocessError(runtime, str, "unexpected escape sequence", mode);
} // switch
if (code < 0 || code > 0xff) raisePreprocessError(runtime, str, "invalid escape code", mode);
if (ctrlPrefix) code &= 0x1f;
if (metaPrefix) code |= 0x80;
to[toP] = (byte)code;
return p;
} // while
}
private static int unescapeEscapedNonAscii(Ruby runtime, ByteList to, byte[]bytes, int p, int end, Encoding enc, Encoding[]encp, ByteList str, ErrorMode mode) {
byte[]chBuf = new byte[enc.maxLength()];
int chLen = 0;
p = readEscapedByte(runtime, chBuf, chLen++, bytes, p, end, str, mode);
while (chLen < enc.maxLength() && StringSupport.preciseLength(enc, chBuf, 0, chLen) < -1) { // MBCLEN_NEEDMORE_P
p = readEscapedByte(runtime, chBuf, chLen++, bytes, p, end, str, mode);
}
int cl = StringSupport.preciseLength(enc, chBuf, 0, chLen);
if (cl == -1) raisePreprocessError(runtime, str, "invalid multibyte escape", mode); // MBCLEN_INVALID_P
if (chLen > 1 || (chBuf[0] & 0x80) != 0) {
to.append(chBuf, 0, chLen);
if (encp[0] == null) {
encp[0] = enc;
} else if (encp[0] != enc) {
raisePreprocessError(runtime, str, "escaped non ASCII character in UTF-8 regexp", mode);
}
} else {
Sprintf.sprintf(runtime, to, "\\x%02X", chBuf[0] & 0xff);
}
return p;
}
private static void checkUnicodeRange(Ruby runtime, int code, ByteList str, ErrorMode mode) {
// Unicode is can be only 21 bits long, int is enough
if ((0xd800 <= code && code <= 0xdfff) /* Surrogates */ || 0x10ffff < code) {
raisePreprocessError(runtime, str, "invalid Unicode range", mode);
}
}
private static void appendUtf8(Ruby runtime, ByteList to, int code, Encoding[]enc, ByteList str, ErrorMode mode) {
checkUnicodeRange(runtime, code, str, mode);
if (code < 0x80) {
Sprintf.sprintf(runtime, to, "\\x%02X", code);
} else {
to.ensure(to.realSize + 6);
to.realSize += Pack.utf8Decode(runtime, to.bytes, to.begin + to.realSize, code);
if (enc[0] == null) {
enc[0] = UTF8Encoding.INSTANCE;
} else if (!(enc[0] instanceof UTF8Encoding)) { // do not load the class if not used
raisePreprocessError(runtime, str, "UTF-8 character in non UTF-8 regexp", mode);
}
}
}
private static int unescapeUnicodeList(Ruby runtime, ByteList to, byte[]bytes, int p, int end, Encoding[]encp, ByteList str, ErrorMode mode) {
while (p < end && ASCIIEncoding.INSTANCE.isSpace(bytes[p] & 0xff)) p++;
boolean hasUnicode = false;
while (true) {
int code = StringSupport.scanHex(bytes, p, end - p);
int len = StringSupport.hexLength(bytes, p, end - p);
if (len == 0) break;
if (len > 6) raisePreprocessError(runtime, str, "invalid Unicode range", mode);
p += len;
appendUtf8(runtime, to, code, encp, str, mode);
hasUnicode = true;
while (p < end && ASCIIEncoding.INSTANCE.isSpace(bytes[p] & 0xff)) p++;
}
if (!hasUnicode) raisePreprocessError(runtime, str, "invalid Unicode list", mode);
return p;
}
private static int unescapeUnicodeBmp(Ruby runtime, ByteList to, byte[]bytes, int p, int end, Encoding[]encp, ByteList str, ErrorMode mode) {
if (p + 4 > end) raisePreprocessError(runtime, str, "invalid Unicode escape", mode);
int code = StringSupport.scanHex(bytes, p, 4);
int len = StringSupport.hexLength(bytes, p, 4);
if (len != 4) raisePreprocessError(runtime, str, "invalid Unicode escape", mode);
appendUtf8(runtime, to, code, encp, str, mode);
return p + 4;
}
private static boolean unescapeNonAscii(Ruby runtime, ByteList to, byte[]bytes, int p, int end, Encoding enc, Encoding[]encp, ByteList str, ErrorMode mode) {
boolean hasProperty = false;
while (p < end) {
int cl = StringSupport.preciseLength(enc, bytes, p, end);
if (cl <= 0) raisePreprocessError(runtime, str, "invalid multibyte character", mode);
if (cl > 1 || (bytes[p] & 0x80) != 0) {
to.append(bytes, p, cl);
p += cl;
if (encp[0] == null) {
encp[0] = enc;
} else if (encp[0] != enc) {
raisePreprocessError(runtime, str, "non ASCII character in UTF-8 regexp", mode);
}
continue;
}
int c;
switch (c = bytes[p++] & 0xff) {
case '\\':
if (p == end) raisePreprocessError(runtime, str, "too short escape sequence", mode);
switch (c = bytes[p++] & 0xff) {
case '1': case '2': case '3':
case '4': case '5': case '6': case '7': /* \O, \OO, \OOO or backref */
if (StringSupport.scanOct(bytes, p - 1, end - (p - 1)) <= 0177) {
to.append('\\').append(c);
break;
}
case '0': /* \0, \0O, \0OO */
case 'x': /* \xHH */
case 'c': /* \cX, \c\M-X */
case 'C': /* \C-X, \C-\M-X */
case 'M': /* \M-X, \M-\C-X, \M-\cX */
p = unescapeEscapedNonAscii(runtime, to, bytes, p - 2, end, enc, encp, str, mode);
break;
case 'u':
if (p == end) raisePreprocessError(runtime, str, "too short escape sequence", mode);
if (bytes[p] == (byte)'{') { /* \\u{H HH HHH HHHH HHHHH HHHHHH ...} */
p++;
p = unescapeUnicodeList(runtime, to, bytes, p, end, encp, str, mode);
if (p == end || bytes[p++] != (byte)'}') raisePreprocessError(runtime, str, "invalid Unicode list", mode);
} else { /* \\uHHHH */
p = unescapeUnicodeBmp(runtime, to, bytes, p, end, encp, str, mode);
}
break;
case 'p': /* \p{Hiragana} */
if (encp[0] == null) hasProperty = true;
to.append('\\').append(c);
break;
default:
to.append('\\').append(c);
break;
} // inner switch
break;
default:
to.append(c);
} // switch
} // while
return hasProperty;
}
private static ByteList preprocess(Ruby runtime, ByteList str, Encoding enc, Encoding[]fixedEnc, ErrorMode mode) {
ByteList to = new ByteList(str.realSize);
if (enc.isAsciiCompatible()) {
fixedEnc[0] = null;
} else {
fixedEnc[0] = enc;
to.encoding = enc;
}
boolean hasProperty = unescapeNonAscii(runtime, to, str.bytes, str.begin, str.begin + str.realSize, enc, fixedEnc, str, mode);
if (hasProperty && fixedEnc[0] == null) fixedEnc[0] = enc;
if (fixedEnc[0] != null) to.encoding = fixedEnc[0];
return to;
}
public static void preprocessCheck(Ruby runtime, IRubyObject obj) {
ByteList bytes = obj.convertToString().getByteList();
preprocess(runtime, bytes, bytes.encoding, new Encoding[]{null}, ErrorMode.RAISE);
}
private void check() {
if (pattern == null) throw getRuntime().newTypeError("uninitialized Regexp");
}
@JRubyMethod(name = {"new", "compile"}, required = 1, optional = 2, meta = true)
public static RubyRegexp newInstance(IRubyObject recv, IRubyObject[] args) {
RubyClass klass = (RubyClass)recv;
RubyRegexp re = (RubyRegexp) klass.allocate();
re.callInit(args, Block.NULL_BLOCK);
return re;
}
@JRubyMethod(name = "try_convert", meta = true, compat = CompatVersion.RUBY1_9)
public static IRubyObject try_convert(ThreadContext context, IRubyObject recv, IRubyObject args) {
return TypeConverter.convertToTypeWithCheck(args, context.getRuntime().getRegexp(), "to_regexp");
}
/** rb_reg_s_quote
*
*/
@JRubyMethod(name = {"quote", "escape"}, required = 1, optional = 1, meta = true, compat = CompatVersion.RUBY1_8)
public static RubyString quote(ThreadContext context, IRubyObject recv, IRubyObject[] args) {
Ruby runtime = context.getRuntime();
final KCode code;
if (args.length == 1 || args[1].isNil()) {
code = runtime.getKCode();
} else {
code = KCode.create(runtime, args[1].toString());
}
RubyString src = args[0].convertToString();
RubyString dst = RubyString.newStringShared(runtime, quote(src.getByteList(), code.getEncoding()));
dst.infectBy(src);
return dst;
}
@JRubyMethod(name = {"quote", "escape"}, meta = true, compat = CompatVersion.RUBY1_9)
public static IRubyObject quote19(ThreadContext context, IRubyObject recv, IRubyObject arg) {
Ruby runtime = context.getRuntime();
RubyString str = operandCheck(runtime, arg);
return RubyString.newStringShared(runtime, quote19(str.getByteList(), str.isAsciiOnly()));
}
/** rb_reg_quote
*
*/
private static ByteList quote(ByteList bs, Encoding enc) {
int p = bs.begin;
int end = p + bs.realSize;
byte[]bytes = bs.bytes;
metaFound: do {
for(; p < end; p++) {
int c = bytes[p] & 0xff;
int cl = enc.length(bytes, p, end);
if (cl != 1) {
while (cl-- > 0 && p < end) p++;
p--;
continue;
}
switch (c) {
case '[': case ']': case '{': case '}':
case '(': case ')': case '|': case '-':
case '*': case '.': case '\\':
case '?': case '+': case '^': case '$':
case ' ': case '#':
case '\t': case '\f': case '\n': case '\r':
break metaFound;
}
}
return bs;
} while (false);
ByteList result = new ByteList(end * 2);
byte[]obytes = result.bytes;
int op = p - bs.begin;
System.arraycopy(bytes, bs.begin, obytes, 0, op);
for(; p < end; p++) {
int c = bytes[p] & 0xff;
int cl = enc.length(bytes, p, end);
if (cl != 1) {
while (cl-- > 0 && p < end) obytes[op++] = bytes[p++];
p--;
continue;
}
switch (c) {
case '[': case ']': case '{': case '}':
case '(': case ')': case '|': case '-':
case '*': case '.': case '\\':
case '?': case '+': case '^': case '$':
case '#': obytes[op++] = '\\'; break;
case ' ': obytes[op++] = '\\'; obytes[op++] = ' '; continue;
case '\t':obytes[op++] = '\\'; obytes[op++] = 't'; continue;
case '\n':obytes[op++] = '\\'; obytes[op++] = 'n'; continue;
case '\r':obytes[op++] = '\\'; obytes[op++] = 'r'; continue;
case '\f':obytes[op++] = '\\'; obytes[op++] = 'f'; continue;
}
obytes[op++] = (byte)c;
}
result.realSize = op;
return result;
}
static ByteList quote19(ByteList bs, boolean asciiOnly) {
int p = bs.begin;
int end = p + bs.realSize;
byte[]bytes = bs.bytes;
Encoding enc = bs.encoding;
metaFound: do {
while (p < end) {
final int c;
final int cl;
if (enc.isAsciiCompatible()) {
cl = 1;
c = bytes[p] & 0xff;
} else {
cl = StringSupport.preciseLength(enc, bytes, p, end);
c = enc.mbcToCode(bytes, p, end);
}
if (!Encoding.isAscii(c)) {
p += StringSupport.length(enc, bytes, p, end);
continue;
}
switch (c) {
case '[': case ']': case '{': case '}':
case '(': case ')': case '|': case '-':
case '*': case '.': case '\\':
case '?': case '+': case '^': case '$':
case ' ': case '#':
case '\t': case '\f': case '\n': case '\r':
break metaFound;
}
p += cl;
}
if (asciiOnly) {
ByteList tmp = bs.shallowDup();
tmp.encoding = USASCIIEncoding.INSTANCE;
return tmp;
}
return bs;
} while (false);
ByteList result = new ByteList(end * 2);
result.encoding = asciiOnly ? USASCIIEncoding.INSTANCE : bs.encoding;
byte[]obytes = result.bytes;
int op = p - bs.begin;
System.arraycopy(bytes, bs.begin, obytes, 0, op);
while (p < end) {
final int c;
final int cl;
if (enc.isAsciiCompatible()) {
cl = 1;
c = bytes[p] & 0xff;
} else {
cl = StringSupport.preciseLength(enc, bytes, p, end);
c = enc.mbcToCode(bytes, p, end);
}
if (!Encoding.isAscii(c)) {
int n = StringSupport.length(enc, bytes, p, end);
while (n-- > 0) obytes[op++] = bytes[p++];
continue;
}
p += cl;
switch (c) {
case '[': case ']': case '{': case '}':
case '(': case ')': case '|': case '-':
case '*': case '.': case '\\':
case '?': case '+': case '^': case '$':
case '#':
op += enc.codeToMbc('\\', obytes, op);
break;
case ' ':
op += enc.codeToMbc('\\', obytes, op);
op += enc.codeToMbc(' ', obytes, op);
continue;
case '\t':
op += enc.codeToMbc('\\', obytes, op);
op += enc.codeToMbc('t', obytes, op);
continue;
case '\n':
op += enc.codeToMbc('\\', obytes, op);
op += enc.codeToMbc('n', obytes, op);
continue;
case '\r':
op += enc.codeToMbc('\\', obytes, op);
op += enc.codeToMbc('r', obytes, op);
continue;
case '\f':
op += enc.codeToMbc('\\', obytes, op);
op += enc.codeToMbc('f', obytes, op);
continue;
}
op += enc.codeToMbc(c, obytes, op);
}
result.realSize = op;
return result;
}
/**
* Variable arity version for compatibility. Not bound to a Ruby method.
* @deprecated Use the versions with zero, one, or two args.
*/
public static IRubyObject last_match_s(ThreadContext context, IRubyObject recv, IRubyObject[] args) {
switch (args.length) {
case 0:
return last_match_s(context, recv);
case 1:
return last_match_s(context, recv, args[0]);
default:
Arity.raiseArgumentError(context.getRuntime(), args.length, 0, 1);
return null; // not reached
}
}
/** rb_reg_s_last_match / match_getter
*
*/
@JRubyMethod(name = "last_match", meta = true, reads = BACKREF)
public static IRubyObject last_match_s(ThreadContext context, IRubyObject recv) {
IRubyObject match = context.getCurrentScope().getBackRef(context.getRuntime());
if (match instanceof RubyMatchData) ((RubyMatchData)match).use();
return match;
}
/** rb_reg_s_last_match
*
*/
@JRubyMethod(name = "last_match", meta = true, reads = BACKREF)
public static IRubyObject last_match_s(ThreadContext context, IRubyObject recv, IRubyObject nth) {
IRubyObject match = context.getCurrentScope().getBackRef(context.getRuntime());
if (match.isNil()) return match;
return nth_match(((RubyMatchData)match).backrefNumber(nth), match);
}
/** rb_reg_s_union
*
*/
@JRubyMethod(name = "union", rest = true, meta = true)
public static IRubyObject union(ThreadContext context, IRubyObject recv, IRubyObject[] args) {
Ruby runtime = context.getRuntime();
IRubyObject[] realArgs = args;
if (args.length == 0) {
return newRegexp(runtime, ByteList.create("(?!)"), 0);
} else if (args.length == 1) {
IRubyObject v = TypeConverter.convertToTypeWithCheck(args[0], runtime.getRegexp(), "to_regexp");
if (!v.isNil()) {
return v;
} else {
IRubyObject a = TypeConverter.convertToTypeWithCheck(args[0], runtime.getArray(), "to_ary");
if (!a.isNil()) {
RubyArray aa = (RubyArray)a;
int len = aa.getLength();
realArgs = new IRubyObject[len];
for(int i = 0; i<len; i++) {
realArgs[i] = aa.entry(i);
}
} else {
// newInstance here
return newRegexp(runtime, quote(context, recv, args).getByteList(), 0);
}
}
}
KCode kcode = null;
IRubyObject kcode_re = runtime.getNil();
RubyString source = runtime.newString();
IRubyObject[] _args = new IRubyObject[3];
for (int i = 0; i < realArgs.length; i++) {
if (0 < i) source.cat((byte)'|');
IRubyObject v = TypeConverter.convertToTypeWithCheck(realArgs[i], runtime.getRegexp(), "to_regexp");
if (!v.isNil()) {
if (!((RubyRegexp)v).isKCodeDefault()) {
if (kcode == null) {
kcode_re = v;
kcode = ((RubyRegexp)v).kcode;
} else if (((RubyRegexp)v).kcode != kcode) {
IRubyObject str1 = kcode_re.inspect();
IRubyObject str2 = v.inspect();
throw runtime.newArgumentError("mixed kcode " + str1 + " and " + str2);
}
}
v = ((RubyRegexp)v).to_s();
} else {
v = quote(context, recv, new IRubyObject[]{realArgs[i]});
}
source.append(v);
}
_args[0] = source;
_args[1] = runtime.getNil();
if (kcode == null) {
_args[2] = runtime.getNil();
} else if (kcode == KCode.NONE) {
_args[2] = runtime.newString("n");
} else if (kcode == KCode.EUC) {
_args[2] = runtime.newString("e");
} else if (kcode == KCode.SJIS) {
_args[2] = runtime.newString("s");
} else if (kcode == KCode.UTF8) {
_args[2] = runtime.newString("u");
}
return recv.callMethod(context, "new", _args);
}
// rb_reg_raise
private static void raiseRegexpError(Ruby runtime, ByteList bytes, Encoding enc, int flags, String err) {
throw runtime.newRegexpError(err + ": " + regexpDescription(runtime, bytes, enc, flags));
}
// rb_reg_desc
private static ByteList regexpDescription(Ruby runtime, ByteList bytes, Encoding enc, int options) {
return regexpDescription(runtime, bytes.bytes, bytes.begin, bytes.realSize, enc, options);
}
private static ByteList regexpDescription(Ruby runtime, byte[] bytes, int start, int len, Encoding enc, int options) {
ByteList description = new ByteList();
description.append((byte)'/');