/
HttpURI.java
1096 lines (1015 loc) · 35.6 KB
/
HttpURI.java
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
//
// ========================================================================
// Copyright (c) 1995-2021 Mort Bay Consulting Pty Ltd and others.
// ------------------------------------------------------------------------
// All rights reserved. This program and the accompanying materials
// are made available under the terms of the Eclipse Public License v1.0
// and Apache License v2.0 which accompanies this distribution.
//
// The Eclipse Public License is available at
// http://www.eclipse.org/legal/epl-v10.html
//
// The Apache License v2.0 is available at
// http://www.opensource.org/licenses/apache2.0.php
//
// You may elect to redistribute this code under either of these licenses.
// ========================================================================
//
package org.eclipse.jetty.http;
import java.io.UnsupportedEncodingException;
import java.net.URI;
import java.net.URISyntaxException;
import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.util.EnumSet;
import java.util.Objects;
import org.eclipse.jetty.util.ArrayTrie;
import org.eclipse.jetty.util.MultiMap;
import org.eclipse.jetty.util.Trie;
import org.eclipse.jetty.util.TypeUtil;
import org.eclipse.jetty.util.URIUtil;
import org.eclipse.jetty.util.UrlEncoded;
/**
* Http URI.
* Parse an HTTP URI from a string or byte array. Given a URI
* {@code http://user@host:port/path;param1/%2e/info;param2?query#fragment}
* this class will split it into the following optional elements:<ul>
* <li>{@link #getScheme()} - http:</li>
* <li>{@link #getAuthority()} - //name@host:port</li>
* <li>{@link #getHost()} - host</li>
* <li>{@link #getPort()} - port</li>
* <li>{@link #getPath()} - /path;param1/%2e/info;param2</li>
* <li>{@link #getDecodedPath()} - /path/info</li>
* <li>{@link #getParam()} - param2</li>
* <li>{@link #getQuery()} - query</li>
* <li>{@link #getFragment()} - fragment</li>
* </ul>
*
* <p>The path part of the URI is provided in both raw form ({@link #getPath()}) and
* decoded form ({@link #getDecodedPath}), which has: path parameters removed,
* percent encoded characters expanded and relative segments resolved. This approach
* is somewhat contrary to <a href="https://tools.ietf.org/html/rfc3986#section-3.3">RFC3986</a>
* which no longer defines path parameters (removed after
* <a href="https://tools.ietf.org/html/rfc2396#section-3.3">RFC2396</a>) and specifies
* that relative segment normalization should take place before percent encoded character
* expansion. A literal interpretation of the RFC can result in URI paths with ambiguities
* when viewed as strings. For example, a URI of {@code /foo%2f..%2fbar} is technically a single
* segment of "/foo/../bar", but could easily be misinterpreted as 3 segments resolving to "/bar"
* by a file system.
* </p>
* <p>
* Thus this class avoid and/or detects such ambiguities. Furthermore, by decoding characters and
* removing parameters before relative path normalization, ambiguous paths will be resolved in such
* a way to be non-standard-but-non-ambiguous to down stream interpretation of the decoded path string.
* The violations are recorded and available by API such as {@link #hasAmbiguousSegment()} so that requests
* containing them may be rejected in case the non-standard-but-non-ambiguous interpretations
* are not satisfactory for a given compliance configuration.
* </p>
* <p>
* Implementations that wish to process ambiguous URI paths must configure the compliance modes
* to accept them and then perform their own decoding of {@link #getPath()}.
* </p>
* <p>
* If there are multiple path parameters, only the last one is returned by {@link #getParam()}.
* </p>
**/
public class HttpURI
{
private enum State
{
START,
HOST_OR_PATH,
SCHEME_OR_PATH,
HOST,
IPV6,
PORT,
PATH,
PARAM,
QUERY,
FRAGMENT,
ASTERISK
}
/**
* Violations of safe URI interpretations
*/
enum Violation
{
/**
* Ambiguous path segments e.g. {@code /foo/%2E%2E/bar}
*/
SEGMENT("Ambiguous path segments"),
/**
* Ambiguous path separator within a URI segment e.g. {@code /foo%2Fbar}
*/
SEPARATOR("Ambiguous path separator"),
/**
* Ambiguous path parameters within a URI segment e.g. {@code /foo/..;/bar}
*/
PARAM("Ambiguous path parameters"),
/**
* Ambiguous double encoding within a URI segment e.g. {@code /%2557EB-INF}
*/
ENCODING("Ambiguous double encoding"),
/**
* Ambiguous empty segments e.g. {@code /foo//bar}
*/
EMPTY("Ambiguous empty segments"),
/**
* Non standard UTF-16 encoding eg {@code /foo%u2192bar}.
*/
UTF16("Non standard UTF-16 encoding");
private final String _message;
Violation(String message)
{
_message = message;
}
String getMessage()
{
return _message;
}
}
private static final Trie<Boolean> __ambiguousSegments = new ArrayTrie<>();
static
{
__ambiguousSegments.put(".", Boolean.FALSE);
__ambiguousSegments.put("%2e", Boolean.TRUE);
__ambiguousSegments.put("%u002e", Boolean.TRUE);
__ambiguousSegments.put("..", Boolean.FALSE);
__ambiguousSegments.put(".%2e", Boolean.TRUE);
__ambiguousSegments.put(".%u002e", Boolean.TRUE);
__ambiguousSegments.put("%2e.", Boolean.TRUE);
__ambiguousSegments.put("%2e%2e", Boolean.TRUE);
__ambiguousSegments.put("%2e%u002e", Boolean.TRUE);
__ambiguousSegments.put("%u002e.", Boolean.TRUE);
__ambiguousSegments.put("%u002e%2e", Boolean.TRUE);
__ambiguousSegments.put("%u002e%u002e", Boolean.TRUE);
}
private String _scheme;
private String _user;
private String _host;
private int _port;
private String _path;
private String _param;
private String _query;
private String _fragment;
private String _uri;
private String _decodedPath;
private final EnumSet<Violation> _violations = EnumSet.noneOf(Violation.class);
private boolean _emptySegment;
/**
* Construct a normalized URI.
* Port is not set if it is the default port.
*
* @param scheme the URI scheme
* @param host the URI hose
* @param port the URI port
* @param path the URI path
* @param param the URI param
* @param query the URI query
* @param fragment the URI fragment
* @return the normalized URI
*/
public static HttpURI createHttpURI(String scheme, String host, int port, String path, String param, String query, String fragment)
{
if (port == 80 && HttpScheme.HTTP.is(scheme))
port = 0;
if (port == 443 && HttpScheme.HTTPS.is(scheme))
port = 0;
return new HttpURI(scheme, host, port, path, param, query, fragment);
}
public HttpURI()
{
}
public HttpURI(String scheme, String host, int port, String path, String param, String query, String fragment)
{
_scheme = scheme;
_host = host;
_port = port;
if (path != null)
parse(State.PATH, path, 0, path.length());
if (param != null)
_param = param;
if (query != null)
_query = query;
if (fragment != null)
_fragment = fragment;
}
public HttpURI(HttpURI uri)
{
_scheme = uri._scheme;
_user = uri._user;
_host = uri._host;
_port = uri._port;
_path = uri._path;
_param = uri._param;
_query = uri._query;
_fragment = uri._fragment;
_uri = uri._uri;
_decodedPath = uri._decodedPath;
_violations.addAll(uri._violations);
_emptySegment = false;
}
public HttpURI(HttpURI schemeHostPort, HttpURI uri)
{
_scheme = schemeHostPort._scheme;
_user = schemeHostPort._user;
_host = schemeHostPort._host;
_port = schemeHostPort._port;
_path = uri._path;
_param = uri._param;
_query = uri._query;
_fragment = uri._fragment;
_uri = uri._uri;
_decodedPath = uri._decodedPath;
_violations.addAll(uri._violations);
_emptySegment = false;
}
public HttpURI(String uri)
{
_port = -1;
parse(State.START, uri, 0, uri.length());
}
public HttpURI(URI uri)
{
_uri = null;
_scheme = uri.getScheme();
_host = uri.getHost();
if (_host == null && uri.getRawSchemeSpecificPart().startsWith("//"))
_host = "";
_port = uri.getPort();
_user = uri.getUserInfo();
String path = uri.getRawPath();
if (path != null)
parse(State.PATH, path, 0, path.length());
_query = uri.getRawQuery();
_fragment = uri.getFragment();
}
public HttpURI(String scheme, String host, int port, String pathQuery)
{
_uri = null;
_scheme = scheme;
_host = host;
_port = port;
if (pathQuery != null)
parse(State.PATH, pathQuery, 0, pathQuery.length());
}
public void clear()
{
_uri = null;
_scheme = null;
_user = null;
_host = null;
_port = -1;
_path = null;
_param = null;
_query = null;
_fragment = null;
_decodedPath = null;
_emptySegment = false;
_violations.clear();
}
public void parse(String uri)
{
clear();
_uri = uri;
parse(State.START, uri, 0, uri.length());
}
/**
* Parse according to https://tools.ietf.org/html/rfc7230#section-5.3
*
* @param method the request method
* @param uri the request uri
*/
public void parseRequestTarget(String method, String uri)
{
clear();
_uri = uri;
if (HttpMethod.CONNECT.is(method))
_path = uri;
else
parse(uri.startsWith("/") ? State.PATH : State.START, uri, 0, uri.length());
}
@Deprecated
public void parseConnect(String uri)
{
clear();
_uri = uri;
_path = uri;
}
public void parse(String uri, int offset, int length)
{
clear();
int end = offset + length;
_uri = uri.substring(offset, end);
parse(State.START, uri, offset, end);
}
private void parse(State state, final String uri, final int offset, final int end)
{
int mark = offset; // the start of the current section being parsed
int pathMark = 0; // the start of the path section
int segment = 0; // the start of the current segment within the path
boolean encodedPath = false; // set to true if the path contains % encoded characters
boolean encodedUtf16 = false; // Is the current encoding for UTF16?
int encodedCharacters = 0; // partial state of parsing a % encoded character<x>
int encodedValue = 0; // the partial encoded value
boolean dot = false; // set to true if the path contains . or .. segments
for (int i = offset; i < end; i++)
{
char c = uri.charAt(i);
switch (state)
{
case START:
{
switch (c)
{
case '/':
mark = i;
state = State.HOST_OR_PATH;
break;
case ';':
checkSegment(uri, segment, i, true);
mark = i + 1;
state = State.PARAM;
break;
case '?':
// assume empty path (if seen at start)
checkSegment(uri, segment, i, false);
_path = "";
mark = i + 1;
state = State.QUERY;
break;
case '#':
// assume empty path (if seen at start)
checkSegment(uri, segment, i, false);
_path = "";
mark = i + 1;
state = State.FRAGMENT;
break;
case '*':
_path = "*";
state = State.ASTERISK;
break;
case '%':
encodedPath = true;
encodedCharacters = 2;
encodedValue = 0;
mark = pathMark = segment = i;
state = State.PATH;
break;
case '.':
dot = true;
pathMark = segment = i;
state = State.PATH;
break;
default:
mark = i;
if (_scheme == null)
state = State.SCHEME_OR_PATH;
else
{
pathMark = segment = i;
state = State.PATH;
}
break;
}
continue;
}
case SCHEME_OR_PATH:
{
switch (c)
{
case ':':
// must have been a scheme
_scheme = uri.substring(mark, i);
// Start again with scheme set
state = State.START;
break;
case '/':
// must have been in a path and still are
segment = i + 1;
state = State.PATH;
break;
case ';':
// must have been in a path
mark = i + 1;
state = State.PARAM;
break;
case '?':
// must have been in a path
_path = uri.substring(mark, i);
mark = i + 1;
state = State.QUERY;
break;
case '%':
// must have been in an encoded path
encodedPath = true;
encodedCharacters = 2;
encodedValue = 0;
state = State.PATH;
break;
case '#':
// must have been in a path
_path = uri.substring(mark, i);
state = State.FRAGMENT;
break;
default:
break;
}
continue;
}
case HOST_OR_PATH:
{
switch (c)
{
case '/':
_host = "";
mark = i + 1;
state = State.HOST;
break;
case '%':
case '@':
case ';':
case '?':
case '#':
case '.':
// was a path, look again
i--;
pathMark = mark;
segment = mark + 1;
state = State.PATH;
break;
default:
// it is a path
pathMark = mark;
segment = mark + 1;
state = State.PATH;
}
continue;
}
case HOST:
{
switch (c)
{
case '/':
_host = uri.substring(mark, i);
pathMark = mark = i;
segment = mark + 1;
state = State.PATH;
break;
case ':':
if (i > mark)
_host = uri.substring(mark, i);
mark = i + 1;
state = State.PORT;
break;
case '@':
if (_user != null)
throw new IllegalArgumentException("Bad authority");
_user = uri.substring(mark, i);
mark = i + 1;
break;
case '[':
state = State.IPV6;
break;
default:
break;
}
break;
}
case IPV6:
{
switch (c)
{
case '/':
throw new IllegalArgumentException("No closing ']' for ipv6 in " + uri);
case ']':
c = uri.charAt(++i);
_host = uri.substring(mark, i);
if (c == ':')
{
mark = i + 1;
state = State.PORT;
}
else
{
pathMark = mark = i;
state = State.PATH;
}
break;
default:
break;
}
break;
}
case PORT:
{
if (c == '@')
{
if (_user != null)
throw new IllegalArgumentException("Bad authority");
// It wasn't a port, but a password!
_user = _host + ":" + uri.substring(mark, i);
mark = i + 1;
state = State.HOST;
}
else if (c == '/')
{
_port = TypeUtil.parseInt(uri, mark, i - mark, 10);
pathMark = mark = i;
segment = i + 1;
state = State.PATH;
}
break;
}
case PATH:
{
if (encodedCharacters > 0)
{
if (encodedCharacters == 2 && c == 'u' && !encodedUtf16)
{
_violations.add(Violation.UTF16);
encodedUtf16 = true;
encodedCharacters = 4;
continue;
}
encodedValue = (encodedValue << 4) + TypeUtil.convertHexDigit(c);
if (--encodedCharacters == 0)
{
switch (encodedValue)
{
case 0:
// Byte 0 cannot be present in a UTF-8 sequence in any position
// other than as the NUL ASCII byte which we do not wish to allow.
throw new IllegalArgumentException("Illegal character in path");
case '/':
_violations.add(Violation.SEPARATOR);
break;
case '%':
_violations.add(Violation.ENCODING);
break;
default:
break;
}
}
}
else
{
switch (c)
{
case ';':
checkSegment(uri, segment, i, true);
mark = i + 1;
state = State.PARAM;
break;
case '?':
checkSegment(uri, segment, i, false);
_path = uri.substring(pathMark, i);
mark = i + 1;
state = State.QUERY;
break;
case '#':
checkSegment(uri, segment, i, false);
_path = uri.substring(pathMark, i);
mark = i + 1;
state = State.FRAGMENT;
break;
case '/':
// There is no leading segment when parsing only a path that starts with slash.
if (i != 0)
checkSegment(uri, segment, i, false);
segment = i + 1;
break;
case '.':
dot |= segment == i;
break;
case '%':
encodedPath = true;
encodedUtf16 = false;
encodedCharacters = 2;
encodedValue = 0;
break;
default:
break;
}
}
break;
}
case PARAM:
{
switch (c)
{
case '?':
_path = uri.substring(pathMark, i);
_param = uri.substring(mark, i);
mark = i + 1;
state = State.QUERY;
break;
case '#':
_path = uri.substring(pathMark, i);
_param = uri.substring(mark, i);
mark = i + 1;
state = State.FRAGMENT;
break;
case '/':
encodedPath = true;
segment = i + 1;
state = State.PATH;
break;
case ';':
// multiple parameters
mark = i + 1;
break;
default:
break;
}
break;
}
case QUERY:
{
if (c == '#')
{
_query = uri.substring(mark, i);
mark = i + 1;
state = State.FRAGMENT;
}
break;
}
case ASTERISK:
{
throw new IllegalArgumentException("Bad character '*'");
}
case FRAGMENT:
{
_fragment = uri.substring(mark, end);
i = end;
break;
}
default:
{
throw new IllegalStateException(state.toString());
}
}
}
switch (state)
{
case START:
_path = "";
checkSegment(uri, segment, end, false);
break;
case ASTERISK:
break;
case SCHEME_OR_PATH:
case HOST_OR_PATH:
_path = uri.substring(mark, end);
break;
case HOST:
if (end > mark)
_host = uri.substring(mark, end);
break;
case IPV6:
throw new IllegalArgumentException("No closing ']' for ipv6 in " + uri);
case PORT:
_port = TypeUtil.parseInt(uri, mark, end - mark, 10);
break;
case PARAM:
_path = uri.substring(pathMark, end);
_param = uri.substring(mark, end);
break;
case PATH:
checkSegment(uri, segment, end, false);
_path = uri.substring(pathMark, end);
break;
case QUERY:
_query = uri.substring(mark, end);
break;
case FRAGMENT:
_fragment = uri.substring(mark, end);
break;
default:
throw new IllegalStateException(state.toString());
}
if (!encodedPath && !dot)
{
if (_param == null)
_decodedPath = _path;
else
_decodedPath = _path.substring(0, _path.length() - _param.length() - 1);
}
else if (_path != null)
{
// The RFC requires this to be canonical before decoding, but this can leave dot segments and dot dot segments
// which are not canonicalized and could be used in an attempt to bypass security checks.
String decodedNonCanonical = URIUtil.decodePath(_path);
_decodedPath = URIUtil.canonicalPath(decodedNonCanonical);
if (_decodedPath == null)
throw new IllegalArgumentException("Bad URI");
}
}
/**
* Check for ambiguous path segments.
*
* An ambiguous path segment is one that is perhaps technically legal, but is considered undesirable to handle
* due to possible ambiguity. Examples include segments like '..;', '%2e', '%2e%2e' etc.
*
* @param uri The URI string
* @param segment The inclusive starting index of the segment (excluding any '/')
* @param end The exclusive end index of the segment
*/
private void checkSegment(String uri, int segment, int end, boolean param)
{
// This method is called once for every segment parsed.
// A URI like "/foo/" has two segments: "foo" and an empty segment.
// Empty segments are only ambiguous if they are not the last segment
// So if this method is called for any segment and we have previously
// seen an empty segment, then it was ambiguous.
if (_emptySegment)
_violations.add(Violation.EMPTY);
if (end == segment)
{
// Empty segments are not ambiguous if followed by a '#', '?' or end of string.
if (end >= uri.length() || ("#?".indexOf(uri.charAt(end)) >= 0))
return;
// If this empty segment is the first segment then it is ambiguous.
if (segment == 0)
{
_violations.add(Violation.EMPTY);
return;
}
// Otherwise remember we have seen an empty segment, which is check if we see a subsequent segment.
if (!_emptySegment)
{
_emptySegment = true;
return;
}
}
// Look for segment in the ambiguous segment index.
Boolean ambiguous = __ambiguousSegments.get(uri, segment, end - segment);
if (ambiguous == Boolean.TRUE)
{
// The segment is always ambiguous.
_violations.add(Violation.SEGMENT);
}
else if (param && ambiguous == Boolean.FALSE)
{
// The segment is ambiguous only when followed by a parameter.
_violations.add(Violation.PARAM);
}
}
/**
* @return True if the URI has a possibly ambiguous segment like '..;' or '%2e%2e'
*/
public boolean hasAmbiguousSegment()
{
return _violations.contains(Violation.SEGMENT);
}
/**
* @return True if the URI empty segment that is ambiguous like '//' or '/;param/'.
*/
public boolean hasAmbiguousEmptySegment()
{
return _violations.contains(Violation.EMPTY);
}
/**
* @return True if the URI has a possibly ambiguous separator of %2f
*/
public boolean hasAmbiguousSeparator()
{
return _violations.contains(Violation.SEPARATOR);
}
/**
* @return True if the URI has a possibly ambiguous path parameter like '..;'
*/
public boolean hasAmbiguousParameter()
{
return _violations.contains(Violation.PARAM);
}
/**
* @return True if the URI has an encoded '%' character.
*/
public boolean hasAmbiguousEncoding()
{
return _violations.contains(Violation.ENCODING);
}
/**
* @return True if the URI has either an {@link #hasAmbiguousSegment()} or {@link #hasAmbiguousEmptySegment()}
* or {@link #hasAmbiguousSeparator()} or {@link #hasAmbiguousParameter()}
*/
public boolean isAmbiguous()
{
return !_violations.isEmpty() && !(_violations.size() == 1 && _violations.contains(Violation.UTF16));
}
/**
* @return True if the URI has any Violations.
*/
public boolean hasViolations()
{
return !_violations.isEmpty();
}
boolean hasViolation(Violation violation)
{
return _violations.contains(violation);
}
/**
* @return True if the URI encodes UTF-16 characters with '%u'.
*/
public boolean hasUtf16Encoding()
{
return _violations.contains(Violation.UTF16);
}
public String getScheme()
{
return _scheme;
}
public String getHost()
{
// Return null for empty host to retain compatibility with java.net.URI
if (_host != null && _host.isEmpty())
return null;
return _host;
}
public int getPort()
{
return _port;
}
/**
* The parsed Path.
*
* @return the path as parsed on valid URI. null for invalid URI.
*/
public String getPath()
{
return _path;
}
/**
* @return The decoded canonical path.
* @see URIUtil#canonicalPath(String)
*/
public String getDecodedPath()
{
return _decodedPath;
}
/**
* Get a URI path parameter. Multiple and in segment parameters are ignored and only
* the last trailing parameter is returned.
* @return The last path parameter or null
*/
public String getParam()
{
return _param;
}
public void setParam(String param)
{
if (!Objects.equals(_param, param))
{
if (_param != null && _path.endsWith(";" + _param))
_path = _path.substring(0, _path.length() - 1 - _param.length());
_param = param;
if (_param != null)
_path = (_path == null ? "" : _path) + ";" + _param;
_uri = null;
}
}
public String getQuery()
{
return _query;
}
public boolean hasQuery()
{
return _query != null && !_query.isEmpty();
}
public String getFragment()
{
return _fragment;
}
public void decodeQueryTo(MultiMap<String> parameters)
{
if (_query == null)
return;
UrlEncoded.decodeUtf8To(_query, parameters);
}
public void decodeQueryTo(MultiMap<String> parameters, String encoding) throws UnsupportedEncodingException
{
decodeQueryTo(parameters, Charset.forName(encoding));
}
public void decodeQueryTo(MultiMap<String> parameters, Charset encoding) throws UnsupportedEncodingException
{
if (_query == null)
return;
if (encoding == null || StandardCharsets.UTF_8.equals(encoding))
UrlEncoded.decodeUtf8To(_query, parameters);
else
UrlEncoded.decodeTo(_query, parameters, encoding);
}
public boolean isAbsolute()
{
return _scheme != null && !_scheme.isEmpty();
}
@Override
public String toString()
{
if (_uri == null)
{
StringBuilder out = new StringBuilder();
if (_scheme != null)
out.append(_scheme).append(':');
if (_host != null)
{
out.append("//");
if (_user != null)
out.append(_user).append('@');
out.append(_host);
}
if (_port > 0)
out.append(':').append(_port);
if (_path != null)
out.append(_path);
if (_query != null)
out.append('?').append(_query);
if (_fragment != null)
out.append('#').append(_fragment);
if (out.length() > 0)