forked from johnezang/JSONKit
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathJSONKit.m
More file actions
1889 lines (1536 loc) · 106 KB
/
JSONKit.m
File metadata and controls
1889 lines (1536 loc) · 106 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
//
// JSONKit.m
// http://github.com/johnezang/JSONKit
// Licensed under the terms of the BSD License, as specified below.
//
/*
Copyright (c) 2011, John Engelhart
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the Zang Industries nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED
TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/*
Acknowledgments:
The bulk of the UTF8 / UTF32 conversion and verification comes
from ConvertUTF.[hc]. It has been modified from the original sources.
The original sources were obtained from http://www.unicode.org/.
However, the web site no longer seems to host the files. Instead,
the Unicode FAQ http://www.unicode.org/faq//utf_bom.html#gen4
points to International Components for Unicode (ICU)
http://site.icu-project.org/ as an example of how to write a UTF
converter.
The decision to use the ConvertUTF.[ch] code was made to leverage
"proven" code. Hopefully the local modifications are bug free.
The code in isValidCodePoint() is derived from the ICU code in
utf.h for the macros U_IS_UNICODE_NONCHAR and U_IS_UNICODE_CHAR.
From the original ConvertUTF.[ch]:
* Copyright 2001-2004 Unicode, Inc.
*
* Disclaimer
*
* This source code is provided as is by Unicode, Inc. No claims are
* made as to fitness for any particular purpose. No warranties of any
* kind are expressed or implied. The recipient agrees to determine
* applicability of information provided. If this file has been
* purchased on magnetic or optical media from Unicode, Inc., the
* sole remedy for any claim will be exchange of defective media
* within 90 days of receipt.
*
* Limitations on Rights to Redistribute This Code
*
* Unicode, Inc. hereby grants the right to freely use the information
* supplied in this file in the creation of products supporting the
* Unicode Standard, and to make copies of this file in any form
* for internal or external distribution as long as this notice
* remains attached.
*/
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <assert.h>
#include <sys/errno.h>
#include <math.h>
#import "JSONKit.h"
//#include <CoreFoundation/CoreFoundation.h>
#include <CoreFoundation/CFString.h>
#include <CoreFoundation/CFArray.h>
#include <CoreFoundation/CFDictionary.h>
#include <CoreFoundation/CFNumber.h>
//#import <Foundation/Foundation.h>
#import <Foundation/NSArray.h>
#import <Foundation/NSData.h>
#import <Foundation/NSDictionary.h>
#import <Foundation/NSException.h>
#import <Foundation/NSNull.h>
#import <Foundation/NSObjCRuntime.h>
#ifdef __OBJC_GC__
#error JSONKit does not support Objective-C Garbage Collection
#endif
// For DJB hash.
#define JK_HASH_INIT (1402737925UL)
// Use __builtin_clz() instead of trailingBytesForUTF8[] table lookup.
#define JK_FAST_TRAILING_BYTES
// JK_CACHE_SLOTS must be a power of 2. Default size is 1024 slots.
#define JK_CACHE_SLOTS_BITS (10)
#define JK_CACHE_SLOTS (1UL << JK_CACHE_SLOTS_BITS)
// JK_CACHE_PROBES is the number of probe attempts.
#define JK_CACHE_PROBES (4UL)
// JK_INIT_CACHE_AGE must be (1 << AGE) - 1
#define JK_INIT_CACHE_AGE (31)
// JK_TOKENBUFFER_SIZE is the default stack size for the temporary buffer used to hold "non-simple" strings (i.e., contains \ escapes)
#define JK_TOKENBUFFER_SIZE (1024UL * 2UL)
// JK_STACK_OBJS is the default number of spaces reserved on the stack for temporarily storing pointers to Obj-C objects before they can be transferred to a NSArray / NSDictionary.
#define JK_STACK_OBJS (1024UL * 1UL)
#define JK_JSONBUFFER_SIZE (1024UL * 4UL)
#define JK_UTF8BUFFER_SIZE (1024UL * 16UL)
#if defined (__GNUC__) && (__GNUC__ >= 4)
#define JK_ATTRIBUTES(attr, ...) __attribute__((attr, ##__VA_ARGS__))
#define JK_EXPECTED(cond, expect) __builtin_expect((long)(cond), (expect))
#define JK_PREFETCH(ptr) __builtin_prefetch(ptr)
#else // defined (__GNUC__) && (__GNUC__ >= 4)
#define JK_ATTRIBUTES(attr, ...)
#define JK_EXPECTED(cond, expect) (cond)
#define JK_PREFETCH(ptr)
#endif // defined (__GNUC__) && (__GNUC__ >= 4)
#define JK_STATIC_INLINE static __inline__ JK_ATTRIBUTES(always_inline)
#define JK_ALIGNED(arg) JK_ATTRIBUTES(aligned(arg))
#define JK_UNUSED_ARG JK_ATTRIBUTES(unused)
#define JK_WARN_UNUSED JK_ATTRIBUTES(warn_unused_result)
#define JK_WARN_UNUSED_CONST JK_ATTRIBUTES(warn_unused_result, const)
#define JK_WARN_UNUSED_PURE JK_ATTRIBUTES(warn_unused_result, pure)
#define JK_WARN_UNUSED_SENTINEL JK_ATTRIBUTES(warn_unused_result, sentinel)
#define JK_NONNULL_ARGS(arg, ...) JK_ATTRIBUTES(nonnull(arg, ##__VA_ARGS__))
#define JK_WARN_UNUSED_NONNULL_ARGS(arg, ...) JK_ATTRIBUTES(warn_unused_result, nonnull(arg, ##__VA_ARGS__))
#define JK_WARN_UNUSED_CONST_NONNULL_ARGS(arg, ...) JK_ATTRIBUTES(warn_unused_result, const, nonnull(arg, ##__VA_ARGS__))
#define JK_WARN_UNUSED_PURE_NONNULL_ARGS(arg, ...) JK_ATTRIBUTES(warn_unused_result, pure, nonnull(arg, ##__VA_ARGS__))
#if defined (__GNUC__) && (__GNUC__ >= 4) && (__GNUC_MINOR__ >= 3)
#define JK_ALLOC_SIZE_NON_NULL_ARGS_WARN_UNUSED(as, nn, ...) JK_ATTRIBUTES(warn_unused_result, nonnull(nn, ##__VA_ARGS__), alloc_size(as))
#else // defined (__GNUC__) && (__GNUC__ >= 4) && (__GNUC_MINOR__ >= 3)
#define JK_ALLOC_SIZE_NON_NULL_ARGS_WARN_UNUSED(as, nn, ...) JK_ATTRIBUTES(warn_unused_result, nonnull(nn, ##__VA_ARGS__))
#endif // defined (__GNUC__) && (__GNUC__ >= 4) && (__GNUC_MINOR__ >= 3)
typedef uint32_t UTF32; /* at least 32 bits */
typedef uint16_t UTF16; /* at least 16 bits */
typedef uint8_t UTF8; /* typically 8 bits */
typedef enum {
conversionOK, /* conversion successful */
sourceExhausted, /* partial character in source, but hit end */
targetExhausted, /* insuff. room in target for conversion */
sourceIllegal /* source sequence is illegal/malformed */
} ConversionResult;
enum {
JKTokenTypeInvalid = 0,
JKTokenTypeNumber = 1,
JKTokenTypeString = 2,
JKTokenTypeObjectBegin = 3,
JKTokenTypeObjectEnd = 4,
JKTokenTypeArrayBegin = 5,
JKTokenTypeArrayEnd = 6,
JKTokenTypeSeparator = 7,
JKTokenTypeComma = 8,
JKTokenTypeTrue = 9,
JKTokenTypeFalse = 10,
JKTokenTypeNull = 11,
JKTokenTypeWhiteSpace = 12,
};
enum {
JKManagedBufferOnStack = 1,
JKManagedBufferOnHeap = 2,
JKManagedBufferLocationMask = (0x3),
JKManagedBufferLocationShift = (0),
JKManagedBufferMustFree = (1 << 2),
};
enum {
JKObjectStackOnStack = 1,
JKObjectStackOnHeap = 2,
JKObjectStackLocationMask = (0x3),
JKObjectStackLocationShift = (0),
JKObjectStackMustFree = (1 << 2),
};
// These are prime numbers to assist with hash slot probing.
enum {
JKValueTypeNone = 0,
JKValueTypeString = 5,
JKValueTypeLongLong = 7,
JKValueTypeUnsignedLongLong = 11,
JKValueTypeDouble = 13,
};
enum {
JSONNumberStateStart = 0,
JSONNumberStateFinished = 1,
JSONNumberStateError = 2,
JSONNumberStateWholeNumberStart = 3,
JSONNumberStateWholeNumberMinus = 4,
JSONNumberStateWholeNumberZero = 5,
JSONNumberStateWholeNumber = 6,
JSONNumberStatePeriod = 7,
JSONNumberStateFractionalNumberStart = 8,
JSONNumberStateFractionalNumber = 9,
JSONNumberStateExponentStart = 10,
JSONNumberStateExponentPlusMinus = 11,
JSONNumberStateExponent = 12,
};
enum {
JSONStringStateStart = 0,
JSONStringStateParsing = 1,
JSONStringStateFinished = 2,
JSONStringStateError = 3,
JSONStringStateEscape = 4,
JSONStringStateEscapedUnicode1 = 5,
JSONStringStateEscapedUnicode2 = 6,
JSONStringStateEscapedUnicode3 = 7,
JSONStringStateEscapedUnicode4 = 8,
JSONStringStateEscapedUnicodeSurrogate1 = 9,
JSONStringStateEscapedUnicodeSurrogate2 = 10,
JSONStringStateEscapedUnicodeSurrogate3 = 11,
JSONStringStateEscapedUnicodeSurrogate4 = 12,
JSONStringStateEscapedNeedEscapeForSurrogate = 13,
JSONStringStateEscapedNeedEscapedUForSurrogate = 14,
};
enum {
JKParseAcceptValue = (1 << 0),
JKParseAcceptComma = (1 << 1),
JKParseAcceptEnd = (1 << 2),
JKParseAcceptValueOrEnd = (JKParseAcceptValue | JKParseAcceptEnd),
JKParseAcceptCommaOrEnd = (JKParseAcceptComma | JKParseAcceptEnd),
};
typedef struct {
void *stringClass;
void *numberClass;
void *arrayClass;
void *dictionaryClass;
void *nullClass;
} JKFastClassLookup;
enum {
JKClassUnknown = 0,
JKClassString = 1,
JKClassNumber = 2,
JKClassArray = 3,
JKClassDictionary = 4,
JKClassNull = 5,
};
typedef struct {
JKManagedBuffer utf8ConversionBuffer;
JKManagedBuffer stringBuffer;
size_t atIndex;
JKFastClassLookup fastClassLookup;
JKSerializeOptionFlags serializeOptionFlags;
NSError *error;
} JKEncodeState;
#define UNI_REPLACEMENT_CHAR (UTF32)0x0000FFFD
#define UNI_MAX_BMP (UTF32)0x0000FFFF
#define UNI_MAX_UTF16 (UTF32)0x0010FFFF
#define UNI_MAX_UTF32 (UTF32)0x7FFFFFFF
#define UNI_MAX_LEGAL_UTF32 (UTF32)0x0010FFFF
#define UNI_SUR_HIGH_START (UTF32)0xD800
#define UNI_SUR_HIGH_END (UTF32)0xDBFF
#define UNI_SUR_LOW_START (UTF32)0xDC00
#define UNI_SUR_LOW_END (UTF32)0xDFFF
#if !defined(JK_FAST_TRAILING_BYTES)
static const char trailingBytesForUTF8[256] = {
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,
1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1, 1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5
};
#endif
static const UTF32 offsetsFromUTF8[6] = { 0x00000000UL, 0x00003080UL, 0x000E2080UL, 0x03C82080UL, 0xFA082080UL, 0x82082080UL };
static const UTF8 firstByteMark[7] = { 0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC };
#ifdef JK_ENABLE_CF_TRANSFER_OWNERSHIP_CALLBACKS
static void jk_CFCallbackRelease(CFAllocatorRef allocator JK_UNUSED_ARG, const void *ptr) { CFRelease((CFTypeRef)ptr); }
static const CFArrayCallBacks jk_transferOwnershipArrayCallBacks = { (CFIndex)0L, NULL, jk_CFCallbackRelease, CFCopyDescription, CFEqual };
static const CFDictionaryKeyCallBacks jk_transferOwnershipDictionaryKeyCallBacks = { (CFIndex)0L, NULL, jk_CFCallbackRelease, CFCopyDescription, CFEqual, CFHash };
static const CFDictionaryValueCallBacks jk_transferOwnershipDictionaryValueCallBacks = { (CFIndex)0L, NULL, jk_CFCallbackRelease, CFCopyDescription, CFEqual };
#define jk_kArrayCallbacks jk_transferOwnershipArrayCallBacks
#define jk_kDictionaryKeyCallBacks jk_transferOwnershipDictionaryKeyCallBacks
#define jk_kDictionaryValueCallBacks jk_transferOwnershipDictionaryValueCallBacks
#define JK_RELEASE_COLLECTION_OBJECTS 0
#else // JK_ENABLE_CF_TRANSFER_OWNERSHIP_CALLBACKS defined
#define jk_kArrayCallbacks kCFTypeArrayCallBacks
#define jk_kDictionaryKeyCallBacks kCFTypeDictionaryKeyCallBacks
#define jk_kDictionaryValueCallBacks kCFTypeDictionaryValueCallBacks
#define JK_RELEASE_COLLECTION_OBJECTS 1
#endif // JK_ENABLE_CF_TRANSFER_OWNERSHIP_CALLBACKS
#define JK_AT_STRING_PTR(x) (&((x)->stringBuffer.bytes.ptr[(x)->atIndex]))
#define JK_END_STRING_PTR(x) (&((x)->stringBuffer.bytes.ptr[(x)->stringBuffer.bytes.length]))
static void jk_managedBuffer_release(JKManagedBuffer *managedBuffer);
static void jk_managedBuffer_setToStackBuffer(JKManagedBuffer *managedBuffer, unsigned char *ptr, size_t length);
static unsigned char *jk_managedBuffer_resize(JKManagedBuffer *managedBuffer, size_t newSize);
static void jk_objectStack_release(JKObjectStack *objectStack);
static void jk_objectStack_setToStackBuffer(JKObjectStack *objectStack, void **objects, void **keys, JKHash *hashes, size_t *sizes, size_t count);
static int jk_objectStack_resize(JKObjectStack *objectStack, size_t newCount);
static void jk_error(JKParseState *parseState, NSString *format, ...);
static int jk_parse_string(JKParseState *parseState);
static int jk_parse_number(JKParseState *parseState);
static size_t jk_parse_is_newline(JKParseState *parseState, const unsigned char *atCharacterPtr);
JK_STATIC_INLINE int jk_parse_skip_newline(JKParseState *parseState);
JK_STATIC_INLINE void jk_parse_skip_whitespace(JKParseState *parseState);
static int jk_parse_next_token(JKParseState *parseState);
static void jk_error_parse_accept_or3(JKParseState *parseState, int state, NSString *or1String, NSString *or2String, NSString *or3String);
static void *jk_create_dictionary(JKParseState *parseState, size_t startingObjectIndex);
static void *jk_parse_dictionary(JKParseState *parseState);
static void *jk_parse_array(JKParseState *parseState);
static void *jk_object_for_token(JKParseState *parseState);
static void *jk_cachedObjects(JKParseState *parseState);
JK_STATIC_INLINE void jk_cache_age(JKParseState *parseState);
JK_STATIC_INLINE void jk_set_parsed_token(JKParseState *parseState, const unsigned char *ptr, size_t length, JKTokenType type, size_t advanceBy);
static void jk_encode_error(JKEncodeState *encodeState, NSString *format, ...);
static int jk_encode_printf(JKEncodeState *encodeState, const char *format, ...);
static int jk_encode_write(JKEncodeState *encodeState, const char *format);
static int jk_encode_add_atom_to_buffer(JKEncodeState *encodeState, void *objectPtr);
static NSData *jk_encode(void *object, JKSerializeOptionFlags optionFlags, NSError **error);
JK_STATIC_INLINE size_t jk_min(size_t a, size_t b);
JK_STATIC_INLINE size_t jk_max(size_t a, size_t b);
JK_STATIC_INLINE JKHash calculateHash(JKHash currentHash, unsigned char c);
JK_STATIC_INLINE size_t jk_min(size_t a, size_t b) { return((a < b) ? a : b); }
JK_STATIC_INLINE size_t jk_max(size_t a, size_t b) { return((a > b) ? a : b); }
JK_STATIC_INLINE JKHash calculateHash(JKHash currentHash, unsigned char c) { return(((currentHash << 5) + currentHash) + c); }
static void jk_error(JKParseState *parseState, NSString *format, ...) {
NSCParameterAssert((parseState != NULL) && (format != NULL));
va_list varArgsList;
va_start(varArgsList, format);
NSString *formatString = [[[NSString alloc] initWithFormat:format arguments:varArgsList] autorelease];
va_end(varArgsList);
#if 0
const unsigned char *lineStart = parseState->stringBuffer.bytes.ptr + parseState->lineStartIndex;
const unsigned char *lineEnd = lineStart;
const unsigned char *atCharacterPtr = NULL;
for(atCharacterPtr = lineStart; atCharacterPtr < JK_END_STRING_PTR(parseState); atCharacterPtr++) { lineEnd = atCharacterPtr; if(jk_parse_is_newline(parseState, atCharacterPtr)) { break; } }
NSString *lineString = @"", *carretString = @"";
if(lineStart < JK_END_STRING_PTR(parseState)) {
lineString = [[[NSString alloc] initWithBytes:lineStart length:(lineEnd - lineStart) encoding:NSUTF8StringEncoding] autorelease];
carretString = [NSString stringWithFormat:@"%*.*s^", (int)(parseState->atIndex - parseState->lineStartIndex), (int)(parseState->atIndex - parseState->lineStartIndex), " "];
}
#endif
if(parseState->error == NULL) {
parseState->error = [NSError errorWithDomain:@"JKErrorDomain" code:-1L userInfo:
[NSDictionary dictionaryWithObjectsAndKeys:
formatString, NSLocalizedDescriptionKey,
[NSNumber numberWithUnsignedLong:parseState->atIndex], @"JKAtIndexKey",
[NSNumber numberWithUnsignedLong:parseState->lineNumber], @"JKLineNumberKey",
//lineString, @"JKErrorLine0Key",
//carretString, @"JKErrorLine1Key",
NULL]];
}
}
static void jk_managedBuffer_release(JKManagedBuffer *managedBuffer) {
if((managedBuffer->flags & JKManagedBufferMustFree)) {
if(managedBuffer->bytes.ptr != NULL) { free(managedBuffer->bytes.ptr); managedBuffer->bytes.ptr = NULL; }
managedBuffer->flags &= ~JKManagedBufferMustFree;
}
managedBuffer->bytes.ptr = NULL;
managedBuffer->bytes.length = 0UL;
managedBuffer->flags &= ~JKManagedBufferLocationMask;
}
static void jk_managedBuffer_setToStackBuffer(JKManagedBuffer *managedBuffer, unsigned char *ptr, size_t length) {
jk_managedBuffer_release(managedBuffer);
managedBuffer->bytes.ptr = ptr;
managedBuffer->bytes.length = length;
managedBuffer->flags = (managedBuffer->flags & ~JKManagedBufferLocationMask) | JKManagedBufferOnStack;
}
static unsigned char *jk_managedBuffer_resize(JKManagedBuffer *managedBuffer, size_t newSize) {
size_t roundedUpNewSize = newSize;
if(managedBuffer->roundSizeUpToMultipleOf > 0UL) { roundedUpNewSize = newSize + ((managedBuffer->roundSizeUpToMultipleOf - (newSize % managedBuffer->roundSizeUpToMultipleOf)) % managedBuffer->roundSizeUpToMultipleOf); }
if((roundedUpNewSize != managedBuffer->bytes.length) && (roundedUpNewSize > managedBuffer->bytes.length)) {
if((managedBuffer->flags & JKManagedBufferLocationMask) == JKManagedBufferOnStack) {
NSCParameterAssert((managedBuffer->flags & JKManagedBufferMustFree) == 0);
unsigned char *newBuffer = NULL, *oldBuffer = managedBuffer->bytes.ptr;
if((newBuffer = (unsigned char *)malloc(roundedUpNewSize)) == NULL) { return(NULL); }
memcpy(newBuffer, oldBuffer, jk_min(managedBuffer->bytes.length, roundedUpNewSize));
managedBuffer->flags = (managedBuffer->flags & ~JKManagedBufferLocationMask) | (JKManagedBufferOnHeap | JKManagedBufferMustFree);
managedBuffer->bytes.ptr = newBuffer;
managedBuffer->bytes.length = roundedUpNewSize;
} else {
NSCParameterAssert(((managedBuffer->flags & JKManagedBufferMustFree) != 0) && ((managedBuffer->flags & JKManagedBufferLocationMask) == JKManagedBufferOnHeap));
if((managedBuffer->bytes.ptr = (unsigned char *)reallocf(managedBuffer->bytes.ptr, roundedUpNewSize)) == NULL) { return(NULL); }
managedBuffer->bytes.length = roundedUpNewSize;
}
}
return(managedBuffer->bytes.ptr);
}
static void jk_objectStack_release(JKObjectStack *objectStack) {
NSCParameterAssert(objectStack != NULL);
NSCParameterAssert(objectStack->index <= objectStack->count);
size_t atIndex = 0UL;
for(atIndex = 0UL; atIndex < objectStack->index; atIndex++) {
if(objectStack->objects[atIndex] != NULL) { CFRelease(objectStack->objects[atIndex]); objectStack->objects[atIndex] = NULL; }
if(objectStack->keys[atIndex] != NULL) { CFRelease(objectStack->keys[atIndex]); objectStack->keys[atIndex] = NULL; }
}
objectStack->index = 0UL;
if(objectStack->flags & JKObjectStackMustFree) {
NSCParameterAssert((objectStack->flags & JKObjectStackLocationMask) == JKObjectStackOnHeap);
if(objectStack->objects != NULL) { free(objectStack->objects); objectStack->objects = NULL; }
if(objectStack->keys != NULL) { free(objectStack->keys); objectStack->keys = NULL; }
if(objectStack->hashes != NULL) { free(objectStack->hashes); objectStack->hashes = NULL; }
if(objectStack->sizes != NULL) { free(objectStack->sizes); objectStack->sizes = NULL; }
objectStack->flags &= ~JKObjectStackMustFree;
}
objectStack->objects = NULL;
objectStack->keys = NULL;
objectStack->hashes = NULL;
objectStack->sizes = NULL;
objectStack->count = 0UL;
objectStack->flags &= ~JKObjectStackLocationMask;
}
static void jk_objectStack_setToStackBuffer(JKObjectStack *objectStack, void **objects, void **keys, JKHash *hashes, size_t *sizes, size_t count) {
NSCParameterAssert((objectStack != NULL) && (objects != NULL) && (keys != NULL) && (hashes != NULL) && (sizes != NULL) && (count > 0UL));
jk_objectStack_release(objectStack);
objectStack->objects = objects;
objectStack->keys = keys;
objectStack->hashes = hashes;
objectStack->sizes = sizes;
objectStack->count = count;
objectStack->flags = (objectStack->flags & ~JKObjectStackLocationMask) | JKObjectStackOnStack;
#ifndef NS_BLOCK_ASSERTIONS
size_t idx;
for(idx = 0UL; idx < objectStack->count; idx++) { objectStack->objects[idx] = NULL; objectStack->keys[idx] = NULL; }
#endif
}
static int jk_objectStack_resize(JKObjectStack *objectStack, size_t newCount) {
size_t roundedUpNewCount = newCount;
int returnCode = 0;
void **newObjects = NULL, **newKeys = NULL;
JKHash *newHashes = NULL;
size_t *newSizes = NULL;
if(objectStack->roundSizeUpToMultipleOf > 0UL) { roundedUpNewCount = newCount + ((objectStack->roundSizeUpToMultipleOf - (newCount % objectStack->roundSizeUpToMultipleOf)) % objectStack->roundSizeUpToMultipleOf); }
if((roundedUpNewCount != objectStack->count) && (roundedUpNewCount > objectStack->count)) {
if((objectStack->flags & JKObjectStackLocationMask) == JKObjectStackOnStack) {
NSCParameterAssert((objectStack->flags & JKObjectStackMustFree) == 0);
if((newObjects = (void **)calloc(1UL, roundedUpNewCount * sizeof(void *))) == NULL) { returnCode = 1; goto errorExit; }
memcpy(newObjects, objectStack->objects, jk_min(objectStack->count, roundedUpNewCount) * sizeof(void *));
if((newKeys = (void **)calloc(1UL, roundedUpNewCount * sizeof(void *))) == NULL) { returnCode = 1; goto errorExit; }
memcpy(newKeys, objectStack->keys, jk_min(objectStack->count, roundedUpNewCount) * sizeof(void *));
if((newHashes = (JKHash *)calloc(1UL, roundedUpNewCount * sizeof(JKHash))) == NULL) { returnCode = 1; goto errorExit; }
memcpy(newHashes, objectStack->hashes, jk_min(objectStack->count, roundedUpNewCount) * sizeof(JKHash));
if((newSizes = (size_t *)calloc(1UL, roundedUpNewCount * sizeof(size_t))) == NULL) { returnCode = 1; goto errorExit; }
memcpy(newSizes, objectStack->sizes, jk_min(objectStack->count, roundedUpNewCount) * sizeof(size_t));
objectStack->flags = (objectStack->flags & ~JKObjectStackLocationMask) | (JKObjectStackOnHeap | JKObjectStackMustFree);
objectStack->objects = newObjects; newObjects = NULL;
objectStack->keys = newKeys; newKeys = NULL;
objectStack->hashes = newHashes; newHashes = NULL;
objectStack->sizes = newSizes; newSizes = NULL;
objectStack->count = roundedUpNewCount;
} else {
NSCParameterAssert(((objectStack->flags & JKObjectStackMustFree) != 0) && ((objectStack->flags & JKObjectStackLocationMask) == JKObjectStackOnHeap));
if((newObjects = (void **)realloc(objectStack->objects, roundedUpNewCount * sizeof(void *))) != NULL) { objectStack->objects = newObjects; newObjects = NULL; } else { returnCode = 1; goto errorExit; }
if((newKeys = (void **)realloc(objectStack->keys, roundedUpNewCount * sizeof(void *))) != NULL) { objectStack->keys = newKeys; newKeys = NULL; } else { returnCode = 1; goto errorExit; }
if((newHashes = (JKHash *)realloc(objectStack->hashes, roundedUpNewCount * sizeof(JKHash))) != NULL) { objectStack->hashes = newHashes; newHashes = NULL; } else { returnCode = 1; goto errorExit; }
if((newSizes = (size_t *)realloc(objectStack->sizes, roundedUpNewCount * sizeof(size_t))) != NULL) { objectStack->sizes = newSizes; newSizes = NULL; } else { returnCode = 1; goto errorExit; }
#ifndef NS_BLOCK_ASSERTIONS
size_t idx;
for(idx = objectStack->count; idx < roundedUpNewCount; idx++) { objectStack->objects[idx] = NULL; objectStack->keys[idx] = NULL; }
#endif
objectStack->count = roundedUpNewCount;
}
}
errorExit:
if(newObjects != NULL) { free(newObjects); newObjects = NULL; }
if(newKeys != NULL) { free(newKeys); newKeys = NULL; }
if(newHashes != NULL) { free(newHashes); newHashes = NULL; }
if(newSizes != NULL) { free(newSizes); newSizes = NULL; }
return(returnCode);
}
JK_STATIC_INLINE ConversionResult isValidCodePoint(UTF32 *u32CodePoint) {
ConversionResult result = conversionOK;
UTF32 ch = *u32CodePoint;
if((ch >= UNI_SUR_HIGH_START) && (JK_EXPECTED(ch <= UNI_SUR_LOW_END, 1U))) { result = sourceIllegal; ch = UNI_REPLACEMENT_CHAR; goto finished; }
if((ch >= 0xFDD0U) && ((JK_EXPECTED(ch <= 0xFDEFU, 0U)) || JK_EXPECTED(((ch & 0xFFFEU) == 0xFFFEU), 0U)) && (JK_EXPECTED(ch <= 0x10FFFFU, 1U))) { result = sourceIllegal; ch = UNI_REPLACEMENT_CHAR; goto finished; }
if(JK_EXPECTED(ch == 0U, 0U)) { result = sourceIllegal; ch = UNI_REPLACEMENT_CHAR; goto finished; }
finished:
*u32CodePoint = ch;
return(result);
}
static int isLegalUTF8(const UTF8 *source, size_t length) {
const UTF8 *srcptr = source + length;
UTF8 a;
switch(length) {
default: return(0); // Everything else falls through when "true"...
case 4: if(JK_EXPECTED(((a = (*--srcptr)) < 0x80) || (a > 0xBF), 0U)) { return(0); }
case 3: if(JK_EXPECTED(((a = (*--srcptr)) < 0x80) || (a > 0xBF), 0U)) { return(0); }
case 2: if(JK_EXPECTED( (a = (*--srcptr)) > 0xBF , 0U)) { return(0); }
switch(*source) { // no fall-through in this inner switch
case 0xE0: if(JK_EXPECTED(a < 0xA0, 0U)) { return(0); } break;
case 0xED: if(JK_EXPECTED(a > 0x9F, 0U)) { return(0); } break;
case 0xF0: if(JK_EXPECTED(a < 0x90, 0U)) { return(0); } break;
case 0xF4: if(JK_EXPECTED(a > 0x8F, 0U)) { return(0); } break;
default: if(JK_EXPECTED(a < 0x80, 0U)) { return(0); }
}
case 1: if(JK_EXPECTED((JK_EXPECTED(*source < 0xC2, 0U)) && JK_EXPECTED(*source >= 0x80, 1U), 0U)) { return(0); }
}
if(JK_EXPECTED(*source > 0xF4, 0U)) { return(0); }
return(1);
}
static ConversionResult ConvertSingleCodePointInUTF8(const UTF8 *sourceStart, const UTF8 *sourceEnd, UTF8 const **nextUTF8, UTF32 *convertedUTF32) {
ConversionResult result = conversionOK;
const UTF8 *source = sourceStart;
UTF32 ch = 0UL;
#if !defined(JK_FAST_TRAILING_BYTES)
unsigned short extraBytesToRead = trailingBytesForUTF8[*source];
#else
unsigned short extraBytesToRead = __builtin_clz(((*source)^0xff) << 25);
#endif
if(JK_EXPECTED((source + extraBytesToRead + 1) > sourceEnd, 0U) || JK_EXPECTED(!isLegalUTF8(source, extraBytesToRead + 1), 0U)) {
source++;
while((source < sourceEnd) && (((*source) & 0xc0) == 0x80) && ((source - sourceStart) < (extraBytesToRead + 1))) { source++; }
NSCParameterAssert(source <= sourceEnd);
result = ((source < sourceEnd) && (((*source) & 0xc0) != 0x80)) ? sourceIllegal : ((sourceStart + extraBytesToRead + 1) > sourceEnd) ? sourceExhausted : sourceIllegal;
ch = UNI_REPLACEMENT_CHAR;
goto finished;
}
switch(extraBytesToRead) { // The cases all fall through.
case 5: ch += *source++; ch <<= 6;
case 4: ch += *source++; ch <<= 6;
case 3: ch += *source++; ch <<= 6;
case 2: ch += *source++; ch <<= 6;
case 1: ch += *source++; ch <<= 6;
case 0: ch += *source++;
}
ch -= offsetsFromUTF8[extraBytesToRead];
result = isValidCodePoint(&ch);
finished:
*nextUTF8 = source;
*convertedUTF32 = ch;
return(result);
}
static ConversionResult ConvertUTF32toUTF8 (UTF32 u32CodePoint, UTF8 **targetStart, UTF8 *targetEnd) {
const UTF32 byteMask = 0xBF, byteMark = 0x80;
ConversionResult result = conversionOK;
UTF8 *target = *targetStart;
UTF32 ch = u32CodePoint;
unsigned short bytesToWrite = 0;
result = isValidCodePoint(&ch);
// Figure out how many bytes the result will require. Turn any illegally large UTF32 things (> Plane 17) into replacement chars.
if(ch < (UTF32)0x80) { bytesToWrite = 1; }
else if(ch < (UTF32)0x800) { bytesToWrite = 2; }
else if(ch < (UTF32)0x10000) { bytesToWrite = 3; }
else if(ch <= UNI_MAX_LEGAL_UTF32) { bytesToWrite = 4; }
else { bytesToWrite = 3; ch = UNI_REPLACEMENT_CHAR; result = sourceIllegal; }
target += bytesToWrite;
if (target > targetEnd) { target -= bytesToWrite; result = targetExhausted; goto finished; }
switch (bytesToWrite) { // note: everything falls through.
case 4: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
case 3: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
case 2: *--target = (UTF8)((ch | byteMark) & byteMask); ch >>= 6;
case 1: *--target = (UTF8) (ch | firstByteMark[bytesToWrite]);
}
target += bytesToWrite;
finished:
*targetStart = target;
return(result);
}
JK_STATIC_INLINE int jk_string_add_unicodeCodePoint(JKParseState *parseState, uint32_t unicodeCodePoint, size_t *tokenBufferIdx, JKHash *stringHash) {
UTF8 *u8s = &parseState->token.tokenBuffer.bytes.ptr[*tokenBufferIdx];
ConversionResult result;
if((result = ConvertUTF32toUTF8(unicodeCodePoint, &u8s, (parseState->token.tokenBuffer.bytes.ptr + parseState->token.tokenBuffer.bytes.length))) != conversionOK) { if(result == targetExhausted) { return(1); } }
size_t utf8len = u8s - &parseState->token.tokenBuffer.bytes.ptr[*tokenBufferIdx], nextIdx = (*tokenBufferIdx) + utf8len;
while(*tokenBufferIdx < nextIdx) { *stringHash = calculateHash(*stringHash, parseState->token.tokenBuffer.bytes.ptr[(*tokenBufferIdx)++]); }
return(0);
}
static int jk_parse_string(JKParseState *parseState) {
NSCParameterAssert((parseState != NULL) && (JK_AT_STRING_PTR(parseState) <= JK_END_STRING_PTR(parseState)));
const unsigned char *stringStart = JK_AT_STRING_PTR(parseState) + 1;
const unsigned char *endOfBuffer = JK_END_STRING_PTR(parseState);
const unsigned char *atStringCharacter = stringStart;
unsigned char *tokenBuffer = parseState->token.tokenBuffer.bytes.ptr;
size_t tokenStartIndex = parseState->atIndex;
size_t tokenBufferIdx = 0UL;
int onlySimpleString = 1, stringState = JSONStringStateStart;
uint16_t escapedUnicode1 = 0U, escapedUnicode2 = 0U;
uint32_t escapedUnicodeCodePoint = 0U;
JKHash stringHash = JK_HASH_INIT;
while(1) {
unsigned long currentChar;
if(JK_EXPECTED(atStringCharacter == endOfBuffer, 0U)) { /* XXX Add error message */ stringState = JSONStringStateError; goto finishedParsing; }
if(JK_EXPECTED((currentChar = *atStringCharacter++) >= 0x80UL, 0U)) {
const unsigned char *nextValidCharacter = NULL;
UTF32 u32ch = 0UL;
ConversionResult result;
if(JK_EXPECTED((result = ConvertSingleCodePointInUTF8(atStringCharacter - 1, endOfBuffer, (UTF8 const **)&nextValidCharacter, &u32ch)) != conversionOK, 0L)) { goto switchToSlowPath; }
stringHash = calculateHash(stringHash, currentChar);
while(atStringCharacter < nextValidCharacter) { stringHash = calculateHash(stringHash, *atStringCharacter++); }
continue;
} else {
if(JK_EXPECTED(currentChar == (unsigned long)'"', 0U)) { stringState = JSONStringStateFinished; goto finishedParsing; }
if(JK_EXPECTED(currentChar == (unsigned long)'\\', 0U)) {
switchToSlowPath:
onlySimpleString = 0;
stringState = JSONStringStateParsing;
tokenBufferIdx = (atStringCharacter - stringStart) - 1L;
if(JK_EXPECTED((tokenBufferIdx + 16UL) > parseState->token.tokenBuffer.bytes.length, 0U)) { if((tokenBuffer = jk_managedBuffer_resize(&parseState->token.tokenBuffer, tokenBufferIdx + 1024UL)) == NULL) { jk_error(parseState, @"Internal error: Unable to resize temporary buffer. %@ line #%ld", [NSString stringWithUTF8String:__FILE__], (long)__LINE__); stringState = JSONStringStateError; goto finishedParsing; } }
memcpy(tokenBuffer, stringStart, tokenBufferIdx);
goto slowMatch;
}
if(JK_EXPECTED(currentChar < 0x20UL, 0U)) { jk_error(parseState, @"Invalid character < 0x20 found in string: 0x%2.2x.", currentChar); stringState = JSONStringStateError; goto finishedParsing; }
stringHash = calculateHash(stringHash, currentChar);
}
}
slowMatch:
for(atStringCharacter = (stringStart + ((atStringCharacter - stringStart) - 1L)); (atStringCharacter < endOfBuffer) && (tokenBufferIdx < parseState->token.tokenBuffer.bytes.length); atStringCharacter++) {
if((tokenBufferIdx + 16UL) > parseState->token.tokenBuffer.bytes.length) { if((tokenBuffer = jk_managedBuffer_resize(&parseState->token.tokenBuffer, tokenBufferIdx + 1024UL)) == NULL) { jk_error(parseState, @"Internal error: Unable to resize temporary buffer. %@ line #%ld", [NSString stringWithUTF8String:__FILE__], (long)__LINE__); stringState = JSONStringStateError; goto finishedParsing; } }
NSCParameterAssert(tokenBufferIdx < parseState->token.tokenBuffer.bytes.length);
unsigned long currentChar = (*atStringCharacter), escapedChar;
if(JK_EXPECTED(stringState == JSONStringStateParsing, 1U)) {
if(JK_EXPECTED(currentChar < (unsigned long)0x80, 1U)) {
if(JK_EXPECTED(currentChar == (unsigned long)'"', 0U)) { stringState = JSONStringStateFinished; atStringCharacter++; goto finishedParsing; }
if(JK_EXPECTED(currentChar == (unsigned long)'\\', 0U)) { stringState = JSONStringStateEscape; continue; }
stringHash = calculateHash(stringHash, currentChar);
tokenBuffer[tokenBufferIdx++] = currentChar;
continue;
}
if(JK_EXPECTED(currentChar >= 0x80UL, 1U)) {
const unsigned char *nextValidCharacter = NULL;
UTF32 u32ch = 0U;
ConversionResult result;
if(JK_EXPECTED((result = ConvertSingleCodePointInUTF8(atStringCharacter, endOfBuffer, (UTF8 const **)&nextValidCharacter, &u32ch)) != conversionOK, 0U)) {
if((result == sourceIllegal) && ((parseState->parseOptionFlags & JKParseOptionLooseUnicode) == 0)) { jk_error(parseState, @"Illegal UTF8 sequence found in \"\" string."); stringState = JSONStringStateError; goto finishedParsing; }
if(result == sourceExhausted) { jk_error(parseState, @"End of buffer reached while parsing UTF8 in \"\" string."); stringState = JSONStringStateError; goto finishedParsing; }
if(jk_string_add_unicodeCodePoint(parseState, u32ch, &tokenBufferIdx, &stringHash)) { jk_error(parseState, @"Internal error: Unable to add UTF8 sequence to internal string buffer. %@ line #%ld", [NSString stringWithUTF8String:__FILE__], (long)__LINE__); stringState = JSONStringStateError; goto finishedParsing; }
atStringCharacter = nextValidCharacter - 1;
continue;
} else {
while(atStringCharacter < nextValidCharacter) { tokenBuffer[tokenBufferIdx++] = *atStringCharacter; stringHash = calculateHash(stringHash, *atStringCharacter++); }
atStringCharacter--;
continue;
}
}
if(JK_EXPECTED(currentChar < 0x20UL, 0U)) { jk_error(parseState, @"Invalid character < 0x20 found in string: 0x%2.2x.", currentChar); stringState = JSONStringStateError; goto finishedParsing; }
} else {
int isSurrogate = 1;
switch(stringState) {
case JSONStringStateEscape:
switch(currentChar) {
case 'u': escapedUnicode1 = 0U; escapedUnicode2 = 0U; escapedUnicodeCodePoint = 0U; stringState = JSONStringStateEscapedUnicode1; break;
case 'b': escapedChar = '\b'; goto parsedEscapedChar;
case 'f': escapedChar = '\f'; goto parsedEscapedChar;
case 'n': escapedChar = '\n'; goto parsedEscapedChar;
case 'r': escapedChar = '\r'; goto parsedEscapedChar;
case 't': escapedChar = '\t'; goto parsedEscapedChar;
case '\\': escapedChar = '\\'; goto parsedEscapedChar;
case '/': escapedChar = '/'; goto parsedEscapedChar;
case '"': escapedChar = '"'; goto parsedEscapedChar;
parsedEscapedChar:
stringState = JSONStringStateParsing;
stringHash = calculateHash(stringHash, escapedChar);
tokenBuffer[tokenBufferIdx++] = escapedChar;
break;
default: jk_error(parseState, @"Invalid escape sequence found in \"\" string."); stringState = JSONStringStateError; goto finishedParsing; break;
}
break;
case JSONStringStateEscapedUnicode1:
case JSONStringStateEscapedUnicode2:
case JSONStringStateEscapedUnicode3:
case JSONStringStateEscapedUnicode4: isSurrogate = 0;
case JSONStringStateEscapedUnicodeSurrogate1:
case JSONStringStateEscapedUnicodeSurrogate2:
case JSONStringStateEscapedUnicodeSurrogate3:
case JSONStringStateEscapedUnicodeSurrogate4:
{
uint16_t hexValue = 0U;
switch(currentChar) {
case '0' ... '9': hexValue = currentChar - '0'; goto parsedHex;
case 'a' ... 'f': hexValue = (currentChar - 'a') + 10U; goto parsedHex;
case 'A' ... 'F': hexValue = (currentChar - 'A') + 10U; goto parsedHex;
parsedHex:
if(!isSurrogate) { escapedUnicode1 = (escapedUnicode1 << 4) | hexValue; } else { escapedUnicode2 = (escapedUnicode2 << 4) | hexValue; }
if(stringState == JSONStringStateEscapedUnicode4) {
if(((escapedUnicode1 >= 0xD800U) && (escapedUnicode1 < 0xE000U))) {
if((escapedUnicode1 >= 0xD800U) && (escapedUnicode1 < 0xDC00U)) { stringState = JSONStringStateEscapedNeedEscapeForSurrogate; }
else if((escapedUnicode1 >= 0xDC00U) && (escapedUnicode1 < 0xE000U)) {
if((parseState->parseOptionFlags & JKParseOptionLooseUnicode)) { escapedUnicodeCodePoint = UNI_REPLACEMENT_CHAR; }
else { jk_error(parseState, @"Illegal \\u Unicode escape sequence."); stringState = JSONStringStateError; goto finishedParsing; }
}
}
else { escapedUnicodeCodePoint = escapedUnicode1; }
}
if(stringState == JSONStringStateEscapedUnicodeSurrogate4) {
if((escapedUnicode2 < 0xdc00) || (escapedUnicode2 >= 0xdfff)) {
if((parseState->parseOptionFlags & JKParseOptionLooseUnicode)) { escapedUnicodeCodePoint = UNI_REPLACEMENT_CHAR; }
else { jk_error(parseState, @"Illegal \\u Unicode escape sequence."); stringState = JSONStringStateError; goto finishedParsing; }
}
else { escapedUnicodeCodePoint = ((escapedUnicode1 - 0xd800) * 0x400) + (escapedUnicode2 - 0xdc00) + 0x10000; }
}
if((stringState == JSONStringStateEscapedUnicode4) || (stringState == JSONStringStateEscapedUnicodeSurrogate4)) {
if((parseState->parseOptionFlags & JKParseOptionLooseUnicode) == 0) {
UTF32 cp = escapedUnicodeCodePoint;
if(isValidCodePoint(&cp) == sourceIllegal) { jk_error(parseState, @"Illegal \\u Unicode escape sequence."); stringState = JSONStringStateError; goto finishedParsing; }
}
stringState = JSONStringStateParsing;
if(jk_string_add_unicodeCodePoint(parseState, escapedUnicodeCodePoint, &tokenBufferIdx, &stringHash)) { jk_error(parseState, @"Internal error: Unable to add UTF8 sequence to internal string buffer. %@ line #%ld", [NSString stringWithUTF8String:__FILE__], (long)__LINE__); stringState = JSONStringStateError; goto finishedParsing; }
}
else if((stringState >= JSONStringStateEscapedUnicode1) && (stringState <= JSONStringStateEscapedUnicodeSurrogate4)) { stringState++; }
break;
default: jk_error(parseState, @"Unexpected character found in \\u Unicode escape sequence. Found '%c', expected [0-9a-fA-F].", currentChar); stringState = JSONStringStateError; goto finishedParsing; break;
}
}
break;
case JSONStringStateEscapedNeedEscapeForSurrogate:
if((currentChar == '\\')) { stringState = JSONStringStateEscapedNeedEscapedUForSurrogate; }
//else { stringState = JSONStringStateParsing; atStringCharacter--; if(jk_string_add_unicodeCodePoint(parseState, UNI_REPLACEMENT_CHAR, &tokenBufferIdx, &stringHash)) { /* XXX Add error message */ stringState = JSONStringStateError; goto finishedParsing; } }
else { jk_error(parseState, @"Required a second \\u Unicode escape sequence following a surrogate \\u Unicode escape sequence."); stringState = JSONStringStateError; goto finishedParsing; }
break;
case JSONStringStateEscapedNeedEscapedUForSurrogate:
if(currentChar == 'u') { stringState = JSONStringStateEscapedUnicodeSurrogate1; }
//else { stringState = JSONStringStateParsing; atStringCharacter -= 2; if(jk_string_add_unicodeCodePoint(parseState, UNI_REPLACEMENT_CHAR, &tokenBufferIdx, &stringHash)) { /* XXX Add error message */ stringState = JSONStringStateError; goto finishedParsing; } }
else { jk_error(parseState, @"Required a second \\u Unicode escape sequence following a surrogate \\u Unicode escape sequence."); stringState = JSONStringStateError; goto finishedParsing; }
break;
default: jk_error(parseState, @"Internal error: Unknown stringState. %@ line #%ld", [NSString stringWithUTF8String:__FILE__], (long)__LINE__); stringState = JSONStringStateError; goto finishedParsing; break;
}
}
}
finishedParsing:
if(stringState == JSONStringStateFinished) {
NSCParameterAssert((parseState->stringBuffer.bytes.ptr + tokenStartIndex) < atStringCharacter);
parseState->token.tokenPtrRange.ptr = parseState->stringBuffer.bytes.ptr + tokenStartIndex;
parseState->token.tokenPtrRange.length = (atStringCharacter - parseState->token.tokenPtrRange.ptr);
if(onlySimpleString) {
NSCParameterAssert(((parseState->token.tokenPtrRange.ptr + 1) < endOfBuffer) && (parseState->token.tokenPtrRange.length >= 2UL) && (((parseState->token.tokenPtrRange.ptr + 1) + (parseState->token.tokenPtrRange.length - 2)) < endOfBuffer));
parseState->token.value.ptrRange.ptr = parseState->token.tokenPtrRange.ptr + 1;
parseState->token.value.ptrRange.length = parseState->token.tokenPtrRange.length - 2UL;
} else {
parseState->token.value.ptrRange.ptr = parseState->token.tokenBuffer.bytes.ptr;
parseState->token.value.ptrRange.length = tokenBufferIdx;
}
parseState->token.value.hash = stringHash;
parseState->token.value.type = JKValueTypeString;
parseState->atIndex = (atStringCharacter - parseState->stringBuffer.bytes.ptr);
}
if(stringState != JSONStringStateFinished) { jk_error(parseState, @"Invalid string."); }
return((stringState == JSONStringStateFinished) ? 0 : 1);
}
static int jk_parse_number(JKParseState *parseState) {
NSCParameterAssert((parseState != NULL) && (JK_AT_STRING_PTR(parseState) <= JK_END_STRING_PTR(parseState)));
const unsigned char *numberStart = JK_AT_STRING_PTR(parseState);
const unsigned char *endOfBuffer = JK_END_STRING_PTR(parseState);
const unsigned char *atNumberCharacter = NULL;
int numberState = JSONNumberStateWholeNumberStart, isFloatingPoint = 0, isNegative = 0, backup = 0;
size_t startingIndex = parseState->atIndex;
for(atNumberCharacter = numberStart; (JK_EXPECTED(atNumberCharacter < endOfBuffer, 1U)) && (JK_EXPECTED(!((numberState == JSONNumberStateFinished) || (numberState == JSONNumberStateError)), 1U)); atNumberCharacter++) {
unsigned long currentChar = (unsigned long)(*atNumberCharacter);
switch(numberState) {
case JSONNumberStateWholeNumberStart: if (currentChar == '-') { numberState = JSONNumberStateWholeNumberMinus; isNegative = 1; break; }
case JSONNumberStateWholeNumberMinus: if (currentChar == '0') { numberState = JSONNumberStateWholeNumberZero; break; }
else if( (currentChar >= '1') && (currentChar <= '9')) { numberState = JSONNumberStateWholeNumber; break; }
else { /* XXX Add error message */ numberState = JSONNumberStateError; break; }
case JSONNumberStateExponentStart: if( (currentChar == '+') || (currentChar == '-')) { numberState = JSONNumberStateExponentPlusMinus; break; }
case JSONNumberStateFractionalNumberStart:
case JSONNumberStateExponentPlusMinus:if(!((currentChar >= '0') && (currentChar <= '9'))) { /* XXX Add error message */ numberState = JSONNumberStateError; break; }
else { if(numberState == JSONNumberStateFractionalNumberStart) { numberState = JSONNumberStateFractionalNumber; }
else { numberState = JSONNumberStateExponent; } break; }
case JSONNumberStateWholeNumberZero:
case JSONNumberStateWholeNumber: if (currentChar == '.') { numberState = JSONNumberStateFractionalNumberStart; isFloatingPoint = 1; break; }
case JSONNumberStateFractionalNumber: if( (currentChar == 'e') || (currentChar == 'E')) { numberState = JSONNumberStateExponentStart; isFloatingPoint = 1; break; }
case JSONNumberStateExponent: if(!((currentChar >= '0') && (currentChar <= '9')) || (numberState == JSONNumberStateWholeNumberZero)) { numberState = JSONNumberStateFinished; backup = 1; break; }
break;
default: /* XXX Add error message */ numberState = JSONNumberStateError; break;
}
}
parseState->token.tokenPtrRange.ptr = parseState->stringBuffer.bytes.ptr + startingIndex;
parseState->token.tokenPtrRange.length = (atNumberCharacter - parseState->token.tokenPtrRange.ptr) - backup;
parseState->atIndex = (parseState->token.tokenPtrRange.ptr + parseState->token.tokenPtrRange.length) - parseState->stringBuffer.bytes.ptr;
if(numberState == JSONNumberStateFinished) {
unsigned char numberTempBuf[parseState->token.tokenPtrRange.length + 4UL];
unsigned char *endOfNumber = NULL;
memcpy(numberTempBuf, parseState->token.tokenPtrRange.ptr, parseState->token.tokenPtrRange.length);
numberTempBuf[parseState->token.tokenPtrRange.length] = 0;
errno = 0;
// Treat "-0" as a floating point number, which is capable of representing negative zeros.
if(isNegative && (parseState->token.tokenPtrRange.length == 2UL) && (numberTempBuf[1] == '0')) { isFloatingPoint = 1; }
if(isFloatingPoint) {
parseState->token.value.number.doubleValue = strtod((const char *)numberTempBuf, (char **)&endOfNumber);
parseState->token.value.type = JKValueTypeDouble;
parseState->token.value.ptrRange.ptr = (const unsigned char *)&parseState->token.value.number.doubleValue;
parseState->token.value.ptrRange.length = sizeof(double);
parseState->token.value.hash = (JK_HASH_INIT + parseState->token.value.type);
} else {
if(isNegative) {
parseState->token.value.number.longLongValue = strtoll((const char *)numberTempBuf, (char **)&endOfNumber, 10);
parseState->token.value.type = JKValueTypeLongLong;
parseState->token.value.ptrRange.ptr = (const unsigned char *)&parseState->token.value.number.longLongValue;
parseState->token.value.ptrRange.length = sizeof(long long);
parseState->token.value.hash = (JK_HASH_INIT + parseState->token.value.type) + (JKHash)parseState->token.value.number.longLongValue;
} else {
parseState->token.value.number.unsignedLongLongValue = strtoull((const char *)numberTempBuf, (char **)&endOfNumber, 10);
parseState->token.value.type = JKValueTypeUnsignedLongLong;
parseState->token.value.ptrRange.ptr = (const unsigned char *)&parseState->token.value.number.unsignedLongLongValue;
parseState->token.value.ptrRange.length = sizeof(unsigned long long);
parseState->token.value.hash = (JK_HASH_INIT + parseState->token.value.type) + (JKHash)parseState->token.value.number.unsignedLongLongValue;
}
}
if(JK_EXPECTED(errno != 0, 0U)) {
numberState = JSONNumberStateError;
if(errno == ERANGE) {
switch(parseState->token.value.type) {
case JKValueTypeDouble: jk_error(parseState, @"The value '%s' could not be represented as a 'double' due to %s.", numberTempBuf, (parseState->token.value.number.doubleValue == 0.0) ? "underflow" : "overflow"); break;
case JKValueTypeLongLong: jk_error(parseState, @"The value '%s' exceeded the minimum value that could be represented: %lld.", numberTempBuf, parseState->token.value.number.longLongValue); break;
case JKValueTypeUnsignedLongLong: jk_error(parseState, @"The value '%s' exceeded the maximum value that could be represented: %llu.", numberTempBuf, parseState->token.value.number.unsignedLongLongValue); break;
default: jk_error(parseState, @"Internal error: Unnkown token value type. %@ line #%ld", [NSString stringWithUTF8String:__FILE__], (long)__LINE__); break;
}
}
}
if(JK_EXPECTED(endOfNumber != &numberTempBuf[parseState->token.tokenPtrRange.length], 0U) && JK_EXPECTED(numberState != JSONNumberStateError, 0U)) { numberState = JSONNumberStateError; jk_error(parseState, @"The conversion function did not consume all of the number tokens characters."); }
size_t hashIndex = 0UL;
for(hashIndex = 0UL; hashIndex < parseState->token.value.ptrRange.length; hashIndex++) { parseState->token.value.hash = calculateHash(parseState->token.value.hash, parseState->token.value.ptrRange.ptr[hashIndex]); }
}
if(JK_EXPECTED(numberState != JSONNumberStateFinished, 0U)) { jk_error(parseState, @"Invalid number."); }
return(JK_EXPECTED((numberState == JSONNumberStateFinished), 1U) ? 0 : 1);
}
JK_STATIC_INLINE void jk_set_parsed_token(JKParseState *parseState, const unsigned char *ptr, size_t length, JKTokenType type, size_t advanceBy) {
parseState->token.tokenPtrRange.ptr = ptr;
parseState->token.tokenPtrRange.length = length;
parseState->token.type = type;
parseState->atIndex += advanceBy;
}
static size_t jk_parse_is_newline(JKParseState *parseState, const unsigned char *atCharacterPtr) {
NSCParameterAssert((parseState != NULL) && (atCharacterPtr != NULL) && (atCharacterPtr >= parseState->stringBuffer.bytes.ptr) && (atCharacterPtr < JK_END_STRING_PTR(parseState)));
const unsigned char *endOfStringPtr = JK_END_STRING_PTR(parseState);
if(JK_EXPECTED(atCharacterPtr >= endOfStringPtr, 0U)) { return(0UL); }
if(JK_EXPECTED((*(atCharacterPtr + 0)) == '\n', 0U)) { return(1UL); }
if(JK_EXPECTED((*(atCharacterPtr + 0)) == '\r', 0U)) { if((JK_EXPECTED((atCharacterPtr + 1) < endOfStringPtr, 1U)) && ((*(atCharacterPtr + 1)) == '\n')) { return(2UL); } return(1UL); }