1 /*
2 * Copyright (c) 1995, 2008, 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.io.OutputStream;
31 import java.util.Hashtable;
32 import java.util.StringTokenizer;
33 import sun.security.util.SecurityConstants;
34
35 /**
36 * Class <code>URL</code> represents a Uniform Resource
37 * Locator, a pointer to a "resource" on the World
38 * Wide Web. A resource can be something as simple as a file or a
39 * directory, or it can be a reference to a more complicated object,
40 * such as a query to a database or to a search engine. More
41 * information on the types of URLs and their formats can be found at:
42 * <blockquote>
43 * <a href="http://www.socs.uts.edu.au/MosaicDocs-old/url-primer.html">
44 * <i>http://www.socs.uts.edu.au/MosaicDocs-old/url-primer.html</i></a>
45 * </blockquote>
46 * <p>
47 * In general, a URL can be broken into several parts. The previous
48 * example of a URL indicates that the protocol to use is
49 * <code>http</code> (HyperText Transfer Protocol) and that the
50 * information resides on a host machine named
51 * <code>www.socs.uts.edu.au</code>. The information on that host
52 * machine is named <code>/MosaicDocs-old/url-primer.html</code>. The exact
53 * meaning of this name on the host machine is both protocol
54 * dependent and host dependent. The information normally resides in
55 * a file, but it could be generated on the fly. This component of
56 * the URL is called the <i>path</i> component.
57 * <p>
58 * A URL can optionally specify a "port", which is the
59 * port number to which the TCP connection is made on the remote host
60 * machine. If the port is not specified, the default port for
61 * the protocol is used instead. For example, the default port for
62 * <code>http</code> is <code>80</code>. An alternative port could be
63 * specified as:
64 * <blockquote><pre>
65 * http://www.socs.uts.edu.au:80/MosaicDocs-old/url-primer.html
66 * </pre></blockquote>
67 * <p>
68 * The syntax of <code>URL</code> is defined by <a
69 * href="http://www.ietf.org/rfc/rfc2396.txt"><i>RFC 2396: Uniform
70 * Resource Identifiers (URI): Generic Syntax</i></a>, amended by <a
71 * href="http://www.ietf.org/rfc/rfc2732.txt"><i>RFC 2732: Format for
72 * Literal IPv6 Addresses in URLs</i></a>. The Literal IPv6 address format
73 * also supports scope_ids. The syntax and usage of scope_ids is described
74 * <a href="Inet6Address.html#scoped">here</a>.
75 * <p>
76 * A URL may have appended to it a "fragment", also known
77 * as a "ref" or a "reference". The fragment is indicated by the sharp
78 * sign character "#" followed by more characters. For example,
79 * <blockquote><pre>
80 * http://java.sun.com/index.html#chapter1
81 * </pre></blockquote>
82 * <p>
83 * This fragment is not technically part of the URL. Rather, it
84 * indicates that after the specified resource is retrieved, the
85 * application is specifically interested in that part of the
86 * document that has the tag <code>chapter1</code> attached to it. The
87 * meaning of a tag is resource specific.
88 * <p>
89 * An application can also specify a "relative URL",
90 * which contains only enough information to reach the resource
91 * relative to another URL. Relative URLs are frequently used within
92 * HTML pages. For example, if the contents of the URL:
93 * <blockquote><pre>
94 * http://java.sun.com/index.html
95 * </pre></blockquote>
96 * contained within it the relative URL:
97 * <blockquote><pre>
98 * FAQ.html
99 * </pre></blockquote>
100 * it would be a shorthand for:
101 * <blockquote><pre>
102 * http://java.sun.com/FAQ.html
103 * </pre></blockquote>
104 * <p>
105 * The relative URL need not specify all the components of a URL. If
106 * the protocol, host name, or port number is missing, the value is
107 * inherited from the fully specified URL. The file component must be
108 * specified. The optional fragment is not inherited.
109 * <p>
110 * The URL class does not itself encode or decode any URL components
111 * according to the escaping mechanism defined in RFC2396. It is the
112 * responsibility of the caller to encode any fields, which need to be
113 * escaped prior to calling URL, and also to decode any escaped fields,
114 * that are returned from URL. Furthermore, because URL has no knowledge
115 * of URL escaping, it does not recognise equivalence between the encoded
116 * or decoded form of the same URL. For example, the two URLs:<br>
117 * <pre> http://foo.com/hello world/ and http://foo.com/hello%20world</pre>
118 * would be considered not equal to each other.
119 * <p>
120 * Note, the {@link java.net.URI} class does perform escaping of its
121 * component fields in certain circumstances. The recommended way
122 * to manage the encoding and decoding of URLs is to use {@link java.net.URI},
123 * and to convert between these two classes using {@link #toURI()} and
124 * {@link URI#toURL()}.
125 * <p>
126 * The {@link URLEncoder} and {@link URLDecoder} classes can also be
127 * used, but only for HTML form encoding, which is not the same
128 * as the encoding scheme defined in RFC2396.
129 *
130 * @author James Gosling
131 * @since JDK1.0
132 */
133 public final class URL implements java.io.Serializable {
134
135 static final long serialVersionUID = -7627629688361524110L;
136
137 /**
138 * The property which specifies the package prefix list to be scanned
139 * for protocol handlers. The value of this property (if any) should
140 * be a vertical bar delimited list of package names to search through
141 * for a protocol handler to load. The policy of this class is that
142 * all protocol handlers will be in a class called <protocolname>.Handler,
143 * and each package in the list is examined in turn for a matching
144 * handler. If none are found (or the property is not specified), the
145 * default package prefix, sun.net.www.protocol, is used. The search
146 * proceeds from the first package in the list to the last and stops
147 * when a match is found.
148 */
149 private static final String protocolPathProp = "java.protocol.handler.pkgs";
150
151 /**
152 * The protocol to use (ftp, http, nntp, ... etc.) .
153 * @serial
154 */
155 private String protocol;
156
157 /**
158 * The host name to connect to.
159 * @serial
160 */
161 private String host;
162
163 /**
164 * The protocol port to connect to.
165 * @serial
166 */
167 private int port = -1;
168
169 /**
170 * The specified file name on that host. <code>file</code> is
171 * defined as <code>path[?query]</code>
172 * @serial
173 */
174 private String file;
175
176 /**
177 * The query part of this URL.
178 */
179 private transient String query;
180
181 /**
182 * The authority part of this URL.
183 * @serial
184 */
185 private String authority;
186
187 /**
188 * The path part of this URL.
189 */
190 private transient String path;
191
192 /**
193 * The userinfo part of this URL.
194 */
195 private transient String userInfo;
196
197 /**
198 * # reference.
199 * @serial
200 */
201 private String ref;
202
203 /**
204 * The host's IP address, used in equals and hashCode.
205 * Computed on demand. An uninitialized or unknown hostAddress is null.
206 */
207 transient InetAddress hostAddress;
208
209 /**
210 * The URLStreamHandler for this URL.
211 */
212 transient URLStreamHandler handler;
213
214 /* Our hash code.
215 * @serial
216 */
217 private int hashCode = -1;
218
219 /**
220 * Creates a <code>URL</code> object from the specified
221 * <code>protocol</code>, <code>host</code>, <code>port</code>
222 * number, and <code>file</code>.<p>
223 *
224 * <code>host</code> can be expressed as a host name or a literal
225 * IP address. If IPv6 literal address is used, it should be
226 * enclosed in square brackets (<tt>'['</tt> and <tt>']'</tt>), as
227 * specified by <a
228 * href="http://www.ietf.org/rfc/rfc2732.txt">RFC 2732</a>;
229 * However, the literal IPv6 address format defined in <a
230 * href="http://www.ietf.org/rfc/rfc2373.txt"><i>RFC 2373: IP
231 * Version 6 Addressing Architecture</i></a> is also accepted.<p>
232 *
233 * Specifying a <code>port</code> number of <code>-1</code>
234 * indicates that the URL should use the default port for the
235 * protocol.<p>
236 *
237 * If this is the first URL object being created with the specified
238 * protocol, a <i>stream protocol handler</i> object, an instance of
239 * class <code>URLStreamHandler</code>, is created for that protocol:
240 * <ol>
241 * <li>If the application has previously set up an instance of
242 * <code>URLStreamHandlerFactory</code> as the stream handler factory,
243 * then the <code>createURLStreamHandler</code> method of that instance
244 * is called with the protocol string as an argument to create the
245 * stream protocol handler.
246 * <li>If no <code>URLStreamHandlerFactory</code> has yet been set up,
247 * or if the factory's <code>createURLStreamHandler</code> method
248 * returns <code>null</code>, then the constructor finds the
249 * value of the system property:
250 * <blockquote><pre>
251 * java.protocol.handler.pkgs
252 * </pre></blockquote>
253 * If the value of that system property is not <code>null</code>,
254 * it is interpreted as a list of packages separated by a vertical
255 * slash character '<code>|</code>'. The constructor tries to load
256 * the class named:
257 * <blockquote><pre>
258 * <<i>package</i>>.<<i>protocol</i>>.Handler
259 * </pre></blockquote>
260 * where <<i>package</i>> is replaced by the name of the package
261 * and <<i>protocol</i>> is replaced by the name of the protocol.
262 * If this class does not exist, or if the class exists but it is not
263 * a subclass of <code>URLStreamHandler</code>, then the next package
264 * in the list is tried.
265 * <li>If the previous step fails to find a protocol handler, then the
266 * constructor tries to load from a system default package.
267 * <blockquote><pre>
268 * <<i>system default package</i>>.<<i>protocol</i>>.Handler
269 * </pre></blockquote>
270 * If this class does not exist, or if the class exists but it is not a
271 * subclass of <code>URLStreamHandler</code>, then a
272 * <code>MalformedURLException</code> is thrown.
273 * </ol>
274 *
275 * <p>Protocol handlers for the following protocols are guaranteed
276 * to exist on the search path :-
277 * <blockquote><pre>
278 * http, https, ftp, file, and jar
279 * </pre></blockquote>
280 * Protocol handlers for additional protocols may also be
281 * available.
282 *
283 * <p>No validation of the inputs is performed by this constructor.
284 *
285 * @param protocol the name of the protocol to use.
286 * @param host the name of the host.
287 * @param port the port number on the host.
288 * @param file the file on the host
289 * @exception MalformedURLException if an unknown protocol is specified.
290 * @see java.lang.System#getProperty(java.lang.String)
291 * @see java.net.URL#setURLStreamHandlerFactory(
292 * java.net.URLStreamHandlerFactory)
293 * @see java.net.URLStreamHandler
294 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler(
295 * java.lang.String)
296 */
297 public URL(String protocol, String host, int port, String file)
298 throws MalformedURLException
299 {
300 this(protocol, host, port, file, null);
301 }
302
303 /**
304 * Creates a URL from the specified <code>protocol</code>
305 * name, <code>host</code> name, and <code>file</code> name. The
306 * default port for the specified protocol is used.
307 * <p>
308 * This method is equivalent to calling the four-argument
309 * constructor with the arguments being <code>protocol</code>,
310 * <code>host</code>, <code>-1</code>, and <code>file</code>.
311 *
312 * No validation of the inputs is performed by this constructor.
313 *
314 * @param protocol the name of the protocol to use.
315 * @param host the name of the host.
316 * @param file the file on the host.
317 * @exception MalformedURLException if an unknown protocol is specified.
318 * @see java.net.URL#URL(java.lang.String, java.lang.String,
319 * int, java.lang.String)
320 */
321 public URL(String protocol, String host, String file)
322 throws MalformedURLException {
323 this(protocol, host, -1, file);
324 }
325
326 /**
327 * Creates a <code>URL</code> object from the specified
328 * <code>protocol</code>, <code>host</code>, <code>port</code>
329 * number, <code>file</code>, and <code>handler</code>. Specifying
330 * a <code>port</code> number of <code>-1</code> indicates that
331 * the URL should use the default port for the protocol. Specifying
332 * a <code>handler</code> of <code>null</code> indicates that the URL
333 * should use a default stream handler for the protocol, as outlined
334 * for:
335 * java.net.URL#URL(java.lang.String, java.lang.String, int,
336 * java.lang.String)
337 *
338 * <p>If the handler is not null and there is a security manager,
339 * the security manager's <code>checkPermission</code>
340 * method is called with a
341 * <code>NetPermission("specifyStreamHandler")</code> permission.
342 * This may result in a SecurityException.
343 *
344 * No validation of the inputs is performed by this constructor.
345 *
346 * @param protocol the name of the protocol to use.
347 * @param host the name of the host.
348 * @param port the port number on the host.
349 * @param file the file on the host
350 * @param handler the stream handler for the URL.
351 * @exception MalformedURLException if an unknown protocol is specified.
352 * @exception SecurityException
353 * if a security manager exists and its
354 * <code>checkPermission</code> method doesn't allow
355 * specifying a stream handler explicitly.
356 * @see java.lang.System#getProperty(java.lang.String)
357 * @see java.net.URL#setURLStreamHandlerFactory(
358 * java.net.URLStreamHandlerFactory)
359 * @see java.net.URLStreamHandler
360 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler(
361 * java.lang.String)
362 * @see SecurityManager#checkPermission
363 * @see java.net.NetPermission
364 */
365 public URL(String protocol, String host, int port, String file,
366 URLStreamHandler handler) throws MalformedURLException {
367 if (handler != null) {
368 SecurityManager sm = System.getSecurityManager();
369 if (sm != null) {
370 // check for permission to specify a handler
371 checkSpecifyHandler(sm);
372 }
373 }
374
375 protocol = protocol.toLowerCase();
376 this.protocol = protocol;
377 if (host != null) {
378
379 /**
380 * if host is a literal IPv6 address,
381 * we will make it conform to RFC 2732
382 */
383 if (host.indexOf(':') >= 0 && !host.startsWith("[")) {
384 host = "["+host+"]";
385 }
386 this.host = host;
387
388 if (port < -1) {
389 throw new MalformedURLException("Invalid port number :" +
390 port);
391 }
392 this.port = port;
393 authority = (port == -1) ? host : host + ":" + port;
394 }
395
396 Parts parts = new Parts(file);
397 path = parts.getPath();
398 query = parts.getQuery();
399
400 if (query != null) {
401 this.file = path + "?" + query;
402 } else {
403 this.file = path;
404 }
405 ref = parts.getRef();
406
407 // Note: we don't do validation of the URL here. Too risky to change
408 // right now, but worth considering for future reference. -br
409 if (handler == null &&
410 (handler = getURLStreamHandler(protocol)) == null) {
411 throw new MalformedURLException("unknown protocol: " + protocol);
412 }
413 this.handler = handler;
414 }
415
416 /**
417 * Creates a <code>URL</code> object from the <code>String</code>
418 * representation.
419 * <p>
420 * This constructor is equivalent to a call to the two-argument
421 * constructor with a <code>null</code> first argument.
422 *
423 * @param spec the <code>String</code> to parse as a URL.
424 * @exception MalformedURLException if no protocol is specified, or an
425 * unknown protocol is found, or <tt>spec</tt> is <tt>null</tt>.
426 * @see java.net.URL#URL(java.net.URL, java.lang.String)
427 */
428 public URL(String spec) throws MalformedURLException {
429 this(null, spec);
430 }
431
432 /**
433 * Creates a URL by parsing the given spec within a specified context.
434 *
435 * The new URL is created from the given context URL and the spec
436 * argument as described in
437 * RFC2396 "Uniform Resource Identifiers : Generic * Syntax" :
438 * <blockquote><pre>
439 * <scheme>://<authority><path>?<query>#<fragment>
440 * </pre></blockquote>
441 * The reference is parsed into the scheme, authority, path, query and
442 * fragment parts. If the path component is empty and the scheme,
443 * authority, and query components are undefined, then the new URL is a
444 * reference to the current document. Otherwise, the fragment and query
445 * parts present in the spec are used in the new URL.
446 * <p>
447 * If the scheme component is defined in the given spec and does not match
448 * the scheme of the context, then the new URL is created as an absolute
449 * URL based on the spec alone. Otherwise the scheme component is inherited
450 * from the context URL.
451 * <p>
452 * If the authority component is present in the spec then the spec is
453 * treated as absolute and the spec authority and path will replace the
454 * context authority and path. If the authority component is absent in the
455 * spec then the authority of the new URL will be inherited from the
456 * context.
457 * <p>
458 * If the spec's path component begins with a slash character
459 * "/" then the
460 * path is treated as absolute and the spec path replaces the context path.
461 * <p>
462 * Otherwise, the path is treated as a relative path and is appended to the
463 * context path, as described in RFC2396. Also, in this case,
464 * the path is canonicalized through the removal of directory
465 * changes made by occurences of ".." and ".".
466 * <p>
467 * For a more detailed description of URL parsing, refer to RFC2396.
468 *
469 * @param context the context in which to parse the specification.
470 * @param spec the <code>String</code> to parse as a URL.
471 * @exception MalformedURLException if no protocol is specified, or an
472 * unknown protocol is found, or <tt>spec</tt> is <tt>null</tt>.
473 * @see java.net.URL#URL(java.lang.String, java.lang.String,
474 * int, java.lang.String)
475 * @see java.net.URLStreamHandler
476 * @see java.net.URLStreamHandler#parseURL(java.net.URL,
477 * java.lang.String, int, int)
478 */
479 public URL(URL context, String spec) throws MalformedURLException {
480 this(context, spec, null);
481 }
482
483 /**
484 * Creates a URL by parsing the given spec with the specified handler
485 * within a specified context. If the handler is null, the parsing
486 * occurs as with the two argument constructor.
487 *
488 * @param context the context in which to parse the specification.
489 * @param spec the <code>String</code> to parse as a URL.
490 * @param handler the stream handler for the URL.
491 * @exception MalformedURLException if no protocol is specified, or an
492 * unknown protocol is found, or <tt>spec</tt> is <tt>null</tt>.
493 * @exception SecurityException
494 * if a security manager exists and its
495 * <code>checkPermission</code> method doesn't allow
496 * specifying a stream handler.
497 * @see java.net.URL#URL(java.lang.String, java.lang.String,
498 * int, java.lang.String)
499 * @see java.net.URLStreamHandler
500 * @see java.net.URLStreamHandler#parseURL(java.net.URL,
501 * java.lang.String, int, int)
502 */
503 public URL(URL context, String spec, URLStreamHandler handler)
504 throws MalformedURLException
505 {
506 String original = spec;
507 int i, limit, c;
508 int start = 0;
509 String newProtocol = null;
510 boolean aRef=false;
511 boolean isRelative = false;
512
513 // Check for permission to specify a handler
514 if (handler != null) {
515 SecurityManager sm = System.getSecurityManager();
516 if (sm != null) {
517 checkSpecifyHandler(sm);
518 }
519 }
520
521 try {
522 limit = spec.length();
523 while ((limit > 0) && (spec.charAt(limit - 1) <= ' ')) {
524 limit--; //eliminate trailing whitespace
525 }
526 while ((start < limit) && (spec.charAt(start) <= ' ')) {
527 start++; // eliminate leading whitespace
528 }
529
530 if (spec.regionMatches(true, start, "url:", 0, 4)) {
531 start += 4;
532 }
533 if (start < spec.length() && spec.charAt(start) == '#') {
534 /* we're assuming this is a ref relative to the context URL.
535 * This means protocols cannot start w/ '#', but we must parse
536 * ref URL's like: "hello:there" w/ a ':' in them.
537 */
538 aRef=true;
539 }
540 for (i = start ; !aRef && (i < limit) &&
541 ((c = spec.charAt(i)) != '/') ; i++) {
542 if (c == ':') {
543
544 String s = spec.substring(start, i).toLowerCase();
545 if (isValidProtocol(s)) {
546 newProtocol = s;
547 start = i + 1;
548 }
549 break;
550 }
551 }
552
553 // Only use our context if the protocols match.
554 protocol = newProtocol;
555 if ((context != null) && ((newProtocol == null) ||
556 newProtocol.equalsIgnoreCase(context.protocol))) {
557 // inherit the protocol handler from the context
558 // if not specified to the constructor
559 if (handler == null) {
560 handler = context.handler;
561 }
562
563 // If the context is a hierarchical URL scheme and the spec
564 // contains a matching scheme then maintain backwards
565 // compatibility and treat it as if the spec didn't contain
566 // the scheme; see 5.2.3 of RFC2396
567 if (context.path != null && context.path.startsWith("/"))
568 newProtocol = null;
569
570 if (newProtocol == null) {
571 protocol = context.protocol;
572 authority = context.authority;
573 userInfo = context.userInfo;
574 host = context.host;
575 port = context.port;
576 file = context.file;
577 path = context.path;
578 isRelative = true;
579 }
580 }
581
582 if (protocol == null) {
583 throw new MalformedURLException("no protocol: "+original);
584 }
585
586 // Get the protocol handler if not specified or the protocol
587 // of the context could not be used
588 if (handler == null &&
589 (handler = getURLStreamHandler(protocol)) == null) {
590 throw new MalformedURLException("unknown protocol: "+protocol);
591 }
592
593 this.handler = handler;
594
595 i = spec.indexOf('#', start);
596 if (i >= 0) {
597 ref = spec.substring(i + 1, limit);
598 limit = i;
599 }
600
601 /*
602 * Handle special case inheritance of query and fragment
603 * implied by RFC2396 section 5.2.2.
604 */
605 if (isRelative && start == limit) {
606 query = context.query;
607 if (ref == null) {
608 ref = context.ref;
609 }
610 }
611
612 handler.parseURL(this, spec, start, limit);
613
614 } catch(MalformedURLException e) {
615 throw e;
616 } catch(Exception e) {
617 MalformedURLException exception = new MalformedURLException(e.getMessage());
618 exception.initCause(e);
619 throw exception;
620 }
621 }
622
623 /*
624 * Returns true if specified string is a valid protocol name.
625 */
626 private boolean isValidProtocol(String protocol) {
627 int len = protocol.length();
628 if (len < 1)
629 return false;
630 char c = protocol.charAt(0);
631 if (!Character.isLetter(c))
632 return false;
633 for (int i = 1; i < len; i++) {
634 c = protocol.charAt(i);
635 if (!Character.isLetterOrDigit(c) && c != '.' && c != '+' &&
636 c != '-') {
637 return false;
638 }
639 }
640 return true;
641 }
642
643 /*
644 * Checks for permission to specify a stream handler.
645 */
646 private void checkSpecifyHandler(SecurityManager sm) {
647 sm.checkPermission(SecurityConstants.SPECIFY_HANDLER_PERMISSION);
648 }
649
650 /**
651 * Sets the fields of the URL. This is not a public method so that
652 * only URLStreamHandlers can modify URL fields. URLs are
653 * otherwise constant.
654 *
655 * @param protocol the name of the protocol to use
656 * @param host the name of the host
657 @param port the port number on the host
658 * @param file the file on the host
659 * @param ref the internal reference in the URL
660 */
661 protected void set(String protocol, String host,
662 int port, String file, String ref) {
663 synchronized (this) {
664 this.protocol = protocol;
665 this.host = host;
666 authority = port == -1 ? host : host + ":" + port;
667 this.port = port;
668 this.file = file;
669 this.ref = ref;
670 /* This is very important. We must recompute this after the
671 * URL has been changed. */
672 hashCode = -1;
673 hostAddress = null;
674 int q = file.lastIndexOf('?');
675 if (q != -1) {
676 query = file.substring(q+1);
677 path = file.substring(0, q);
678 } else
679 path = file;
680 }
681 }
682
683 /**
684 * Sets the specified 8 fields of the URL. This is not a public method so
685 * that only URLStreamHandlers can modify URL fields. URLs are otherwise
686 * constant.
687 *
688 * @param protocol the name of the protocol to use
689 * @param host the name of the host
690 * @param port the port number on the host
691 * @param authority the authority part for the url
692 * @param userInfo the username and password
693 * @param path the file on the host
694 * @param ref the internal reference in the URL
695 * @param query the query part of this URL
696 * @since 1.3
697 */
698 protected void set(String protocol, String host, int port,
699 String authority, String userInfo, String path,
700 String query, String ref) {
701 synchronized (this) {
702 this.protocol = protocol;
703 this.host = host;
704 this.port = port;
705 this.file = query == null ? path : path + "?" + query;
706 this.userInfo = userInfo;
707 this.path = path;
708 this.ref = ref;
709 /* This is very important. We must recompute this after the
710 * URL has been changed. */
711 hashCode = -1;
712 hostAddress = null;
713 this.query = query;
714 this.authority = authority;
715 }
716 }
717
718 /**
719 * Gets the query part of this <code>URL</code>.
720 *
721 * @return the query part of this <code>URL</code>,
722 * or <CODE>null</CODE> if one does not exist
723 * @since 1.3
724 */
725 public String getQuery() {
726 return query;
727 }
728
729 /**
730 * Gets the path part of this <code>URL</code>.
731 *
732 * @return the path part of this <code>URL</code>, or an
733 * empty string if one does not exist
734 * @since 1.3
735 */
736 public String getPath() {
737 return path;
738 }
739
740 /**
741 * Gets the userInfo part of this <code>URL</code>.
742 *
743 * @return the userInfo part of this <code>URL</code>, or
744 * <CODE>null</CODE> if one does not exist
745 * @since 1.3
746 */
747 public String getUserInfo() {
748 return userInfo;
749 }
750
751 /**
752 * Gets the authority part of this <code>URL</code>.
753 *
754 * @return the authority part of this <code>URL</code>
755 * @since 1.3
756 */
757 public String getAuthority() {
758 return authority;
759 }
760
761 /**
762 * Gets the port number of this <code>URL</code>.
763 *
764 * @return the port number, or -1 if the port is not set
765 */
766 public int getPort() {
767 return port;
768 }
769
770 /**
771 * Gets the default port number of the protocol associated
772 * with this <code>URL</code>. If the URL scheme or the URLStreamHandler
773 * for the URL do not define a default port number,
774 * then -1 is returned.
775 *
776 * @return the port number
777 * @since 1.4
778 */
779 public int getDefaultPort() {
780 return handler.getDefaultPort();
781 }
782
783 /**
784 * Gets the protocol name of this <code>URL</code>.
785 *
786 * @return the protocol of this <code>URL</code>.
787 */
788 public String getProtocol() {
789 return protocol;
790 }
791
792 /**
793 * Gets the host name of this <code>URL</code>, if applicable.
794 * The format of the host conforms to RFC 2732, i.e. for a
795 * literal IPv6 address, this method will return the IPv6 address
796 * enclosed in square brackets (<tt>'['</tt> and <tt>']'</tt>).
797 *
798 * @return the host name of this <code>URL</code>.
799 */
800 public String getHost() {
801 return host;
802 }
803
804 /**
805 * Gets the file name of this <code>URL</code>.
806 * The returned file portion will be
807 * the same as <CODE>getPath()</CODE>, plus the concatenation of
808 * the value of <CODE>getQuery()</CODE>, if any. If there is
809 * no query portion, this method and <CODE>getPath()</CODE> will
810 * return identical results.
811 *
812 * @return the file name of this <code>URL</code>,
813 * or an empty string if one does not exist
814 */
815 public String getFile() {
816 return file;
817 }
818
819 /**
820 * Gets the anchor (also known as the "reference") of this
821 * <code>URL</code>.
822 *
823 * @return the anchor (also known as the "reference") of this
824 * <code>URL</code>, or <CODE>null</CODE> if one does not exist
825 */
826 public String getRef() {
827 return ref;
828 }
829
830 /**
831 * Compares this URL for equality with another object.<p>
832 *
833 * If the given object is not a URL then this method immediately returns
834 * <code>false</code>.<p>
835 *
836 * Two URL objects are equal if they have the same protocol, reference
837 * equivalent hosts, have the same port number on the host, and the same
838 * file and fragment of the file.<p>
839 *
840 * Two hosts are considered equivalent if both host names can be resolved
841 * into the same IP addresses; else if either host name can't be
842 * resolved, the host names must be equal without regard to case; or both
843 * host names equal to null.<p>
844 *
845 * Since hosts comparison requires name resolution, this operation is a
846 * blocking operation. <p>
847 *
848 * Note: The defined behavior for <code>equals</code> is known to
849 * be inconsistent with virtual hosting in HTTP.
850 *
851 * @param obj the URL to compare against.
852 * @return <code>true</code> if the objects are the same;
853 * <code>false</code> otherwise.
854 */
855 public boolean equals(Object obj) {
856 if (!(obj instanceof URL))
857 return false;
858 URL u2 = (URL)obj;
859
860 return handler.equals(this, u2);
861 }
862
863 /**
864 * Creates an integer suitable for hash table indexing.<p>
865 *
866 * The hash code is based upon all the URL components relevant for URL
867 * comparison. As such, this operation is a blocking operation.<p>
868 *
869 * @return a hash code for this <code>URL</code>.
870 */
871 public synchronized int hashCode() {
872 if (hashCode != -1)
873 return hashCode;
874
875 hashCode = handler.hashCode(this);
876 return hashCode;
877 }
878
879 /**
880 * Compares two URLs, excluding the fragment component.<p>
881 *
882 * Returns <code>true</code> if this <code>URL</code> and the
883 * <code>other</code> argument are equal without taking the
884 * fragment component into consideration.
885 *
886 * @param other the <code>URL</code> to compare against.
887 * @return <code>true</code> if they reference the same remote object;
888 * <code>false</code> otherwise.
889 */
890 public boolean sameFile(URL other) {
891 return handler.sameFile(this, other);
892 }
893
894 /**
895 * Constructs a string representation of this <code>URL</code>. The
896 * string is created by calling the <code>toExternalForm</code>
897 * method of the stream protocol handler for this object.
898 *
899 * @return a string representation of this object.
900 * @see java.net.URL#URL(java.lang.String, java.lang.String, int,
901 * java.lang.String)
902 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL)
903 */
904 public String toString() {
905 return toExternalForm();
906 }
907
908 /**
909 * Constructs a string representation of this <code>URL</code>. The
910 * string is created by calling the <code>toExternalForm</code>
911 * method of the stream protocol handler for this object.
912 *
913 * @return a string representation of this object.
914 * @see java.net.URL#URL(java.lang.String, java.lang.String,
915 * int, java.lang.String)
916 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL)
917 */
918 public String toExternalForm() {
919 return handler.toExternalForm(this);
920 }
921
922 /**
923 * Returns a {@link java.net.URI} equivalent to this URL.
924 * This method functions in the same way as <code>new URI (this.toString())</code>.
925 * <p>Note, any URL instance that complies with RFC 2396 can be converted
926 * to a URI. However, some URLs that are not strictly in compliance
927 * can not be converted to a URI.
928 *
929 * @exception URISyntaxException if this URL is not formatted strictly according to
930 * to RFC2396 and cannot be converted to a URI.
931 *
932 * @return a URI instance equivalent to this URL.
933 * @since 1.5
934 */
935 public URI toURI() throws URISyntaxException {
936 return new URI (toString());
937 }
938
939 /**
940 * Returns a {@link java.net.URLConnection URLConnection} instance that
941 * represents a connection to the remote object referred to by the
942 * {@code URL}.
943 *
944 * <P>A new instance of {@linkplain java.net.URLConnection URLConnection} is
945 * created every time when invoking the
946 * {@linkplain java.net.URLStreamHandler#openConnection(URL)
947 * URLStreamHandler.openConnection(URL)} method of the protocol handler for
948 * this URL.</P>
949 *
950 * <P>It should be noted that a URLConnection instance does not establish
951 * the actual network connection on creation. This will happen only when
952 * calling {@linkplain java.net.URLConnection#connect() URLConnection.connect()}.</P>
953 *
954 * <P>If for the URL's protocol (such as HTTP or JAR), there
955 * exists a public, specialized URLConnection subclass belonging
956 * to one of the following packages or one of their subpackages:
957 * java.lang, java.io, java.util, java.net, the connection
958 * returned will be of that subclass. For example, for HTTP an
959 * HttpURLConnection will be returned, and for JAR a
960 * JarURLConnection will be returned.</P>
961 *
962 * @return a {@link java.net.URLConnection URLConnection} linking
963 * to the URL.
964 * @exception IOException if an I/O exception occurs.
965 * @see java.net.URL#URL(java.lang.String, java.lang.String,
966 * int, java.lang.String)
967 */
968 public URLConnection openConnection() throws java.io.IOException {
969 return handler.openConnection(this);
970 }
971
972 /**
973 * Same as {@link #openConnection()}, except that the connection will be
974 * made through the specified proxy; Protocol handlers that do not
975 * support proxing will ignore the proxy parameter and make a
976 * normal connection.
977 *
978 * Invoking this method preempts the system's default ProxySelector
979 * settings.
980 *
981 * @param proxy the Proxy through which this connection
982 * will be made. If direct connection is desired,
983 * Proxy.NO_PROXY should be specified.
984 * @return a <code>URLConnection</code> to the URL.
985 * @exception IOException if an I/O exception occurs.
986 * @exception SecurityException if a security manager is present
987 * and the caller doesn't have permission to connect
988 * to the proxy.
989 * @exception IllegalArgumentException will be thrown if proxy is null,
990 * or proxy has the wrong type
991 * @exception UnsupportedOperationException if the subclass that
992 * implements the protocol handler doesn't support
993 * this method.
994 * @see java.net.URL#URL(java.lang.String, java.lang.String,
995 * int, java.lang.String)
996 * @see java.net.URLConnection
997 * @see java.net.URLStreamHandler#openConnection(java.net.URL,
998 * java.net.Proxy)
999 * @since 1.5
1000 */
1001 public URLConnection openConnection(Proxy proxy)
1002 throws java.io.IOException {
1003 if (proxy == null) {
1004 throw new IllegalArgumentException("proxy can not be null");
1005 }
1006
1007 // Create a copy of Proxy as a security measure
1008 Proxy p = proxy == Proxy.NO_PROXY ? Proxy.NO_PROXY : sun.net.ApplicationProxy.create(proxy);
1009 SecurityManager sm = System.getSecurityManager();
1010 if (p.type() != Proxy.Type.DIRECT && sm != null) {
1011 InetSocketAddress epoint = (InetSocketAddress) p.address();
1012 if (epoint.isUnresolved())
1013 sm.checkConnect(epoint.getHostName(), epoint.getPort());
1014 else
1015 sm.checkConnect(epoint.getAddress().getHostAddress(),
1016 epoint.getPort());
1017 }
1018 return handler.openConnection(this, p);
1019 }
1020
1021 /**
1022 * Opens a connection to this <code>URL</code> and returns an
1023 * <code>InputStream</code> for reading from that connection. This
1024 * method is a shorthand for:
1025 * <blockquote><pre>
1026 * openConnection().getInputStream()
1027 * </pre></blockquote>
1028 *
1029 * @return an input stream for reading from the URL connection.
1030 * @exception IOException if an I/O exception occurs.
1031 * @see java.net.URL#openConnection()
1032 * @see java.net.URLConnection#getInputStream()
1033 */
1034 public final InputStream openStream() throws java.io.IOException {
1035 return openConnection().getInputStream();
1036 }
1037
1038 /**
1039 * Gets the contents of this URL. This method is a shorthand for:
1040 * <blockquote><pre>
1041 * openConnection().getContent()
1042 * </pre></blockquote>
1043 *
1044 * @return the contents of this URL.
1045 * @exception IOException if an I/O exception occurs.
1046 * @see java.net.URLConnection#getContent()
1047 */
1048 public final Object getContent() throws java.io.IOException {
1049 return openConnection().getContent();
1050 }
1051
1052 /**
1053 * Gets the contents of this URL. This method is a shorthand for:
1054 * <blockquote><pre>
1055 * openConnection().getContent(Class[])
1056 * </pre></blockquote>
1057 *
1058 * @param classes an array of Java types
1059 * @return the content object of this URL that is the first match of
1060 * the types specified in the classes array.
1061 * null if none of the requested types are supported.
1062 * @exception IOException if an I/O exception occurs.
1063 * @see java.net.URLConnection#getContent(Class[])
1064 * @since 1.3
1065 */
1066 public final Object getContent(Class[] classes)
1067 throws java.io.IOException {
1068 return openConnection().getContent(classes);
1069 }
1070
1071 /**
1072 * The URLStreamHandler factory.
1073 */
1074 static URLStreamHandlerFactory factory;
1075
1076 /**
1077 * Sets an application's <code>URLStreamHandlerFactory</code>.
1078 * This method can be called at most once in a given Java Virtual
1079 * Machine.
1080 *
1081 *<p> The <code>URLStreamHandlerFactory</code> instance is used to
1082 *construct a stream protocol handler from a protocol name.
1083 *
1084 * <p> If there is a security manager, this method first calls
1085 * the security manager's <code>checkSetFactory</code> method
1086 * to ensure the operation is allowed.
1087 * This could result in a SecurityException.
1088 *
1089 * @param fac the desired factory.
1090 * @exception Error if the application has already set a factory.
1091 * @exception SecurityException if a security manager exists and its
1092 * <code>checkSetFactory</code> method doesn't allow
1093 * the operation.
1094 * @see java.net.URL#URL(java.lang.String, java.lang.String,
1095 * int, java.lang.String)
1096 * @see java.net.URLStreamHandlerFactory
1097 * @see SecurityManager#checkSetFactory
1098 */
1099 public static void setURLStreamHandlerFactory(URLStreamHandlerFactory fac) {
1100 synchronized (streamHandlerLock) {
1101 if (factory != null) {
1102 throw new Error("factory already defined");
1103 }
1104 SecurityManager security = System.getSecurityManager();
1105 if (security != null) {
1106 security.checkSetFactory();
1107 }
1108 handlers.clear();
1109 factory = fac;
1110 }
1111 }
1112
1113 /**
1114 * A table of protocol handlers.
1115 */
1116 static Hashtable handlers = new Hashtable();
1117 private static Object streamHandlerLock = new Object();
1118
1119 /**
1120 * Returns the Stream Handler.
1121 * @param protocol the protocol to use
1122 */
1123 static URLStreamHandler getURLStreamHandler(String protocol) {
1124
1125 URLStreamHandler handler = (URLStreamHandler)handlers.get(protocol);
1126 if (handler == null) {
1127
1128 boolean checkedWithFactory = false;
1129
1130 // Use the factory (if any)
1131 if (factory != null) {
1132 handler = factory.createURLStreamHandler(protocol);
1133 checkedWithFactory = true;
1134 }
1135
1136 // Try java protocol handler
1137 if (handler == null) {
1138 String packagePrefixList = null;
1139
1140 packagePrefixList
1141 = java.security.AccessController.doPrivileged(
1142 new sun.security.action.GetPropertyAction(
1143 protocolPathProp,""));
1144 if (packagePrefixList != "") {
1145 packagePrefixList += "|";
1146 }
1147
1148 // REMIND: decide whether to allow the "null" class prefix
1149 // or not.
1150 packagePrefixList += "sun.net.www.protocol";
1151
1152 StringTokenizer packagePrefixIter =
1153 new StringTokenizer(packagePrefixList, "|");
1154
1155 while (handler == null &&
1156 packagePrefixIter.hasMoreTokens()) {
1157
1158 String packagePrefix =
1159 packagePrefixIter.nextToken().trim();
1160 try {
1161 String clsName = packagePrefix + "." + protocol +
1162 ".Handler";
1163 Class cls = null;
1164 try {
1165 cls = Class.forName(clsName);
1166 } catch (ClassNotFoundException e) {
1167 ClassLoader cl = ClassLoader.getSystemClassLoader();
1168 if (cl != null) {
1169 cls = cl.loadClass(clsName);
1170 }
1171 }
1172 if (cls != null) {
1173 handler =
1174 (URLStreamHandler)cls.newInstance();
1175 }
1176 } catch (Exception e) {
1177 // any number of exceptions can get thrown here
1178 }
1179 }
1180 }
1181
1182 synchronized (streamHandlerLock) {
1183
1184 URLStreamHandler handler2 = null;
1185
1186 // Check again with hashtable just in case another
1187 // thread created a handler since we last checked
1188 handler2 = (URLStreamHandler)handlers.get(protocol);
1189
1190 if (handler2 != null) {
1191 return handler2;
1192 }
1193
1194 // Check with factory if another thread set a
1195 // factory since our last check
1196 if (!checkedWithFactory && factory != null) {
1197 handler2 = factory.createURLStreamHandler(protocol);
1198 }
1199
1200 if (handler2 != null) {
1201 // The handler from the factory must be given more
1202 // importance. Discard the default handler that
1203 // this thread created.
1204 handler = handler2;
1205 }
1206
1207 // Insert this handler into the hashtable
1208 if (handler != null) {
1209 handlers.put(protocol, handler);
1210 }
1211
1212 }
1213 }
1214
1215 return handler;
1216
1217 }
1218
1219 /**
1220 * WriteObject is called to save the state of the URL to an
1221 * ObjectOutputStream. The handler is not saved since it is
1222 * specific to this system.
1223 *
1224 * @serialData the default write object value. When read back in,
1225 * the reader must ensure that calling getURLStreamHandler with
1226 * the protocol variable returns a valid URLStreamHandler and
1227 * throw an IOException if it does not.
1228 */
1229 private synchronized void writeObject(java.io.ObjectOutputStream s)
1230 throws IOException
1231 {
1232 s.defaultWriteObject(); // write the fields
1233 }
1234
1235 /**
1236 * readObject is called to restore the state of the URL from the
1237 * stream. It reads the components of the URL and finds the local
1238 * stream handler.
1239 */
1240 private synchronized void readObject(java.io.ObjectInputStream s)
1241 throws IOException, ClassNotFoundException
1242 {
1243 s.defaultReadObject(); // read the fields
1244 if ((handler = getURLStreamHandler(protocol)) == null) {
1245 throw new IOException("unknown protocol: " + protocol);
1246 }
1247
1248 // Construct authority part
1249 if (authority == null &&
1250 ((host != null && host.length() > 0) || port != -1)) {
1251 if (host == null)
1252 host = "";
1253 authority = (port == -1) ? host : host + ":" + port;
1254
1255 // Handle hosts with userInfo in them
1256 int at = host.lastIndexOf('@');
1257 if (at != -1) {
1258 userInfo = host.substring(0, at);
1259 host = host.substring(at+1);
1260 }
1261 } else if (authority != null) {
1262 // Construct user info part
1263 int ind = authority.indexOf('@');
1264 if (ind != -1)
1265 userInfo = authority.substring(0, ind);
1266 }
1267
1268 // Construct path and query part
1269 path = null;
1270 query = null;
1271 if (file != null) {
1272 // Fix: only do this if hierarchical?
1273 int q = file.lastIndexOf('?');
1274 if (q != -1) {
1275 query = file.substring(q+1);
1276 path = file.substring(0, q);
1277 } else
1278 path = file;
1279 }
1280 }
1281 }
1282
1283 class Parts {
1284 String path, query, ref;
1285
1286 Parts(String file) {
1287 int ind = file.indexOf('#');
1288 ref = ind < 0 ? null: file.substring(ind + 1);
1289 file = ind < 0 ? file: file.substring(0, ind);
1290 int q = file.lastIndexOf('?');
1291 if (q != -1) {
1292 query = file.substring(q+1);
1293 path = file.substring(0, q);
1294 } else {
1295 path = file;
1296 }
1297 }
1298
1299 String getPath() {
1300 return path;
1301 }
1302
1303 String getQuery() {
1304 return query;
1305 }
1306
1307 String getRef() {
1308 return ref;
1309 }
1310 }
Save This Page