-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathCFURL.c
4871 lines (4503 loc) · 204 KB
/
CFURL.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (c) 2008-2012 Brent Fulgham <bfulgham@gmail.org>. All rights reserved.
*
* This source code is a modified version of the CoreFoundation sources released by Apple Inc. under
* the terms of the APSL version 2.0 (see below).
*
* For information about changes from the original Apple source release can be found by reviewing the
* source control system for the project at https://sourceforge.net/svn/?group_id=246198.
*
* The original license information is as follows:
*
* Copyright (c) 2011 Apple Inc. All rights reserved.
*
* @APPLE_LICENSE_HEADER_START@
*
* This file contains Original Code and/or Modifications of Original Code
* as defined in and that are subject to the Apple Public Source License
* Version 2.0 (the 'License'). You may not use this file except in
* compliance with the License. Please obtain a copy of the License at
* http://www.opensource.apple.com/apsl/ and read it before using this
* file.
*
* The Original Code and all software distributed under the License are
* distributed on an 'AS IS' basis, WITHOUT WARRANTY OF ANY KIND, EITHER
* EXPRESS OR IMPLIED, AND APPLE HEREBY DISCLAIMS ALL SUCH WARRANTIES,
* INCLUDING WITHOUT LIMITATION, ANY WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE, QUIET ENJOYMENT OR NON-INFRINGEMENT.
* Please see the License for the specific language governing rights and
* limitations under the License.
*
* @APPLE_LICENSE_HEADER_END@
*/
/* CFURL.c
Copyright (c) 1998-2011, Apple Inc. All rights reserved.
Responsibility: John Iarocci
*/
#include <CoreFoundation/CFURL.h>
#include <CoreFoundation/CFPriv.h>
#include <CoreFoundation/CFCharacterSetPriv.h>
#include <CoreFoundation/CFNumber.h>
#include <CoreFoundation/CoreFoundation_Prefix.h>
#include "CFInternal.h"
#include <CoreFoundation/CFStringEncodingConverter.h>
#include <CoreFoundation/CFURLPriv.h>
#include <limits.h>
#include <stdlib.h>
#include <stdio.h>
#include <string.h>
#if DEPLOYMENT_TARGET_MACOSX || DEPLOYMENT_TARGET_EMBEDDED || DEPLOYMENT_TARGET_LINUX
#if DEPLOYMENT_TARGET_MACOSX
#include <CoreFoundation/CFNumberFormatter.h>
#endif
#include <unistd.h>
#include <sys/stat.h>
#include <sys/types.h>
#elif DEPLOYMENT_TARGET_EMBEDDED || DEPLOYMENT_TARGET_LINUX || DEPLOYMENT_TARGET_FREEBSD
#include <CoreFoundation/CFNumberFormatter.h>
#include <unistd.h>
#include <sys/stat.h>
#include <sys/types.h>
#elif DEPLOYMENT_TARGET_WINDOWS
#include <CoreFoundation/CFNumberFormatter.h>
#else
#error Unknown or unspecified DEPLOYMENT_TARGET
#endif
#if DEPLOYMENT_TARGET_MACOSX || DEPLOYMENT_TARGET_EMBEDDED
static CFArrayRef HFSPathToURLComponents(CFStringRef path, CFAllocatorRef alloc, Boolean isDir);
#endif
static CFArrayRef WindowsPathToURLComponents(CFStringRef path, CFAllocatorRef alloc, Boolean isDir);
static CFStringRef WindowsPathToURLPath(CFStringRef path, CFAllocatorRef alloc, Boolean isDir);
static CFStringRef POSIXPathToURLPath(CFStringRef path, CFAllocatorRef alloc, Boolean isDirectory);
CFStringRef CFURLCreateStringWithFileSystemPath(CFAllocatorRef allocator, CFURLRef anURL, CFURLPathStyle fsType, Boolean resolveAgainstBase);
CF_EXPORT CFURLRef _CFURLCreateCurrentDirectoryURL(CFAllocatorRef allocator);
#if DEPLOYMENT_TARGET_MACOSX || DEPLOYMENT_TARGET_EMBEDDED
static CFStringRef HFSPathToURLPath(CFStringRef path, CFAllocatorRef alloc, Boolean isDir);
#elif DEPLOYMENT_TARGET_WINDOWS || DEPLOYMENT_TARGET_LINUX || DEPLOYMENT_TARGET_FREEBSD
#else
#error Unknown or unspecified DEPLOYMENT_TARGET
#endif
#ifndef DEBUG_URL_MEMORY_USAGE
#define DEBUG_URL_MEMORY_USAGE 0
#endif
#if DEBUG_URL_MEMORY_USAGE
static CFAllocatorRef URLAllocator = NULL;
static UInt32 numFileURLsCreated = 0;
static UInt32 numFileURLsConverted = 0;
static UInt32 numFileURLsDealloced = 0;
static UInt32 numURLs = 0;
static UInt32 numDealloced = 0;
static UInt32 numExtraDataAllocated = 0;
static UInt32 numURLsWithBaseURL = 0;
static UInt32 numNonUTF8EncodedURLs = 0;
#endif
/* The bit flags in myURL->_flags */
#define HAS_SCHEME (0x0001)
#define HAS_USER (0x0002)
#define HAS_PASSWORD (0x0004)
#define HAS_HOST (0x0008)
#define HAS_PORT (0x0010)
#define HAS_PATH (0x0020)
#define HAS_PARAMETERS (0x0040)
#define HAS_QUERY (0x0080)
#define HAS_FRAGMENT (0x0100)
#define HAS_HTTP_SCHEME (0x0200)
// Last free bit (0x200) in lower word goes here!
#define IS_IPV6_ENCODED (0x0400)
#define IS_OLD_UTF8_STYLE (0x0800)
#define IS_DIRECTORY (0x1000)
#define IS_PARSED (0x2000)
#define IS_ABSOLUTE (0x4000)
#define IS_DECOMPOSABLE (0x8000)
#define PATH_TYPE_MASK (0x000F0000)
/* POSIX_AND_URL_PATHS_MATCH will only be true if the URL and POSIX paths are identical, character for character, except for the presence/absence of a trailing slash on directories */
#define POSIX_AND_URL_PATHS_MATCH (0x00100000)
#define ORIGINAL_AND_URL_STRINGS_MATCH (0x00200000)
/* If ORIGINAL_AND_URL_STRINGS_MATCH is false, these bits determine where they differ */
// Scheme can actually never differ because if there were escaped characters prior to the colon, we'd interpret the string as a relative path
// #define SCHEME_DIFFERS (0x00400000) unused
#define USER_DIFFERS (0x00800000)
#define PASSWORD_DIFFERS (0x01000000)
#define HOST_DIFFERS (0x02000000)
// Port can actually never differ because if there were a non-digit following a colon in the net location, we'd interpret the whole net location as the host
#define PORT_DIFFERS (0x04000000)
// #define PATH_DIFFERS (0x08000000) unused
// #define PARAMETERS_DIFFER (0x10000000) unused
// #define QUERY_DIFFERS (0x20000000) unused
#define PATH_HAS_FILE_ID (0x40000000)
#define HAS_FILE_SCHEME (0x80000000)
// Number of bits to shift to get from HAS_FOO to FOO_DIFFERS flag
#define BIT_SHIFT_FROM_COMPONENT_TO_DIFFERS_FLAG (22)
// Other useful defines
#define NET_LOCATION_MASK (HAS_HOST | HAS_USER | HAS_PASSWORD | HAS_PORT)
#define RESOURCE_SPECIFIER_MASK (HAS_PARAMETERS | HAS_QUERY | HAS_FRAGMENT)
#define FULL_URL_REPRESENTATION (0xF)
/* URL_PATH_TYPE(anURL) will be one of the CFURLPathStyle constants, in which case string is a file system path, or will be FULL_URL_REPRESENTATION, in which case the string is the full URL string. One caveat - string always has a trailing path delimiter if the url is a directory URL. This must be stripped before returning file system representations! */
#define URL_PATH_TYPE(url) (((url->_flags) & PATH_TYPE_MASK) >> 16)
#define PATH_DELIM_FOR_TYPE(fsType) ((fsType) == kCFURLHFSPathStyle ? ':' : (((fsType) == kCFURLWindowsPathStyle) ? '\\' : '/'))
#define PATH_DELIM_AS_STRING_FOR_TYPE(fsType) ((fsType) == kCFURLHFSPathStyle ? CFSTR(":") : (((fsType) == kCFURLWindowsPathStyle) ? CFSTR("\\") : CFSTR("/")))
#define FILE_ID_PREFIX ".file"
#define FILE_ID_KEY "id"
#define FILE_ID_PREAMBLE "/.file/id="
#define FILE_ID_PREAMBLE_LENGTH 10
#define ASSERT_CHECK_PATHSTYLE(x) 0
#if DEPLOYMENT_TARGET_WINDOWS
#define PATH_SEP '\\'
#define PATH_MAX MAX_PATH
#else
#define PATH_SEP '/'
#endif
// In order to reduce the sizeof ( __CFURL ), move these items into a seperate structure which is
// only allocated when necessary. In my tests, it's almost never needed -- very rarely does a CFURL have
// either a sanitized string or a reserved pointer for URLHandle.
struct _CFURLAdditionalData {
void *_reserved; // Reserved for URLHandle's use.
CFMutableStringRef _sanitizedString; // The fully compliant RFC string. This is only non-NULL if ORIGINAL_AND_URL_STRINGS_MATCH is false. This should never be mutated except when the sanatized string is first computed
CFHashCode hashValue;
};
struct __CFURL {
CFRuntimeBase _cfBase;
UInt32 _flags;
CFStringEncoding _encoding; // The encoding to use when asked to remove percent escapes; this is never consulted if IS_OLD_UTF8_STYLE is set.
CFStringRef _string; // Never NULL; the meaning of _string depends on URL_PATH_TYPE(myURL) (see above)
CFURLRef _base;
CFRange *ranges;
struct _CFURLAdditionalData* extra;
void *_resourceInfo; // For use by CarbonCore to cache property values. Retained and released by CFURL.
};
CF_INLINE void* _getReserved ( const struct __CFURL* url )
{
if ( url && url->extra )
return url->extra->_reserved;
return NULL;
}
CF_INLINE CFMutableStringRef _getSanitizedString ( const struct __CFURL* url )
{
if ( url && url->extra )
return url->extra->_sanitizedString;
return NULL;
}
static void* _getResourceInfo ( const struct __CFURL* url )
{
if ( url ) {
return url->_resourceInfo;
}
return NULL;
}
static void _CFURLAllocateExtraDataspace( struct __CFURL* url )
{
if ( url && ! url->extra )
{ struct _CFURLAdditionalData* extra = (struct _CFURLAdditionalData*) CFAllocatorAllocate( CFGetAllocator( url), sizeof( struct _CFURLAdditionalData ), __kCFAllocatorGCScannedMemory);
extra->_reserved = _getReserved( url );
extra->_sanitizedString = _getSanitizedString( url );
extra->hashValue = 0;
url->extra = extra;
#if DEBUG_URL_MEMORY_USAGE
numExtraDataAllocated ++;
#endif
}
}
CF_INLINE void _setReserved ( struct __CFURL* url, void* reserved )
{
if ( url )
{
// Don't allocate extra space if we're just going to be storing NULL
if ( ! url->extra && reserved )
_CFURLAllocateExtraDataspace( url );
if ( url->extra )
__CFAssignWithWriteBarrier((void **)&url->extra->_reserved, reserved);
}
}
CF_INLINE void _setSanitizedString ( struct __CFURL* url, CFMutableStringRef sanitizedString )
{
if ( url )
{
// Don't allocate extra space if we're just going to be storing NULL
if ( ! url->extra && sanitizedString )
_CFURLAllocateExtraDataspace( url );
if ( url->extra )
url->extra->_sanitizedString = sanitizedString;
}
}
static void _setResourceInfo ( struct __CFURL* url, void* resourceInfo )
{
// Must be atomic
// Never a GC object
if ( url && OSAtomicCompareAndSwapPtrBarrier( NULL, resourceInfo, &url->_resourceInfo )) {
CFRetain( resourceInfo );
}
}
static void _convertToURLRepresentation(struct __CFURL *url);
static CFURLRef _CFURLCopyAbsoluteFileURL(CFURLRef relativeURL);
static CFStringRef _resolveFileSystemPaths(CFStringRef relativePath, CFStringRef basePath, Boolean baseIsDir, CFURLPathStyle fsType, CFAllocatorRef alloc);
static void _parseComponents(CFAllocatorRef alloc, CFStringRef string, CFURLRef base, UInt32 *flags, CFRange **range);
static CFRange _rangeForComponent(UInt32 flags, CFRange *ranges, UInt32 compFlag);
static CFRange _netLocationRange(UInt32 flags, CFRange *ranges);
static UInt32 _firstResourceSpecifierFlag(UInt32 flags);
static void computeSanitizedString(CFURLRef url);
static CFStringRef correctedComponent(CFStringRef component, UInt32 compFlag, CFStringEncoding enc);
static CFMutableStringRef resolveAbsoluteURLString(CFAllocatorRef alloc, CFStringRef relString, UInt32 relFlags, CFRange *relRanges, CFStringRef baseString, UInt32 baseFlags, CFRange *baseRanges);
static CFStringRef _resolvedPath(UniChar *pathStr, UniChar *end, UniChar pathDelimiter, Boolean stripLeadingDotDots, Boolean stripTrailingDelimiter, CFAllocatorRef alloc);
CF_INLINE void _parseComponentsOfURL(CFURLRef url) {
_parseComponents(CFGetAllocator(url), url->_string, url->_base, &(((struct __CFURL *)url)->_flags), &(((struct __CFURL *)url)->ranges));
}
static Boolean _createOldUTF8StyleURLs = false;
CF_INLINE Boolean createOldUTF8StyleURLs(void) {
return (_createOldUTF8StyleURLs);
}
// Our backdoor in case removing the UTF8 constraint for URLs creates unexpected problems. See radar 2902530 -- REW
CF_EXPORT
void _CFURLCreateOnlyUTF8CompatibleURLs(Boolean createUTF8URLs) {
_createOldUTF8StyleURLs = createUTF8URLs;
}
enum {
VALID = 1,
UNRESERVED = 2,
PATHVALID = 4,
SCHEME = 8,
HEXDIGIT = 16
};
static const unsigned char sURLValidCharacters[] = {
/* ' ' 32 */ 0,
/* '!' 33 */ VALID | UNRESERVED | PATHVALID ,
/* '"' 34 */ 0,
/* '#' 35 */ 0,
/* '$' 36 */ VALID | PATHVALID ,
/* '%' 37 */ 0,
/* '&' 38 */ VALID | PATHVALID ,
/* ''' 39 */ VALID | UNRESERVED | PATHVALID ,
/* '(' 40 */ VALID | UNRESERVED | PATHVALID ,
/* ')' 41 */ VALID | UNRESERVED | PATHVALID ,
/* '*' 42 */ VALID | UNRESERVED | PATHVALID ,
/* '+' 43 */ VALID | SCHEME | PATHVALID ,
/* ',' 44 */ VALID | PATHVALID ,
/* '-' 45 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* '.' 46 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* '/' 47 */ VALID | PATHVALID ,
/* '0' 48 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '1' 49 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '2' 50 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '3' 51 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '4' 52 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '5' 53 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '6' 54 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '7' 55 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '8' 56 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* '9' 57 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* ':' 58 */ VALID ,
/* ';' 59 */ VALID ,
/* '<' 60 */ 0,
/* '=' 61 */ VALID | PATHVALID ,
/* '>' 62 */ 0,
/* '?' 63 */ VALID ,
/* '@' 64 */ VALID ,
/* 'A' 65 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'B' 66 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'C' 67 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'D' 68 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'E' 69 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'F' 70 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'G' 71 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'H' 72 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'I' 73 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'J' 74 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'K' 75 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'L' 76 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'M' 77 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'N' 78 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'O' 79 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'P' 80 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'Q' 81 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'R' 82 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'S' 83 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'T' 84 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'U' 85 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'V' 86 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'W' 87 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'X' 88 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'Y' 89 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'Z' 90 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* '[' 91 */ 0,
/* '\' 92 */ 0,
/* ']' 93 */ 0,
/* '^' 94 */ 0,
/* '_' 95 */ VALID | UNRESERVED | PATHVALID ,
/* '`' 96 */ 0,
/* 'a' 97 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'b' 98 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'c' 99 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'd' 100 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'e' 101 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'f' 102 */ VALID | UNRESERVED | SCHEME | PATHVALID | HEXDIGIT ,
/* 'g' 103 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'h' 104 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'i' 105 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'j' 106 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'k' 107 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'l' 108 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'm' 109 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'n' 110 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'o' 111 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'p' 112 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'q' 113 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'r' 114 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 's' 115 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 't' 116 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'u' 117 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'v' 118 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'w' 119 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'x' 120 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'y' 121 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* 'z' 122 */ VALID | UNRESERVED | SCHEME | PATHVALID ,
/* '{' 123 */ 0,
/* '|' 124 */ 0,
/* '}' 125 */ 0,
/* '~' 126 */ VALID | UNRESERVED | PATHVALID ,
/* '' 127 */ 0
};
CF_INLINE Boolean isURLLegalCharacter(UniChar ch) {
return ( ( 32 <= ch ) && ( ch <= 127 ) ) ? ( sURLValidCharacters[ ch - 32 ] & VALID ) : false;
}
CF_INLINE Boolean scheme_valid(UniChar ch) {
return ( ( 32 <= ch ) && ( ch <= 127 ) ) ? ( sURLValidCharacters[ ch - 32 ] & SCHEME ) : false;
}
// "Unreserved" as defined by RFC 2396
CF_INLINE Boolean isUnreservedCharacter(UniChar ch) {
return ( ( 32 <= ch ) && ( ch <= 127 ) ) ? ( sURLValidCharacters[ ch - 32 ] & UNRESERVED ) : false;
}
CF_INLINE Boolean isPathLegalCharacter(UniChar ch) {
return ( ( 32 <= ch ) && ( ch <= 127 ) ) ? ( sURLValidCharacters[ ch - 32 ] & PATHVALID ) : false;
}
CF_INLINE Boolean isHexDigit(UniChar ch) {
return ( ( 32 <= ch ) && ( ch <= 127 ) ) ? ( sURLValidCharacters[ ch - 32 ] & HEXDIGIT ) : false;
}
// Returns false if ch1 or ch2 isn't properly formatted
CF_INLINE Boolean _translateBytes(UniChar ch1, UniChar ch2, uint8_t *result) {
*result = 0;
if (ch1 >= '0' && ch1 <= '9') *result += (ch1 - '0');
else if (ch1 >= 'a' && ch1 <= 'f') *result += 10 + ch1 - 'a';
else if (ch1 >= 'A' && ch1 <= 'F') *result += 10 + ch1 - 'A';
else return false;
*result = (*result) << 4;
if (ch2 >= '0' && ch2 <= '9') *result += (ch2 - '0');
else if (ch2 >= 'a' && ch2 <= 'f') *result += 10 + ch2 - 'a';
else if (ch2 >= 'A' && ch2 <= 'F') *result += 10 + ch2 - 'A';
else return false;
return true;
}
CF_INLINE Boolean _haveTestedOriginalString(CFURLRef url) {
return ((url->_flags & ORIGINAL_AND_URL_STRINGS_MATCH) != 0) || (_getSanitizedString(url) != NULL);
}
typedef CFStringRef (*StringTransformation)(CFAllocatorRef, CFStringRef, CFIndex);
#if DEPLOYMENT_TARGET_MACOSX || DEPLOYMENT_TARGET_EMBEDDED
static CFArrayRef copyStringArrayWithTransformation(CFArrayRef array, StringTransformation transformation) {
CFAllocatorRef alloc = CFGetAllocator(array);
CFMutableArrayRef mArray = NULL;
CFIndex i, c = CFArrayGetCount(array);
for (i = 0; i < c; i ++) {
CFStringRef origComp = (CFStringRef)CFArrayGetValueAtIndex(array, i);
CFStringRef unescapedComp = transformation(alloc, origComp, i);
if (!unescapedComp) {
break;
}
if (unescapedComp != origComp) {
if (!mArray) {
mArray = CFArrayCreateMutableCopy(alloc, c, array);
}
CFArraySetValueAtIndex(mArray, i, unescapedComp);
}
CFRelease(unescapedComp);
}
if (i != c) {
if (mArray) CFRelease(mArray);
return NULL;
} else if (mArray) {
return mArray;
} else {
CFRetain(array);
return array;
}
}
#endif
// Returns NULL if str cannot be converted for whatever reason, str if str contains no characters in need of escaping, or a newly-created string with the appropriate % escape codes in place. Caller must always release the returned string.
CF_INLINE CFStringRef _replacePathIllegalCharacters(CFStringRef str, CFAllocatorRef alloc, Boolean preserveSlashes) {
if (preserveSlashes) {
return CFURLCreateStringByAddingPercentEscapes(alloc, str, NULL, CFSTR(";?"), kCFStringEncodingUTF8);
} else {
return CFURLCreateStringByAddingPercentEscapes(alloc, str, NULL, CFSTR(";?/"), kCFStringEncodingUTF8);
}
}
#if DEPLOYMENT_TARGET_MACOSX || DEPLOYMENT_TARGET_EMBEDDED
static CFStringRef escapePathComponent(CFAllocatorRef alloc, CFStringRef origComponent, CFIndex componentIndex) {
return CFURLCreateStringByAddingPercentEscapes(alloc, origComponent, NULL, CFSTR(";?/"), kCFStringEncodingUTF8);
}
#endif
// We have 2 UniChars of a surrogate; we must convert to the correct percent-encoded UTF8 string and append to str. Added so that file system URLs can always be converted from POSIX to full URL representation. -- REW, 8/20/2001
static Boolean _hackToConvertSurrogates(UniChar highChar, UniChar lowChar, CFMutableStringRef str) {
UniChar surrogate[2];
uint8_t bytes[6]; // Aki sez it should never take more than 6 bytes
CFIndex len;
uint8_t *currByte;
surrogate[0] = highChar;
surrogate[1] = lowChar;
if (CFStringEncodingUnicodeToBytes(kCFStringEncodingUTF8, 0, surrogate, 2, NULL, bytes, 6, &len) != kCFStringEncodingConversionSuccess) {
return false;
}
for (currByte = bytes; currByte < bytes + len; currByte ++) {
UniChar escapeSequence[3] = {'%', '\0', '\0'};
unsigned char high, low;
high = ((*currByte) & 0xf0) >> 4;
low = (*currByte) & 0x0f;
escapeSequence[1] = (high < 10) ? '0' + high : 'A' + high - 10;
escapeSequence[2] = (low < 10) ? '0' + low : 'A' + low - 10;
CFStringAppendCharacters(str, escapeSequence, 3);
}
return true;
}
static Boolean _appendPercentEscapesForCharacter(UniChar ch, CFStringEncoding encoding, CFMutableStringRef str) {
uint8_t bytes[6]; // 6 bytes is the maximum a single character could require in UTF8 (most common case); other encodings could require more
uint8_t *bytePtr = bytes, *currByte;
CFIndex byteLength;
CFAllocatorRef alloc = NULL;
if (CFStringEncodingUnicodeToBytes(encoding, 0, &ch, 1, NULL, bytePtr, 6, &byteLength) != kCFStringEncodingConversionSuccess) {
byteLength = CFStringEncodingByteLengthForCharacters(encoding, 0, &ch, 1);
if (byteLength <= 6) {
// The encoding cannot accomodate the character
return false;
}
alloc = CFGetAllocator(str);
bytePtr = (uint8_t *)CFAllocatorAllocate(alloc, byteLength, 0);
if (!bytePtr || CFStringEncodingUnicodeToBytes(encoding, 0, &ch, 1, NULL, bytePtr, byteLength, &byteLength) != kCFStringEncodingConversionSuccess) {
if (bytePtr) CFAllocatorDeallocate(alloc, bytePtr);
return false;
}
}
for (currByte = bytePtr; currByte < bytePtr + byteLength; currByte ++) {
UniChar escapeSequence[3] = {'%', '\0', '\0'};
unsigned char high, low;
high = ((*currByte) & 0xf0) >> 4;
low = (*currByte) & 0x0f;
escapeSequence[1] = (high < 10) ? '0' + high : 'A' + high - 10;
escapeSequence[2] = (low < 10) ? '0' + low : 'A' + low - 10;
CFStringAppendCharacters(str, escapeSequence, 3);
}
if (bytePtr != bytes) {
CFAllocatorDeallocate(alloc, bytePtr);
}
return true;
}
// Uses UTF-8 to translate all percent escape sequences; returns NULL if it encounters a format failure. May return the original string.
CFStringRef CFURLCreateStringByReplacingPercentEscapes(CFAllocatorRef alloc, CFStringRef originalString, CFStringRef charactersToLeaveEscaped) {
CFMutableStringRef newStr = NULL;
CFIndex length;
CFIndex mark = 0;
CFRange percentRange, searchRange;
CFStringRef escapedStr = NULL;
CFMutableStringRef strForEscapedChar = NULL;
UniChar escapedChar;
Boolean escapeAll = (charactersToLeaveEscaped && CFStringGetLength(charactersToLeaveEscaped) == 0);
Boolean failed = false;
if (!originalString) return NULL;
if (charactersToLeaveEscaped == NULL) {
return (CFStringRef)CFStringCreateCopy(alloc, originalString);
}
length = CFStringGetLength(originalString);
searchRange = CFRangeMake(0, length);
while (!failed && CFStringFindWithOptions(originalString, CFSTR("%"), searchRange, 0, &percentRange)) {
uint8_t bytes[4]; // Single UTF-8 character could require up to 4 bytes.
uint8_t numBytesExpected;
UniChar ch1, ch2;
escapedStr = NULL;
// Make sure we have at least 2 more characters
if (length - percentRange.location < 3) { failed = true; break; }
// if we don't have at least 2 more characters, we can't interpret the percent escape code,
// so we assume the percent character is legit, and let it pass into the string
ch1 = CFStringGetCharacterAtIndex(originalString, percentRange.location+1);
ch2 = CFStringGetCharacterAtIndex(originalString, percentRange.location+2);
if (!_translateBytes(ch1, ch2, bytes)) { failed = true; break; }
if (!(bytes[0] & 0x80)) {
numBytesExpected = 1;
} else if (!(bytes[0] & 0x20)) {
numBytesExpected = 2;
} else if (!(bytes[0] & 0x10)) {
numBytesExpected = 3;
} else {
numBytesExpected = 4;
}
if (numBytesExpected == 1) {
// one byte sequence (most common case); handle this specially
escapedChar = bytes[0];
if (!strForEscapedChar) {
strForEscapedChar = CFStringCreateMutableWithExternalCharactersNoCopy(alloc, &escapedChar, 1, 1, kCFAllocatorNull);
}
escapedStr = (CFStringRef)CFRetain(strForEscapedChar);
} else {
CFIndex j;
// Make sure up front that we have enough characters
if (length < percentRange.location + numBytesExpected * 3) { failed = true; break; }
for (j = 1; j < numBytesExpected; j ++) {
if (CFStringGetCharacterAtIndex(originalString, percentRange.location + 3*j) != '%') { failed = true; break; }
ch1 = CFStringGetCharacterAtIndex(originalString, percentRange.location + 3*j + 1);
ch2 = CFStringGetCharacterAtIndex(originalString, percentRange.location + 3*j + 2);
if (!_translateBytes(ch1, ch2, bytes+j)) { failed = true; break; }
}
// !!! We should do the low-level bit-twiddling ourselves; this is expensive! REW, 6/10/99
escapedStr = CFStringCreateWithBytes(alloc, bytes, numBytesExpected, kCFStringEncodingUTF8, false);
if (!escapedStr) {
failed = true;
} else if (CFStringGetLength(escapedStr) == 0 && numBytesExpected == 3 && bytes[0] == 0xef && bytes[1] == 0xbb && bytes[2] == 0xbf) {
// Somehow, the UCS-2 BOM got translated in to a UTF8 string
escapedChar = 0xfeff;
if (!strForEscapedChar) {
strForEscapedChar = CFStringCreateMutableWithExternalCharactersNoCopy(alloc, &escapedChar, 1, 1, kCFAllocatorNull);
}
CFRelease(escapedStr);
escapedStr = (CFStringRef)CFRetain(strForEscapedChar);
}
if (failed) break;
}
// The new character is in escapedChar; the number of percent escapes it took is in numBytesExpected.
searchRange.location = percentRange.location + 3 * numBytesExpected;
searchRange.length = length - searchRange.location;
if (!escapeAll) {
if (CFStringFind(charactersToLeaveEscaped, escapedStr, 0).location != kCFNotFound) {
if (escapedStr) {
CFRelease(escapedStr);
escapedStr = NULL;
}
continue;
}
}
if (!newStr) {
newStr = CFStringCreateMutable(alloc, length);
}
if (percentRange.location - mark > 0) {
// The creation of this temporary string is unfortunate.
CFStringRef substring = CFStringCreateWithSubstring(alloc, originalString, CFRangeMake(mark, percentRange.location - mark));
CFStringAppend(newStr, substring);
CFRelease(substring);
}
CFStringAppend(newStr, escapedStr);
if (escapedStr) {
CFRelease(escapedStr);
escapedStr = NULL;
}
mark = searchRange.location;// We need mark to be the index of the first character beyond the escape sequence
}
if (escapedStr) CFRelease(escapedStr);
if (strForEscapedChar) CFRelease(strForEscapedChar);
if (failed) {
if (newStr) CFRelease(newStr);
return NULL;
} else if (newStr) {
if (mark < length) {
// Need to cat on the remainder of the string
CFStringRef substring = CFStringCreateWithSubstring(alloc, originalString, CFRangeMake(mark, length - mark));
CFStringAppend(newStr, substring);
CFRelease(substring);
}
return newStr;
} else {
return (CFStringRef)CFStringCreateCopy(alloc, originalString);
}
}
CF_EXPORT
CFStringRef CFURLCreateStringByReplacingPercentEscapesUsingEncoding(CFAllocatorRef alloc, CFStringRef originalString, CFStringRef charactersToLeaveEscaped, CFStringEncoding enc) {
if (enc == kCFStringEncodingUTF8) {
return CFURLCreateStringByReplacingPercentEscapes(alloc, originalString, charactersToLeaveEscaped);
} else {
CFMutableStringRef newStr = NULL;
CFMutableStringRef escapedStr = NULL;
CFIndex length;
CFIndex mark = 0;
CFRange percentRange, searchRange;
Boolean escapeAll = (charactersToLeaveEscaped && CFStringGetLength(charactersToLeaveEscaped) == 0);
Boolean failed = false;
uint8_t byteBuffer[8];
uint8_t *bytes = byteBuffer;
int capacityOfBytes = 8;
if (!originalString) return NULL;
if (charactersToLeaveEscaped == NULL) {
return (CFStringRef)CFStringCreateCopy(alloc, originalString);
}
length = CFStringGetLength(originalString);
searchRange = CFRangeMake(0, length);
while (!failed && CFStringFindWithOptions(originalString, CFSTR("%"), searchRange, 0, &percentRange)) {
UniChar ch1, ch2;
CFIndex percentLoc = percentRange.location;
CFStringRef convertedString;
int numBytesUsed = 0;
do {
// Make sure we have at least 2 more characters
if (length - percentLoc < 3) { failed = true; break; }
if (numBytesUsed == capacityOfBytes) {
if (bytes == byteBuffer) {
bytes = (uint8_t *)CFAllocatorAllocate(alloc, 16 * sizeof(uint8_t), 0);
memmove(bytes, byteBuffer, capacityOfBytes);
capacityOfBytes = 16;
} else {
void *oldbytes = bytes;
int oldcap = capacityOfBytes;
capacityOfBytes = 2*capacityOfBytes;
bytes = (uint8_t *)CFAllocatorAllocate(alloc, capacityOfBytes * sizeof(uint8_t), 0);
memmove(bytes, oldbytes, oldcap);
CFAllocatorDeallocate(alloc, oldbytes);
}
}
percentLoc ++;
ch1 = CFStringGetCharacterAtIndex(originalString, percentLoc);
percentLoc ++;
ch2 = CFStringGetCharacterAtIndex(originalString, percentLoc);
percentLoc ++;
if (!_translateBytes(ch1, ch2, bytes + numBytesUsed)) { failed = true; break; }
numBytesUsed ++;
} while (CFStringGetCharacterAtIndex(originalString, percentLoc) == '%');
searchRange.location = percentLoc;
searchRange.length = length - searchRange.location;
if (failed) break;
convertedString = CFStringCreateWithBytes(alloc, bytes, numBytesUsed, enc, false);
if (!convertedString) {
failed = true;
break;
}
if (!newStr) {
newStr = CFStringCreateMutable(alloc, length);
}
if (percentRange.location - mark > 0) {
// The creation of this temporary string is unfortunate.
CFStringRef substring = CFStringCreateWithSubstring(alloc, originalString, CFRangeMake(mark, percentRange.location - mark));
CFStringAppend(newStr, substring);
CFRelease(substring);
}
if (escapeAll) {
CFStringAppend(newStr, convertedString);
} else {
CFIndex i, c = CFStringGetLength(convertedString);
if (!escapedStr) {
escapedStr = CFStringCreateMutableWithExternalCharactersNoCopy(alloc, &ch1, 1, 1, kCFAllocatorNull);
}
for (i = 0; i < c; i ++) {
ch1 = CFStringGetCharacterAtIndex(convertedString, i);
if (CFStringFind(charactersToLeaveEscaped, escapedStr, 0).location == kCFNotFound) {
CFStringAppendCharacters(newStr, &ch1, 1);
} else {
// Must regenerate the escape sequence for this character; because we started with percent escapes, we know this call cannot fail
_appendPercentEscapesForCharacter(ch1, enc, newStr);
}
}
}
CFRelease(convertedString);
mark = searchRange.location;// We need mark to be the index of the first character beyond the escape sequence
}
if (escapedStr) CFRelease(escapedStr);
if (bytes != byteBuffer) CFAllocatorDeallocate(alloc, bytes);
if (failed) {
if (newStr) CFRelease(newStr);
return NULL;
} else if (newStr) {
if (mark < length) {
// Need to cat on the remainder of the string
CFStringRef substring = CFStringCreateWithSubstring(alloc, originalString, CFRangeMake(mark, length - mark));
CFStringAppend(newStr, substring);
CFRelease(substring);
}
return newStr;
} else {
return (CFStringRef)CFStringCreateCopy(alloc, originalString);
}
}
}
static CFStringRef _addPercentEscapesToString(CFAllocatorRef allocator, CFStringRef originalString, Boolean (*shouldReplaceChar)(UniChar, void*), CFIndex (*handlePercentChar)(CFIndex, CFStringRef, CFStringRef *, void *), CFStringEncoding encoding, void *context) {
CFMutableStringRef newString = NULL;
CFIndex idx, length;
CFStringInlineBuffer buf;
if (!originalString) return NULL;
length = CFStringGetLength(originalString);
if (length == 0) return (CFStringRef)CFStringCreateCopy(allocator, originalString);
CFStringInitInlineBuffer(originalString, &buf, CFRangeMake(0, length));
for (idx = 0; idx < length; idx ++) {
UniChar ch = CFStringGetCharacterFromInlineBuffer(&buf, idx);
Boolean shouldReplace = shouldReplaceChar(ch, context);
if (shouldReplace) {
// Perform the replacement
if (!newString) {
newString = CFStringCreateMutableCopy(CFGetAllocator(originalString), 0, originalString);
CFStringDelete(newString, CFRangeMake(idx, length-idx));
}
if (!_appendPercentEscapesForCharacter(ch, encoding, newString)) {
//#warning FIXME - once CFString supports finding glyph boundaries walk by glyph boundaries instead of by unichars
if (encoding == kCFStringEncodingUTF8 && CFCharacterSetIsSurrogateHighCharacter(ch) && idx + 1 < length && CFCharacterSetIsSurrogateLowCharacter(CFStringGetCharacterFromInlineBuffer(&buf, idx+1))) {
// Hack to guarantee we always safely convert file URLs between POSIX & full URL representation
if (_hackToConvertSurrogates(ch, CFStringGetCharacterFromInlineBuffer(&buf, idx+1), newString)) {
idx ++; // We consumed 2 characters, not 1
} else {
break;
}
} else {
break;
}
}
} else if (ch == '%' && handlePercentChar) {
CFStringRef replacementString = NULL;
CFIndex newIndex = handlePercentChar(idx, originalString, &replacementString, context);
if (newIndex < 0) {
break;
} else if (replacementString) {
if (!newString) {
newString = CFStringCreateMutableCopy(CFGetAllocator(originalString), 0, originalString);
CFStringDelete(newString, CFRangeMake(idx, length-idx));
}
CFStringAppend(newString, replacementString);
CFRelease(replacementString);
}
if (newIndex == idx) {
if (newString) {
CFStringAppendCharacters(newString, &ch, 1);
}
} else {
if (!replacementString && newString) {
CFIndex tmpIndex;
for (tmpIndex = idx; tmpIndex < newIndex; tmpIndex ++) {
ch = CFStringGetCharacterAtIndex(originalString, idx);
CFStringAppendCharacters(newString, &ch, 1);
}
}
idx = newIndex - 1;
}
} else if (newString) {
CFStringAppendCharacters(newString, &ch, 1);
}
}
if (idx < length) {
// Ran in to an encoding failure
if (newString) CFRelease(newString);
return NULL;
} else if (newString) {
return newString;
} else {
return (CFStringRef)CFStringCreateCopy(CFGetAllocator(originalString), originalString);
}
}
static Boolean _stringContainsCharacter(CFStringRef string, UniChar ch) {
CFIndex i, c = CFStringGetLength(string);
CFStringInlineBuffer buf;
CFStringInitInlineBuffer(string, &buf, CFRangeMake(0, c));
for (i = 0; i < c; i ++) if (__CFStringGetCharacterFromInlineBufferQuick(&buf, i) == ch) return true;
return false;
}
static Boolean _shouldPercentReplaceChar(UniChar ch, void *context) {
CFStringRef unescape = ((CFStringRef *)context)[0];
CFStringRef escape = ((CFStringRef *)context)[1];
Boolean shouldReplace = (isURLLegalCharacter(ch) == false);
if (shouldReplace) {
if (unescape && _stringContainsCharacter(unescape, ch)) {
shouldReplace = false;
}
} else if (escape && _stringContainsCharacter(escape, ch)) {
shouldReplace = true;
}
return shouldReplace;
}
CF_EXPORT CFStringRef CFURLCreateStringByAddingPercentEscapes(CFAllocatorRef allocator, CFStringRef originalString, CFStringRef charactersToLeaveUnescaped, CFStringRef legalURLCharactersToBeEscaped, CFStringEncoding encoding) {
CFStringRef strings[2];
strings[0] = charactersToLeaveUnescaped;
strings[1] = legalURLCharactersToBeEscaped;
return _addPercentEscapesToString(allocator, originalString, _shouldPercentReplaceChar, NULL, encoding, strings);
}
#if 0
static Boolean __CFURLCompare(CFTypeRef cf1, CFTypeRef cf2) {
CFURLRef url1 = (CFURLRef)cf1;
CFURLRef url2 = (CFURLRef)cf2;
UInt32 pathType1, pathType2;
__CFGenericValidateType(cf1, CFURLGetTypeID());
__CFGenericValidateType(cf2, CFURLGetTypeID());
if (url1 == url2) return kCFCompareEqualTo;
if ( url1->_base ) {
if (! url2->_base) return kCFCompareEqualTo;
if (!CFEqual( url1->_base, url2->_base )) return false;
} else if ( url2->_base) {
return false;
}
pathType1 = URL_PATH_TYPE(url1);
pathType2 = URL_PATH_TYPE(url2);
if (pathType1 == pathType2) {
if (pathType1 != FULL_URL_REPRESENTATION) {
return CFEqual(url1->_string, url2->_string);
} else {
// Do not compare the original strings; compare the sanatized strings.
return CFEqual(CFURLGetString(url1), CFURLGetString(url2));
}
} else {
// Try hard to avoid the expensive conversion from a file system representation to the canonical form
CFStringRef scheme1 = CFURLCopyScheme(url1);
CFStringRef scheme2 = CFURLCopyScheme(url2);
Boolean eq;
if (scheme1 && scheme2) {
eq = CFEqual(scheme1, scheme2);
CFRelease(scheme1);
CFRelease(scheme2);
} else if (!scheme1 && !scheme2) {
eq = TRUE;
} else {
eq = FALSE;
if (scheme1) CFRelease(scheme1);
else CFRelease(scheme2);
}
if (!eq) return false;
if (pathType1 == FULL_URL_REPRESENTATION) {
if (!(url1->_flags & IS_PARSED)) {
_parseComponentsOfURL(url1);
}
if (url1->_flags & (HAS_USER | HAS_PORT | HAS_PASSWORD | HAS_QUERY | HAS_PARAMETERS | HAS_FRAGMENT )) {
return false;
}
}
if (pathType2 == FULL_URL_REPRESENTATION) {
if (!(url2->_flags & IS_PARSED)) {
_parseComponentsOfURL(url2);
}
if (url2->_flags & (HAS_USER | HAS_PORT | HAS_PASSWORD | HAS_QUERY | HAS_PARAMETERS | HAS_FRAGMENT )) {
return false;
}
}
// No help for it; we now must convert to the canonical representation and compare.
return CFEqual(CFURLGetString(url1), CFURLGetString(url2));
}
}
#endif
static Boolean __CFURLEqual(CFTypeRef cf1, CFTypeRef cf2) {
CFURLRef url1 = (CFURLRef)cf1;
CFURLRef url2 = (CFURLRef)cf2;
UInt32 pathType1, pathType2;
__CFGenericValidateType(cf1, CFURLGetTypeID());
__CFGenericValidateType(cf2, CFURLGetTypeID());
if (url1 == url2) return true;
if ((url1->_flags & IS_PARSED) && (url2->_flags & IS_PARSED) && (url1->_flags & IS_DIRECTORY) != (url2->_flags & IS_DIRECTORY)) return false;
if ( url1->_base ) {
if (! url2->_base) return false;
if (!CFEqual( url1->_base, url2->_base )) return false;
} else if ( url2->_base) {
return false;
}
pathType1 = URL_PATH_TYPE(url1);
pathType2 = URL_PATH_TYPE(url2);
if (pathType1 == pathType2) {
if (pathType1 != FULL_URL_REPRESENTATION) {
return CFEqual(url1->_string, url2->_string);
} else {
// Do not compare the original strings; compare the sanatized strings.
return CFEqual(CFURLGetString(url1), CFURLGetString(url2));
}
} else {
// Try hard to avoid the expensive conversion from a file system representation to the canonical form
CFStringRef scheme1 = CFURLCopyScheme(url1);
CFStringRef scheme2 = CFURLCopyScheme(url2);
Boolean eq;
if (scheme1 && scheme2) {
eq = CFEqual(scheme1, scheme2);
CFRelease(scheme1);
CFRelease(scheme2);
} else if (!scheme1 && !scheme2) {
eq = TRUE;