1 /*
2 * Copyright (c) 1995, 2013, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation. Oracle designates this
8 * particular file as subject to the "Classpath" exception as provided
9 * by Oracle in the LICENSE file that accompanied this code.
10 *
11 * This code is distributed in the hope that it will be useful, but WITHOUT
12 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
13 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
14 * version 2 for more details (a copy is included in the LICENSE file that
15 * accompanied this code).
16 *
17 * You should have received a copy of the GNU General Public License version
18 * 2 along with this work; if not, write to the Free Software Foundation,
19 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
20 *
21 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
22 * or visit www.oracle.com if you need additional information or have any
23 * questions.
24 */
25
26 package java.net;
27
28 import java.io.IOException;
29 import java.io.InputStream;
30 import java.util.Hashtable;
31 import java.util.StringTokenizer;
32 import sun.security.util.SecurityConstants;
33
34 /**
35 * Class {@code URL} represents a Uniform Resource
36 * Locator, a pointer to a "resource" on the World
37 * Wide Web. A resource can be something as simple as a file or a
38 * directory, or it can be a reference to a more complicated object,
39 * such as a query to a database or to a search engine. More
40 * information on the types of URLs and their formats can be found at:
41 * <a href=
42 * "http://web.archive.org/web/20051219043731/http://archive.ncsa.uiuc.edu/SDG/Software/Mosaic/Demo/url-primer.html">
43 * <i>Types of URL</i></a>
44 * <p>
45 * In general, a URL can be broken into several parts. Consider the
46 * following example:
47 * <blockquote><pre>
48 * http://www.example.com/docs/resource1.html
49 * </pre></blockquote>
50 * <p>
51 * The URL above indicates that the protocol to use is
52 * {@code http} (HyperText Transfer Protocol) and that the
53 * information resides on a host machine named
54 * {@code www.example.com}. The information on that host
55 * machine is named {@code /docs/resource1.html}. The exact
56 * meaning of this name on the host machine is both protocol
57 * dependent and host dependent. The information normally resides in
58 * a file, but it could be generated on the fly. This component of
59 * the URL is called the <i>path</i> component.
60 * <p>
61 * A URL can optionally specify a "port", which is the
62 * port number to which the TCP connection is made on the remote host
63 * machine. If the port is not specified, the default port for
64 * the protocol is used instead. For example, the default port for
65 * {@code http} is {@code 80}. An alternative port could be
66 * specified as:
67 * <blockquote><pre>
68 * http://www.example.com:1080/docs/resource1.html
69 * </pre></blockquote>
70 * <p>
71 * The syntax of {@code URL} is defined by <a
72 * href="http://www.ietf.org/rfc/rfc2396.txt"><i>RFC 2396: Uniform
73 * Resource Identifiers (URI): Generic Syntax</i></a>, amended by <a
74 * href="http://www.ietf.org/rfc/rfc2732.txt"><i>RFC 2732: Format for
75 * Literal IPv6 Addresses in URLs</i></a>. The Literal IPv6 address format
76 * also supports scope_ids. The syntax and usage of scope_ids is described
77 * <a href="Inet6Address.html#scoped">here</a>.
78 * <p>
79 * A URL may have appended to it a "fragment", also known
80 * as a "ref" or a "reference". The fragment is indicated by the sharp
81 * sign character "#" followed by more characters. For example,
82 * <blockquote><pre>
83 * http://java.sun.com/index.html#chapter1
84 * </pre></blockquote>
85 * <p>
86 * This fragment is not technically part of the URL. Rather, it
87 * indicates that after the specified resource is retrieved, the
88 * application is specifically interested in that part of the
89 * document that has the tag {@code chapter1} attached to it. The
90 * meaning of a tag is resource specific.
91 * <p>
92 * An application can also specify a "relative URL",
93 * which contains only enough information to reach the resource
94 * relative to another URL. Relative URLs are frequently used within
95 * HTML pages. For example, if the contents of the URL:
96 * <blockquote><pre>
97 * http://java.sun.com/index.html
98 * </pre></blockquote>
99 * contained within it the relative URL:
100 * <blockquote><pre>
101 * FAQ.html
102 * </pre></blockquote>
103 * it would be a shorthand for:
104 * <blockquote><pre>
105 * http://java.sun.com/FAQ.html
106 * </pre></blockquote>
107 * <p>
108 * The relative URL need not specify all the components of a URL. If
109 * the protocol, host name, or port number is missing, the value is
110 * inherited from the fully specified URL. The file component must be
111 * specified. The optional fragment is not inherited.
112 * <p>
113 * The URL class does not itself encode or decode any URL components
114 * according to the escaping mechanism defined in RFC2396. It is the
115 * responsibility of the caller to encode any fields, which need to be
116 * escaped prior to calling URL, and also to decode any escaped fields,
117 * that are returned from URL. Furthermore, because URL has no knowledge
118 * of URL escaping, it does not recognise equivalence between the encoded
119 * or decoded form of the same URL. For example, the two URLs:<br>
120 * <pre> http://foo.com/hello world/ and http://foo.com/hello%20world</pre>
121 * would be considered not equal to each other.
122 * <p>
123 * Note, the {@link java.net.URI} class does perform escaping of its
124 * component fields in certain circumstances. The recommended way
125 * to manage the encoding and decoding of URLs is to use {@link java.net.URI},
126 * and to convert between these two classes using {@link #toURI()} and
127 * {@link URI#toURL()}.
128 * <p>
129 * The {@link URLEncoder} and {@link URLDecoder} classes can also be
130 * used, but only for HTML form encoding, which is not the same
131 * as the encoding scheme defined in RFC2396.
132 *
133 * @author James Gosling
134 * @since JDK1.0
135 */
136 public final class URL implements java.io.Serializable {
137
138 static final long serialVersionUID = -7627629688361524110L;
139
140 /**
141 * The property which specifies the package prefix list to be scanned
142 * for protocol handlers. The value of this property (if any) should
143 * be a vertical bar delimited list of package names to search through
144 * for a protocol handler to load. The policy of this class is that
145 * all protocol handlers will be in a class called <protocolname>.Handler,
146 * and each package in the list is examined in turn for a matching
147 * handler. If none are found (or the property is not specified), the
148 * default package prefix, sun.net.www.protocol, is used. The search
149 * proceeds from the first package in the list to the last and stops
150 * when a match is found.
151 */
152 private static final String protocolPathProp = "java.protocol.handler.pkgs";
153
154 /**
155 * The protocol to use (ftp, http, nntp, ... etc.) .
156 * @serial
157 */
158 private String protocol;
159
160 /**
161 * The host name to connect to.
162 * @serial
163 */
164 private String host;
165
166 /**
167 * The protocol port to connect to.
168 * @serial
169 */
170 private int port = -1;
171
172 /**
173 * The specified file name on that host. {@code file} is
174 * defined as {@code path[?query]}
175 * @serial
176 */
177 private String file;
178
179 /**
180 * The query part of this URL.
181 */
182 private transient String query;
183
184 /**
185 * The authority part of this URL.
186 * @serial
187 */
188 private String authority;
189
190 /**
191 * The path part of this URL.
192 */
193 private transient String path;
194
195 /**
196 * The userinfo part of this URL.
197 */
198 private transient String userInfo;
199
200 /**
201 * # reference.
202 * @serial
203 */
204 private String ref;
205
206 /**
207 * The host's IP address, used in equals and hashCode.
208 * Computed on demand. An uninitialized or unknown hostAddress is null.
209 */
210 transient InetAddress hostAddress;
211
212 /**
213 * The URLStreamHandler for this URL.
214 */
215 transient URLStreamHandler handler;
216
217 /* Our hash code.
218 * @serial
219 */
220 private int hashCode = -1;
221
222 /**
223 * Creates a {@code URL} object from the specified
224 * {@code protocol}, {@code host}, {@code port}
225 * number, and {@code file}.<p>
226 *
227 * {@code host} can be expressed as a host name or a literal
228 * IP address. If IPv6 literal address is used, it should be
229 * enclosed in square brackets ({@code '['} and {@code ']'}), as
230 * specified by <a
231 * href="http://www.ietf.org/rfc/rfc2732.txt">RFC 2732</a>;
232 * However, the literal IPv6 address format defined in <a
233 * href="http://www.ietf.org/rfc/rfc2373.txt"><i>RFC 2373: IP
234 * Version 6 Addressing Architecture</i></a> is also accepted.<p>
235 *
236 * Specifying a {@code port} number of {@code -1}
237 * indicates that the URL should use the default port for the
238 * protocol.<p>
239 *
240 * If this is the first URL object being created with the specified
241 * protocol, a <i>stream protocol handler</i> object, an instance of
242 * class {@code URLStreamHandler}, is created for that protocol:
243 * <ol>
244 * <li>If the application has previously set up an instance of
245 * {@code URLStreamHandlerFactory} as the stream handler factory,
246 * then the {@code createURLStreamHandler} method of that instance
247 * is called with the protocol string as an argument to create the
248 * stream protocol handler.
249 * <li>If no {@code URLStreamHandlerFactory} has yet been set up,
250 * or if the factory's {@code createURLStreamHandler} method
251 * returns {@code null}, then the constructor finds the
252 * value of the system property:
253 * <blockquote><pre>
254 * java.protocol.handler.pkgs
255 * </pre></blockquote>
256 * If the value of that system property is not {@code null},
257 * it is interpreted as a list of packages separated by a vertical
258 * slash character '{@code |}'. The constructor tries to load
259 * the class named:
260 * <blockquote><pre>
261 * <<i>package</i>>.<<i>protocol</i>>.Handler
262 * </pre></blockquote>
263 * where <<i>package</i>> is replaced by the name of the package
264 * and <<i>protocol</i>> is replaced by the name of the protocol.
265 * If this class does not exist, or if the class exists but it is not
266 * a subclass of {@code URLStreamHandler}, then the next package
267 * in the list is tried.
268 * <li>If the previous step fails to find a protocol handler, then the
269 * constructor tries to load from a system default package.
270 * <blockquote><pre>
271 * <<i>system default package</i>>.<<i>protocol</i>>.Handler
272 * </pre></blockquote>
273 * If this class does not exist, or if the class exists but it is not a
274 * subclass of {@code URLStreamHandler}, then a
275 * {@code MalformedURLException} is thrown.
276 * </ol>
277 *
278 * <p>Protocol handlers for the following protocols are guaranteed
279 * to exist on the search path :-
280 * <blockquote><pre>
281 * http, https, file, and jar
282 * </pre></blockquote>
283 * Protocol handlers for additional protocols may also be
284 * available.
285 *
286 * <p>No validation of the inputs is performed by this constructor.
287 *
288 * @param protocol the name of the protocol to use.
289 * @param host the name of the host.
290 * @param port the port number on the host.
291 * @param file the file on the host
292 * @exception MalformedURLException if an unknown protocol is specified.
293 * @see java.lang.System#getProperty(java.lang.String)
294 * @see java.net.URL#setURLStreamHandlerFactory(
295 * java.net.URLStreamHandlerFactory)
296 * @see java.net.URLStreamHandler
297 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler(
298 * java.lang.String)
299 */
300 public URL(String protocol, String host, int port, String file)
301 throws MalformedURLException
302 {
303 this(protocol, host, port, file, null);
304 }
305
306 /**
307 * Creates a URL from the specified {@code protocol}
308 * name, {@code host} name, and {@code file} name. The
309 * default port for the specified protocol is used.
310 * <p>
311 * This method is equivalent to calling the four-argument
312 * constructor with the arguments being {@code protocol},
313 * {@code host}, {@code -1}, and {@code file}.
314 *
315 * No validation of the inputs is performed by this constructor.
316 *
317 * @param protocol the name of the protocol to use.
318 * @param host the name of the host.
319 * @param file the file on the host.
320 * @exception MalformedURLException if an unknown protocol is specified.
321 * @see java.net.URL#URL(java.lang.String, java.lang.String,
322 * int, java.lang.String)
323 */
324 public URL(String protocol, String host, String file)
325 throws MalformedURLException {
326 this(protocol, host, -1, file);
327 }
328
329 /**
330 * Creates a {@code URL} object from the specified
331 * {@code protocol}, {@code host}, {@code port}
332 * number, {@code file}, and {@code handler}. Specifying
333 * a {@code port} number of {@code -1} indicates that
334 * the URL should use the default port for the protocol. Specifying
335 * a {@code handler} of {@code null} indicates that the URL
336 * should use a default stream handler for the protocol, as outlined
337 * for:
338 * java.net.URL#URL(java.lang.String, java.lang.String, int,
339 * java.lang.String)
340 *
341 * <p>If the handler is not null and there is a security manager,
342 * the security manager's {@code checkPermission}
343 * method is called with a
344 * {@code NetPermission("specifyStreamHandler")} permission.
345 * This may result in a SecurityException.
346 *
347 * No validation of the inputs is performed by this constructor.
348 *
349 * @param protocol the name of the protocol to use.
350 * @param host the name of the host.
351 * @param port the port number on the host.
352 * @param file the file on the host
353 * @param handler the stream handler for the URL.
354 * @exception MalformedURLException if an unknown protocol is specified.
355 * @exception SecurityException
356 * if a security manager exists and its
357 * {@code checkPermission} method doesn't allow
358 * specifying a stream handler explicitly.
359 * @see java.lang.System#getProperty(java.lang.String)
360 * @see java.net.URL#setURLStreamHandlerFactory(
361 * java.net.URLStreamHandlerFactory)
362 * @see java.net.URLStreamHandler
363 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler(
364 * java.lang.String)
365 * @see SecurityManager#checkPermission
366 * @see java.net.NetPermission
367 */
368 public URL(String protocol, String host, int port, String file,
369 URLStreamHandler handler) throws MalformedURLException {
370 if (handler != null) {
371 SecurityManager sm = System.getSecurityManager();
372 if (sm != null) {
373 // check for permission to specify a handler
374 checkSpecifyHandler(sm);
375 }
376 }
377
378 protocol = protocol.toLowerCase();
379 this.protocol = protocol;
380 if (host != null) {
381
382 /**
383 * if host is a literal IPv6 address,
384 * we will make it conform to RFC 2732
385 */
386 if (host.indexOf(':') >= 0 && !host.startsWith("[")) {
387 host = "["+host+"]";
388 }
389 this.host = host;
390
391 if (port < -1) {
392 throw new MalformedURLException("Invalid port number :" +
393 port);
394 }
395 this.port = port;
396 authority = (port == -1) ? host : host + ":" + port;
397 }
398
399 Parts parts = new Parts(file);
400 path = parts.getPath();
401 query = parts.getQuery();
402
403 if (query != null) {
404 this.file = path + "?" + query;
405 } else {
406 this.file = path;
407 }
408 ref = parts.getRef();
409
410 // Note: we don't do validation of the URL here. Too risky to change
411 // right now, but worth considering for future reference. -br
412 if (handler == null &&
413 (handler = getURLStreamHandler(protocol)) == null) {
414 throw new MalformedURLException("unknown protocol: " + protocol);
415 }
416 this.handler = handler;
417 }
418
419 /**
420 * Creates a {@code URL} object from the {@code String}
421 * representation.
422 * <p>
423 * This constructor is equivalent to a call to the two-argument
424 * constructor with a {@code null} first argument.
425 *
426 * @param spec the {@code String} to parse as a URL.
427 * @exception MalformedURLException if no protocol is specified, or an
428 * unknown protocol is found, or {@code spec} is {@code null}.
429 * @see java.net.URL#URL(java.net.URL, java.lang.String)
430 */
431 public URL(String spec) throws MalformedURLException {
432 this(null, spec);
433 }
434
435 /**
436 * Creates a URL by parsing the given spec within a specified context.
437 *
438 * The new URL is created from the given context URL and the spec
439 * argument as described in
440 * RFC2396 "Uniform Resource Identifiers : Generic * Syntax" :
441 * <blockquote><pre>
442 * <scheme>://<authority><path>?<query>#<fragment>
443 * </pre></blockquote>
444 * The reference is parsed into the scheme, authority, path, query and
445 * fragment parts. If the path component is empty and the scheme,
446 * authority, and query components are undefined, then the new URL is a
447 * reference to the current document. Otherwise, the fragment and query
448 * parts present in the spec are used in the new URL.
449 * <p>
450 * If the scheme component is defined in the given spec and does not match
451 * the scheme of the context, then the new URL is created as an absolute
452 * URL based on the spec alone. Otherwise the scheme component is inherited
453 * from the context URL.
454 * <p>
455 * If the authority component is present in the spec then the spec is
456 * treated as absolute and the spec authority and path will replace the
457 * context authority and path. If the authority component is absent in the
458 * spec then the authority of the new URL will be inherited from the
459 * context.
460 * <p>
461 * If the spec's path component begins with a slash character
462 * "/" then the
463 * path is treated as absolute and the spec path replaces the context path.
464 * <p>
465 * Otherwise, the path is treated as a relative path and is appended to the
466 * context path, as described in RFC2396. Also, in this case,
467 * the path is canonicalized through the removal of directory
468 * changes made by occurences of ".." and ".".
469 * <p>
470 * For a more detailed description of URL parsing, refer to RFC2396.
471 *
472 * @param context the context in which to parse the specification.
473 * @param spec the {@code String} to parse as a URL.
474 * @exception MalformedURLException if no protocol is specified, or an
475 * unknown protocol is found, or {@code spec} is {@code null}.
476 * @see java.net.URL#URL(java.lang.String, java.lang.String,
477 * int, java.lang.String)
478 * @see java.net.URLStreamHandler
479 * @see java.net.URLStreamHandler#parseURL(java.net.URL,
480 * java.lang.String, int, int)
481 */
482 public URL(URL context, String spec) throws MalformedURLException {
483 this(context, spec, null);
484 }
485
486 /**
487 * Creates a URL by parsing the given spec with the specified handler
488 * within a specified context. If the handler is null, the parsing
489 * occurs as with the two argument constructor.
490 *
491 * @param context the context in which to parse the specification.
492 * @param spec the {@code String} to parse as a URL.
493 * @param handler the stream handler for the URL.
494 * @exception MalformedURLException if no protocol is specified, or an
495 * unknown protocol is found, or {@code spec} is {@code null}.
496 * @exception SecurityException
497 * if a security manager exists and its
498 * {@code checkPermission} method doesn't allow
499 * specifying a stream handler.
500 * @see java.net.URL#URL(java.lang.String, java.lang.String,
501 * int, java.lang.String)
502 * @see java.net.URLStreamHandler
503 * @see java.net.URLStreamHandler#parseURL(java.net.URL,
504 * java.lang.String, int, int)
505 */
506 public URL(URL context, String spec, URLStreamHandler handler)
507 throws MalformedURLException
508 {
509 String original = spec;
510 int i, limit, c;
511 int start = 0;
512 String newProtocol = null;
513 boolean aRef=false;
514 boolean isRelative = false;
515
516 // Check for permission to specify a handler
517 if (handler != null) {
518 SecurityManager sm = System.getSecurityManager();
519 if (sm != null) {
520 checkSpecifyHandler(sm);
521 }
522 }
523
524 try {
525 limit = spec.length();
526 while ((limit > 0) && (spec.charAt(limit - 1) <= ' ')) {
527 limit--; //eliminate trailing whitespace
528 }
529 while ((start < limit) && (spec.charAt(start) <= ' ')) {
530 start++; // eliminate leading whitespace
531 }
532
533 if (spec.regionMatches(true, start, "url:", 0, 4)) {
534 start += 4;
535 }
536 if (start < spec.length() && spec.charAt(start) == '#') {
537 /* we're assuming this is a ref relative to the context URL.
538 * This means protocols cannot start w/ '#', but we must parse
539 * ref URL's like: "hello:there" w/ a ':' in them.
540 */
541 aRef=true;
542 }
543 for (i = start ; !aRef && (i < limit) &&
544 ((c = spec.charAt(i)) != '/') ; i++) {
545 if (c == ':') {
546
547 String s = spec.substring(start, i).toLowerCase();
548 if (isValidProtocol(s)) {
549 newProtocol = s;
550 start = i + 1;
551 }
552 break;
553 }
554 }
555
556 // Only use our context if the protocols match.
557 protocol = newProtocol;
558 if ((context != null) && ((newProtocol == null) ||
559 newProtocol.equalsIgnoreCase(context.protocol))) {
560 // inherit the protocol handler from the context
561 // if not specified to the constructor
562 if (handler == null) {
563 handler = context.handler;
564 }
565
566 // If the context is a hierarchical URL scheme and the spec
567 // contains a matching scheme then maintain backwards
568 // compatibility and treat it as if the spec didn't contain
569 // the scheme; see 5.2.3 of RFC2396
570 if (context.path != null && context.path.startsWith("/"))
571 newProtocol = null;
572
573 if (newProtocol == null) {
574 protocol = context.protocol;
575 authority = context.authority;
576 userInfo = context.userInfo;
577 host = context.host;
578 port = context.port;
579 file = context.file;
580 path = context.path;
581 isRelative = true;
582 }
583 }
584
585 if (protocol == null) {
586 throw new MalformedURLException("no protocol: "+original);
587 }
588
589 // Get the protocol handler if not specified or the protocol
590 // of the context could not be used
591 if (handler == null &&
592 (handler = getURLStreamHandler(protocol)) == null) {
593 throw new MalformedURLException("unknown protocol: "+protocol);
594 }
595
596 this.handler = handler;
597
598 i = spec.indexOf('#', start);
599 if (i >= 0) {
600 ref = spec.substring(i + 1, limit);
601 limit = i;
602 }
603
604 /*
605 * Handle special case inheritance of query and fragment
606 * implied by RFC2396 section 5.2.2.
607 */
608 if (isRelative && start == limit) {
609 query = context.query;
610 if (ref == null) {
611 ref = context.ref;
612 }
613 }
614
615 handler.parseURL(this, spec, start, limit);
616
617 } catch(MalformedURLException e) {
618 throw e;
619 } catch(Exception e) {
620 MalformedURLException exception = new MalformedURLException(e.getMessage());
621 exception.initCause(e);
622 throw exception;
623 }
624 }
625
626 /*
627 * Returns true if specified string is a valid protocol name.
628 */
629 private boolean isValidProtocol(String protocol) {
630 int len = protocol.length();
631 if (len < 1)
632 return false;
633 char c = protocol.charAt(0);
634 if (!Character.isLetter(c))
635 return false;
636 for (int i = 1; i < len; i++) {
637 c = protocol.charAt(i);
638 if (!Character.isLetterOrDigit(c) && c != '.' && c != '+' &&
639 c != '-') {
640 return false;
641 }
642 }
643 return true;
644 }
645
646 /*
647 * Checks for permission to specify a stream handler.
648 */
649 private void checkSpecifyHandler(SecurityManager sm) {
650 sm.checkPermission(SecurityConstants.SPECIFY_HANDLER_PERMISSION);
651 }
652
653 /**
654 * Sets the fields of the URL. This is not a public method so that
655 * only URLStreamHandlers can modify URL fields. URLs are
656 * otherwise constant.
657 *
658 * @param protocol the name of the protocol to use
659 * @param host the name of the host
660 @param port the port number on the host
661 * @param file the file on the host
662 * @param ref the internal reference in the URL
663 */
664 void set(String protocol, String host, int port,
665 String file, String ref) {
666 synchronized (this) {
667 this.protocol = protocol;
668 this.host = host;
669 authority = port == -1 ? host : host + ":" + port;
670 this.port = port;
671 this.file = file;
672 this.ref = ref;
673 /* This is very important. We must recompute this after the
674 * URL has been changed. */
675 hashCode = -1;
676 hostAddress = null;
677 int q = file.lastIndexOf('?');
678 if (q != -1) {
679 query = file.substring(q+1);
680 path = file.substring(0, q);
681 } else
682 path = file;
683 }
684 }
685
686 /**
687 * Sets the specified 8 fields of the URL. This is not a public method so
688 * that only URLStreamHandlers can modify URL fields. URLs are otherwise
689 * constant.
690 *
691 * @param protocol the name of the protocol to use
692 * @param host the name of the host
693 * @param port the port number on the host
694 * @param authority the authority part for the url
695 * @param userInfo the username and password
696 * @param path the file on the host
697 * @param ref the internal reference in the URL
698 * @param query the query part of this URL
699 * @since 1.3
700 */
701 void set(String protocol, String host, int port,
702 String authority, String userInfo, String path,
703 String query, String ref) {
704 synchronized (this) {
705 this.protocol = protocol;
706 this.host = host;
707 this.port = port;
708 this.file = query == null ? path : path + "?" + query;
709 this.userInfo = userInfo;
710 this.path = path;
711 this.ref = ref;
712 /* This is very important. We must recompute this after the
713 * URL has been changed. */
714 hashCode = -1;
715 hostAddress = null;
716 this.query = query;
717 this.authority = authority;
718 }
719 }
720
721 /**
722 * Gets the query part of this {@code URL}.
723 *
724 * @return the query part of this {@code URL},
725 * or <CODE>null</CODE> if one does not exist
726 * @since 1.3
727 */
728 public String getQuery() {
729 return query;
730 }
731
732 /**
733 * Gets the path part of this {@code URL}.
734 *
735 * @return the path part of this {@code URL}, or an
736 * empty string if one does not exist
737 * @since 1.3
738 */
739 public String getPath() {
740 return path;
741 }
742
743 /**
744 * Gets the userInfo part of this {@code URL}.
745 *
746 * @return the userInfo part of this {@code URL}, or
747 * <CODE>null</CODE> if one does not exist
748 * @since 1.3
749 */
750 public String getUserInfo() {
751 return userInfo;
752 }
753
754 /**
755 * Gets the authority part of this {@code URL}.
756 *
757 * @return the authority part of this {@code URL}
758 * @since 1.3
759 */
760 public String getAuthority() {
761 return authority;
762 }
763
764 /**
765 * Gets the port number of this {@code URL}.
766 *
767 * @return the port number, or -1 if the port is not set
768 */
769 public int getPort() {
770 return port;
771 }
772
773 /**
774 * Gets the default port number of the protocol associated
775 * with this {@code URL}. If the URL scheme or the URLStreamHandler
776 * for the URL do not define a default port number,
777 * then -1 is returned.
778 *
779 * @return the port number
780 * @since 1.4
781 */
782 public int getDefaultPort() {
783 return handler.getDefaultPort();
784 }
785
786 /**
787 * Gets the protocol name of this {@code URL}.
788 *
789 * @return the protocol of this {@code URL}.
790 */
791 public String getProtocol() {
792 return protocol;
793 }
794
795 /**
796 * Gets the host name of this {@code URL}, if applicable.
797 * The format of the host conforms to RFC 2732, i.e. for a
798 * literal IPv6 address, this method will return the IPv6 address
799 * enclosed in square brackets ({@code '['} and {@code ']'}).
800 *
801 * @return the host name of this {@code URL}.
802 */
803 public String getHost() {
804 return host;
805 }
806
807 /**
808 * Gets the file name of this {@code URL}.
809 * The returned file portion will be
810 * the same as <CODE>getPath()</CODE>, plus the concatenation of
811 * the value of <CODE>getQuery()</CODE>, if any. If there is
812 * no query portion, this method and <CODE>getPath()</CODE> will
813 * return identical results.
814 *
815 * @return the file name of this {@code URL},
816 * or an empty string if one does not exist
817 */
818 public String getFile() {
819 return file;
820 }
821
822 /**
823 * Gets the anchor (also known as the "reference") of this
824 * {@code URL}.
825 *
826 * @return the anchor (also known as the "reference") of this
827 * {@code URL}, or <CODE>null</CODE> if one does not exist
828 */
829 public String getRef() {
830 return ref;
831 }
832
833 /**
834 * Compares this URL for equality with another object.<p>
835 *
836 * If the given object is not a URL then this method immediately returns
837 * {@code false}.<p>
838 *
839 * Two URL objects are equal if they have the same protocol, reference
840 * equivalent hosts, have the same port number on the host, and the same
841 * file and fragment of the file.<p>
842 *
843 * Two hosts are considered equivalent if both host names can be resolved
844 * into the same IP addresses; else if either host name can't be
845 * resolved, the host names must be equal without regard to case; or both
846 * host names equal to null.<p>
847 *
848 * Since hosts comparison requires name resolution, this operation is a
849 * blocking operation. <p>
850 *
851 * Note: The defined behavior for {@code equals} is known to
852 * be inconsistent with virtual hosting in HTTP.
853 *
854 * @param obj the URL to compare against.
855 * @return {@code true} if the objects are the same;
856 * {@code false} otherwise.
857 */
858 public boolean equals(Object obj) {
859 if (!(obj instanceof URL))
860 return false;
861 URL u2 = (URL)obj;
862
863 return handler.equals(this, u2);
864 }
865
866 /**
867 * Creates an integer suitable for hash table indexing.<p>
868 *
869 * The hash code is based upon all the URL components relevant for URL
870 * comparison. As such, this operation is a blocking operation.<p>
871 *
872 * @return a hash code for this {@code URL}.
873 */
874 public synchronized int hashCode() {
875 if (hashCode != -1)
876 return hashCode;
877
878 hashCode = handler.hashCode(this);
879 return hashCode;
880 }
881
882 /**
883 * Compares two URLs, excluding the fragment component.<p>
884 *
885 * Returns {@code true} if this {@code URL} and the
886 * {@code other} argument are equal without taking the
887 * fragment component into consideration.
888 *
889 * @param other the {@code URL} to compare against.
890 * @return {@code true} if they reference the same remote object;
891 * {@code false} otherwise.
892 */
893 public boolean sameFile(URL other) {
894 return handler.sameFile(this, other);
895 }
896
897 /**
898 * Constructs a string representation of this {@code URL}. The
899 * string is created by calling the {@code toExternalForm}
900 * method of the stream protocol handler for this object.
901 *
902 * @return a string representation of this object.
903 * @see java.net.URL#URL(java.lang.String, java.lang.String, int,
904 * java.lang.String)
905 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL)
906 */
907 public String toString() {
908 return toExternalForm();
909 }
910
911 /**
912 * Constructs a string representation of this {@code URL}. The
913 * string is created by calling the {@code toExternalForm}
914 * method of the stream protocol handler for this object.
915 *
916 * @return a string representation of this object.
917 * @see java.net.URL#URL(java.lang.String, java.lang.String,
918 * int, java.lang.String)
919 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL)
920 */
921 public String toExternalForm() {
922 return handler.toExternalForm(this);
923 }
924
925 /**
926 * Returns a {@link java.net.URI} equivalent to this URL.
927 * This method functions in the same way as {@code new URI (this.toString())}.
928 * <p>Note, any URL instance that complies with RFC 2396 can be converted
929 * to a URI. However, some URLs that are not strictly in compliance
930 * can not be converted to a URI.
931 *
932 * @exception URISyntaxException if this URL is not formatted strictly according to
933 * to RFC2396 and cannot be converted to a URI.
934 *
935 * @return a URI instance equivalent to this URL.
936 * @since 1.5
937 */
938 public URI toURI() throws URISyntaxException {
939 return new URI (toString());
940 }
941
942 /**
943 * Returns a {@link java.net.URLConnection URLConnection} instance that
944 * represents a connection to the remote object referred to by the
945 * {@code URL}.
946 *
947 * <P>A new instance of {@linkplain java.net.URLConnection URLConnection} is
948 * created every time when invoking the
949 * {@linkplain java.net.URLStreamHandler#openConnection(URL)
950 * URLStreamHandler.openConnection(URL)} method of the protocol handler for
951 * this URL.</P>
952 *
953 * <P>It should be noted that a URLConnection instance does not establish
954 * the actual network connection on creation. This will happen only when
955 * calling {@linkplain java.net.URLConnection#connect() URLConnection.connect()}.</P>
956 *
957 * <P>If for the URL's protocol (such as HTTP or JAR), there
958 * exists a public, specialized URLConnection subclass belonging
959 * to one of the following packages or one of their subpackages:
960 * java.lang, java.io, java.util, java.net, the connection
961 * returned will be of that subclass. For example, for HTTP an
962 * HttpURLConnection will be returned, and for JAR a
963 * JarURLConnection will be returned.</P>
964 *
965 * @return a {@link java.net.URLConnection URLConnection} linking
966 * to the URL.
967 * @exception IOException if an I/O exception occurs.
968 * @see java.net.URL#URL(java.lang.String, java.lang.String,
969 * int, java.lang.String)
970 */
971 public URLConnection openConnection() throws java.io.IOException {
972 return handler.openConnection(this);
973 }
974
975 /**
976 * Same as {@link #openConnection()}, except that the connection will be
977 * made through the specified proxy; Protocol handlers that do not
978 * support proxing will ignore the proxy parameter and make a
979 * normal connection.
980 *
981 * Invoking this method preempts the system's default ProxySelector
982 * settings.
983 *
984 * @param proxy the Proxy through which this connection
985 * will be made. If direct connection is desired,
986 * Proxy.NO_PROXY should be specified.
987 * @return a {@code URLConnection} to the URL.
988 * @exception IOException if an I/O exception occurs.
989 * @exception SecurityException if a security manager is present
990 * and the caller doesn't have permission to connect
991 * to the proxy.
992 * @exception IllegalArgumentException will be thrown if proxy is null,
993 * or proxy has the wrong type
994 * @exception UnsupportedOperationException if the subclass that
995 * implements the protocol handler doesn't support
996 * this method.
997 * @see java.net.URL#URL(java.lang.String, java.lang.String,
998 * int, java.lang.String)
999 * @see java.net.URLConnection
1000 * @see java.net.URLStreamHandler#openConnection(java.net.URL,
1001 * java.net.Proxy)
1002 * @since 1.5
1003 */
1004 public URLConnection openConnection(Proxy proxy)
1005 throws java.io.IOException {
1006 if (proxy == null) {
1007 throw new IllegalArgumentException("proxy can not be null");
1008 }
1009
1010 // Create a copy of Proxy as a security measure
1011 Proxy p = proxy == Proxy.NO_PROXY ? Proxy.NO_PROXY : sun.net.ApplicationProxy.create(proxy);
1012 SecurityManager sm = System.getSecurityManager();
1013 if (p.type() != Proxy.Type.DIRECT && sm != null) {
1014 InetSocketAddress epoint = (InetSocketAddress) p.address();
1015 if (epoint.isUnresolved())
1016 sm.checkConnect(epoint.getHostName(), epoint.getPort());
1017 else
1018 sm.checkConnect(epoint.getAddress().getHostAddress(),
1019 epoint.getPort());
1020 }
1021 return handler.openConnection(this, p);
1022 }
1023
1024 /**
1025 * Opens a connection to this {@code URL} and returns an
1026 * {@code InputStream} for reading from that connection. This
1027 * method is a shorthand for:
1028 * <blockquote><pre>
1029 * openConnection().getInputStream()
1030 * </pre></blockquote>
1031 *
1032 * @return an input stream for reading from the URL connection.
1033 * @exception IOException if an I/O exception occurs.
1034 * @see java.net.URL#openConnection()
1035 * @see java.net.URLConnection#getInputStream()
1036 */
1037 public final InputStream openStream() throws java.io.IOException {
1038 return openConnection().getInputStream();
1039 }
1040
1041 /**
1042 * Gets the contents of this URL. This method is a shorthand for:
1043 * <blockquote><pre>
1044 * openConnection().getContent()
1045 * </pre></blockquote>
1046 *
1047 * @return the contents of this URL.
1048 * @exception IOException if an I/O exception occurs.
1049 * @see java.net.URLConnection#getContent()
1050 */
1051 public final Object getContent() throws java.io.IOException {
1052 return openConnection().getContent();
1053 }
1054
1055 /**
1056 * Gets the contents of this URL. This method is a shorthand for:
1057 * <blockquote><pre>
1058 * openConnection().getContent(Class[])
1059 * </pre></blockquote>
1060 *
1061 * @param classes an array of Java types
1062 * @return the content object of this URL that is the first match of
1063 * the types specified in the classes array.
1064 * null if none of the requested types are supported.
1065 * @exception IOException if an I/O exception occurs.
1066 * @see java.net.URLConnection#getContent(Class[])
1067 * @since 1.3
1068 */
1069 public final Object getContent(Class[] classes)
1070 throws java.io.IOException {
1071 return openConnection().getContent(classes);
1072 }
1073
1074 /**
1075 * The URLStreamHandler factory.
1076 */
1077 static URLStreamHandlerFactory factory;
1078
1079 /**
1080 * Sets an application's {@code URLStreamHandlerFactory}.
1081 * This method can be called at most once in a given Java Virtual
1082 * Machine.
1083 *
1084 *<p> The {@code URLStreamHandlerFactory} instance is used to
1085 *construct a stream protocol handler from a protocol name.
1086 *
1087 * <p> If there is a security manager, this method first calls
1088 * the security manager's {@code checkSetFactory} method
1089 * to ensure the operation is allowed.
1090 * This could result in a SecurityException.
1091 *
1092 * @param fac the desired factory.
1093 * @exception Error if the application has already set a factory.
1094 * @exception SecurityException if a security manager exists and its
1095 * {@code checkSetFactory} method doesn't allow
1096 * the operation.
1097 * @see java.net.URL#URL(java.lang.String, java.lang.String,
1098 * int, java.lang.String)
1099 * @see java.net.URLStreamHandlerFactory
1100 * @see SecurityManager#checkSetFactory
1101 */
1102 public static void setURLStreamHandlerFactory(URLStreamHandlerFactory fac) {
1103 synchronized (streamHandlerLock) {
1104 if (factory != null) {
1105 throw new Error("factory already defined");
1106 }
1107 SecurityManager security = System.getSecurityManager();
1108 if (security != null) {
1109 security.checkSetFactory();
1110 }
1111 handlers.clear();
1112 factory = fac;
1113 }
1114 }
1115
1116 /**
1117 * A table of protocol handlers.
1118 */
1119 static Hashtable<String,URLStreamHandler> handlers = new Hashtable<>();
1120 private static Object streamHandlerLock = new Object();
1121
1122 /**
1123 * Returns the Stream Handler.
1124 * @param protocol the protocol to use
1125 */
1126 static URLStreamHandler getURLStreamHandler(String protocol) {
1127
1128 URLStreamHandler handler = handlers.get(protocol);
1129 if (handler == null) {
1130
1131 boolean checkedWithFactory = false;
1132
1133 // Use the factory (if any)
1134 if (factory != null) {
1135 handler = factory.createURLStreamHandler(protocol);
1136 checkedWithFactory = true;
1137 }
1138
1139 // Try java protocol handler
1140 if (handler == null) {
1141 String packagePrefixList = null;
1142
1143 packagePrefixList
1144 = java.security.AccessController.doPrivileged(
1145 new sun.security.action.GetPropertyAction(
1146 protocolPathProp,""));
1147 if (packagePrefixList != "") {
1148 packagePrefixList += "|";
1149 }
1150
1151 // REMIND: decide whether to allow the "null" class prefix
1152 // or not.
1153 packagePrefixList += "sun.net.www.protocol";
1154
1155 StringTokenizer packagePrefixIter =
1156 new StringTokenizer(packagePrefixList, "|");
1157
1158 while (handler == null &&
1159 packagePrefixIter.hasMoreTokens()) {
1160
1161 String packagePrefix =
1162 packagePrefixIter.nextToken().trim();
1163 try {
1164 String clsName = packagePrefix + "." + protocol +
1165 ".Handler";
1166 Class<?> cls = null;
1167 try {
1168 cls = Class.forName(clsName);
1169 } catch (ClassNotFoundException e) {
1170 ClassLoader cl = ClassLoader.getSystemClassLoader();
1171 if (cl != null) {
1172 cls = cl.loadClass(clsName);
1173 }
1174 }
1175 if (cls != null) {
1176 handler =
1177 (URLStreamHandler)cls.newInstance();
1178 }
1179 } catch (Exception e) {
1180 // any number of exceptions can get thrown here
1181 }
1182 }
1183 }
1184
1185 synchronized (streamHandlerLock) {
1186
1187 URLStreamHandler handler2 = null;
1188
1189 // Check again with hashtable just in case another
1190 // thread created a handler since we last checked
1191 handler2 = handlers.get(protocol);
1192
1193 if (handler2 != null) {
1194 return handler2;
1195 }
1196
1197 // Check with factory if another thread set a
1198 // factory since our last check
1199 if (!checkedWithFactory && factory != null) {
1200 handler2 = factory.createURLStreamHandler(protocol);
1201 }
1202
1203 if (handler2 != null) {
1204 // The handler from the factory must be given more
1205 // importance. Discard the default handler that
1206 // this thread created.
1207 handler = handler2;
1208 }
1209
1210 // Insert this handler into the hashtable
1211 if (handler != null) {
1212 handlers.put(protocol, handler);
1213 }
1214
1215 }
1216 }
1217
1218 return handler;
1219
1220 }
1221
1222 /**
1223 * WriteObject is called to save the state of the URL to an
1224 * ObjectOutputStream. The handler is not saved since it is
1225 * specific to this system.
1226 *
1227 * @serialData the default write object value. When read back in,
1228 * the reader must ensure that calling getURLStreamHandler with
1229 * the protocol variable returns a valid URLStreamHandler and
1230 * throw an IOException if it does not.
1231 */
1232 private synchronized void writeObject(java.io.ObjectOutputStream s)
1233 throws IOException
1234 {
1235 s.defaultWriteObject(); // write the fields
1236 }
1237
1238 /**
1239 * readObject is called to restore the state of the URL from the
1240 * stream. It reads the components of the URL and finds the local
1241 * stream handler.
1242 */
1243 private synchronized void readObject(java.io.ObjectInputStream s)
1244 throws IOException, ClassNotFoundException
1245 {
1246 s.defaultReadObject(); // read the fields
1247 if ((handler = getURLStreamHandler(protocol)) == null) {
1248 throw new IOException("unknown protocol: " + protocol);
1249 }
1250
1251 // Construct authority part
1252 if (authority == null &&
1253 ((host != null && host.length() > 0) || port != -1)) {
1254 if (host == null)
1255 host = "";
1256 authority = (port == -1) ? host : host + ":" + port;
1257
1258 // Handle hosts with userInfo in them
1259 int at = host.lastIndexOf('@');
1260 if (at != -1) {
1261 userInfo = host.substring(0, at);
1262 host = host.substring(at+1);
1263 }
1264 } else if (authority != null) {
1265 // Construct user info part
1266 int ind = authority.indexOf('@');
1267 if (ind != -1)
1268 userInfo = authority.substring(0, ind);
1269 }
1270
1271 // Construct path and query part
1272 path = null;
1273 query = null;
1274 if (file != null) {
1275 // Fix: only do this if hierarchical?
1276 int q = file.lastIndexOf('?');
1277 if (q != -1) {
1278 query = file.substring(q+1);
1279 path = file.substring(0, q);
1280 } else
1281 path = file;
1282 }
1283 }
1284 }
1285
1286 class Parts {
1287 String path, query, ref;
1288
1289 Parts(String file) {
1290 int ind = file.indexOf('#');
1291 ref = ind < 0 ? null: file.substring(ind + 1);
1292 file = ind < 0 ? file: file.substring(0, ind);
1293 int q = file.lastIndexOf('?');
1294 if (q != -1) {
1295 query = file.substring(q+1);
1296 path = file.substring(0, q);
1297 } else {
1298 path = file;
1299 }
1300 }
1301
1302 String getPath() {
1303 return path;
1304 }
1305
1306 String getQuery() {
1307 return query;
1308 }
1309
1310 String getRef() {
1311 return ref;
1312 }
1313 }