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.net.spi.URLStreamHandlerProvider;
31 import java.security.AccessController;
32 import java.security.PrivilegedAction;
33 import java.util.Hashtable;
34 import java.util.Iterator;
35 import java.util.NoSuchElementException;
36 import java.util.ServiceConfigurationError;
37 import java.util.ServiceLoader;
38
39 import sun.security.util.SecurityConstants;
40
41 /**
42 * Class {@code URL} represents a Uniform Resource
43 * Locator, a pointer to a "resource" on the World
44 * Wide Web. A resource can be something as simple as a file or a
45 * directory, or it can be a reference to a more complicated object,
46 * such as a query to a database or to a search engine. More
47 * information on the types of URLs and their formats can be found at:
48 * <a href=
49 * "http://web.archive.org/web/20051219043731/http://archive.ncsa.uiuc.edu/SDG/Software/Mosaic/Demo/url-primer.html">
50 * <i>Types of URL</i></a>
51 * <p>
52 * In general, a URL can be broken into several parts. Consider the
53 * following example:
54 * <blockquote><pre>
55 * http://www.example.com/docs/resource1.html
56 * </pre></blockquote>
57 * <p>
58 * The URL above indicates that the protocol to use is
59 * {@code http} (HyperText Transfer Protocol) and that the
60 * information resides on a host machine named
61 * {@code www.example.com}. The information on that host
62 * machine is named {@code /docs/resource1.html}. The exact
63 * meaning of this name on the host machine is both protocol
64 * dependent and host dependent. The information normally resides in
65 * a file, but it could be generated on the fly. This component of
66 * the URL is called the <i>path</i> component.
67 * <p>
68 * A URL can optionally specify a "port", which is the
69 * port number to which the TCP connection is made on the remote host
70 * machine. If the port is not specified, the default port for
71 * the protocol is used instead. For example, the default port for
72 * {@code http} is {@code 80}. An alternative port could be
73 * specified as:
74 * <blockquote><pre>
75 * http://www.example.com:1080/docs/resource1.html
76 * </pre></blockquote>
77 * <p>
78 * The syntax of {@code URL} is defined by <a
79 * href="http://www.ietf.org/rfc/rfc2396.txt"><i>RFC 2396: Uniform
80 * Resource Identifiers (URI): Generic Syntax</i></a>, amended by <a
81 * href="http://www.ietf.org/rfc/rfc2732.txt"><i>RFC 2732: Format for
82 * Literal IPv6 Addresses in URLs</i></a>. The Literal IPv6 address format
83 * also supports scope_ids. The syntax and usage of scope_ids is described
84 * <a href="Inet6Address.html#scoped">here</a>.
85 * <p>
86 * A URL may have appended to it a "fragment", also known
87 * as a "ref" or a "reference". The fragment is indicated by the sharp
88 * sign character "#" followed by more characters. For example,
89 * <blockquote><pre>
90 * http://java.sun.com/index.html#chapter1
91 * </pre></blockquote>
92 * <p>
93 * This fragment is not technically part of the URL. Rather, it
94 * indicates that after the specified resource is retrieved, the
95 * application is specifically interested in that part of the
96 * document that has the tag {@code chapter1} attached to it. The
97 * meaning of a tag is resource specific.
98 * <p>
99 * An application can also specify a "relative URL",
100 * which contains only enough information to reach the resource
101 * relative to another URL. Relative URLs are frequently used within
102 * HTML pages. For example, if the contents of the URL:
103 * <blockquote><pre>
104 * http://java.sun.com/index.html
105 * </pre></blockquote>
106 * contained within it the relative URL:
107 * <blockquote><pre>
108 * FAQ.html
109 * </pre></blockquote>
110 * it would be a shorthand for:
111 * <blockquote><pre>
112 * http://java.sun.com/FAQ.html
113 * </pre></blockquote>
114 * <p>
115 * The relative URL need not specify all the components of a URL. If
116 * the protocol, host name, or port number is missing, the value is
117 * inherited from the fully specified URL. The file component must be
118 * specified. The optional fragment is not inherited.
119 * <p>
120 * The URL class does not itself encode or decode any URL components
121 * according to the escaping mechanism defined in RFC2396. It is the
122 * responsibility of the caller to encode any fields, which need to be
123 * escaped prior to calling URL, and also to decode any escaped fields,
124 * that are returned from URL. Furthermore, because URL has no knowledge
125 * of URL escaping, it does not recognise equivalence between the encoded
126 * or decoded form of the same URL. For example, the two URLs:<br>
127 * <pre> http://foo.com/hello world/ and http://foo.com/hello%20world</pre>
128 * would be considered not equal to each other.
129 * <p>
130 * Note, the {@link java.net.URI} class does perform escaping of its
131 * component fields in certain circumstances. The recommended way
132 * to manage the encoding and decoding of URLs is to use {@link java.net.URI},
133 * and to convert between these two classes using {@link #toURI()} and
134 * {@link URI#toURL()}.
135 * <p>
136 * The {@link URLEncoder} and {@link URLDecoder} classes can also be
137 * used, but only for HTML form encoding, which is not the same
138 * as the encoding scheme defined in RFC2396.
139 *
140 * @author James Gosling
141 * @since 1.0
142 */
143 public final class URL implements java.io.Serializable {
144
145 static final long serialVersionUID = -7627629688361524110L;
146
147 /**
148 * The property which specifies the package prefix list to be scanned
149 * for protocol handlers. The value of this property (if any) should
150 * be a vertical bar delimited list of package names to search through
151 * for a protocol handler to load. The policy of this class is that
152 * all protocol handlers will be in a class called <protocolname>.Handler,
153 * and each package in the list is examined in turn for a matching
154 * handler. If none are found (or the property is not specified), the
155 * default package prefix, sun.net.www.protocol, is used. The search
156 * proceeds from the first package in the list to the last and stops
157 * when a match is found.
158 */
159 private static final String protocolPathProp = "java.protocol.handler.pkgs";
160
161 /**
162 * The protocol to use (ftp, http, nntp, ... etc.) .
163 * @serial
164 */
165 private String protocol;
166
167 /**
168 * The host name to connect to.
169 * @serial
170 */
171 private String host;
172
173 /**
174 * The protocol port to connect to.
175 * @serial
176 */
177 private int port = -1;
178
179 /**
180 * The specified file name on that host. {@code file} is
181 * defined as {@code path[?query]}
182 * @serial
183 */
184 private String file;
185
186 /**
187 * The query part of this URL.
188 */
189 private transient String query;
190
191 /**
192 * The authority part of this URL.
193 * @serial
194 */
195 private String authority;
196
197 /**
198 * The path part of this URL.
199 */
200 private transient String path;
201
202 /**
203 * The userinfo part of this URL.
204 */
205 private transient String userInfo;
206
207 /**
208 * # reference.
209 * @serial
210 */
211 private String ref;
212
213 /**
214 * The host's IP address, used in equals and hashCode.
215 * Computed on demand. An uninitialized or unknown hostAddress is null.
216 */
217 transient InetAddress hostAddress;
218
219 /**
220 * The URLStreamHandler for this URL.
221 */
222 transient URLStreamHandler handler;
223
224 /* Our hash code.
225 * @serial
226 */
227 private int hashCode = -1;
228
229 /**
230 * Creates a {@code URL} object from the specified
231 * {@code protocol}, {@code host}, {@code port}
232 * number, and {@code file}.<p>
233 *
234 * {@code host} can be expressed as a host name or a literal
235 * IP address. If IPv6 literal address is used, it should be
236 * enclosed in square brackets ({@code '['} and {@code ']'}), as
237 * specified by <a
238 * href="http://www.ietf.org/rfc/rfc2732.txt">RFC 2732</a>;
239 * However, the literal IPv6 address format defined in <a
240 * href="http://www.ietf.org/rfc/rfc2373.txt"><i>RFC 2373: IP
241 * Version 6 Addressing Architecture</i></a> is also accepted.<p>
242 *
243 * Specifying a {@code port} number of {@code -1}
244 * indicates that the URL should use the default port for the
245 * protocol.<p>
246 *
247 * If this is the first URL object being created with the specified
248 * protocol, a <i>stream protocol handler</i> object, an instance of
249 * class {@code URLStreamHandler}, is created for that protocol:
250 * <ol>
251 * <li>If the application has previously set up an instance of
252 * {@code URLStreamHandlerFactory} as the stream handler factory,
253 * then the {@code createURLStreamHandler} method of that instance
254 * is called with the protocol string as an argument to create the
255 * stream protocol handler.
256 * <li>If no {@code URLStreamHandlerFactory} has yet been set up,
257 * or if the factory's {@code createURLStreamHandler} method
258 * returns {@code null}, then the {@linkplain java.util.ServiceLoader
259 * ServiceLoader} mechanism is used to locate {@linkplain
260 * java.net.spi.URLStreamHandlerProvider URLStreamHandlerProvider}
261 * implementations using the system class
262 * loader. The order that providers are located is implementation
263 * specific, and an implementation is free to cache the located
264 * providers. A {@linkplain java.util.ServiceConfigurationError
265 * ServiceConfigurationError}, {@code Error} or {@code RuntimeException}
266 * thrown from the {@code createURLStreamHandler}, if encountered, will
267 * be propagated to the calling thread. The {@code
268 * createURLStreamHandler} method of each provider, if instantiated, is
269 * invoked, with the protocol string, until a provider returns non-null,
270 * or all providers have been exhausted.
271 * <li>If the previous step fails to find a protocol handler, then the
272 * constructor tries to load a built-in protocol handler.
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 available.
284 * Some protocol handlers, for example those used for loading platform
285 * classes or classes on the class path, may not be overridden. The details
286 * of such restrictions, and when those restrictions apply (during
287 * initialization of the runtime for example), are implementation specific
288 * and therefore not specified
289 *
290 * <p>No validation of the inputs is performed by this constructor.
291 *
292 * @param protocol the name of the protocol to use.
293 * @param host the name of the host.
294 * @param port the port number on the host.
295 * @param file the file on the host
296 * @exception MalformedURLException if an unknown protocol is specified.
297 * @see java.lang.System#getProperty(java.lang.String)
298 * @see java.net.URL#setURLStreamHandlerFactory(
299 * java.net.URLStreamHandlerFactory)
300 * @see java.net.URLStreamHandler
301 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler(
302 * java.lang.String)
303 */
304 public URL(String protocol, String host, int port, String file)
305 throws MalformedURLException
306 {
307 this(protocol, host, port, file, null);
308 }
309
310 /**
311 * Creates a URL from the specified {@code protocol}
312 * name, {@code host} name, and {@code file} name. The
313 * default port for the specified protocol is used.
314 * <p>
315 * This method is equivalent to calling the four-argument
316 * constructor with the arguments being {@code protocol},
317 * {@code host}, {@code -1}, and {@code file}.
318 *
319 * No validation of the inputs is performed by this constructor.
320 *
321 * @param protocol the name of the protocol to use.
322 * @param host the name of the host.
323 * @param file the file on the host.
324 * @exception MalformedURLException if an unknown protocol is specified.
325 * @see java.net.URL#URL(java.lang.String, java.lang.String,
326 * int, java.lang.String)
327 */
328 public URL(String protocol, String host, String file)
329 throws MalformedURLException {
330 this(protocol, host, -1, file);
331 }
332
333 /**
334 * Creates a {@code URL} object from the specified
335 * {@code protocol}, {@code host}, {@code port}
336 * number, {@code file}, and {@code handler}. Specifying
337 * a {@code port} number of {@code -1} indicates that
338 * the URL should use the default port for the protocol. Specifying
339 * a {@code handler} of {@code null} indicates that the URL
340 * should use a default stream handler for the protocol, as outlined
341 * for:
342 * java.net.URL#URL(java.lang.String, java.lang.String, int,
343 * java.lang.String)
344 *
345 * <p>If the handler is not null and there is a security manager,
346 * the security manager's {@code checkPermission}
347 * method is called with a
348 * {@code NetPermission("specifyStreamHandler")} permission.
349 * This may result in a SecurityException.
350 *
351 * No validation of the inputs is performed by this constructor.
352 *
353 * @param protocol the name of the protocol to use.
354 * @param host the name of the host.
355 * @param port the port number on the host.
356 * @param file the file on the host
357 * @param handler the stream handler for the URL.
358 * @exception MalformedURLException if an unknown protocol is specified.
359 * @exception SecurityException
360 * if a security manager exists and its
361 * {@code checkPermission} method doesn't allow
362 * specifying a stream handler explicitly.
363 * @see java.lang.System#getProperty(java.lang.String)
364 * @see java.net.URL#setURLStreamHandlerFactory(
365 * java.net.URLStreamHandlerFactory)
366 * @see java.net.URLStreamHandler
367 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler(
368 * java.lang.String)
369 * @see SecurityManager#checkPermission
370 * @see java.net.NetPermission
371 */
372 public URL(String protocol, String host, int port, String file,
373 URLStreamHandler handler) throws MalformedURLException {
374 if (handler != null) {
375 SecurityManager sm = System.getSecurityManager();
376 if (sm != null) {
377 // check for permission to specify a handler
378 checkSpecifyHandler(sm);
379 }
380 }
381
382 protocol = protocol.toLowerCase();
383 this.protocol = protocol;
384 if (host != null) {
385
386 /**
387 * if host is a literal IPv6 address,
388 * we will make it conform to RFC 2732
389 */
390 if (host.indexOf(':') >= 0 && !host.startsWith("[")) {
391 host = "["+host+"]";
392 }
393 this.host = host;
394
395 if (port < -1) {
396 throw new MalformedURLException("Invalid port number :" +
397 port);
398 }
399 this.port = port;
400 authority = (port == -1) ? host : host + ":" + port;
401 }
402
403 Parts parts = new Parts(file);
404 path = parts.getPath();
405 query = parts.getQuery();
406
407 if (query != null) {
408 this.file = path + "?" + query;
409 } else {
410 this.file = path;
411 }
412 ref = parts.getRef();
413
414 // Note: we don't do validation of the URL here. Too risky to change
415 // right now, but worth considering for future reference. -br
416 if (handler == null &&
417 (handler = getURLStreamHandler(protocol)) == null) {
418 throw new MalformedURLException("unknown protocol: " + protocol);
419 }
420 this.handler = handler;
421 }
422
423 /**
424 * Creates a {@code URL} object from the {@code String}
425 * representation.
426 * <p>
427 * This constructor is equivalent to a call to the two-argument
428 * constructor with a {@code null} first argument.
429 *
430 * @param spec the {@code String} to parse as a URL.
431 * @exception MalformedURLException if no protocol is specified, or an
432 * unknown protocol is found, or {@code spec} is {@code null}.
433 * @see java.net.URL#URL(java.net.URL, java.lang.String)
434 */
435 public URL(String spec) throws MalformedURLException {
436 this(null, spec);
437 }
438
439 /**
440 * Creates a URL by parsing the given spec within a specified context.
441 *
442 * The new URL is created from the given context URL and the spec
443 * argument as described in
444 * RFC2396 "Uniform Resource Identifiers : Generic * Syntax" :
445 * <blockquote><pre>
446 * <scheme>://<authority><path>?<query>#<fragment>
447 * </pre></blockquote>
448 * The reference is parsed into the scheme, authority, path, query and
449 * fragment parts. If the path component is empty and the scheme,
450 * authority, and query components are undefined, then the new URL is a
451 * reference to the current document. Otherwise, the fragment and query
452 * parts present in the spec are used in the new URL.
453 * <p>
454 * If the scheme component is defined in the given spec and does not match
455 * the scheme of the context, then the new URL is created as an absolute
456 * URL based on the spec alone. Otherwise the scheme component is inherited
457 * from the context URL.
458 * <p>
459 * If the authority component is present in the spec then the spec is
460 * treated as absolute and the spec authority and path will replace the
461 * context authority and path. If the authority component is absent in the
462 * spec then the authority of the new URL will be inherited from the
463 * context.
464 * <p>
465 * If the spec's path component begins with a slash character
466 * "/" then the
467 * path is treated as absolute and the spec path replaces the context path.
468 * <p>
469 * Otherwise, the path is treated as a relative path and is appended to the
470 * context path, as described in RFC2396. Also, in this case,
471 * the path is canonicalized through the removal of directory
472 * changes made by occurrences of ".." and ".".
473 * <p>
474 * For a more detailed description of URL parsing, refer to RFC2396.
475 *
476 * @param context the context in which to parse the specification.
477 * @param spec the {@code String} to parse as a URL.
478 * @exception MalformedURLException if no protocol is specified, or an
479 * unknown protocol is found, or {@code spec} is {@code null}.
480 * @see java.net.URL#URL(java.lang.String, java.lang.String,
481 * int, java.lang.String)
482 * @see java.net.URLStreamHandler
483 * @see java.net.URLStreamHandler#parseURL(java.net.URL,
484 * java.lang.String, int, int)
485 */
486 public URL(URL context, String spec) throws MalformedURLException {
487 this(context, spec, null);
488 }
489
490 /**
491 * Creates a URL by parsing the given spec with the specified handler
492 * within a specified context. If the handler is null, the parsing
493 * occurs as with the two argument constructor.
494 *
495 * @param context the context in which to parse the specification.
496 * @param spec the {@code String} to parse as a URL.
497 * @param handler the stream handler for the URL.
498 * @exception MalformedURLException if no protocol is specified, or an
499 * unknown protocol is found, or {@code spec} is {@code null}.
500 * @exception SecurityException
501 * if a security manager exists and its
502 * {@code checkPermission} method doesn't allow
503 * specifying a stream handler.
504 * @see java.net.URL#URL(java.lang.String, java.lang.String,
505 * int, java.lang.String)
506 * @see java.net.URLStreamHandler
507 * @see java.net.URLStreamHandler#parseURL(java.net.URL,
508 * java.lang.String, int, int)
509 */
510 public URL(URL context, String spec, URLStreamHandler handler)
511 throws MalformedURLException
512 {
513 String original = spec;
514 int i, limit, c;
515 int start = 0;
516 String newProtocol = null;
517 boolean aRef=false;
518 boolean isRelative = false;
519
520 // Check for permission to specify a handler
521 if (handler != null) {
522 SecurityManager sm = System.getSecurityManager();
523 if (sm != null) {
524 checkSpecifyHandler(sm);
525 }
526 }
527
528 try {
529 limit = spec.length();
530 while ((limit > 0) && (spec.charAt(limit - 1) <= ' ')) {
531 limit--; //eliminate trailing whitespace
532 }
533 while ((start < limit) && (spec.charAt(start) <= ' ')) {
534 start++; // eliminate leading whitespace
535 }
536
537 if (spec.regionMatches(true, start, "url:", 0, 4)) {
538 start += 4;
539 }
540 if (start < spec.length() && spec.charAt(start) == '#') {
541 /* we're assuming this is a ref relative to the context URL.
542 * This means protocols cannot start w/ '#', but we must parse
543 * ref URL's like: "hello:there" w/ a ':' in them.
544 */
545 aRef=true;
546 }
547 for (i = start ; !aRef && (i < limit) &&
548 ((c = spec.charAt(i)) != '/') ; i++) {
549 if (c == ':') {
550
551 String s = spec.substring(start, i).toLowerCase();
552 if (isValidProtocol(s)) {
553 newProtocol = s;
554 start = i + 1;
555 }
556 break;
557 }
558 }
559
560 // Only use our context if the protocols match.
561 protocol = newProtocol;
562 if ((context != null) && ((newProtocol == null) ||
563 newProtocol.equalsIgnoreCase(context.protocol))) {
564 // inherit the protocol handler from the context
565 // if not specified to the constructor
566 if (handler == null) {
567 handler = context.handler;
568 }
569
570 // If the context is a hierarchical URL scheme and the spec
571 // contains a matching scheme then maintain backwards
572 // compatibility and treat it as if the spec didn't contain
573 // the scheme; see 5.2.3 of RFC2396
574 if (context.path != null && context.path.startsWith("/"))
575 newProtocol = null;
576
577 if (newProtocol == null) {
578 protocol = context.protocol;
579 authority = context.authority;
580 userInfo = context.userInfo;
581 host = context.host;
582 port = context.port;
583 file = context.file;
584 path = context.path;
585 isRelative = true;
586 }
587 }
588
589 if (protocol == null) {
590 throw new MalformedURLException("no protocol: "+original);
591 }
592
593 // Get the protocol handler if not specified or the protocol
594 // of the context could not be used
595 if (handler == null &&
596 (handler = getURLStreamHandler(protocol)) == null) {
597 throw new MalformedURLException("unknown protocol: "+protocol);
598 }
599
600 this.handler = handler;
601
602 i = spec.indexOf('#', start);
603 if (i >= 0) {
604 ref = spec.substring(i + 1, limit);
605 limit = i;
606 }
607
608 /*
609 * Handle special case inheritance of query and fragment
610 * implied by RFC2396 section 5.2.2.
611 */
612 if (isRelative && start == limit) {
613 query = context.query;
614 if (ref == null) {
615 ref = context.ref;
616 }
617 }
618
619 handler.parseURL(this, spec, start, limit);
620
621 } catch(MalformedURLException e) {
622 throw e;
623 } catch(Exception e) {
624 MalformedURLException exception = new MalformedURLException(e.getMessage());
625 exception.initCause(e);
626 throw exception;
627 }
628 }
629
630 /*
631 * Returns true if specified string is a valid protocol name.
632 */
633 private boolean isValidProtocol(String protocol) {
634 int len = protocol.length();
635 if (len < 1)
636 return false;
637 char c = protocol.charAt(0);
638 if (!Character.isLetter(c))
639 return false;
640 for (int i = 1; i < len; i++) {
641 c = protocol.charAt(i);
642 if (!Character.isLetterOrDigit(c) && c != '.' && c != '+' &&
643 c != '-') {
644 return false;
645 }
646 }
647 return true;
648 }
649
650 /*
651 * Checks for permission to specify a stream handler.
652 */
653 private void checkSpecifyHandler(SecurityManager sm) {
654 sm.checkPermission(SecurityConstants.SPECIFY_HANDLER_PERMISSION);
655 }
656
657 /**
658 * Sets the fields of the URL. This is not a public method so that
659 * only URLStreamHandlers can modify URL fields. URLs are
660 * otherwise constant.
661 *
662 * @param protocol the name of the protocol to use
663 * @param host the name of the host
664 @param port the port number on the host
665 * @param file the file on the host
666 * @param ref the internal reference in the URL
667 */
668 void set(String protocol, String host, int port,
669 String file, String ref) {
670 synchronized (this) {
671 this.protocol = protocol;
672 this.host = host;
673 authority = port == -1 ? host : host + ":" + port;
674 this.port = port;
675 this.file = file;
676 this.ref = ref;
677 /* This is very important. We must recompute this after the
678 * URL has been changed. */
679 hashCode = -1;
680 hostAddress = null;
681 int q = file.lastIndexOf('?');
682 if (q != -1) {
683 query = file.substring(q+1);
684 path = file.substring(0, q);
685 } else
686 path = file;
687 }
688 }
689
690 /**
691 * Sets the specified 8 fields of the URL. This is not a public method so
692 * that only URLStreamHandlers can modify URL fields. URLs are otherwise
693 * constant.
694 *
695 * @param protocol the name of the protocol to use
696 * @param host the name of the host
697 * @param port the port number on the host
698 * @param authority the authority part for the url
699 * @param userInfo the username and password
700 * @param path the file on the host
701 * @param ref the internal reference in the URL
702 * @param query the query part of this URL
703 * @since 1.3
704 */
705 void set(String protocol, String host, int port,
706 String authority, String userInfo, String path,
707 String query, String ref) {
708 synchronized (this) {
709 this.protocol = protocol;
710 this.host = host;
711 this.port = port;
712 this.file = query == null ? path : path + "?" + query;
713 this.userInfo = userInfo;
714 this.path = path;
715 this.ref = ref;
716 /* This is very important. We must recompute this after the
717 * URL has been changed. */
718 hashCode = -1;
719 hostAddress = null;
720 this.query = query;
721 this.authority = authority;
722 }
723 }
724
725 /**
726 * Gets the query part of this {@code URL}.
727 *
728 * @return the query part of this {@code URL},
729 * or <CODE>null</CODE> if one does not exist
730 * @since 1.3
731 */
732 public String getQuery() {
733 return query;
734 }
735
736 /**
737 * Gets the path part of this {@code URL}.
738 *
739 * @return the path part of this {@code URL}, or an
740 * empty string if one does not exist
741 * @since 1.3
742 */
743 public String getPath() {
744 return path;
745 }
746
747 /**
748 * Gets the userInfo part of this {@code URL}.
749 *
750 * @return the userInfo part of this {@code URL}, or
751 * <CODE>null</CODE> if one does not exist
752 * @since 1.3
753 */
754 public String getUserInfo() {
755 return userInfo;
756 }
757
758 /**
759 * Gets the authority part of this {@code URL}.
760 *
761 * @return the authority part of this {@code URL}
762 * @since 1.3
763 */
764 public String getAuthority() {
765 return authority;
766 }
767
768 /**
769 * Gets the port number of this {@code URL}.
770 *
771 * @return the port number, or -1 if the port is not set
772 */
773 public int getPort() {
774 return port;
775 }
776
777 /**
778 * Gets the default port number of the protocol associated
779 * with this {@code URL}. If the URL scheme or the URLStreamHandler
780 * for the URL do not define a default port number,
781 * then -1 is returned.
782 *
783 * @return the port number
784 * @since 1.4
785 */
786 public int getDefaultPort() {
787 return handler.getDefaultPort();
788 }
789
790 /**
791 * Gets the protocol name of this {@code URL}.
792 *
793 * @return the protocol of this {@code URL}.
794 */
795 public String getProtocol() {
796 return protocol;
797 }
798
799 /**
800 * Gets the host name of this {@code URL}, if applicable.
801 * The format of the host conforms to RFC 2732, i.e. for a
802 * literal IPv6 address, this method will return the IPv6 address
803 * enclosed in square brackets ({@code '['} and {@code ']'}).
804 *
805 * @return the host name of this {@code URL}.
806 */
807 public String getHost() {
808 return host;
809 }
810
811 /**
812 * Gets the file name of this {@code URL}.
813 * The returned file portion will be
814 * the same as <CODE>getPath()</CODE>, plus the concatenation of
815 * the value of <CODE>getQuery()</CODE>, if any. If there is
816 * no query portion, this method and <CODE>getPath()</CODE> will
817 * return identical results.
818 *
819 * @return the file name of this {@code URL},
820 * or an empty string if one does not exist
821 */
822 public String getFile() {
823 return file;
824 }
825
826 /**
827 * Gets the anchor (also known as the "reference") of this
828 * {@code URL}.
829 *
830 * @return the anchor (also known as the "reference") of this
831 * {@code URL}, or <CODE>null</CODE> if one does not exist
832 */
833 public String getRef() {
834 return ref;
835 }
836
837 /**
838 * Compares this URL for equality with another object.<p>
839 *
840 * If the given object is not a URL then this method immediately returns
841 * {@code false}.<p>
842 *
843 * Two URL objects are equal if they have the same protocol, reference
844 * equivalent hosts, have the same port number on the host, and the same
845 * file and fragment of the file.<p>
846 *
847 * Two hosts are considered equivalent if both host names can be resolved
848 * into the same IP addresses; else if either host name can't be
849 * resolved, the host names must be equal without regard to case; or both
850 * host names equal to null.<p>
851 *
852 * Since hosts comparison requires name resolution, this operation is a
853 * blocking operation. <p>
854 *
855 * Note: The defined behavior for {@code equals} is known to
856 * be inconsistent with virtual hosting in HTTP.
857 *
858 * @param obj the URL to compare against.
859 * @return {@code true} if the objects are the same;
860 * {@code false} otherwise.
861 */
862 public boolean equals(Object obj) {
863 if (!(obj instanceof URL))
864 return false;
865 URL u2 = (URL)obj;
866
867 return handler.equals(this, u2);
868 }
869
870 /**
871 * Creates an integer suitable for hash table indexing.<p>
872 *
873 * The hash code is based upon all the URL components relevant for URL
874 * comparison. As such, this operation is a blocking operation.
875 *
876 * @return a hash code for this {@code URL}.
877 */
878 public synchronized int hashCode() {
879 if (hashCode != -1)
880 return hashCode;
881
882 hashCode = handler.hashCode(this);
883 return hashCode;
884 }
885
886 /**
887 * Compares two URLs, excluding the fragment component.<p>
888 *
889 * Returns {@code true} if this {@code URL} and the
890 * {@code other} argument are equal without taking the
891 * fragment component into consideration.
892 *
893 * @param other the {@code URL} to compare against.
894 * @return {@code true} if they reference the same remote object;
895 * {@code false} otherwise.
896 */
897 public boolean sameFile(URL other) {
898 return handler.sameFile(this, other);
899 }
900
901 /**
902 * Constructs a string representation of this {@code URL}. The
903 * string is created by calling the {@code toExternalForm}
904 * method of the stream protocol handler for this object.
905 *
906 * @return a string representation of this object.
907 * @see java.net.URL#URL(java.lang.String, java.lang.String, int,
908 * java.lang.String)
909 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL)
910 */
911 public String toString() {
912 return toExternalForm();
913 }
914
915 /**
916 * Constructs a string representation of this {@code URL}. The
917 * string is created by calling the {@code toExternalForm}
918 * method of the stream protocol handler for this object.
919 *
920 * @return a string representation of this object.
921 * @see java.net.URL#URL(java.lang.String, java.lang.String,
922 * int, java.lang.String)
923 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL)
924 */
925 public String toExternalForm() {
926 return handler.toExternalForm(this);
927 }
928
929 /**
930 * Returns a {@link java.net.URI} equivalent to this URL.
931 * This method functions in the same way as {@code new URI (this.toString())}.
932 * <p>Note, any URL instance that complies with RFC 2396 can be converted
933 * to a URI. However, some URLs that are not strictly in compliance
934 * can not be converted to a URI.
935 *
936 * @exception URISyntaxException if this URL is not formatted strictly according to
937 * to RFC2396 and cannot be converted to a URI.
938 *
939 * @return a URI instance equivalent to this URL.
940 * @since 1.5
941 */
942 public URI toURI() throws URISyntaxException {
943 return new URI (toString());
944 }
945
946 /**
947 * Returns a {@link java.net.URLConnection URLConnection} instance that
948 * represents a connection to the remote object referred to by the
949 * {@code URL}.
950 *
951 * <P>A new instance of {@linkplain java.net.URLConnection URLConnection} is
952 * created every time when invoking the
953 * {@linkplain java.net.URLStreamHandler#openConnection(URL)
954 * URLStreamHandler.openConnection(URL)} method of the protocol handler for
955 * this URL.</P>
956 *
957 * <P>It should be noted that a URLConnection instance does not establish
958 * the actual network connection on creation. This will happen only when
959 * calling {@linkplain java.net.URLConnection#connect() URLConnection.connect()}.</P>
960 *
961 * <P>If for the URL's protocol (such as HTTP or JAR), there
962 * exists a public, specialized URLConnection subclass belonging
963 * to one of the following packages or one of their subpackages:
964 * java.lang, java.io, java.util, java.net, the connection
965 * returned will be of that subclass. For example, for HTTP an
966 * HttpURLConnection will be returned, and for JAR a
967 * JarURLConnection will be returned.</P>
968 *
969 * @return a {@link java.net.URLConnection URLConnection} linking
970 * to the URL.
971 * @exception IOException if an I/O exception occurs.
972 * @see java.net.URL#URL(java.lang.String, java.lang.String,
973 * int, java.lang.String)
974 */
975 public URLConnection openConnection() throws java.io.IOException {
976 return handler.openConnection(this);
977 }
978
979 /**
980 * Same as {@link #openConnection()}, except that the connection will be
981 * made through the specified proxy; Protocol handlers that do not
982 * support proxing will ignore the proxy parameter and make a
983 * normal connection.
984 *
985 * Invoking this method preempts the system's default
986 * {@link java.net.ProxySelector ProxySelector} settings.
987 *
988 * @param proxy the Proxy through which this connection
989 * will be made. If direct connection is desired,
990 * Proxy.NO_PROXY should be specified.
991 * @return a {@code URLConnection} to the URL.
992 * @exception IOException if an I/O exception occurs.
993 * @exception SecurityException if a security manager is present
994 * and the caller doesn't have permission to connect
995 * to the proxy.
996 * @exception IllegalArgumentException will be thrown if proxy is null,
997 * or proxy has the wrong type
998 * @exception UnsupportedOperationException if the subclass that
999 * implements the protocol handler doesn't support
1000 * this method.
1001 * @see java.net.URL#URL(java.lang.String, java.lang.String,
1002 * int, java.lang.String)
1003 * @see java.net.URLConnection
1004 * @see java.net.URLStreamHandler#openConnection(java.net.URL,
1005 * java.net.Proxy)
1006 * @since 1.5
1007 */
1008 public URLConnection openConnection(Proxy proxy)
1009 throws java.io.IOException {
1010 if (proxy == null) {
1011 throw new IllegalArgumentException("proxy can not be null");
1012 }
1013
1014 // Create a copy of Proxy as a security measure
1015 Proxy p = proxy == Proxy.NO_PROXY ? Proxy.NO_PROXY : sun.net.ApplicationProxy.create(proxy);
1016 SecurityManager sm = System.getSecurityManager();
1017 if (p.type() != Proxy.Type.DIRECT && sm != null) {
1018 InetSocketAddress epoint = (InetSocketAddress) p.address();
1019 if (epoint.isUnresolved())
1020 sm.checkConnect(epoint.getHostName(), epoint.getPort());
1021 else
1022 sm.checkConnect(epoint.getAddress().getHostAddress(),
1023 epoint.getPort());
1024 }
1025 return handler.openConnection(this, p);
1026 }
1027
1028 /**
1029 * Opens a connection to this {@code URL} and returns an
1030 * {@code InputStream} for reading from that connection. This
1031 * method is a shorthand for:
1032 * <blockquote><pre>
1033 * openConnection().getInputStream()
1034 * </pre></blockquote>
1035 *
1036 * @return an input stream for reading from the URL connection.
1037 * @exception IOException if an I/O exception occurs.
1038 * @see java.net.URL#openConnection()
1039 * @see java.net.URLConnection#getInputStream()
1040 */
1041 public final InputStream openStream() throws java.io.IOException {
1042 return openConnection().getInputStream();
1043 }
1044
1045 /**
1046 * Gets the contents of this URL. This method is a shorthand for:
1047 * <blockquote><pre>
1048 * openConnection().getContent()
1049 * </pre></blockquote>
1050 *
1051 * @return the contents of this URL.
1052 * @exception IOException if an I/O exception occurs.
1053 * @see java.net.URLConnection#getContent()
1054 */
1055 public final Object getContent() throws java.io.IOException {
1056 return openConnection().getContent();
1057 }
1058
1059 /**
1060 * Gets the contents of this URL. This method is a shorthand for:
1061 * <blockquote><pre>
1062 * openConnection().getContent(classes)
1063 * </pre></blockquote>
1064 *
1065 * @param classes an array of Java types
1066 * @return the content object of this URL that is the first match of
1067 * the types specified in the classes array.
1068 * null if none of the requested types are supported.
1069 * @exception IOException if an I/O exception occurs.
1070 * @see java.net.URLConnection#getContent(Class[])
1071 * @since 1.3
1072 */
1073 public final Object getContent(Class<?>[] classes)
1074 throws java.io.IOException {
1075 return openConnection().getContent(classes);
1076 }
1077
1078 /**
1079 * The URLStreamHandler factory.
1080 */
1081 private static volatile URLStreamHandlerFactory factory;
1082
1083 /**
1084 * Sets an application's {@code URLStreamHandlerFactory}.
1085 * This method can be called at most once in a given Java Virtual
1086 * Machine.
1087 *
1088 *<p> The {@code URLStreamHandlerFactory} instance is used to
1089 *construct a stream protocol handler from a protocol name.
1090 *
1091 * <p> If there is a security manager, this method first calls
1092 * the security manager's {@code checkSetFactory} method
1093 * to ensure the operation is allowed.
1094 * This could result in a SecurityException.
1095 *
1096 * @param fac the desired factory.
1097 * @exception Error if the application has already set a factory.
1098 * @exception SecurityException if a security manager exists and its
1099 * {@code checkSetFactory} method doesn't allow
1100 * the operation.
1101 * @see java.net.URL#URL(java.lang.String, java.lang.String,
1102 * int, java.lang.String)
1103 * @see java.net.URLStreamHandlerFactory
1104 * @see SecurityManager#checkSetFactory
1105 */
1106 public static void setURLStreamHandlerFactory(URLStreamHandlerFactory fac) {
1107 synchronized (streamHandlerLock) {
1108 if (factory != null) {
1109 throw new Error("factory already defined");
1110 }
1111 SecurityManager security = System.getSecurityManager();
1112 if (security != null) {
1113 security.checkSetFactory();
1114 }
1115 handlers.clear();
1116
1117 // safe publication of URLStreamHandlerFactory with volatile write
1118 factory = fac;
1119 }
1120 }
1121
1122 private static final URLStreamHandlerFactory defaultFactory = new DefaultFactory();
1123
1124 private static class DefaultFactory implements URLStreamHandlerFactory {
1125 private static String PREFIX = "sun.net.www.protocol";
1126
1127 public URLStreamHandler createURLStreamHandler(String protocol) {
1128 String name = PREFIX + "." + protocol + ".Handler";
1129 try {
1130 Class<?> c = Class.forName(name);
1131 return (URLStreamHandler)c.newInstance();
1132 } catch (ClassNotFoundException x) {
1133 // ignore
1134 } catch (Exception e) {
1135 // For compatibility, all Exceptions are ignored.
1136 // any number of exceptions can get thrown here
1137 }
1138 return null;
1139 }
1140 }
1141
1142 private static Iterator<URLStreamHandlerProvider> providers() {
1143 return new Iterator<URLStreamHandlerProvider>() {
1144
1145 ClassLoader cl = ClassLoader.getSystemClassLoader();
1146 ServiceLoader<URLStreamHandlerProvider> sl =
1147 ServiceLoader.load(URLStreamHandlerProvider.class, cl);
1148 Iterator<URLStreamHandlerProvider> i = sl.iterator();
1149
1150 URLStreamHandlerProvider next = null;
1151
1152 private boolean getNext() {
1153 while (next == null) {
1154 try {
1155 if (!i.hasNext())
1156 return false;
1157 next = i.next();
1158 } catch (ServiceConfigurationError sce) {
1159 if (sce.getCause() instanceof SecurityException) {
1160 // Ignore security exceptions
1161 continue;
1162 }
1163 throw sce;
1164 }
1165 }
1166 return true;
1167 }
1168
1169 public boolean hasNext() {
1170 return getNext();
1171 }
1172
1173 public URLStreamHandlerProvider next() {
1174 if (!getNext())
1175 throw new NoSuchElementException();
1176 URLStreamHandlerProvider n = next;
1177 next = null;
1178 return n;
1179 }
1180 };
1181 }
1182
1183 // Thread-local gate to prevent recursive provider lookups
1184 private static ThreadLocal<Object> gate = new ThreadLocal<>();
1185
1186 private static URLStreamHandler lookupViaProviders(final String protocol) {
1187 if (!sun.misc.VM.isBooted())
1188 return null;
1189
1190 if (gate.get() != null)
1191 throw new Error("Circular loading of URL stream handler providers detected");
1192
1193 gate.set(gate);
1194 try {
1195 return AccessController.doPrivileged(
1196 new PrivilegedAction<URLStreamHandler>() {
1197 public URLStreamHandler run() {
1198 Iterator<URLStreamHandlerProvider> itr = providers();
1199 while (itr.hasNext()) {
1200 URLStreamHandlerProvider f = itr.next();
1201 URLStreamHandler h = f.createURLStreamHandler(protocol);
1202 if (h != null)
1203 return h;
1204 }
1205 return null;
1206 }
1207 });
1208 } finally {
1209 gate.set(null);
1210 }
1211 }
1212
1213 private static final String[] NON_OVERRIDEABLE_PROTOCOLS = {"file", "jrt"};
1214 private static boolean isOverrideable(String protocol) {
1215 for (String p : NON_OVERRIDEABLE_PROTOCOLS)
1216 if (protocol.equalsIgnoreCase(p))
1217 return false;
1218 return true;
1219 }
1220
1221 /**
1222 * A table of protocol handlers.
1223 */
1224 static Hashtable<String,URLStreamHandler> handlers = new Hashtable<>();
1225 private static final Object streamHandlerLock = new Object();
1226
1227 /**
1228 * Returns the Stream Handler.
1229 * @param protocol the protocol to use
1230 */
1231 static URLStreamHandler getURLStreamHandler(String protocol) {
1232
1233 URLStreamHandler handler = handlers.get(protocol);
1234
1235 if (handler != null) {
1236 return handler;
1237 }
1238
1239 URLStreamHandlerFactory fac;
1240 boolean checkedWithFactory = false;
1241
1242 if (isOverrideable(protocol)) {
1243 // Use the factory (if any). Volatile read makes
1244 // URLStreamHandlerFactory appear fully initialized to current thread.
1245 fac = factory;
1246 if (fac != null) {
1247 handler = fac.createURLStreamHandler(protocol);
1248 checkedWithFactory = true;
1249 }
1250
1251 if (handler == null && !protocol.equalsIgnoreCase("jar")) {
1252 handler = lookupViaProviders(protocol);
1253 }
1254 }
1255
1256 synchronized (streamHandlerLock) {
1257 if (handler == null) {
1258 // Try the built-in protocol handler
1259 handler = defaultFactory.createURLStreamHandler(protocol);
1260 } else {
1261 URLStreamHandler handler2 = null;
1262
1263 // Check again with hashtable just in case another
1264 // thread created a handler since we last checked
1265 handler2 = handlers.get(protocol);
1266
1267 if (handler2 != null) {
1268 return handler2;
1269 }
1270
1271 // Check with factory if another thread set a
1272 // factory since our last check
1273 if (!checkedWithFactory && (fac = factory) != null) {
1274 handler2 = fac.createURLStreamHandler(protocol);
1275 }
1276
1277 if (handler2 != null) {
1278 // The handler from the factory must be given more
1279 // importance. Discard the default handler that
1280 // this thread created.
1281 handler = handler2;
1282 }
1283 }
1284
1285 // Insert this handler into the hashtable
1286 if (handler != null) {
1287 handlers.put(protocol, handler);
1288 }
1289 }
1290
1291 return handler;
1292 }
1293
1294 /**
1295 * WriteObject is called to save the state of the URL to an
1296 * ObjectOutputStream. The handler is not saved since it is
1297 * specific to this system.
1298 *
1299 * @serialData the default write object value. When read back in,
1300 * the reader must ensure that calling getURLStreamHandler with
1301 * the protocol variable returns a valid URLStreamHandler and
1302 * throw an IOException if it does not.
1303 */
1304 private synchronized void writeObject(java.io.ObjectOutputStream s)
1305 throws IOException
1306 {
1307 s.defaultWriteObject(); // write the fields
1308 }
1309
1310 /**
1311 * readObject is called to restore the state of the URL from the
1312 * stream. It reads the components of the URL and finds the local
1313 * stream handler.
1314 */
1315 private synchronized void readObject(java.io.ObjectInputStream s)
1316 throws IOException, ClassNotFoundException
1317 {
1318 s.defaultReadObject(); // read the fields
1319 if ((handler = getURLStreamHandler(protocol)) == null) {
1320 throw new IOException("unknown protocol: " + protocol);
1321 }
1322
1323 // Construct authority part
1324 if (authority == null &&
1325 ((host != null && host.length() > 0) || port != -1)) {
1326 if (host == null)
1327 host = "";
1328 authority = (port == -1) ? host : host + ":" + port;
1329
1330 // Handle hosts with userInfo in them
1331 int at = host.lastIndexOf('@');
1332 if (at != -1) {
1333 userInfo = host.substring(0, at);
1334 host = host.substring(at+1);
1335 }
1336 } else if (authority != null) {
1337 // Construct user info part
1338 int ind = authority.indexOf('@');
1339 if (ind != -1)
1340 userInfo = authority.substring(0, ind);
1341 }
1342
1343 // Construct path and query part
1344 path = null;
1345 query = null;
1346 if (file != null) {
1347 // Fix: only do this if hierarchical?
1348 int q = file.lastIndexOf('?');
1349 if (q != -1) {
1350 query = file.substring(q+1);
1351 path = file.substring(0, q);
1352 } else
1353 path = file;
1354 }
1355 }
1356 }
1357
1358 class Parts {
1359 String path, query, ref;
1360
1361 Parts(String file) {
1362 int ind = file.indexOf('#');
1363 ref = ind < 0 ? null: file.substring(ind + 1);
1364 file = ind < 0 ? file: file.substring(0, ind);
1365 int q = file.lastIndexOf('?');
1366 if (q != -1) {
1367 query = file.substring(q+1);
1368 path = file.substring(0, q);
1369 } else {
1370 path = file;
1371 }
1372 }
1373
1374 String getPath() {
1375 return path;
1376 }
1377
1378 String getQuery() {
1379 return query;
1380 }
1381
1382 String getRef() {
1383 return ref;
1384 }
1385 }