forked from openjdk/jdk
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathURI.java
More file actions
3664 lines (3381 loc) · 138 KB
/
Copy pathURI.java
File metadata and controls
3664 lines (3381 loc) · 138 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright (c) 2000, 2019, Oracle and/or its affiliates. All rights reserved.
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This code is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License version 2 only, as
* published by the Free Software Foundation. Oracle designates this
* particular file as subject to the "Classpath" exception as provided
* by Oracle in the LICENSE file that accompanied this code.
*
* This code is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* version 2 for more details (a copy is included in the LICENSE file that
* accompanied this code).
*
* You should have received a copy of the GNU General Public License version
* 2 along with this work; if not, write to the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
*
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
* or visit www.oracle.com if you need additional information or have any
* questions.
*/
package java.net;
import java.io.File;
import java.io.IOException;
import java.io.InvalidObjectException;
import java.io.ObjectInputStream;
import java.io.ObjectOutputStream;
import java.io.Serializable;
import java.nio.ByteBuffer;
import java.nio.CharBuffer;
import java.nio.charset.CharsetDecoder;
import java.nio.charset.CoderResult;
import java.nio.charset.CodingErrorAction;
import java.nio.charset.CharacterCodingException;
import java.nio.file.Path;
import java.text.Normalizer;
import jdk.internal.access.JavaNetUriAccess;
import jdk.internal.access.SharedSecrets;
import sun.nio.cs.ThreadLocalCoders;
import sun.nio.cs.UTF_8;
import java.lang.Character; // for javadoc
import java.lang.NullPointerException; // for javadoc
/**
* Represents a Uniform Resource Identifier (URI) reference.
*
* <p> Aside from some minor deviations noted below, an instance of this
* class represents a URI reference as defined by
* <a href="http://www.ietf.org/rfc/rfc2396.txt"><i>RFC 2396: Uniform
* Resource Identifiers (URI): Generic Syntax</i></a>, amended by <a
* href="http://www.ietf.org/rfc/rfc2732.txt"><i>RFC 2732: Format for
* Literal IPv6 Addresses in URLs</i></a>. The Literal IPv6 address format
* also supports scope_ids. The syntax and usage of scope_ids is described
* <a href="Inet6Address.html#scoped">here</a>.
* This class provides constructors for creating URI instances from
* their components or by parsing their string forms, methods for accessing the
* various components of an instance, and methods for normalizing, resolving,
* and relativizing URI instances. Instances of this class are immutable.
*
*
* <h2> URI syntax and components </h2>
*
* At the highest level a URI reference (hereinafter simply "URI") in string
* form has the syntax
*
* <blockquote>
* [<i>scheme</i><b>{@code :}</b>]<i>scheme-specific-part</i>[<b>{@code #}</b><i>fragment</i>]
* </blockquote>
*
* where square brackets [...] delineate optional components and the characters
* <b>{@code :}</b> and <b>{@code #}</b> stand for themselves.
*
* <p> An <i>absolute</i> URI specifies a scheme; a URI that is not absolute is
* said to be <i>relative</i>. URIs are also classified according to whether
* they are <i>opaque</i> or <i>hierarchical</i>.
*
* <p> An <i>opaque</i> URI is an absolute URI whose scheme-specific part does
* not begin with a slash character ({@code '/'}). Opaque URIs are not
* subject to further parsing. Some examples of opaque URIs are:
*
* <blockquote><ul style="list-style-type:none">
* <li>{@code mailto:java-net@www.example.com}</li>
* <li>{@code news:comp.lang.java}</li>
* <li>{@code urn:isbn:096139210x}</li>
* </ul></blockquote>
*
* <p> A <i>hierarchical</i> URI is either an absolute URI whose
* scheme-specific part begins with a slash character, or a relative URI, that
* is, a URI that does not specify a scheme. Some examples of hierarchical
* URIs are:
*
* <blockquote>
* {@code http://example.com/languages/java/}<br>
* {@code sample/a/index.html#28}<br>
* {@code ../../demo/b/index.html}<br>
* {@code file:///~/calendar}
* </blockquote>
*
* <p> A hierarchical URI is subject to further parsing according to the syntax
*
* <blockquote>
* [<i>scheme</i><b>{@code :}</b>][<b>{@code //}</b><i>authority</i>][<i>path</i>][<b>{@code ?}</b><i>query</i>][<b>{@code #}</b><i>fragment</i>]
* </blockquote>
*
* where the characters <b>{@code :}</b>, <b>{@code /}</b>,
* <b>{@code ?}</b>, and <b>{@code #}</b> stand for themselves. The
* scheme-specific part of a hierarchical URI consists of the characters
* between the scheme and fragment components.
*
* <p> The authority component of a hierarchical URI is, if specified, either
* <i>server-based</i> or <i>registry-based</i>. A server-based authority
* parses according to the familiar syntax
*
* <blockquote>
* [<i>user-info</i><b>{@code @}</b>]<i>host</i>[<b>{@code :}</b><i>port</i>]
* </blockquote>
*
* where the characters <b>{@code @}</b> and <b>{@code :}</b> stand for
* themselves. Nearly all URI schemes currently in use are server-based. An
* authority component that does not parse in this way is considered to be
* registry-based.
*
* <p> The path component of a hierarchical URI is itself said to be absolute
* if it begins with a slash character ({@code '/'}); otherwise it is
* relative. The path of a hierarchical URI that is either absolute or
* specifies an authority is always absolute.
*
* <p> All told, then, a URI instance has the following nine components:
*
* <table class="striped" style="margin-left:2em">
* <caption style="display:none">Describes the components of a URI:scheme,scheme-specific-part,authority,user-info,host,port,path,query,fragment</caption>
* <thead>
* <tr><th scope="col">Component</th><th scope="col">Type</th></tr>
* </thead>
* <tbody style="text-align:left">
* <tr><th scope="row">scheme</th><td>{@code String}</td></tr>
* <tr><th scope="row">scheme-specific-part</th><td>{@code String}</td></tr>
* <tr><th scope="row">authority</th><td>{@code String}</td></tr>
* <tr><th scope="row">user-info</th><td>{@code String}</td></tr>
* <tr><th scope="row">host</th><td>{@code String}</td></tr>
* <tr><th scope="row">port</th><td>{@code int}</td></tr>
* <tr><th scope="row">path</th><td>{@code String}</td></tr>
* <tr><th scope="row">query</th><td>{@code String}</td></tr>
* <tr><th scope="row">fragment</th><td>{@code String}</td></tr>
* </tbody>
* </table>
*
* In a given instance any particular component is either <i>undefined</i> or
* <i>defined</i> with a distinct value. Undefined string components are
* represented by {@code null}, while undefined integer components are
* represented by {@code -1}. A string component may be defined to have the
* empty string as its value; this is not equivalent to that component being
* undefined.
*
* <p> Whether a particular component is or is not defined in an instance
* depends upon the type of the URI being represented. An absolute URI has a
* scheme component. An opaque URI has a scheme, a scheme-specific part, and
* possibly a fragment, but has no other components. A hierarchical URI always
* has a path (though it may be empty) and a scheme-specific-part (which at
* least contains the path), and may have any of the other components. If the
* authority component is present and is server-based then the host component
* will be defined and the user-information and port components may be defined.
*
*
* <h3> Operations on URI instances </h3>
*
* The key operations supported by this class are those of
* <i>normalization</i>, <i>resolution</i>, and <i>relativization</i>.
*
* <p> <i>Normalization</i> is the process of removing unnecessary {@code "."}
* and {@code ".."} segments from the path component of a hierarchical URI.
* Each {@code "."} segment is simply removed. A {@code ".."} segment is
* removed only if it is preceded by a non-{@code ".."} segment.
* Normalization has no effect upon opaque URIs.
*
* <p> <i>Resolution</i> is the process of resolving one URI against another,
* <i>base</i> URI. The resulting URI is constructed from components of both
* URIs in the manner specified by RFC 2396, taking components from the
* base URI for those not specified in the original. For hierarchical URIs,
* the path of the original is resolved against the path of the base and then
* normalized. The result, for example, of resolving
*
* <blockquote>
* {@code sample/a/index.html#28}
*
* (1)
* </blockquote>
*
* against the base URI {@code http://example.com/languages/java/} is the result
* URI
*
* <blockquote>
* {@code http://example.com/languages/java/sample/a/index.html#28}
* </blockquote>
*
* Resolving the relative URI
*
* <blockquote>
* {@code ../../demo/b/index.html} (2)
* </blockquote>
*
* against this result yields, in turn,
*
* <blockquote>
* {@code http://example.com/languages/java/demo/b/index.html}
* </blockquote>
*
* Resolution of both absolute and relative URIs, and of both absolute and
* relative paths in the case of hierarchical URIs, is supported. Resolving
* the URI {@code file:///~calendar} against any other URI simply yields the
* original URI, since it is absolute. Resolving the relative URI (2) above
* against the relative base URI (1) yields the normalized, but still relative,
* URI
*
* <blockquote>
* {@code demo/b/index.html}
* </blockquote>
*
* <p> <i>Relativization</i>, finally, is the inverse of resolution: For any
* two normalized URIs <i>u</i> and <i>v</i>,
*
* <blockquote>
* <i>u</i>{@code .relativize(}<i>u</i>{@code .resolve(}<i>v</i>{@code )).equals(}<i>v</i>{@code )} and<br>
* <i>u</i>{@code .resolve(}<i>u</i>{@code .relativize(}<i>v</i>{@code )).equals(}<i>v</i>{@code )} .<br>
* </blockquote>
*
* This operation is often useful when constructing a document containing URIs
* that must be made relative to the base URI of the document wherever
* possible. For example, relativizing the URI
*
* <blockquote>
* {@code http://example.com/languages/java/sample/a/index.html#28}
* </blockquote>
*
* against the base URI
*
* <blockquote>
* {@code http://example.com/languages/java/}
* </blockquote>
*
* yields the relative URI {@code sample/a/index.html#28}.
*
*
* <h3> Character categories </h3>
*
* RFC 2396 specifies precisely which characters are permitted in the
* various components of a URI reference. The following categories, most of
* which are taken from that specification, are used below to describe these
* constraints:
*
* <table class="striped" style="margin-left:2em">
* <caption style="display:none">Describes categories alpha,digit,alphanum,unreserved,punct,reserved,escaped,and other</caption>
* <thead>
* <tr><th scope="col">Category</th><th scope="col">Description</th></tr>
* </thead>
* <tbody style="text-align:left">
* <tr><th scope="row" style="vertical-align:top">alpha</th>
* <td>The US-ASCII alphabetic characters,
* {@code 'A'} through {@code 'Z'}
* and {@code 'a'} through {@code 'z'}</td></tr>
* <tr><th scope="row" style="vertical-align:top">digit</th>
* <td>The US-ASCII decimal digit characters,
* {@code '0'} through {@code '9'}</td></tr>
* <tr><th scope="row" style="vertical-align:top">alphanum</th>
* <td>All <i>alpha</i> and <i>digit</i> characters</td></tr>
* <tr><th scope="row" style="vertical-align:top">unreserved</th>
* <td>All <i>alphanum</i> characters together with those in the string
* {@code "_-!.~'()*"}</td></tr>
* <tr><th scope="row" style="vertical-align:top">punct</th>
* <td>The characters in the string {@code ",;:$&+="}</td></tr>
* <tr><th scope="row" style="vertical-align:top">reserved</th>
* <td>All <i>punct</i> characters together with those in the string
* {@code "?/[]@"}</td></tr>
* <tr><th scope="row" style="vertical-align:top">escaped</th>
* <td>Escaped octets, that is, triplets consisting of the percent
* character ({@code '%'}) followed by two hexadecimal digits
* ({@code '0'}-{@code '9'}, {@code 'A'}-{@code 'F'}, and
* {@code 'a'}-{@code 'f'})</td></tr>
* <tr><th scope="row" style="vertical-align:top">other</th>
* <td>The Unicode characters that are not in the US-ASCII character set,
* are not control characters (according to the {@link
* java.lang.Character#isISOControl(char) Character.isISOControl}
* method), and are not space characters (according to the {@link
* java.lang.Character#isSpaceChar(char) Character.isSpaceChar}
* method) <i>(<b>Deviation from RFC 2396</b>, which is
* limited to US-ASCII)</i></td></tr>
* </tbody>
* </table>
*
* <p><a id="legal-chars"></a> The set of all legal URI characters consists of
* the <i>unreserved</i>, <i>reserved</i>, <i>escaped</i>, and <i>other</i>
* characters.
*
*
* <h3> Escaped octets, quotation, encoding, and decoding </h3>
*
* RFC 2396 allows escaped octets to appear in the user-info, path, query, and
* fragment components. Escaping serves two purposes in URIs:
*
* <ul>
*
* <li><p> To <i>encode</i> non-US-ASCII characters when a URI is required to
* conform strictly to RFC 2396 by not containing any <i>other</i>
* characters. </p></li>
*
* <li><p> To <i>quote</i> characters that are otherwise illegal in a
* component. The user-info, path, query, and fragment components differ
* slightly in terms of which characters are considered legal and illegal.
* </p></li>
*
* </ul>
*
* These purposes are served in this class by three related operations:
*
* <ul>
*
* <li><p><a id="encode"></a> A character is <i>encoded</i> by replacing it
* with the sequence of escaped octets that represent that character in the
* UTF-8 character set. The Euro currency symbol ({@code '\u005Cu20AC'}),
* for example, is encoded as {@code "%E2%82%AC"}. <i>(<b>Deviation from
* RFC 2396</b>, which does not specify any particular character
* set.)</i> </p></li>
*
* <li><p><a id="quote"></a> An illegal character is <i>quoted</i> simply by
* encoding it. The space character, for example, is quoted by replacing it
* with {@code "%20"}. UTF-8 contains US-ASCII, hence for US-ASCII
* characters this transformation has exactly the effect required by
* RFC 2396. </p></li>
*
* <li><p><a id="decode"></a>
* A sequence of escaped octets is <i>decoded</i> by
* replacing it with the sequence of characters that it represents in the
* UTF-8 character set. UTF-8 contains US-ASCII, hence decoding has the
* effect of de-quoting any quoted US-ASCII characters as well as that of
* decoding any encoded non-US-ASCII characters. If a <a
* href="../nio/charset/CharsetDecoder.html#ce">decoding error</a> occurs
* when decoding the escaped octets then the erroneous octets are replaced by
* {@code '\u005CuFFFD'}, the Unicode replacement character. </p></li>
*
* </ul>
*
* These operations are exposed in the constructors and methods of this class
* as follows:
*
* <ul>
*
* <li><p> The {@linkplain #URI(java.lang.String) single-argument
* constructor} requires any illegal characters in its argument to be
* quoted and preserves any escaped octets and <i>other</i> characters that
* are present. </p></li>
*
* <li><p> The {@linkplain
* #URI(java.lang.String,java.lang.String,java.lang.String,int,java.lang.String,java.lang.String,java.lang.String)
* multi-argument constructors} quote illegal characters as
* required by the components in which they appear. The percent character
* ({@code '%'}) is always quoted by these constructors. Any <i>other</i>
* characters are preserved. </p></li>
*
* <li><p> The {@link #getRawUserInfo() getRawUserInfo}, {@link #getRawPath()
* getRawPath}, {@link #getRawQuery() getRawQuery}, {@link #getRawFragment()
* getRawFragment}, {@link #getRawAuthority() getRawAuthority}, and {@link
* #getRawSchemeSpecificPart() getRawSchemeSpecificPart} methods return the
* values of their corresponding components in raw form, without interpreting
* any escaped octets. The strings returned by these methods may contain
* both escaped octets and <i>other</i> characters, and will not contain any
* illegal characters. </p></li>
*
* <li><p> The {@link #getUserInfo() getUserInfo}, {@link #getPath()
* getPath}, {@link #getQuery() getQuery}, {@link #getFragment()
* getFragment}, {@link #getAuthority() getAuthority}, and {@link
* #getSchemeSpecificPart() getSchemeSpecificPart} methods decode any escaped
* octets in their corresponding components. The strings returned by these
* methods may contain both <i>other</i> characters and illegal characters,
* and will not contain any escaped octets. </p></li>
*
* <li><p> The {@link #toString() toString} method returns a URI string with
* all necessary quotation but which may contain <i>other</i> characters.
* </p></li>
*
* <li><p> The {@link #toASCIIString() toASCIIString} method returns a fully
* quoted and encoded URI string that does not contain any <i>other</i>
* characters. </p></li>
*
* </ul>
*
*
* <h3> Identities </h3>
*
* For any URI <i>u</i>, it is always the case that
*
* <blockquote>
* {@code new URI(}<i>u</i>{@code .toString()).equals(}<i>u</i>{@code )} .
* </blockquote>
*
* For any URI <i>u</i> that does not contain redundant syntax such as two
* slashes before an empty authority (as in {@code file:///tmp/} ) or a
* colon following a host name but no port (as in
* {@code http://www.example.com:} ), and that does not encode characters
* except those that must be quoted, the following identities also hold:
* <pre>
* new URI(<i>u</i>.getScheme(),
* <i>u</i>.getSchemeSpecificPart(),
* <i>u</i>.getFragment())
* .equals(<i>u</i>)</pre>
* in all cases,
* <pre>
* new URI(<i>u</i>.getScheme(),
* <i>u</i>.getAuthority(),
* <i>u</i>.getPath(), <i>u</i>.getQuery(),
* <i>u</i>.getFragment())
* .equals(<i>u</i>)</pre>
* if <i>u</i> is hierarchical, and
* <pre>
* new URI(<i>u</i>.getScheme(),
* <i>u</i>.getUserInfo(), <i>u</i>.getHost(), <i>u</i>.getPort(),
* <i>u</i>.getPath(), <i>u</i>.getQuery(),
* <i>u</i>.getFragment())
* .equals(<i>u</i>)</pre>
* if <i>u</i> is hierarchical and has either no authority or a server-based
* authority.
*
*
* <h3> URIs, URLs, and URNs </h3>
*
* A URI is a uniform resource <i>identifier</i> while a URL is a uniform
* resource <i>locator</i>. Hence every URL is a URI, abstractly speaking, but
* not every URI is a URL. This is because there is another subcategory of
* URIs, uniform resource <i>names</i> (URNs), which name resources but do not
* specify how to locate them. The {@code mailto}, {@code news}, and
* {@code isbn} URIs shown above are examples of URNs.
*
* <p> The conceptual distinction between URIs and URLs is reflected in the
* differences between this class and the {@link URL} class.
*
* <p> An instance of this class represents a URI reference in the syntactic
* sense defined by RFC 2396. A URI may be either absolute or relative.
* A URI string is parsed according to the generic syntax without regard to the
* scheme, if any, that it specifies. No lookup of the host, if any, is
* performed, and no scheme-dependent stream handler is constructed. Equality,
* hashing, and comparison are defined strictly in terms of the character
* content of the instance. In other words, a URI instance is little more than
* a structured string that supports the syntactic, scheme-independent
* operations of comparison, normalization, resolution, and relativization.
*
* <p> An instance of the {@link URL} class, by contrast, represents the
* syntactic components of a URL together with some of the information required
* to access the resource that it describes. A URL must be absolute, that is,
* it must always specify a scheme. A URL string is parsed according to its
* scheme. A stream handler is always established for a URL, and in fact it is
* impossible to create a URL instance for a scheme for which no handler is
* available. Equality and hashing depend upon both the scheme and the
* Internet address of the host, if any; comparison is not defined. In other
* words, a URL is a structured string that supports the syntactic operation of
* resolution as well as the network I/O operations of looking up the host and
* opening a connection to the specified resource.
*
* @apiNote
*
* Applications working with file paths and file URIs should take great
* care to use the appropriate methods to convert between the two.
* The {@link Path#of(URI)} factory method and the {@link File#File(URI)}
* constructor can be used to create {@link Path} or {@link File}
* objects from a file URI. {@link Path#toUri()} and {@link File#toURI()}
* can be used to create a {@link URI} from a file path.
* Applications should never try to {@linkplain
* #URI(String, String, String, int, String, String, String)
* construct}, {@linkplain #URI(String) parse}, or
* {@linkplain #resolve(String) resolve} a {@code URI}
* from the direct string representation of a {@code File} or {@code Path}
* instance.
* <p>
* Some components of a URL or URI, such as <i>userinfo</i>, may
* be abused to construct misleading URLs or URIs. Applications
* that deal with URLs or URIs should take into account
* the recommendations advised in <a
* href="https://tools.ietf.org/html/rfc3986#section-7">RFC3986,
* Section 7, Security Considerations</a>.
*
* @author Mark Reinhold
* @since 1.4
*
* @see <a href="http://www.ietf.org/rfc/rfc2279.txt"><i>RFC 2279: UTF-8, a
* transformation format of ISO 10646</i></a>, <br><a
* href="http://www.ietf.org/rfc/rfc2373.txt"><i>RFC 2373: IPv6 Addressing
* Architecture</i></a>, <br><a
* href="http://www.ietf.org/rfc/rfc2396.txt"><i>RFC 2396: Uniform
* Resource Identifiers (URI): Generic Syntax</i></a>, <br><a
* href="http://www.ietf.org/rfc/rfc2732.txt"><i>RFC 2732: Format for
* Literal IPv6 Addresses in URLs</i></a>, <br><a
* href="URISyntaxException.html">URISyntaxException</a>
*/
public final class URI
implements Comparable<URI>, Serializable
{
// Note: Comments containing the word "ASSERT" indicate places where a
// throw of an InternalError should be replaced by an appropriate assertion
// statement once asserts are enabled in the build.
@java.io.Serial
static final long serialVersionUID = -6052424284110960213L;
// -- Properties and components of this instance --
// Components of all URIs: [<scheme>:]<scheme-specific-part>[#<fragment>]
private transient String scheme; // null ==> relative URI
private transient String fragment;
// Hierarchical URI components: [//<authority>]<path>[?<query>]
private transient String authority; // Registry or server
// Server-based authority: [<userInfo>@]<host>[:<port>]
private transient String userInfo;
private transient String host; // null ==> registry-based
private transient int port = -1; // -1 ==> undefined
// Remaining components of hierarchical URIs
private transient String path; // null ==> opaque
private transient String query;
// The remaining fields may be computed on demand, which is safe even in
// the face of multiple threads racing to initialize them
private transient String schemeSpecificPart;
private transient int hash; // Zero ==> undefined
private transient String decodedUserInfo;
private transient String decodedAuthority;
private transient String decodedPath;
private transient String decodedQuery;
private transient String decodedFragment;
private transient String decodedSchemeSpecificPart;
/**
* The string form of this URI.
*
* @serial
*/
private volatile String string; // The only serializable field
// -- Constructors and factories --
private URI() { } // Used internally
/**
* Constructs a URI by parsing the given string.
*
* <p> This constructor parses the given string exactly as specified by the
* grammar in <a
* href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>,
* Appendix A, <b><i>except for the following deviations:</i></b> </p>
*
* <ul>
*
* <li><p> An empty authority component is permitted as long as it is
* followed by a non-empty path, a query component, or a fragment
* component. This allows the parsing of URIs such as
* {@code "file:///foo/bar"}, which seems to be the intent of
* RFC 2396 although the grammar does not permit it. If the
* authority component is empty then the user-information, host, and port
* components are undefined. </p></li>
*
* <li><p> Empty relative paths are permitted; this seems to be the
* intent of RFC 2396 although the grammar does not permit it. The
* primary consequence of this deviation is that a standalone fragment
* such as {@code "#foo"} parses as a relative URI with an empty path
* and the given fragment, and can be usefully <a
* href="#resolve-frag">resolved</a> against a base URI.
*
* <li><p> IPv4 addresses in host components are parsed rigorously, as
* specified by <a
* href="http://www.ietf.org/rfc/rfc2732.txt">RFC 2732</a>: Each
* element of a dotted-quad address must contain no more than three
* decimal digits. Each element is further constrained to have a value
* no greater than 255. </p></li>
*
* <li> <p> Hostnames in host components that comprise only a single
* domain label are permitted to start with an <i>alphanum</i>
* character. This seems to be the intent of <a
* href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>
* section 3.2.2 although the grammar does not permit it. The
* consequence of this deviation is that the authority component of a
* hierarchical URI such as {@code s://123}, will parse as a server-based
* authority. </p></li>
*
* <li><p> IPv6 addresses are permitted for the host component. An IPv6
* address must be enclosed in square brackets ({@code '['} and
* {@code ']'}) as specified by <a
* href="http://www.ietf.org/rfc/rfc2732.txt">RFC 2732</a>. The
* IPv6 address itself must parse according to <a
* href="http://www.ietf.org/rfc/rfc2373.txt">RFC 2373</a>. IPv6
* addresses are further constrained to describe no more than sixteen
* bytes of address information, a constraint implicit in RFC 2373
* but not expressible in the grammar. </p></li>
*
* <li><p> Characters in the <i>other</i> category are permitted wherever
* RFC 2396 permits <i>escaped</i> octets, that is, in the
* user-information, path, query, and fragment components, as well as in
* the authority component if the authority is registry-based. This
* allows URIs to contain Unicode characters beyond those in the US-ASCII
* character set. </p></li>
*
* </ul>
*
* @param str The string to be parsed into a URI
*
* @throws NullPointerException
* If {@code str} is {@code null}
*
* @throws URISyntaxException
* If the given string violates RFC 2396, as augmented
* by the above deviations
*/
public URI(String str) throws URISyntaxException {
new Parser(str).parse(false);
}
/**
* Constructs a hierarchical URI from the given components.
*
* <p> If a scheme is given then the path, if also given, must either be
* empty or begin with a slash character ({@code '/'}). Otherwise a
* component of the new URI may be left undefined by passing {@code null}
* for the corresponding parameter or, in the case of the {@code port}
* parameter, by passing {@code -1}.
*
* <p> This constructor first builds a URI string from the given components
* according to the rules specified in <a
* href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>,
* section 5.2, step 7: </p>
*
* <ol>
*
* <li><p> Initially, the result string is empty. </p></li>
*
* <li><p> If a scheme is given then it is appended to the result,
* followed by a colon character ({@code ':'}). </p></li>
*
* <li><p> If user information, a host, or a port are given then the
* string {@code "//"} is appended. </p></li>
*
* <li><p> If user information is given then it is appended, followed by
* a commercial-at character ({@code '@'}). Any character not in the
* <i>unreserved</i>, <i>punct</i>, <i>escaped</i>, or <i>other</i>
* categories is <a href="#quote">quoted</a>. </p></li>
*
* <li><p> If a host is given then it is appended. If the host is a
* literal IPv6 address but is not enclosed in square brackets
* ({@code '['} and {@code ']'}) then the square brackets are added.
* </p></li>
*
* <li><p> If a port number is given then a colon character
* ({@code ':'}) is appended, followed by the port number in decimal.
* </p></li>
*
* <li><p> If a path is given then it is appended. Any character not in
* the <i>unreserved</i>, <i>punct</i>, <i>escaped</i>, or <i>other</i>
* categories, and not equal to the slash character ({@code '/'}) or the
* commercial-at character ({@code '@'}), is quoted. </p></li>
*
* <li><p> If a query is given then a question-mark character
* ({@code '?'}) is appended, followed by the query. Any character that
* is not a <a href="#legal-chars">legal URI character</a> is quoted.
* </p></li>
*
* <li><p> Finally, if a fragment is given then a hash character
* ({@code '#'}) is appended, followed by the fragment. Any character
* that is not a legal URI character is quoted. </p></li>
*
* </ol>
*
* <p> The resulting URI string is then parsed as if by invoking the {@link
* #URI(String)} constructor and then invoking the {@link
* #parseServerAuthority()} method upon the result; this may cause a {@link
* URISyntaxException} to be thrown. </p>
*
* @param scheme Scheme name
* @param userInfo User name and authorization information
* @param host Host name
* @param port Port number
* @param path Path
* @param query Query
* @param fragment Fragment
*
* @throws URISyntaxException
* If both a scheme and a path are given but the path is relative,
* if the URI string constructed from the given components violates
* RFC 2396, or if the authority component of the string is
* present but cannot be parsed as a server-based authority
*/
public URI(String scheme,
String userInfo, String host, int port,
String path, String query, String fragment)
throws URISyntaxException
{
String s = toString(scheme, null,
null, userInfo, host, port,
path, query, fragment);
checkPath(s, scheme, path);
new Parser(s).parse(true);
}
/**
* Constructs a hierarchical URI from the given components.
*
* <p> If a scheme is given then the path, if also given, must either be
* empty or begin with a slash character ({@code '/'}). Otherwise a
* component of the new URI may be left undefined by passing {@code null}
* for the corresponding parameter.
*
* <p> This constructor first builds a URI string from the given components
* according to the rules specified in <a
* href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>,
* section 5.2, step 7: </p>
*
* <ol>
*
* <li><p> Initially, the result string is empty. </p></li>
*
* <li><p> If a scheme is given then it is appended to the result,
* followed by a colon character ({@code ':'}). </p></li>
*
* <li><p> If an authority is given then the string {@code "//"} is
* appended, followed by the authority. If the authority contains a
* literal IPv6 address then the address must be enclosed in square
* brackets ({@code '['} and {@code ']'}). Any character not in the
* <i>unreserved</i>, <i>punct</i>, <i>escaped</i>, or <i>other</i>
* categories, and not equal to the commercial-at character
* ({@code '@'}), is <a href="#quote">quoted</a>. </p></li>
*
* <li><p> If a path is given then it is appended. Any character not in
* the <i>unreserved</i>, <i>punct</i>, <i>escaped</i>, or <i>other</i>
* categories, and not equal to the slash character ({@code '/'}) or the
* commercial-at character ({@code '@'}), is quoted. </p></li>
*
* <li><p> If a query is given then a question-mark character
* ({@code '?'}) is appended, followed by the query. Any character that
* is not a <a href="#legal-chars">legal URI character</a> is quoted.
* </p></li>
*
* <li><p> Finally, if a fragment is given then a hash character
* ({@code '#'}) is appended, followed by the fragment. Any character
* that is not a legal URI character is quoted. </p></li>
*
* </ol>
*
* <p> The resulting URI string is then parsed as if by invoking the {@link
* #URI(String)} constructor and then invoking the {@link
* #parseServerAuthority()} method upon the result; this may cause a {@link
* URISyntaxException} to be thrown. </p>
*
* @param scheme Scheme name
* @param authority Authority
* @param path Path
* @param query Query
* @param fragment Fragment
*
* @throws URISyntaxException
* If both a scheme and a path are given but the path is relative,
* if the URI string constructed from the given components violates
* RFC 2396, or if the authority component of the string is
* present but cannot be parsed as a server-based authority
*/
public URI(String scheme,
String authority,
String path, String query, String fragment)
throws URISyntaxException
{
String s = toString(scheme, null,
authority, null, null, -1,
path, query, fragment);
checkPath(s, scheme, path);
new Parser(s).parse(false);
}
/**
* Constructs a hierarchical URI from the given components.
*
* <p> A component may be left undefined by passing {@code null}.
*
* <p> This convenience constructor works as if by invoking the
* seven-argument constructor as follows:
*
* <blockquote>
* {@code new} {@link #URI(String, String, String, int, String, String, String)
* URI}{@code (scheme, null, host, -1, path, null, fragment);}
* </blockquote>
*
* @param scheme Scheme name
* @param host Host name
* @param path Path
* @param fragment Fragment
*
* @throws URISyntaxException
* If the URI string constructed from the given components
* violates RFC 2396
*/
public URI(String scheme, String host, String path, String fragment)
throws URISyntaxException
{
this(scheme, null, host, -1, path, null, fragment);
}
/**
* Constructs a URI from the given components.
*
* <p> A component may be left undefined by passing {@code null}.
*
* <p> This constructor first builds a URI in string form using the given
* components as follows: </p>
*
* <ol>
*
* <li><p> Initially, the result string is empty. </p></li>
*
* <li><p> If a scheme is given then it is appended to the result,
* followed by a colon character ({@code ':'}). </p></li>
*
* <li><p> If a scheme-specific part is given then it is appended. Any
* character that is not a <a href="#legal-chars">legal URI character</a>
* is <a href="#quote">quoted</a>. </p></li>
*
* <li><p> Finally, if a fragment is given then a hash character
* ({@code '#'}) is appended to the string, followed by the fragment.
* Any character that is not a legal URI character is quoted. </p></li>
*
* </ol>
*
* <p> The resulting URI string is then parsed in order to create the new
* URI instance as if by invoking the {@link #URI(String)} constructor;
* this may cause a {@link URISyntaxException} to be thrown. </p>
*
* @param scheme Scheme name
* @param ssp Scheme-specific part
* @param fragment Fragment
*
* @throws URISyntaxException
* If the URI string constructed from the given components
* violates RFC 2396
*/
public URI(String scheme, String ssp, String fragment)
throws URISyntaxException
{
new Parser(toString(scheme, ssp,
null, null, null, -1,
null, null, fragment))
.parse(false);
}
/**
* Constructs a simple URI consisting of only a scheme and a pre-validated
* path. Provides a fast-path for some internal cases.
*/
URI(String scheme, String path) {
assert validSchemeAndPath(scheme, path);
this.scheme = scheme;
this.path = path;
}
private static boolean validSchemeAndPath(String scheme, String path) {
try {
URI u = new URI(scheme + ":" + path);
return scheme.equals(u.scheme) && path.equals(u.path);
} catch (URISyntaxException e) {
return false;
}
}
/**
* Creates a URI by parsing the given string.
*
* <p> This convenience factory method works as if by invoking the {@link
* #URI(String)} constructor; any {@link URISyntaxException} thrown by the
* constructor is caught and wrapped in a new {@link
* IllegalArgumentException} object, which is then thrown.
*
* <p> This method is provided for use in situations where it is known that
* the given string is a legal URI, for example for URI constants declared
* within a program, and so it would be considered a programming error
* for the string not to parse as such. The constructors, which throw
* {@link URISyntaxException} directly, should be used in situations where a
* URI is being constructed from user input or from some other source that
* may be prone to errors. </p>
*
* @param str The string to be parsed into a URI
* @return The new URI
*
* @throws NullPointerException
* If {@code str} is {@code null}
*
* @throws IllegalArgumentException
* If the given string violates RFC 2396
*/
public static URI create(String str) {
try {
return new URI(str);
} catch (URISyntaxException x) {
throw new IllegalArgumentException(x.getMessage(), x);
}
}
// -- Operations --
/**
* Attempts to parse this URI's authority component, if defined, into
* user-information, host, and port components.
*
* <p> If this URI's authority component has already been recognized as
* being server-based then it will already have been parsed into
* user-information, host, and port components. In this case, or if this
* URI has no authority component, this method simply returns this URI.
*
* <p> Otherwise this method attempts once more to parse the authority
* component into user-information, host, and port components, and throws
* an exception describing why the authority component could not be parsed
* in that way.
*
* <p> This method is provided because the generic URI syntax specified in
* <a href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>
* cannot always distinguish a malformed server-based authority from a
* legitimate registry-based authority. It must therefore treat some
* instances of the former as instances of the latter. The authority
* component in the URI string {@code "//foo:bar"}, for example, is not a
* legal server-based authority but it is legal as a registry-based
* authority.
*
* <p> In many common situations, for example when working URIs that are
* known to be either URNs or URLs, the hierarchical URIs being used will
* always be server-based. They therefore must either be parsed as such or
* treated as an error. In these cases a statement such as
*
* <blockquote>
* {@code URI }<i>u</i>{@code = new URI(str).parseServerAuthority();}
* </blockquote>
*
* <p> can be used to ensure that <i>u</i> always refers to a URI that, if
* it has an authority component, has a server-based authority with proper
* user-information, host, and port components. Invoking this method also
* ensures that if the authority could not be parsed in that way then an
* appropriate diagnostic message can be issued based upon the exception
* that is thrown. </p>
*
* @return A URI whose authority field has been parsed
* as a server-based authority
*
* @throws URISyntaxException
* If the authority component of this URI is defined
* but cannot be parsed as a server-based authority
* according to RFC 2396
*/
public URI parseServerAuthority()
throws URISyntaxException
{
// We could be clever and cache the error message and index from the
// exception thrown during the original parse, but that would require
// either more fields or a more-obscure representation.
if ((host != null) || (authority == null))
return this;
new Parser(toString()).parse(true);
return this;
}
/**
* Normalizes this URI's path.
*
* <p> If this URI is opaque, or if its path is already in normal form,
* then this URI is returned. Otherwise a new URI is constructed that is
* identical to this URI except that its path is computed by normalizing
* this URI's path in a manner consistent with <a
* href="http://www.ietf.org/rfc/rfc2396.txt">RFC 2396</a>,
* section 5.2, step 6, sub-steps c through f; that is:
* </p>
*
* <ol>
*
* <li><p> All {@code "."} segments are removed. </p></li>
*
* <li><p> If a {@code ".."} segment is preceded by a non-{@code ".."}
* segment then both of these segments are removed. This step is
* repeated until it is no longer applicable. </p></li>
*
* <li><p> If the path is relative, and if its first segment contains a
* colon character ({@code ':'}), then a {@code "."} segment is
* prepended. This prevents a relative URI with a path such as
* {@code "a:b/c/d"} from later being re-parsed as an opaque URI with a
* scheme of {@code "a"} and a scheme-specific part of {@code "b/c/d"}.
* <b><i>(Deviation from RFC 2396)</i></b> </p></li>
*
* </ol>
*
* <p> A normalized path will begin with one or more {@code ".."} segments