-
Notifications
You must be signed in to change notification settings - Fork 369
/
uri.c
2812 lines (2567 loc) · 69.3 KB
/
uri.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
/**
* uri.c: set of generic URI related routines
*
* Reference: RFCs 3986, 2732 and 2373
*
* See Copyright for the status of this software.
*
*/
#define IN_LIBXML
#include "libxml.h"
#include <limits.h>
#include <string.h>
#include <libxml/xmlmemory.h>
#include <libxml/uri.h>
#include <libxml/xmlerror.h>
#include "private/error.h"
/**
* MAX_URI_LENGTH:
*
* The definition of the URI regexp in the above RFC has no size limit
* In practice they are usually relatively short except for the
* data URI scheme as defined in RFC 2397. Even for data URI the usual
* maximum size before hitting random practical limits is around 64 KB
* and 4KB is usually a maximum admitted limit for proper operations.
* The value below is more a security limit than anything else and
* really should never be hit by 'normal' operations
* Set to 1 MByte in 2012, this is only enforced on output
*/
#define MAX_URI_LENGTH 1024 * 1024
#define PORT_EMPTY 0
#define PORT_EMPTY_SERVER -1
static void xmlCleanURI(xmlURIPtr uri);
/*
* Old rule from 2396 used in legacy handling code
* alpha = lowalpha | upalpha
*/
#define IS_ALPHA(x) (IS_LOWALPHA(x) || IS_UPALPHA(x))
/*
* lowalpha = "a" | "b" | "c" | "d" | "e" | "f" | "g" | "h" | "i" | "j" |
* "k" | "l" | "m" | "n" | "o" | "p" | "q" | "r" | "s" | "t" |
* "u" | "v" | "w" | "x" | "y" | "z"
*/
#define IS_LOWALPHA(x) (((x) >= 'a') && ((x) <= 'z'))
/*
* upalpha = "A" | "B" | "C" | "D" | "E" | "F" | "G" | "H" | "I" | "J" |
* "K" | "L" | "M" | "N" | "O" | "P" | "Q" | "R" | "S" | "T" |
* "U" | "V" | "W" | "X" | "Y" | "Z"
*/
#define IS_UPALPHA(x) (((x) >= 'A') && ((x) <= 'Z'))
#ifdef IS_DIGIT
#undef IS_DIGIT
#endif
/*
* digit = "0" | "1" | "2" | "3" | "4" | "5" | "6" | "7" | "8" | "9"
*/
#define IS_DIGIT(x) (((x) >= '0') && ((x) <= '9'))
/*
* alphanum = alpha | digit
*/
#define IS_ALPHANUM(x) (IS_ALPHA(x) || IS_DIGIT(x))
/*
* mark = "-" | "_" | "." | "!" | "~" | "*" | "'" | "(" | ")"
*/
#define IS_MARK(x) (((x) == '-') || ((x) == '_') || ((x) == '.') || \
((x) == '!') || ((x) == '~') || ((x) == '*') || ((x) == '\'') || \
((x) == '(') || ((x) == ')'))
/*
* unwise = "{" | "}" | "|" | "\" | "^" | "`"
*/
#define IS_UNWISE(p) \
(((*(p) == '{')) || ((*(p) == '}')) || ((*(p) == '|')) || \
((*(p) == '\\')) || ((*(p) == '^')) || ((*(p) == '[')) || \
((*(p) == ']')) || ((*(p) == '`')))
/*
* reserved = ";" | "/" | "?" | ":" | "@" | "&" | "=" | "+" | "$" | "," |
* "[" | "]"
*/
#define IS_RESERVED(x) (((x) == ';') || ((x) == '/') || ((x) == '?') || \
((x) == ':') || ((x) == '@') || ((x) == '&') || ((x) == '=') || \
((x) == '+') || ((x) == '$') || ((x) == ',') || ((x) == '[') || \
((x) == ']'))
/*
* unreserved = alphanum | mark
*/
#define IS_UNRESERVED(x) (IS_ALPHANUM(x) || IS_MARK(x))
/*
* Skip to next pointer char, handle escaped sequences
*/
#define NEXT(p) ((*p == '%')? p += 3 : p++)
/*
* Productions from the spec.
*
* authority = server | reg_name
* reg_name = 1*( unreserved | escaped | "$" | "," |
* ";" | ":" | "@" | "&" | "=" | "+" )
*
* path = [ abs_path | opaque_part ]
*/
#define STRNDUP(s, n) (char *) xmlStrndup((const xmlChar *)(s), (n))
/************************************************************************
* *
* RFC 3986 parser *
* *
************************************************************************/
#define ISA_DIGIT(p) ((*(p) >= '0') && (*(p) <= '9'))
#define ISA_ALPHA(p) (((*(p) >= 'a') && (*(p) <= 'z')) || \
((*(p) >= 'A') && (*(p) <= 'Z')))
#define ISA_HEXDIG(p) \
(ISA_DIGIT(p) || ((*(p) >= 'a') && (*(p) <= 'f')) || \
((*(p) >= 'A') && (*(p) <= 'F')))
/*
* sub-delims = "!" / "$" / "&" / "'" / "(" / ")"
* / "*" / "+" / "," / ";" / "="
*/
#define ISA_SUB_DELIM(p) \
(((*(p) == '!')) || ((*(p) == '$')) || ((*(p) == '&')) || \
((*(p) == '(')) || ((*(p) == ')')) || ((*(p) == '*')) || \
((*(p) == '+')) || ((*(p) == ',')) || ((*(p) == ';')) || \
((*(p) == '=')) || ((*(p) == '\'')))
/*
* gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@"
*/
#define ISA_GEN_DELIM(p) \
(((*(p) == ':')) || ((*(p) == '/')) || ((*(p) == '?')) || \
((*(p) == '#')) || ((*(p) == '[')) || ((*(p) == ']')) || \
((*(p) == '@')))
/*
* reserved = gen-delims / sub-delims
*/
#define ISA_RESERVED(p) (ISA_GEN_DELIM(p) || (ISA_SUB_DELIM(p)))
/*
* unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
*/
#define ISA_STRICTLY_UNRESERVED(p) \
((ISA_ALPHA(p)) || (ISA_DIGIT(p)) || ((*(p) == '-')) || \
((*(p) == '.')) || ((*(p) == '_')) || ((*(p) == '~')))
/*
* pct-encoded = "%" HEXDIG HEXDIG
*/
#define ISA_PCT_ENCODED(p) \
((*(p) == '%') && (ISA_HEXDIG(p + 1)) && (ISA_HEXDIG(p + 2)))
/*
* pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
*/
#define ISA_PCHAR(u, p) \
(ISA_UNRESERVED(u, p) || ISA_PCT_ENCODED(p) || ISA_SUB_DELIM(p) || \
((*(p) == ':')) || ((*(p) == '@')))
/*
* From https://www.w3.org/TR/leiri/
*
* " " / "<" / ">" / '"' / "{" / "}" / "|"
* / "\" / "^" / "`" / %x0-1F / %x7F-D7FF
* / %xE000-FFFD / %x10000-10FFFF
*/
#define ISA_UCSCHAR(p) \
((*(p) <= 0x20) || (*(p) >= 0x7F) || (*(p) == '<') || (*(p) == '>') || \
(*(p) == '"') || (*(p) == '{') || (*(p) == '}') || (*(p) == '|') || \
(*(p) == '\\') || (*(p) == '^') || (*(p) == '`'))
#define ISA_UNRESERVED(u, p) (xmlIsUnreserved(u, p))
#define XML_URI_ALLOW_UNWISE 1
#define XML_URI_NO_UNESCAPE 2
#define XML_URI_ALLOW_UCSCHAR 4
static int
xmlIsUnreserved(xmlURIPtr uri, const char *cur) {
if (uri == NULL)
return(0);
if (ISA_STRICTLY_UNRESERVED(cur))
return(1);
if (uri->cleanup & XML_URI_ALLOW_UNWISE) {
if (IS_UNWISE(cur))
return(1);
} else if (uri->cleanup & XML_URI_ALLOW_UCSCHAR) {
if (ISA_UCSCHAR(cur))
return(1);
}
return(0);
}
/**
* xmlParse3986Scheme:
* @uri: pointer to an URI structure
* @str: pointer to the string to analyze
*
* Parse an URI scheme
*
* ALPHA *( ALPHA / DIGIT / "+" / "-" / "." )
*
* Returns 0 or the error code
*/
static int
xmlParse3986Scheme(xmlURIPtr uri, const char **str) {
const char *cur;
cur = *str;
if (!ISA_ALPHA(cur))
return(1);
cur++;
while (ISA_ALPHA(cur) || ISA_DIGIT(cur) ||
(*cur == '+') || (*cur == '-') || (*cur == '.')) cur++;
if (uri != NULL) {
if (uri->scheme != NULL) xmlFree(uri->scheme);
uri->scheme = STRNDUP(*str, cur - *str);
if (uri->scheme == NULL)
return(-1);
}
*str = cur;
return(0);
}
/**
* xmlParse3986Fragment:
* @uri: pointer to an URI structure
* @str: pointer to the string to analyze
*
* Parse the query part of an URI
*
* fragment = *( pchar / "/" / "?" )
* NOTE: the strict syntax as defined by 3986 does not allow '[' and ']'
* in the fragment identifier but this is used very broadly for
* xpointer scheme selection, so we are allowing it here to not break
* for example all the DocBook processing chains.
*
* Returns 0 or the error code
*/
static int
xmlParse3986Fragment(xmlURIPtr uri, const char **str)
{
const char *cur;
cur = *str;
while ((ISA_PCHAR(uri, cur)) || (*cur == '/') || (*cur == '?') ||
(*cur == '[') || (*cur == ']'))
NEXT(cur);
if (uri != NULL) {
if (uri->fragment != NULL)
xmlFree(uri->fragment);
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->fragment = STRNDUP(*str, cur - *str);
else
uri->fragment = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->fragment == NULL)
return (-1);
}
*str = cur;
return (0);
}
/**
* xmlParse3986Query:
* @uri: pointer to an URI structure
* @str: pointer to the string to analyze
*
* Parse the query part of an URI
*
* query = *uric
*
* Returns 0 or the error code
*/
static int
xmlParse3986Query(xmlURIPtr uri, const char **str)
{
const char *cur;
cur = *str;
while ((ISA_PCHAR(uri, cur)) || (*cur == '/') || (*cur == '?'))
NEXT(cur);
if (uri != NULL) {
if (uri->query != NULL)
xmlFree(uri->query);
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->query = STRNDUP(*str, cur - *str);
else
uri->query = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->query == NULL)
return (-1);
/* Save the raw bytes of the query as well.
* See: http://mail.gnome.org/archives/xml/2007-April/thread.html#00114
*/
if (uri->query_raw != NULL)
xmlFree (uri->query_raw);
uri->query_raw = STRNDUP (*str, cur - *str);
if (uri->query_raw == NULL)
return (-1);
}
*str = cur;
return (0);
}
/**
* xmlParse3986Port:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse a port part and fills in the appropriate fields
* of the @uri structure
*
* port = *DIGIT
*
* Returns 0 or the error code
*/
static int
xmlParse3986Port(xmlURIPtr uri, const char **str)
{
const char *cur = *str;
int port = 0;
if (ISA_DIGIT(cur)) {
while (ISA_DIGIT(cur)) {
int digit = *cur - '0';
if (port > INT_MAX / 10)
return(1);
port *= 10;
if (port > INT_MAX - digit)
return(1);
port += digit;
cur++;
}
if (uri != NULL)
uri->port = port;
*str = cur;
return(0);
}
return(1);
}
/**
* xmlParse3986Userinfo:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an user information part and fills in the appropriate fields
* of the @uri structure
*
* userinfo = *( unreserved / pct-encoded / sub-delims / ":" )
*
* Returns 0 or the error code
*/
static int
xmlParse3986Userinfo(xmlURIPtr uri, const char **str)
{
const char *cur;
cur = *str;
while (ISA_UNRESERVED(uri, cur) || ISA_PCT_ENCODED(cur) ||
ISA_SUB_DELIM(cur) || (*cur == ':'))
NEXT(cur);
if (*cur == '@') {
if (uri != NULL) {
if (uri->user != NULL) xmlFree(uri->user);
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->user = STRNDUP(*str, cur - *str);
else
uri->user = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->user == NULL)
return(-1);
}
*str = cur;
return(0);
}
return(1);
}
/**
* xmlParse3986DecOctet:
* @str: the string to analyze
*
* dec-octet = DIGIT ; 0-9
* / %x31-39 DIGIT ; 10-99
* / "1" 2DIGIT ; 100-199
* / "2" %x30-34 DIGIT ; 200-249
* / "25" %x30-35 ; 250-255
*
* Skip a dec-octet.
*
* Returns 0 if found and skipped, 1 otherwise
*/
static int
xmlParse3986DecOctet(const char **str) {
const char *cur = *str;
if (!(ISA_DIGIT(cur)))
return(1);
if (!ISA_DIGIT(cur+1))
cur++;
else if ((*cur != '0') && (ISA_DIGIT(cur + 1)) && (!ISA_DIGIT(cur+2)))
cur += 2;
else if ((*cur == '1') && (ISA_DIGIT(cur + 1)) && (ISA_DIGIT(cur + 2)))
cur += 3;
else if ((*cur == '2') && (*(cur + 1) >= '0') &&
(*(cur + 1) <= '4') && (ISA_DIGIT(cur + 2)))
cur += 3;
else if ((*cur == '2') && (*(cur + 1) == '5') &&
(*(cur + 2) >= '0') && (*(cur + 1) <= '5'))
cur += 3;
else
return(1);
*str = cur;
return(0);
}
/**
* xmlParse3986Host:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an host part and fills in the appropriate fields
* of the @uri structure
*
* host = IP-literal / IPv4address / reg-name
* IP-literal = "[" ( IPv6address / IPvFuture ) "]"
* IPv4address = dec-octet "." dec-octet "." dec-octet "." dec-octet
* reg-name = *( unreserved / pct-encoded / sub-delims )
*
* Returns 0 or the error code
*/
static int
xmlParse3986Host(xmlURIPtr uri, const char **str)
{
const char *cur = *str;
const char *host;
host = cur;
/*
* IPv6 and future addressing scheme are enclosed between brackets
*/
if (*cur == '[') {
cur++;
while ((*cur != ']') && (*cur != 0))
cur++;
if (*cur != ']')
return(1);
cur++;
goto found;
}
/*
* try to parse an IPv4
*/
if (ISA_DIGIT(cur)) {
if (xmlParse3986DecOctet(&cur) != 0)
goto not_ipv4;
if (*cur != '.')
goto not_ipv4;
cur++;
if (xmlParse3986DecOctet(&cur) != 0)
goto not_ipv4;
if (*cur != '.')
goto not_ipv4;
if (xmlParse3986DecOctet(&cur) != 0)
goto not_ipv4;
if (*cur != '.')
goto not_ipv4;
if (xmlParse3986DecOctet(&cur) != 0)
goto not_ipv4;
goto found;
not_ipv4:
cur = *str;
}
/*
* then this should be a hostname which can be empty
*/
while (ISA_UNRESERVED(uri, cur) ||
ISA_PCT_ENCODED(cur) || ISA_SUB_DELIM(cur))
NEXT(cur);
found:
if (uri != NULL) {
if (uri->authority != NULL) xmlFree(uri->authority);
uri->authority = NULL;
if (uri->server != NULL) xmlFree(uri->server);
if (cur != host) {
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->server = STRNDUP(host, cur - host);
else
uri->server = xmlURIUnescapeString(host, cur - host, NULL);
if (uri->server == NULL)
return(-1);
} else
uri->server = NULL;
}
*str = cur;
return(0);
}
/**
* xmlParse3986Authority:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an authority part and fills in the appropriate fields
* of the @uri structure
*
* authority = [ userinfo "@" ] host [ ":" port ]
*
* Returns 0 or the error code
*/
static int
xmlParse3986Authority(xmlURIPtr uri, const char **str)
{
const char *cur;
int ret;
cur = *str;
/*
* try to parse an userinfo and check for the trailing @
*/
ret = xmlParse3986Userinfo(uri, &cur);
if (ret < 0)
return(ret);
if ((ret != 0) || (*cur != '@'))
cur = *str;
else
cur++;
ret = xmlParse3986Host(uri, &cur);
if (ret != 0) return(ret);
if (*cur == ':') {
cur++;
ret = xmlParse3986Port(uri, &cur);
if (ret != 0) return(ret);
}
*str = cur;
return(0);
}
/**
* xmlParse3986Segment:
* @str: the string to analyze
* @forbid: an optional forbidden character
* @empty: allow an empty segment
*
* Parse a segment and fills in the appropriate fields
* of the @uri structure
*
* segment = *pchar
* segment-nz = 1*pchar
* segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
* ; non-zero-length segment without any colon ":"
*
* Returns 0 or the error code
*/
static int
xmlParse3986Segment(xmlURIPtr uri, const char **str, char forbid, int empty)
{
const char *cur;
cur = *str;
if (!ISA_PCHAR(uri, cur)) {
if (empty)
return(0);
return(1);
}
while (ISA_PCHAR(uri, cur) && (*cur != forbid))
NEXT(cur);
*str = cur;
return (0);
}
/**
* xmlParse3986PathAbEmpty:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an path absolute or empty and fills in the appropriate fields
* of the @uri structure
*
* path-abempty = *( "/" segment )
*
* Returns 0 or the error code
*/
static int
xmlParse3986PathAbEmpty(xmlURIPtr uri, const char **str)
{
const char *cur;
int ret;
cur = *str;
while (*cur == '/') {
cur++;
ret = xmlParse3986Segment(uri, &cur, 0, 1);
if (ret != 0) return(ret);
}
if (uri != NULL) {
if (uri->path != NULL) xmlFree(uri->path);
if (*str != cur) {
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->path = STRNDUP(*str, cur - *str);
else
uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->path == NULL)
return (-1);
} else {
uri->path = NULL;
}
}
*str = cur;
return (0);
}
/**
* xmlParse3986PathAbsolute:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an path absolute and fills in the appropriate fields
* of the @uri structure
*
* path-absolute = "/" [ segment-nz *( "/" segment ) ]
*
* Returns 0 or the error code
*/
static int
xmlParse3986PathAbsolute(xmlURIPtr uri, const char **str)
{
const char *cur;
int ret;
cur = *str;
if (*cur != '/')
return(1);
cur++;
ret = xmlParse3986Segment(uri, &cur, 0, 0);
if (ret == 0) {
while (*cur == '/') {
cur++;
ret = xmlParse3986Segment(uri, &cur, 0, 1);
if (ret != 0) return(ret);
}
}
if (uri != NULL) {
if (uri->path != NULL) xmlFree(uri->path);
if (cur != *str) {
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->path = STRNDUP(*str, cur - *str);
else
uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->path == NULL)
return (-1);
} else {
uri->path = NULL;
}
}
*str = cur;
return (0);
}
/**
* xmlParse3986PathRootless:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an path without root and fills in the appropriate fields
* of the @uri structure
*
* path-rootless = segment-nz *( "/" segment )
*
* Returns 0 or the error code
*/
static int
xmlParse3986PathRootless(xmlURIPtr uri, const char **str)
{
const char *cur;
int ret;
cur = *str;
ret = xmlParse3986Segment(uri, &cur, 0, 0);
if (ret != 0) return(ret);
while (*cur == '/') {
cur++;
ret = xmlParse3986Segment(uri, &cur, 0, 1);
if (ret != 0) return(ret);
}
if (uri != NULL) {
if (uri->path != NULL) xmlFree(uri->path);
if (cur != *str) {
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->path = STRNDUP(*str, cur - *str);
else
uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->path == NULL)
return (-1);
} else {
uri->path = NULL;
}
}
*str = cur;
return (0);
}
/**
* xmlParse3986PathNoScheme:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an path which is not a scheme and fills in the appropriate fields
* of the @uri structure
*
* path-noscheme = segment-nz-nc *( "/" segment )
*
* Returns 0 or the error code
*/
static int
xmlParse3986PathNoScheme(xmlURIPtr uri, const char **str)
{
const char *cur;
int ret;
cur = *str;
ret = xmlParse3986Segment(uri, &cur, ':', 0);
if (ret != 0) return(ret);
while (*cur == '/') {
cur++;
ret = xmlParse3986Segment(uri, &cur, 0, 1);
if (ret != 0) return(ret);
}
if (uri != NULL) {
if (uri->path != NULL) xmlFree(uri->path);
if (cur != *str) {
if (uri->cleanup & XML_URI_NO_UNESCAPE)
uri->path = STRNDUP(*str, cur - *str);
else
uri->path = xmlURIUnescapeString(*str, cur - *str, NULL);
if (uri->path == NULL)
return (-1);
} else {
uri->path = NULL;
}
}
*str = cur;
return (0);
}
/**
* xmlParse3986HierPart:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an hierarchical part and fills in the appropriate fields
* of the @uri structure
*
* hier-part = "//" authority path-abempty
* / path-absolute
* / path-rootless
* / path-empty
*
* Returns 0 or the error code
*/
static int
xmlParse3986HierPart(xmlURIPtr uri, const char **str)
{
const char *cur;
int ret;
cur = *str;
if ((*cur == '/') && (*(cur + 1) == '/')) {
cur += 2;
ret = xmlParse3986Authority(uri, &cur);
if (ret != 0) return(ret);
/*
* An empty server is marked with a special URI value.
*/
if ((uri->server == NULL) && (uri->port == PORT_EMPTY))
uri->port = PORT_EMPTY_SERVER;
ret = xmlParse3986PathAbEmpty(uri, &cur);
if (ret != 0) return(ret);
*str = cur;
return(0);
} else if (*cur == '/') {
ret = xmlParse3986PathAbsolute(uri, &cur);
if (ret != 0) return(ret);
} else if (ISA_PCHAR(uri, cur)) {
ret = xmlParse3986PathRootless(uri, &cur);
if (ret != 0) return(ret);
} else {
/* path-empty is effectively empty */
if (uri != NULL) {
if (uri->path != NULL) xmlFree(uri->path);
uri->path = NULL;
}
}
*str = cur;
return (0);
}
/**
* xmlParse3986RelativeRef:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an URI string and fills in the appropriate fields
* of the @uri structure
*
* relative-ref = relative-part [ "?" query ] [ "#" fragment ]
* relative-part = "//" authority path-abempty
* / path-absolute
* / path-noscheme
* / path-empty
*
* Returns 0 or the error code
*/
static int
xmlParse3986RelativeRef(xmlURIPtr uri, const char *str) {
int ret;
if ((*str == '/') && (*(str + 1) == '/')) {
str += 2;
ret = xmlParse3986Authority(uri, &str);
if (ret != 0) return(ret);
ret = xmlParse3986PathAbEmpty(uri, &str);
if (ret != 0) return(ret);
} else if (*str == '/') {
ret = xmlParse3986PathAbsolute(uri, &str);
if (ret != 0) return(ret);
} else if (ISA_PCHAR(uri, str)) {
ret = xmlParse3986PathNoScheme(uri, &str);
if (ret != 0) return(ret);
} else {
/* path-empty is effectively empty */
if (uri != NULL) {
if (uri->path != NULL) xmlFree(uri->path);
uri->path = NULL;
}
}
if (*str == '?') {
str++;
ret = xmlParse3986Query(uri, &str);
if (ret != 0) return(ret);
}
if (*str == '#') {
str++;
ret = xmlParse3986Fragment(uri, &str);
if (ret != 0) return(ret);
}
if (*str != 0) {
xmlCleanURI(uri);
return(1);
}
return(0);
}
/**
* xmlParse3986URI:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an URI string and fills in the appropriate fields
* of the @uri structure
*
* scheme ":" hier-part [ "?" query ] [ "#" fragment ]
*
* Returns 0 or the error code
*/
static int
xmlParse3986URI(xmlURIPtr uri, const char *str) {
int ret;
ret = xmlParse3986Scheme(uri, &str);
if (ret != 0) return(ret);
if (*str != ':') {
return(1);
}
str++;
ret = xmlParse3986HierPart(uri, &str);
if (ret != 0) return(ret);
if (*str == '?') {
str++;
ret = xmlParse3986Query(uri, &str);
if (ret != 0) return(ret);
}
if (*str == '#') {
str++;
ret = xmlParse3986Fragment(uri, &str);
if (ret != 0) return(ret);
}
if (*str != 0) {
xmlCleanURI(uri);
return(1);
}
return(0);
}
/**
* xmlParse3986URIReference:
* @uri: pointer to an URI structure
* @str: the string to analyze
*
* Parse an URI reference string and fills in the appropriate fields
* of the @uri structure
*
* URI-reference = URI / relative-ref
*
* Returns 0 or the error code
*/
static int
xmlParse3986URIReference(xmlURIPtr uri, const char *str) {
int ret;
if (str == NULL)
return(-1);
xmlCleanURI(uri);
/*
* Try first to parse absolute refs, then fallback to relative if
* it fails.
*/
ret = xmlParse3986URI(uri, str);
if (ret < 0)
return(ret);
if (ret != 0) {
xmlCleanURI(uri);
ret = xmlParse3986RelativeRef(uri, str);
if (ret != 0) {
xmlCleanURI(uri);
return(ret);
}
}
return(0);
}
/**
* xmlParseURISafe:
* @str: the URI string to analyze
* @uriOut: optional pointer to parsed URI
*
* Parse an URI based on RFC 3986
*
* URI-reference = [ absoluteURI | relativeURI ] [ "#" fragment ]
*
* Available since 2.13.0.
*
* Returns 0 on success, an error code (typically 1) if the URI is invalid
* or -1 if a memory allocation failed.
*/
int
xmlParseURISafe(const char *str, xmlURIPtr *uriOut) {
xmlURIPtr uri;
int ret;
if (uriOut == NULL)
return(1);
*uriOut = NULL;
if (str == NULL)
return(1);
uri = xmlCreateURI();
if (uri == NULL)
return(-1);
ret = xmlParse3986URIReference(uri, str);
if (ret) {
xmlFreeURI(uri);
return(ret);
}
*uriOut = uri;
return(0);