ObjFW  Check-in [3e5e97315c]

Overview
Comment:OFXMLParser: Make state enum private
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA3-256: 3e5e97315c3fce08749491f39b903ea1d0ff5d6a10da90502af6b8db6ba2c1f7
User & Date: js on 2021-04-30 21:09:01
Other Links: manifest | tags
Context
2021-04-30
21:11
OFPlugin: Document how to create a plugin check-in: eaea08f31d user: js tags: trunk
21:09
OFXMLParser: Make state enum private check-in: 3e5e97315c user: js tags: trunk
2021-04-29
23:46
ofhttp: Make GCC 5.3 happy again check-in: a50ae2cc3f user: js tags: trunk
Changes

Modified src/OFXMLParser.h from [1fb96ae9fc] to [fd86d1b01d].

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
126
127
128
129
130
131
132






















133
134
135
136
137
138
139
140







-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+







 * OFXMLParser is an event-based XML parser which calls the delegate's callbacks
 * as soon as it finds something, thus suitable for streams as well.
 */
OF_SUBCLASSING_RESTRICTED
@interface OFXMLParser: OFObject
{
	id <OFXMLParserDelegate> _Nullable _delegate;
	enum {
		OFXMLParserStateInByteOrderMark,
		OFXMLParserStateOutsideTag,
		OFXMLParserStateTagOpened,
		OFXMLParserStateInProcessingInstruction,
		OFXMLParserStateInTagName,
		OFXMLParserStateInCloseTagName,
		OFXMLParserStateInTag,
		OFXMLParserStateInAttributeName,
		OFXMLParserStateExpectAttributeEqualSign,
		OFXMLParserStateExpectAttributeDelimiter,
		OFXMLParserStateInAttributeValue,
		OFXMLParserStateExpectTagClose,
		OFXMLParserStateExpectSpaceOrTagClose,
		OFXMLParserStateInExclamationMark,
		OFXMLParserStateInCDATAOpening,
		OFXMLParserStateInCDATA,
		OFXMLParserStateInCommentOpening,
		OFXMLParserStateInComment1,
		OFXMLParserStateInComment2,
		OFXMLParserStateInDOCTYPE
	} _state;
	uint_least8_t _state;
	size_t _i, _last;
	const char *_Nullable _data;
	OFMutableData *_buffer;
	OFString *_Nullable _name, *_Nullable _prefix;
	OFMutableArray
	    OF_GENERIC(OFMutableDictionary OF_GENERIC(OFString *, OFString *) *)
	    *_namespaces;

Modified src/OFXMLParser.m from [a4ea06f928] to [885a5c6d01].

35
36
37
38
39
40
41























42
43
44
45
46
47
48
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







+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+







#import "OFInitializationFailedException.h"
#import "OFInvalidArgumentException.h"
#import "OFInvalidEncodingException.h"
#import "OFInvalidFormatException.h"
#import "OFMalformedXMLException.h"
#import "OFOutOfRangeException.h"
#import "OFUnboundPrefixException.h"

enum {
	stateInByteOrderMark,
	stateOutsideTag,
	stateTagOpened,
	stateInProcessingInstruction,
	stateInTagName,
	stateInCloseTagName,
	stateInTag,
	stateInAttributeName,
	stateExpectAttributeEqualSign,
	stateExpectAttributeDelimiter,
	stateInAttributeValue,
	stateExpectTagClose,
	stateExpectSpaceOrTagClose,
	stateInExclamationMark,
	stateInCDATAOpening,
	stateInCDATA,
	stateInCommentOpening,
	stateInComment1,
	stateInComment2,
	stateInDOCTYPE
};

@interface OFXMLParser () <OFStringXMLUnescapingDelegate>
@end

static void inByteOrderMarkState(OFXMLParser *);
static void outsideTagState(OFXMLParser *);
static void tagOpenedState(OFXMLParser *);
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
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







-
-
-
-
+
+
+
+
-
-
-
-
-
+
+
+
+
-
-
+
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+







static void inCDATAState(OFXMLParser *);
static void inCommentOpeningState(OFXMLParser *);
static void inCommentState1(OFXMLParser *);
static void inCommentState2(OFXMLParser *);
static void inDOCTYPEState(OFXMLParser *);
typedef void (*StateFunction)(OFXMLParser *);
static StateFunction lookupTable[] = {
	[OFXMLParserStateInByteOrderMark] = inByteOrderMarkState,
	[OFXMLParserStateOutsideTag] = outsideTagState,
	[OFXMLParserStateTagOpened] = tagOpenedState,
	[OFXMLParserStateInProcessingInstruction] =
	[stateInByteOrderMark] = inByteOrderMarkState,
	[stateOutsideTag] = outsideTagState,
	[stateTagOpened] = tagOpenedState,
	[stateInProcessingInstruction] = inProcessingInstructionState,
	    inProcessingInstructionState,
	[OFXMLParserStateInTagName] = inTagNameState,
	[OFXMLParserStateInCloseTagName] = inCloseTagNameState,
	[OFXMLParserStateInTag] = inTagState,
	[OFXMLParserStateInAttributeName] = inAttributeNameState,
	[stateInTagName] = inTagNameState,
	[stateInCloseTagName] = inCloseTagNameState,
	[stateInTag] = inTagState,
	[stateInAttributeName] = inAttributeNameState,
	[OFXMLParserStateExpectAttributeEqualSign] =
	    expectAttributeEqualSignState,
	[stateExpectAttributeEqualSign] = expectAttributeEqualSignState,
	[OFXMLParserStateExpectAttributeDelimiter] =
	    expectAttributeDelimiterState,
	[OFXMLParserStateInAttributeValue] = inAttributeValueState,
	[OFXMLParserStateExpectTagClose] = expectTagCloseState,
	[OFXMLParserStateExpectSpaceOrTagClose] = expectSpaceOrTagCloseState,
	[OFXMLParserStateInExclamationMark] = inExclamationMarkState,
	[OFXMLParserStateInCDATAOpening] = inCDATAOpeningState,
	[OFXMLParserStateInCDATA] = inCDATAState,
	[OFXMLParserStateInCommentOpening] = inCommentOpeningState,
	[OFXMLParserStateInComment1] = inCommentState1,
	[OFXMLParserStateInComment2] = inCommentState2,
	[OFXMLParserStateInDOCTYPE] = inDOCTYPEState
	[stateExpectAttributeDelimiter] = expectAttributeDelimiterState,
	[stateInAttributeValue] = inAttributeValueState,
	[stateExpectTagClose] = expectTagCloseState,
	[stateExpectSpaceOrTagClose] = expectSpaceOrTagCloseState,
	[stateInExclamationMark] = inExclamationMarkState,
	[stateInCDATAOpening] = inCDATAOpeningState,
	[stateInCDATA] = inCDATAState,
	[stateInCommentOpening] = inCommentOpeningState,
	[stateInComment1] = inCommentState1,
	[stateInComment2] = inCommentState2,
	[stateInDOCTYPE] = inDOCTYPEState
};

static OF_INLINE void
appendToBuffer(OFMutableData *buffer, const char *string,
    OFStringEncoding encoding, size_t length)
{
	if OF_LIKELY(encoding == OFStringEncodingUTF8)
254
255
256
257
258
259
260
261
262


263
264
265
266
267
268
269
274
275
276
277
278
279
280


281
282
283
284
285
286
287
288
289







-
-
+
+







		if (_data[_i] == '\r' || (_data[_i] == '\n' &&
		    !_lastCarriageReturn))
			_lineNumber++;

		_lastCarriageReturn = (_data[_i] == '\r');
	}

	/* In OFXMLParserStateInTag, there can be only spaces */
	if (length - _last > 0 && _state != OFXMLParserStateInTag)
	/* In stateInTag, there can be only spaces */
	if (length - _last > 0 && _state != stateInTag)
		appendToBuffer(_buffer, _data + _last, _encoding,
		    length - _last);
}

- (void)parseString: (OFString *)string
{
	[self parseBuffer: string.UTF8String length: string.UTF8StringLength];
286
287
288
289
290
291
292
293

294
295
296
297
298
299
300
301
302

303
304
305
306
307
308
309
306
307
308
309
310
311
312

313
314
315
316
317
318
319
320
321

322
323
324
325
326
327
328
329







-
+








-
+







}

static void
inByteOrderMarkState(OFXMLParser *self)
{
	if (self->_data[self->_i] != "\xEF\xBB\xBF"[self->_level]) {
		if (self->_level == 0) {
			self->_state = OFXMLParserStateOutsideTag;
			self->_state = stateOutsideTag;
			self->_i--;
			return;
		}

		@throw [OFMalformedXMLException exceptionWithParser: self];
	}

	if (self->_level++ == 2)
		self->_state = OFXMLParserStateOutsideTag;
		self->_state = stateOutsideTag;

	self->_last = self->_i + 1;
}

/* Not in a tag */
static void
outsideTagState(OFXMLParser *self)
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
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







-
+













-
+




-
+




-
+







-
+








		objc_autoreleasePoolPop(pool);
	}

	[self->_buffer removeAllItems];

	self->_last = self->_i + 1;
	self->_state = OFXMLParserStateTagOpened;
	self->_state = stateTagOpened;
}

/* Tag was just opened */
static void
tagOpenedState(OFXMLParser *self)
{
	if (self->_finishedParsing && self->_data[self->_i] != '!' &&
	    self->_data[self->_i] != '?')
		@throw [OFMalformedXMLException exceptionWithParser: self];

	switch (self->_data[self->_i]) {
	case '?':
		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateInProcessingInstruction;
		self->_state = stateInProcessingInstruction;
		self->_level = 0;
		break;
	case '/':
		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateInCloseTagName;
		self->_state = stateInCloseTagName;
		self->_acceptProlog = false;
		break;
	case '!':
		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateInExclamationMark;
		self->_state = stateInExclamationMark;
		self->_acceptProlog = false;
		break;
	default:
		if (self->_depthLimit > 0 &&
		    self->_previous.count >= self->_depthLimit)
			@throw [OFOutOfRangeException exception];

		self->_state = OFXMLParserStateInTagName;
		self->_state = stateInTagName;
		self->_acceptProlog = false;
		self->_i--;
		break;
	}
}

/* <?xml […]?> */
512
513
514
515
516
517
518
519

520
521
522
523
524
525
526
532
533
534
535
536
537
538

539
540
541
542
543
544
545
546







-
+







							    data: data];

		objc_autoreleasePoolPop(pool);

		[self->_buffer removeAllItems];

		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateOutsideTag;
		self->_state = stateOutsideTag;
	} else
		self->_level = 0;
}

/* Inside a tag, no name yet */
static void
inTagNameState(OFXMLParser *self)
590
591
592
593
594
595
596
597

598
599
600

601
602
603
604
605
606
607
610
611
612
613
614
615
616

617

618

619
620
621
622
623
624
625
626







-
+
-

-
+







			[self->_previous addObject: bufferString];

		[self->_name release];
		[self->_prefix release];
		self->_name = self->_prefix = nil;

		self->_state = (self->_data[self->_i] == '/'
		    ? OFXMLParserStateExpectTagClose
		    ? stateExpectTagClose : stateOutsideTag);
		    : OFXMLParserStateOutsideTag);
	} else
		self->_state = OFXMLParserStateInTag;
		self->_state = stateInTag;

	if (self->_data[self->_i] != '/')
		[self->_namespaces addObject: [OFMutableDictionary dictionary]];

	objc_autoreleasePoolPop(pool);

	[self->_buffer removeAllItems];
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
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







-
-
+




















-
+







	[self->_namespaces removeLastObject];
	[self->_name release];
	[self->_prefix release];
	self->_name = self->_prefix = nil;

	self->_last = self->_i + 1;
	self->_state = (self->_data[self->_i] == '>'
	    ? OFXMLParserStateOutsideTag
	    : OFXMLParserStateExpectSpaceOrTagClose);
	    ? stateOutsideTag : stateExpectSpaceOrTagClose);

	if (self->_previous.count == 0)
		self->_finishedParsing = true;
}

/* Inside a tag, name found */
static void
inTagState(OFXMLParser *self)
{
	void *pool;
	OFString *namespace;
	OFXMLAttribute *const *attributesObjects;
	size_t attributesCount;

	if (self->_data[self->_i] != '>' && self->_data[self->_i] != '/') {
		if (self->_data[self->_i] != ' ' &&
		    self->_data[self->_i] != '\t' &&
		    self->_data[self->_i] != '\n' &&
		    self->_data[self->_i] != '\r') {
			self->_last = self->_i;
			self->_state = OFXMLParserStateInAttributeName;
			self->_state = stateInAttributeName;
			self->_i--;
		}

		return;
	}

	attributesObjects = self->_attributes.objects;
752
753
754
755
756
757
758
759

760
761
762
763
764
765
766
770
771
772
773
774
775
776

777
778
779
780
781
782
783
784







-
+







	[self->_name release];
	[self->_prefix release];
	[self->_attributes removeAllObjects];
	self->_name = self->_prefix = nil;

	self->_last = self->_i + 1;
	self->_state = (self->_data[self->_i] == '/'
	    ? OFXMLParserStateExpectTagClose : OFXMLParserStateOutsideTag);
	    ? stateExpectTagClose : stateOutsideTag);
}

/* Looking for attribute name */
static void
inAttributeNameState(OFXMLParser *self)
{
	void *pool;
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
818
819
820
821
822
823
824

825

826
827
828
829
830
831
832
833

834
835
836
837
838
839
840
841







-
+
-








-
+








	objc_autoreleasePoolPop(pool);

	[self->_buffer removeAllItems];

	self->_last = self->_i + 1;
	self->_state = (self->_data[self->_i] == '='
	    ? OFXMLParserStateExpectAttributeDelimiter
	    ? stateExpectAttributeDelimiter : stateExpectAttributeEqualSign);
	    : OFXMLParserStateExpectAttributeEqualSign);
}

/* Expecting equal sign of an attribute */
static void
expectAttributeEqualSignState(OFXMLParser *self)
{
	if (self->_data[self->_i] == '=') {
		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateExpectAttributeDelimiter;
		self->_state = stateExpectAttributeDelimiter;
		return;
	}

	if (self->_data[self->_i] != ' '  && self->_data[self->_i] != '\t' &&
	    self->_data[self->_i] != '\n' && self->_data[self->_i] != '\r')
		@throw [OFMalformedXMLException exceptionWithParser: self];
}
833
834
835
836
837
838
839
840

841
842
843
844
845
846
847
850
851
852
853
854
855
856

857
858
859
860
861
862
863
864







-
+







	    self->_data[self->_i] == '\n' || self->_data[self->_i] == '\r')
		return;

	if (self->_data[self->_i] != '\'' && self->_data[self->_i] != '"')
		@throw [OFMalformedXMLException exceptionWithParser: self];

	self->_delimiter = self->_data[self->_i];
	self->_state = OFXMLParserStateInAttributeValue;
	self->_state = stateInAttributeValue;
}

/* Looking for attribute value */
static void
inAttributeValueState(OFXMLParser *self)
{
	void *pool;
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
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







-
+








-
+










-
+














-
+

-
+


-
+















-
+








	[self->_buffer removeAllItems];
	[self->_attributeName release];
	[self->_attributePrefix release];
	self->_attributeName = self->_attributePrefix = nil;

	self->_last = self->_i + 1;
	self->_state = OFXMLParserStateInTag;
	self->_state = stateInTag;
}

/* Expecting closing '>' */
static void
expectTagCloseState(OFXMLParser *self)
{
	if (self->_data[self->_i] == '>') {
		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateOutsideTag;
		self->_state = stateOutsideTag;
	} else
		@throw [OFMalformedXMLException exceptionWithParser: self];
}

/* Expecting closing '>' or space */
static void
expectSpaceOrTagCloseState(OFXMLParser *self)
{
	if (self->_data[self->_i] == '>') {
		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateOutsideTag;
		self->_state = stateOutsideTag;
	} else if (self->_data[self->_i] != ' ' &&
	    self->_data[self->_i] != '\t' && self->_data[self->_i] != '\n' &&
	    self->_data[self->_i] != '\r')
		@throw [OFMalformedXMLException exceptionWithParser: self];
}

/* In <! */
static void
inExclamationMarkState(OFXMLParser *self)
{
	if (self->_finishedParsing && self->_data[self->_i] != '-')
		@throw [OFMalformedXMLException exceptionWithParser: self];

	if (self->_data[self->_i] == '-')
		self->_state = OFXMLParserStateInCommentOpening;
		self->_state = stateInCommentOpening;
	else if (self->_data[self->_i] == '[') {
		self->_state = OFXMLParserStateInCDATAOpening;
		self->_state = stateInCDATAOpening;
		self->_level = 0;
	} else if (self->_data[self->_i] == 'D') {
		self->_state = OFXMLParserStateInDOCTYPE;
		self->_state = stateInDOCTYPE;
		self->_level = 0;
	} else
		@throw [OFMalformedXMLException exceptionWithParser: self];

	self->_last = self->_i + 1;
}

/* CDATA */
static void
inCDATAOpeningState(OFXMLParser *self)
{
	if (self->_data[self->_i] != "CDATA["[self->_level])
		@throw [OFMalformedXMLException exceptionWithParser: self];

	if (++self->_level == 6) {
		self->_state = OFXMLParserStateInCDATA;
		self->_state = stateInCDATA;
		self->_level = 0;
	}

	self->_last = self->_i + 1;
}

static void
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
1001
1002
979
980
981
982
983
984
985

986
987
988
989
990
991
992
993
994
995
996
997
998

999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011

1012
1013
1014
1015
1016
1017
1018
1019







-
+












-
+












-
+







			[self->_delegate parser: self foundCDATA: CDATA];

		objc_autoreleasePoolPop(pool);

		[self->_buffer removeAllItems];

		self->_last = self->_i + 1;
		self->_state = OFXMLParserStateOutsideTag;
		self->_state = stateOutsideTag;
	} else
		self->_level = 0;
}

/* Comment */
static void
inCommentOpeningState(OFXMLParser *self)
{
	if (self->_data[self->_i] != '-')
		@throw [OFMalformedXMLException exceptionWithParser: self];

	self->_last = self->_i + 1;
	self->_state = OFXMLParserStateInComment1;
	self->_state = stateInComment1;
	self->_level = 0;
}

static void
inCommentState1(OFXMLParser *self)
{
	if (self->_data[self->_i] == '-')
		self->_level++;
	else
		self->_level = 0;

	if (self->_level == 2)
		self->_state = OFXMLParserStateInComment2;
		self->_state = stateInComment2;
}

static void
inCommentState2(OFXMLParser *self)
{
	void *pool;
	OFString *comment;
1015
1016
1017
1018
1019
1020
1021
1022

1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039

1040
1041
1042
1043
1044
1045
1046
1032
1033
1034
1035
1036
1037
1038

1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055

1056
1057
1058
1059
1060
1061
1062
1063







-
+
















-
+







		[self->_delegate parser: self foundComment: comment];

	objc_autoreleasePoolPop(pool);

	[self->_buffer removeAllItems];

	self->_last = self->_i + 1;
	self->_state = OFXMLParserStateOutsideTag;
	self->_state = stateOutsideTag;
}

/* In <!DOCTYPE ...> */
static void
inDOCTYPEState(OFXMLParser *self)
{
	if ((self->_level < 6 &&
	    self->_data[self->_i] != "OCTYPE"[self->_level]) ||
	    (self->_level == 6 && self->_data[self->_i] != ' ' &&
	    self->_data[self->_i] != '\t' && self->_data[self->_i] != '\n' &&
	    self->_data[self->_i] != '\r'))
		@throw [OFMalformedXMLException exceptionWithParser: self];

	self->_level++;

	if (self->_level > 6 && self->_data[self->_i] == '>')
		self->_state = OFXMLParserStateOutsideTag;
		self->_state = stateOutsideTag;

	self->_last = self->_i + 1;
}

- (size_t)lineNumber
{
	return _lineNumber;