/
NonBlockingJsonParser.java
2869 lines (2692 loc) · 105 KB
/
NonBlockingJsonParser.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
package com.fasterxml.jackson.core.json.async;
import java.io.IOException;
import java.io.OutputStream;
import com.fasterxml.jackson.core.*;
import com.fasterxml.jackson.core.async.ByteArrayFeeder;
import com.fasterxml.jackson.core.async.NonBlockingInputFeeder;
import com.fasterxml.jackson.core.io.CharTypes;
import com.fasterxml.jackson.core.io.IOContext;
import com.fasterxml.jackson.core.sym.ByteQuadsCanonicalizer;
import com.fasterxml.jackson.core.util.VersionUtil;
public class NonBlockingJsonParser
extends NonBlockingJsonParserBase
implements ByteArrayFeeder
{
@SuppressWarnings("deprecation")
private final static int FEAT_MASK_TRAILING_COMMA = Feature.ALLOW_TRAILING_COMMA.getMask();
@SuppressWarnings("deprecation")
private final static int FEAT_MASK_LEADING_ZEROS = Feature.ALLOW_NUMERIC_LEADING_ZEROS.getMask();
@SuppressWarnings("deprecation")
private final static int FEAT_MASK_ALLOW_MISSING = Feature.ALLOW_MISSING_VALUES.getMask();
private final static int FEAT_MASK_ALLOW_SINGLE_QUOTES = Feature.ALLOW_SINGLE_QUOTES.getMask();
private final static int FEAT_MASK_ALLOW_UNQUOTED_NAMES = Feature.ALLOW_UNQUOTED_FIELD_NAMES.getMask();
private final static int FEAT_MASK_ALLOW_JAVA_COMMENTS = Feature.ALLOW_COMMENTS.getMask();
private final static int FEAT_MASK_ALLOW_YAML_COMMENTS = Feature.ALLOW_YAML_COMMENTS.getMask();
// This is the main input-code lookup table, fetched eagerly
private final static int[] _icUTF8 = CharTypes.getInputCodeUtf8();
// Latin1 encoding is not supported, but we do use 8-bit subset for
// pre-processing task, to simplify first pass, keep it fast.
protected final static int[] _icLatin1 = CharTypes.getInputCodeLatin1();
/*
/**********************************************************************
/* Input source config
/**********************************************************************
*/
/**
* This buffer is actually provided via {@link NonBlockingInputFeeder}
*/
protected byte[] _inputBuffer = NO_BYTES;
/**
* In addition to current buffer pointer, and end pointer,
* we will also need to know number of bytes originally
* contained. This is needed to correctly update location
* information when the block has been completed.
*/
protected int _origBufferLen;
// And from ParserBase:
// protected int _inputPtr;
// protected int _inputEnd;
/*
/**********************************************************************
/* Life-cycle
/**********************************************************************
*/
public NonBlockingJsonParser(IOContext ctxt, int parserFeatures,
ByteQuadsCanonicalizer sym)
{
super(ctxt, parserFeatures, sym);
}
/*
/**********************************************************************
/* AsyncInputFeeder impl
/**********************************************************************
*/
@Override
public ByteArrayFeeder getNonBlockingInputFeeder() {
return this;
}
@Override
public final boolean needMoreInput() {
return (_inputPtr >=_inputEnd) && !_endOfInput;
}
@Override
public void feedInput(byte[] buf, int start, int end) throws IOException
{
// Must not have remaining input
if (_inputPtr < _inputEnd) {
_reportError("Still have %d undecoded bytes, should not call 'feedInput'", _inputEnd - _inputPtr);
}
if (end < start) {
_reportError("Input end (%d) may not be before start (%d)", end, start);
}
// and shouldn't have been marked as end-of-input
if (_endOfInput) {
_reportError("Already closed, can not feed more input");
}
// Time to update pointers first
_currInputProcessed += _origBufferLen;
// Also need to adjust row start, to work as if it extended into the past wrt new buffer
_currInputRowStart = start - (_inputEnd - _currInputRowStart);
// And then update buffer settings
_currBufferStart = start;
_inputBuffer = buf;
_inputPtr = start;
_inputEnd = end;
_origBufferLen = end - start;
}
@Override
public void endOfInput() {
_endOfInput = true;
}
/*
/**********************************************************************
/* Abstract methods/overrides from JsonParser
/**********************************************************************
*/
/* Implementing these methods efficiently for non-blocking cases would
* be complicated; so for now let's just use the default non-optimized
* implementation
*/
// public boolean nextFieldName(SerializableString str) throws IOException
// public String nextTextValue() throws IOException
// public int nextIntValue(int defaultValue) throws IOException
// public long nextLongValue(long defaultValue) throws IOException
// public Boolean nextBooleanValue() throws IOException
@Override
public int releaseBuffered(OutputStream out) throws IOException {
int avail = _inputEnd - _inputPtr;
if (avail > 0) {
out.write(_inputBuffer, _inputPtr, avail);
}
return avail;
}
// Should never be called: can not be implemented quite as expected
// due to non-blocking behavior
@Override
protected char _decodeEscaped() throws IOException {
VersionUtil.throwInternal();
return ' ';
}
/*
/**********************************************************************
/* Main-level decoding
/**********************************************************************
*/
@Override
public JsonToken nextToken() throws IOException
{
// First: regardless of where we really are, need at least one more byte;
// can simplify some of the checks by short-circuiting right away
if (_inputPtr >= _inputEnd) {
if (_closed) {
return null;
}
// note: if so, do not even bother changing state
if (_endOfInput) { // except for this special case
// End-of-input within (possibly...) started token is bit complicated,
// so offline
if (_currToken == JsonToken.NOT_AVAILABLE) {
return _finishTokenWithEOF();
}
return _eofAsNextToken();
}
return JsonToken.NOT_AVAILABLE;
}
// in the middle of tokenization?
if (_currToken == JsonToken.NOT_AVAILABLE) {
return _finishToken();
}
// No: fresh new token; may or may not have existing one
_numTypesValid = NR_UNKNOWN;
_tokenInputTotal = _currInputProcessed + _inputPtr;
// also: clear any data retained so far
_binaryValue = null;
int ch = _inputBuffer[_inputPtr++] & 0xFF;
switch (_majorState) {
case MAJOR_INITIAL:
return _startDocument(ch);
case MAJOR_ROOT:
return _startValue(ch);
case MAJOR_OBJECT_FIELD_FIRST: // expect field-name or end-object
return _startFieldName(ch);
case MAJOR_OBJECT_FIELD_NEXT: // expect comma + field-name or end-object
return _startFieldNameAfterComma(ch);
case MAJOR_OBJECT_VALUE: // expect colon, followed by value
return _startValueExpectColon(ch);
case MAJOR_ARRAY_ELEMENT_FIRST: // expect value or end-array
return _startValue(ch);
case MAJOR_ARRAY_ELEMENT_NEXT: // expect leading comma + value or end-array
return _startValueExpectComma(ch);
default:
}
VersionUtil.throwInternal();
return null;
}
/**
* Method called when decoding of a token has been started, but not yet completed due
* to missing input; method is to continue decoding due to at least one more byte
* being made available to decode.
*/
protected final JsonToken _finishToken() throws IOException
{
// NOTE: caller ensures there's input available...
switch (_minorState) {
case MINOR_ROOT_BOM:
return _finishBOM(_pending32);
case MINOR_FIELD_LEADING_WS:
return _startFieldName(_inputBuffer[_inputPtr++] & 0xFF);
case MINOR_FIELD_LEADING_COMMA:
return _startFieldNameAfterComma(_inputBuffer[_inputPtr++] & 0xFF);
// Field name states
case MINOR_FIELD_NAME:
return _parseEscapedName(_quadLength, _pending32, _pendingBytes);
case MINOR_FIELD_NAME_ESCAPE:
return _finishFieldWithEscape();
case MINOR_FIELD_APOS_NAME:
return _finishAposName(_quadLength, _pending32, _pendingBytes);
case MINOR_FIELD_UNQUOTED_NAME:
return _finishUnquotedName(_quadLength, _pending32, _pendingBytes);
// Value states
case MINOR_VALUE_LEADING_WS:
return _startValue(_inputBuffer[_inputPtr++] & 0xFF);
case MINOR_VALUE_WS_AFTER_COMMA:
return _startValueAfterComma(_inputBuffer[_inputPtr++] & 0xFF);
case MINOR_VALUE_EXPECTING_COMMA:
return _startValueExpectComma(_inputBuffer[_inputPtr++] & 0xFF);
case MINOR_VALUE_EXPECTING_COLON:
return _startValueExpectColon(_inputBuffer[_inputPtr++] & 0xFF);
case MINOR_VALUE_TOKEN_NULL:
return _finishKeywordToken("null", _pending32, JsonToken.VALUE_NULL);
case MINOR_VALUE_TOKEN_TRUE:
return _finishKeywordToken("true", _pending32, JsonToken.VALUE_TRUE);
case MINOR_VALUE_TOKEN_FALSE:
return _finishKeywordToken("false", _pending32, JsonToken.VALUE_FALSE);
case MINOR_VALUE_TOKEN_NON_STD:
return _finishNonStdToken(_nonStdTokenType, _pending32);
case MINOR_NUMBER_MINUS:
return _finishNumberMinus(_inputBuffer[_inputPtr++] & 0xFF);
case MINOR_NUMBER_ZERO:
return _finishNumberLeadingZeroes();
case MINOR_NUMBER_MINUSZERO:
return _finishNumberLeadingNegZeroes();
case MINOR_NUMBER_INTEGER_DIGITS:
return _finishNumberIntegralPart(_textBuffer.getBufferWithoutReset(),
_textBuffer.getCurrentSegmentSize());
case MINOR_NUMBER_FRACTION_DIGITS:
return _finishFloatFraction();
case MINOR_NUMBER_EXPONENT_MARKER:
return _finishFloatExponent(true, _inputBuffer[_inputPtr++] & 0xFF);
case MINOR_NUMBER_EXPONENT_DIGITS:
return _finishFloatExponent(false, _inputBuffer[_inputPtr++] & 0xFF);
case MINOR_VALUE_STRING:
return _finishRegularString();
case MINOR_VALUE_STRING_UTF8_2:
_textBuffer.append((char) _decodeUTF8_2(_pending32, _inputBuffer[_inputPtr++]));
if (_minorStateAfterSplit == MINOR_VALUE_APOS_STRING) {
return _finishAposString();
}
return _finishRegularString();
case MINOR_VALUE_STRING_UTF8_3:
if (!_decodeSplitUTF8_3(_pending32, _pendingBytes, _inputBuffer[_inputPtr++])) {
return JsonToken.NOT_AVAILABLE;
}
if (_minorStateAfterSplit == MINOR_VALUE_APOS_STRING) {
return _finishAposString();
}
return _finishRegularString();
case MINOR_VALUE_STRING_UTF8_4:
if (!_decodeSplitUTF8_4(_pending32, _pendingBytes, _inputBuffer[_inputPtr++])) {
return JsonToken.NOT_AVAILABLE;
}
if (_minorStateAfterSplit == MINOR_VALUE_APOS_STRING) {
return _finishAposString();
}
return _finishRegularString();
case MINOR_VALUE_STRING_ESCAPE:
{
int c = _decodeSplitEscaped(_quoted32, _quotedDigits);
if (c < 0) {
return JsonToken.NOT_AVAILABLE;
}
_textBuffer.append((char) c);
}
if (_minorStateAfterSplit == MINOR_VALUE_APOS_STRING) {
return _finishAposString();
}
return _finishRegularString();
case MINOR_VALUE_APOS_STRING:
return _finishAposString();
case MINOR_VALUE_TOKEN_ERROR: // case of "almost token", just need tokenize for error
return _finishErrorToken();
// Comments
case MINOR_COMMENT_LEADING_SLASH:
return _startSlashComment(_pending32);
case MINOR_COMMENT_CLOSING_ASTERISK:
return _finishCComment(_pending32, true);
case MINOR_COMMENT_C:
return _finishCComment(_pending32, false);
case MINOR_COMMENT_CPP:
return _finishCppComment(_pending32);
case MINOR_COMMENT_YAML:
return _finishHashComment(_pending32);
}
VersionUtil.throwInternal();
return null;
}
/**
* Method similar to {@link #_finishToken}, but called when no more input is
* available, and end-of-input has been detected. This is usually problem
* case, but not always: root-level values may be properly terminated by
* this, and similarly trailing white-space may have been skipped.
*/
protected final JsonToken _finishTokenWithEOF() throws IOException
{
// NOTE: caller ensures there's input available...
JsonToken t = _currToken;
switch (_minorState) {
case MINOR_ROOT_GOT_SEPARATOR: // fine, just skip some trailing space
return _eofAsNextToken();
case MINOR_VALUE_LEADING_WS: // finished at token boundary; probably fine
return _eofAsNextToken();
// case MINOR_VALUE_EXPECTING_COMMA: // not fine
// case MINOR_VALUE_EXPECTING_COLON: // not fine
case MINOR_VALUE_TOKEN_NULL:
return _finishKeywordTokenWithEOF("null", _pending32, JsonToken.VALUE_NULL);
case MINOR_VALUE_TOKEN_TRUE:
return _finishKeywordTokenWithEOF("true", _pending32, JsonToken.VALUE_TRUE);
case MINOR_VALUE_TOKEN_FALSE:
return _finishKeywordTokenWithEOF("false", _pending32, JsonToken.VALUE_FALSE);
case MINOR_VALUE_TOKEN_NON_STD:
return _finishNonStdTokenWithEOF(_nonStdTokenType, _pending32);
case MINOR_VALUE_TOKEN_ERROR: // case of "almost token", just need tokenize for error
return _finishErrorTokenWithEOF();
// Number-parsing states; valid stopping points, more explicit errors
case MINOR_NUMBER_ZERO:
case MINOR_NUMBER_MINUSZERO:
// NOTE: does NOT retain possible leading minus-sign (can change if
// absolutely needs be)
return _valueCompleteInt(0, "0");
case MINOR_NUMBER_INTEGER_DIGITS:
// Fine: just need to ensure we have value fully defined
{
int len = _textBuffer.getCurrentSegmentSize();
if (_numberNegative) {
--len;
}
_intLength = len;
}
return _valueComplete(JsonToken.VALUE_NUMBER_INT);
case MINOR_NUMBER_FRACTION_DIGITS:
_expLength = 0;
// fall through
case MINOR_NUMBER_EXPONENT_DIGITS:
return _valueComplete(JsonToken.VALUE_NUMBER_FLOAT);
case MINOR_NUMBER_EXPONENT_MARKER:
_reportInvalidEOF(": was expecting fraction after exponent marker", JsonToken.VALUE_NUMBER_FLOAT);
// How about comments?
// Inside C-comments; not legal
// case MINOR_COMMENT_LEADING_SLASH: // not legal, but use default error
case MINOR_COMMENT_CLOSING_ASTERISK:
case MINOR_COMMENT_C:
_reportInvalidEOF(": was expecting closing '*/' for comment", JsonToken.NOT_AVAILABLE);
case MINOR_COMMENT_CPP:
case MINOR_COMMENT_YAML:
// within C++/YAML comments, ok, as long as major state agrees...
return _eofAsNextToken();
default:
}
_reportInvalidEOF(": was expecting rest of token (internal state: "+_minorState+")", _currToken);
return t; // never gets here
}
/*
/**********************************************************************
/* Second-level decoding, root level
/**********************************************************************
*/
private final JsonToken _startDocument(int ch) throws IOException
{
ch &= 0xFF;
// Very first byte: could be BOM
if ((ch == 0xEF) && (_minorState != MINOR_ROOT_BOM)) {
return _finishBOM(1);
}
// If not BOM (or we got past it), could be whitespace or comment to skip
while (ch <= 0x020) {
if (ch != INT_SPACE) {
if (ch == INT_LF) {
++_currInputRow;
_currInputRowStart = _inputPtr;
} else if (ch == INT_CR) {
++_currInputRowAlt;
_currInputRowStart = _inputPtr;
} else if (ch != INT_TAB) {
_throwInvalidSpace(ch);
}
}
if (_inputPtr >= _inputEnd) {
_minorState = MINOR_ROOT_GOT_SEPARATOR;
if (_closed) {
return null;
}
// note: if so, do not even bother changing state
if (_endOfInput) { // except for this special case
return _eofAsNextToken();
}
return JsonToken.NOT_AVAILABLE;
}
ch = _inputBuffer[_inputPtr++] & 0xFF;
}
return _startValue(ch);
}
private final JsonToken _finishBOM(int bytesHandled) throws IOException
{
// public final static byte UTF8_BOM_1 = (byte) 0xEF;
// public final static byte UTF8_BOM_2 = (byte) 0xBB;
// public final static byte UTF8_BOM_3 = (byte) 0xBF;
while (_inputPtr < _inputEnd) {
int ch = _inputBuffer[_inputPtr++] & 0xFF;
switch (bytesHandled) {
case 3:
// got it all; go back to "start document" handling, without changing
// minor state (to let it know we've done BOM)
_currInputProcessed -= 3;
return _startDocument(ch);
case 2:
if (ch != 0xBF) {
_reportError("Unexpected byte 0x%02x following 0xEF 0xBB; should get 0xBF as third byte of UTF-8 BOM", ch);
}
break;
case 1:
if (ch != 0xBB) {
_reportError("Unexpected byte 0x%02x following 0xEF; should get 0xBB as second byte UTF-8 BOM", ch);
}
break;
}
++bytesHandled;
}
_pending32 = bytesHandled;
_minorState = MINOR_ROOT_BOM;
return (_currToken = JsonToken.NOT_AVAILABLE);
}
/*
/**********************************************************************
/* Second-level decoding, primary field name decoding
/**********************************************************************
*/
/**
* Method that handles initial token type recognition for token
* that has to be either FIELD_NAME or END_OBJECT.
*/
private final JsonToken _startFieldName(int ch) throws IOException
{
// First: any leading white space?
if (ch <= 0x0020) {
ch = _skipWS(ch);
if (ch <= 0) {
_minorState = MINOR_FIELD_LEADING_WS;
return _currToken;
}
}
_updateTokenLocation();
if (ch != INT_QUOTE) {
if (ch == INT_RCURLY) {
return _closeObjectScope();
}
return _handleOddName(ch);
}
// First: can we optimize out bounds checks?
if ((_inputPtr + 13) <= _inputEnd) { // Need up to 12 chars, plus one trailing (quote)
String n = _fastParseName();
if (n != null) {
return _fieldComplete(n);
}
}
return _parseEscapedName(0, 0, 0);
}
private final JsonToken _startFieldNameAfterComma(int ch) throws IOException
{
// First: any leading white space?
if (ch <= 0x0020) {
ch = _skipWS(ch); // will skip through all available ws (and comments)
if (ch <= 0) {
_minorState = MINOR_FIELD_LEADING_COMMA;
return _currToken;
}
}
if (ch != INT_COMMA) { // either comma, separating entries, or closing right curly
if (ch == INT_RCURLY) {
return _closeObjectScope();
}
if (ch == INT_HASH) {
return _finishHashComment(MINOR_FIELD_LEADING_COMMA);
}
if (ch == INT_SLASH) {
return _startSlashComment(MINOR_FIELD_LEADING_COMMA);
}
_reportUnexpectedChar(ch, "was expecting comma to separate "+_parsingContext.typeDesc()+" entries");
}
int ptr = _inputPtr;
if (ptr >= _inputEnd) {
_minorState = MINOR_FIELD_LEADING_WS;
return (_currToken = JsonToken.NOT_AVAILABLE);
}
ch = _inputBuffer[ptr];
_inputPtr = ptr+1;
if (ch <= 0x0020) {
ch = _skipWS(ch);
if (ch <= 0) {
_minorState = MINOR_FIELD_LEADING_WS;
return _currToken;
}
}
_updateTokenLocation();
if (ch != INT_QUOTE) {
if (ch == INT_RCURLY) {
if ((_features & FEAT_MASK_TRAILING_COMMA) != 0) {
return _closeObjectScope();
}
}
return _handleOddName(ch);
}
// First: can we optimize out bounds checks?
if ((_inputPtr + 13) <= _inputEnd) { // Need up to 12 chars, plus one trailing (quote)
String n = _fastParseName();
if (n != null) {
return _fieldComplete(n);
}
}
return _parseEscapedName(0, 0, 0);
}
/*
/**********************************************************************
/* Second-level decoding, value decoding
/**********************************************************************
*/
/**
* Helper method called to detect type of a value token (at any level), and possibly
* decode it if contained in input buffer.
* Value may be preceded by leading white-space, but no separator (comma).
*/
private final JsonToken _startValue(int ch) throws IOException
{
// First: any leading white space?
if (ch <= 0x0020) {
ch = _skipWS(ch);
if (ch <= 0) {
_minorState = MINOR_VALUE_LEADING_WS;
return _currToken;
}
}
_updateTokenLocation();
if (ch == INT_QUOTE) {
return _startString();
}
switch (ch) {
case '#':
return _finishHashComment(MINOR_VALUE_LEADING_WS);
case '-':
return _startNegativeNumber();
case '/': // c/c++ comments
return _startSlashComment(MINOR_VALUE_LEADING_WS);
// Should we have separate handling for plus? Although
// it is not allowed per se, it may be erroneously used,
// and could be indicate by a more specific error message.
case '0':
return _startNumberLeadingZero();
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
return _startPositiveNumber(ch);
case 'f':
return _startFalseToken();
case 'n':
return _startNullToken();
case 't':
return _startTrueToken();
case '[':
return _startArrayScope();
case INT_RBRACKET:
return _closeArrayScope();
case '{':
return _startObjectScope();
case INT_RCURLY:
return _closeObjectScope();
default:
}
return _startUnexpectedValue(false, ch);
}
/**
* Helper method called to parse token that is either a value token in array
* or end-array marker
*/
private final JsonToken _startValueExpectComma(int ch) throws IOException
{
// First: any leading white space?
if (ch <= 0x0020) {
ch = _skipWS(ch); // will skip through all available ws (and comments)
if (ch <= 0) {
_minorState = MINOR_VALUE_EXPECTING_COMMA;
return _currToken;
}
}
if (ch != INT_COMMA) {
if (ch == INT_RBRACKET) {
return _closeArrayScope();
}
if (ch == INT_RCURLY){
return _closeObjectScope();
}
if (ch == INT_SLASH) {
return _startSlashComment(MINOR_VALUE_EXPECTING_COMMA);
}
if (ch == INT_HASH) {
return _finishHashComment(MINOR_VALUE_EXPECTING_COMMA);
}
_reportUnexpectedChar(ch, "was expecting comma to separate "+_parsingContext.typeDesc()+" entries");
}
// 17-Sep-2019, tatu: [core#563] Need to call this to update index within array
_parsingContext.expectComma();
int ptr = _inputPtr;
if (ptr >= _inputEnd) {
_minorState = MINOR_VALUE_WS_AFTER_COMMA;
return (_currToken = JsonToken.NOT_AVAILABLE);
}
ch = _inputBuffer[ptr];
_inputPtr = ptr+1;
if (ch <= 0x0020) {
ch = _skipWS(ch);
if (ch <= 0) {
_minorState = MINOR_VALUE_WS_AFTER_COMMA;
return _currToken;
}
}
_updateTokenLocation();
if (ch == INT_QUOTE) {
return _startString();
}
switch (ch) {
case '#':
return _finishHashComment(MINOR_VALUE_WS_AFTER_COMMA);
case '-':
return _startNegativeNumber();
case '/':
return _startSlashComment(MINOR_VALUE_WS_AFTER_COMMA);
// Should we have separate handling for plus? Although
// it is not allowed per se, it may be erroneously used,
// and could be indicate by a more specific error message.
case '0':
return _startNumberLeadingZero();
case '1':
case '2': case '3':
case '4': case '5':
case '6': case '7':
case '8': case '9':
return _startPositiveNumber(ch);
case 'f':
return _startFalseToken();
case 'n':
return _startNullToken();
case 't':
return _startTrueToken();
case '[':
return _startArrayScope();
case INT_RBRACKET:
// Was that a trailing comma?
if ((_features & FEAT_MASK_TRAILING_COMMA) != 0) {
return _closeArrayScope();
}
break;
case '{':
return _startObjectScope();
case INT_RCURLY:
// Was that a trailing comma?
if ((_features & FEAT_MASK_TRAILING_COMMA) != 0) {
return _closeObjectScope();
}
break;
default:
}
return _startUnexpectedValue(true, ch);
}
/**
* Helper method called to detect type of a value token (at any level), and possibly
* decode it if contained in input buffer.
* Value MUST be preceded by a semi-colon (which may be surrounded by white-space)
*/
private final JsonToken _startValueExpectColon(int ch) throws IOException
{
// First: any leading white space?
if (ch <= 0x0020) {
ch = _skipWS(ch); // will skip through all available ws (and comments)
if (ch <= 0) {
_minorState = MINOR_VALUE_EXPECTING_COLON;
return _currToken;
}
}
if (ch != INT_COLON) {
if (ch == INT_SLASH) {
return _startSlashComment(MINOR_VALUE_EXPECTING_COLON);
}
if (ch == INT_HASH) {
return _finishHashComment(MINOR_VALUE_EXPECTING_COLON);
}
// can not omit colon here
_reportUnexpectedChar(ch, "was expecting a colon to separate field name and value");
}
int ptr = _inputPtr;
if (ptr >= _inputEnd) {
_minorState = MINOR_VALUE_LEADING_WS;
return (_currToken = JsonToken.NOT_AVAILABLE);
}
ch = _inputBuffer[ptr];
_inputPtr = ptr+1;
if (ch <= 0x0020) {
ch = _skipWS(ch); // will skip through all available ws (and comments)
if (ch <= 0) {
_minorState = MINOR_VALUE_LEADING_WS;
return _currToken;
}
}
_updateTokenLocation();
if (ch == INT_QUOTE) {
return _startString();
}
switch (ch) {
case '#':
return _finishHashComment(MINOR_VALUE_LEADING_WS);
case '-':
return _startNegativeNumber();
case '/':
return _startSlashComment(MINOR_VALUE_LEADING_WS);
// Should we have separate handling for plus? Although
// it is not allowed per se, it may be erroneously used,
// and could be indicate by a more specific error message.
case '0':
return _startNumberLeadingZero();
case '1':
case '2': case '3':
case '4': case '5':
case '6': case '7':
case '8': case '9':
return _startPositiveNumber(ch);
case 'f':
return _startFalseToken();
case 'n':
return _startNullToken();
case 't':
return _startTrueToken();
case '[':
return _startArrayScope();
case '{':
return _startObjectScope();
default:
}
return _startUnexpectedValue(false, ch);
}
/* Method called when we have already gotten a comma (i.e. not the first value)
*/
private final JsonToken _startValueAfterComma(int ch) throws IOException
{
// First: any leading white space?
if (ch <= 0x0020) {
ch = _skipWS(ch);
if (ch <= 0) {
_minorState = MINOR_VALUE_WS_AFTER_COMMA;
return _currToken;
}
}
_updateTokenLocation();
if (ch == INT_QUOTE) {
return _startString();
}
switch (ch) {
case '#':
return _finishHashComment(MINOR_VALUE_WS_AFTER_COMMA);
case '-':
return _startNegativeNumber();
case '/':
return _startSlashComment(MINOR_VALUE_WS_AFTER_COMMA);
// Should we have separate handling for plus? Although
// it is not allowed per se, it may be erroneously used,
// and could be indicate by a more specific error message.
case '0':
return _startNumberLeadingZero();
case '1':
case '2':
case '3':
case '4':
case '5':
case '6':
case '7':
case '8':
case '9':
return _startPositiveNumber(ch);
case 'f':
return _startFalseToken();
case 'n':
return _startNullToken();
case 't':
return _startTrueToken();
case '[':
return _startArrayScope();
case INT_RBRACKET:
// Was that a trailing comma?
if ((_features & FEAT_MASK_TRAILING_COMMA) != 0) {
return _closeArrayScope();
}
break;
case '{':
return _startObjectScope();
case INT_RCURLY:
// Was that a trailing comma?
if ((_features & FEAT_MASK_TRAILING_COMMA) != 0) {
return _closeObjectScope();
}
break;
default:
}
return _startUnexpectedValue(true, ch);
}
protected JsonToken _startUnexpectedValue(boolean leadingComma, int ch) throws IOException
{
switch (ch) {
case INT_RBRACKET:
if (!_parsingContext.inArray()) {
break;
}
// fall through
case ',':
// 28-Mar-2016: [core#116]: If Feature.ALLOW_MISSING_VALUES is enabled
// we may allow "missing values", that is, encountering a trailing
// comma or closing marker where value would be expected
if ((_features & FEAT_MASK_ALLOW_MISSING) != 0) {
--_inputPtr;
return _valueComplete(JsonToken.VALUE_NULL);
}
// fall through
case INT_RCURLY:
// Error: neither is valid at this point; valid closers have
// been handled earlier
break;
case '\'':
if ((_features & FEAT_MASK_ALLOW_SINGLE_QUOTES) != 0) {
return _startAposString();
}
break;
case '+':
return _finishNonStdToken(NON_STD_TOKEN_PLUS_INFINITY, 1);
case 'N':
return _finishNonStdToken(NON_STD_TOKEN_NAN, 1);
case 'I':
return _finishNonStdToken(NON_STD_TOKEN_INFINITY, 1);
}
// !!! TODO: maybe try to collect more information for better diagnostics
_reportUnexpectedChar(ch, "expected a valid value "+_validJsonValueList());
return null;
}
/*
/**********************************************************************
/* Second-level decoding, skipping white-space, comments
/**********************************************************************
*/
private final int _skipWS(int ch) throws IOException
{
do {
if (ch != INT_SPACE) {
if (ch == INT_LF) {
++_currInputRow;
_currInputRowStart = _inputPtr;
} else if (ch == INT_CR) {
++_currInputRowAlt;
_currInputRowStart = _inputPtr;
} else if (ch != INT_TAB) {
_throwInvalidSpace(ch);
}
}
if (_inputPtr >= _inputEnd) {
_currToken = JsonToken.NOT_AVAILABLE;
return 0;
}
ch = _inputBuffer[_inputPtr++] & 0xFF;
} while (ch <= 0x0020);
return ch;
}
private final JsonToken _startSlashComment(int fromMinorState) throws IOException
{
if ((_features & FEAT_MASK_ALLOW_JAVA_COMMENTS) == 0) {
_reportUnexpectedChar('/', "maybe a (non-standard) comment? (not recognized as one since Feature 'ALLOW_COMMENTS' not enabled for parser)");
}
// After that, need to verify if we have c/c++ comment
if (_inputPtr >= _inputEnd) {
_pending32 = fromMinorState;
_minorState = MINOR_COMMENT_LEADING_SLASH;
return (_currToken = JsonToken.NOT_AVAILABLE);
}
int ch = _inputBuffer[_inputPtr++];
if (ch == INT_ASTERISK) { // c-style
return _finishCComment(fromMinorState, false);
}
if (ch == INT_SLASH) { // c++-style
return _finishCppComment(fromMinorState);
}
_reportUnexpectedChar(ch & 0xFF, "was expecting either '*' or '/' for a comment");
return null;
}
private final JsonToken _finishHashComment(int fromMinorState) throws IOException
{
// Could by-pass this check by refactoring, but for now simplest way...
if ((_features & FEAT_MASK_ALLOW_YAML_COMMENTS) == 0) {
_reportUnexpectedChar('#', "maybe a (non-standard) comment? (not recognized as one since Feature 'ALLOW_YAML_COMMENTS' not enabled for parser)");
}
while (true) {
if (_inputPtr >= _inputEnd) {
_minorState = MINOR_COMMENT_YAML;
_pending32 = fromMinorState;
return (_currToken = JsonToken.NOT_AVAILABLE);
}
int ch = _inputBuffer[_inputPtr++] & 0xFF;
if (ch < 0x020) {
if (ch == INT_LF) {
++_currInputRow;
_currInputRowStart = _inputPtr;
break;
} else if (ch == INT_CR) {