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, the 272 * constructor reads the value of the system property: 273 * <blockquote>{@code 274 * java.protocol.handler.pkgs 275 * }</blockquote> 276 * If the value of that system property is not {@code null}, 277 * it is interpreted as a list of packages separated by a vertical 278 * slash character '{@code |}'. The constructor tries to load 279 * the class named: 280 * <blockquote>{@code 281 * <package>.<protocol>.Handler 282 * }</blockquote> 283 * where {@code <package>} is replaced by the name of the package 284 * and {@code <protocol>} is replaced by the name of the protocol. 285 * If this class does not exist, or if the class exists but it is not 286 * a subclass of {@code URLStreamHandler}, then the next package 287 * in the list is tried. 288 * <li>If the previous step fails to find a protocol handler, then the 289 * constructor tries to load a built-in protocol handler. 290 * If this class does not exist, or if the class exists but it is not a 291 * subclass of {@code URLStreamHandler}, then a 292 * {@code MalformedURLException} is thrown. 293 * </ol> 294 * 295 * <p>Protocol handlers for the following protocols are guaranteed 296 * to exist on the search path :- 297 * <blockquote><pre> 298 * http, https, file, and jar 299 * </pre></blockquote> 300 * Protocol handlers for additional protocols may also be available. 301 * Some protocol handlers, for example those used for loading platform 302 * classes or classes on the class path, may not be overridden. The details 303 * of such restrictions, and when those restrictions apply (during 304 * initialization of the runtime for example), are implementation specific 305 * and therefore not specified 306 * 307 * <p>No validation of the inputs is performed by this constructor. 308 * 309 * @param protocol the name of the protocol to use. 310 * @param host the name of the host. 311 * @param port the port number on the host. 312 * @param file the file on the host 313 * @exception MalformedURLException if an unknown protocol is specified. 314 * @see java.lang.System#getProperty(java.lang.String) 315 * @see java.net.URL#setURLStreamHandlerFactory( 316 * java.net.URLStreamHandlerFactory) 317 * @see java.net.URLStreamHandler 318 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler( 319 * java.lang.String) 320 */ 321 public URL(String protocol, String host, int port, String file) 322 throws MalformedURLException 323 { 324 this(protocol, host, port, file, null); 325 } 326 327 /** 328 * Creates a URL from the specified {@code protocol} 329 * name, {@code host} name, and {@code file} name. The 330 * default port for the specified protocol is used. 331 * <p> 332 * This method is equivalent to calling the four-argument 333 * constructor with the arguments being {@code protocol}, 334 * {@code host}, {@code -1}, and {@code file}. 335 * 336 * No validation of the inputs is performed by this constructor. 337 * 338 * @param protocol the name of the protocol to use. 339 * @param host the name of the host. 340 * @param file the file on the host. 341 * @exception MalformedURLException if an unknown protocol is specified. 342 * @see java.net.URL#URL(java.lang.String, java.lang.String, 343 * int, java.lang.String) 344 */ 345 public URL(String protocol, String host, String file) 346 throws MalformedURLException { 347 this(protocol, host, -1, file); 348 } 349 350 /** 351 * Creates a {@code URL} object from the specified 352 * {@code protocol}, {@code host}, {@code port} 353 * number, {@code file}, and {@code handler}. Specifying 354 * a {@code port} number of {@code -1} indicates that 355 * the URL should use the default port for the protocol. Specifying 356 * a {@code handler} of {@code null} indicates that the URL 357 * should use a default stream handler for the protocol, as outlined 358 * for: 359 * java.net.URL#URL(java.lang.String, java.lang.String, int, 360 * java.lang.String) 361 * 362 * <p>If the handler is not null and there is a security manager, 363 * the security manager's {@code checkPermission} 364 * method is called with a 365 * {@code NetPermission("specifyStreamHandler")} permission. 366 * This may result in a SecurityException. 367 * 368 * No validation of the inputs is performed by this constructor. 369 * 370 * @param protocol the name of the protocol to use. 371 * @param host the name of the host. 372 * @param port the port number on the host. 373 * @param file the file on the host 374 * @param handler the stream handler for the URL. 375 * @exception MalformedURLException if an unknown protocol is specified. 376 * @exception SecurityException 377 * if a security manager exists and its 378 * {@code checkPermission} method doesn't allow 379 * specifying a stream handler explicitly. 380 * @see java.lang.System#getProperty(java.lang.String) 381 * @see java.net.URL#setURLStreamHandlerFactory( 382 * java.net.URLStreamHandlerFactory) 383 * @see java.net.URLStreamHandler 384 * @see java.net.URLStreamHandlerFactory#createURLStreamHandler( 385 * java.lang.String) 386 * @see SecurityManager#checkPermission 387 * @see java.net.NetPermission 388 */ 389 public URL(String protocol, String host, int port, String file, 390 URLStreamHandler handler) throws MalformedURLException { 391 if (handler != null) { 392 SecurityManager sm = System.getSecurityManager(); 393 if (sm != null) { 394 // check for permission to specify a handler 395 checkSpecifyHandler(sm); 396 } 397 } 398 399 protocol = protocol.toLowerCase(); 400 this.protocol = protocol; 401 if (host != null) { 402 403 /** 404 * if host is a literal IPv6 address, 405 * we will make it conform to RFC 2732 406 */ 407 if (host.indexOf(':') >= 0 && !host.startsWith("[")) { 408 host = "["+host+"]"; 409 } 410 this.host = host; 411 412 if (port < -1) { 413 throw new MalformedURLException("Invalid port number :" + 414 port); 415 } 416 this.port = port; 417 authority = (port == -1) ? host : host + ":" + port; 418 } 419 420 Parts parts = new Parts(file); 421 path = parts.getPath(); 422 query = parts.getQuery(); 423 424 if (query != null) { 425 this.file = path + "?" + query; 426 } else { 427 this.file = path; 428 } 429 ref = parts.getRef(); 430 431 // Note: we don't do validation of the URL here. Too risky to change 432 // right now, but worth considering for future reference. -br 433 if (handler == null && 434 (handler = getURLStreamHandler(protocol)) == null) { 435 throw new MalformedURLException("unknown protocol: " + protocol); 436 } 437 this.handler = handler; 438 } 439 440 /** 441 * Creates a {@code URL} object from the {@code String} 442 * representation. 443 * <p> 444 * This constructor is equivalent to a call to the two-argument 445 * constructor with a {@code null} first argument. 446 * 447 * @param spec the {@code String} to parse as a URL. 448 * @exception MalformedURLException if no protocol is specified, or an 449 * unknown protocol is found, or {@code spec} is {@code null}. 450 * @see java.net.URL#URL(java.net.URL, java.lang.String) 451 */ 452 public URL(String spec) throws MalformedURLException { 453 this(null, spec); 454 } 455 456 /** 457 * Creates a URL by parsing the given spec within a specified context. 458 * 459 * The new URL is created from the given context URL and the spec 460 * argument as described in 461 * RFC2396 "Uniform Resource Identifiers : Generic * Syntax" : 462 * <blockquote><pre> 463 * <scheme>://<authority><path>?<query>#<fragment> 464 * </pre></blockquote> 465 * The reference is parsed into the scheme, authority, path, query and 466 * fragment parts. If the path component is empty and the scheme, 467 * authority, and query components are undefined, then the new URL is a 468 * reference to the current document. Otherwise, the fragment and query 469 * parts present in the spec are used in the new URL. 470 * <p> 471 * If the scheme component is defined in the given spec and does not match 472 * the scheme of the context, then the new URL is created as an absolute 473 * URL based on the spec alone. Otherwise the scheme component is inherited 474 * from the context URL. 475 * <p> 476 * If the authority component is present in the spec then the spec is 477 * treated as absolute and the spec authority and path will replace the 478 * context authority and path. If the authority component is absent in the 479 * spec then the authority of the new URL will be inherited from the 480 * context. 481 * <p> 482 * If the spec's path component begins with a slash character 483 * "/" then the 484 * path is treated as absolute and the spec path replaces the context path. 485 * <p> 486 * Otherwise, the path is treated as a relative path and is appended to the 487 * context path, as described in RFC2396. Also, in this case, 488 * the path is canonicalized through the removal of directory 489 * changes made by occurrences of ".." and ".". 490 * <p> 491 * For a more detailed description of URL parsing, refer to RFC2396. 492 * 493 * @param context the context in which to parse the specification. 494 * @param spec the {@code String} to parse as a URL. 495 * @exception MalformedURLException if no protocol is specified, or an 496 * unknown protocol is found, or {@code spec} is {@code null}. 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) throws MalformedURLException { 504 this(context, spec, null); 505 } 506 507 /** 508 * Creates a URL by parsing the given spec with the specified handler 509 * within a specified context. If the handler is null, the parsing 510 * occurs as with the two argument constructor. 511 * 512 * @param context the context in which to parse the specification. 513 * @param spec the {@code String} to parse as a URL. 514 * @param handler the stream handler for the URL. 515 * @exception MalformedURLException if no protocol is specified, or an 516 * unknown protocol is found, or {@code spec} is {@code null}. 517 * @exception SecurityException 518 * if a security manager exists and its 519 * {@code checkPermission} method doesn't allow 520 * specifying a stream handler. 521 * @see java.net.URL#URL(java.lang.String, java.lang.String, 522 * int, java.lang.String) 523 * @see java.net.URLStreamHandler 524 * @see java.net.URLStreamHandler#parseURL(java.net.URL, 525 * java.lang.String, int, int) 526 */ 527 public URL(URL context, String spec, URLStreamHandler handler) 528 throws MalformedURLException 529 { 530 String original = spec; 531 int i, limit, c; 532 int start = 0; 533 String newProtocol = null; 534 boolean aRef=false; 535 boolean isRelative = false; 536 537 // Check for permission to specify a handler 538 if (handler != null) { 539 SecurityManager sm = System.getSecurityManager(); 540 if (sm != null) { 541 checkSpecifyHandler(sm); 542 } 543 } 544 545 try { 546 limit = spec.length(); 547 while ((limit > 0) && (spec.charAt(limit - 1) <= ' ')) { 548 limit--; //eliminate trailing whitespace 549 } 550 while ((start < limit) && (spec.charAt(start) <= ' ')) { 551 start++; // eliminate leading whitespace 552 } 553 554 if (spec.regionMatches(true, start, "url:", 0, 4)) { 555 start += 4; 556 } 557 if (start < spec.length() && spec.charAt(start) == '#') { 558 /* we're assuming this is a ref relative to the context URL. 559 * This means protocols cannot start w/ '#', but we must parse 560 * ref URL's like: "hello:there" w/ a ':' in them. 561 */ 562 aRef=true; 563 } 564 for (i = start ; !aRef && (i < limit) && 565 ((c = spec.charAt(i)) != '/') ; i++) { 566 if (c == ':') { 567 568 String s = spec.substring(start, i).toLowerCase(); 569 if (isValidProtocol(s)) { 570 newProtocol = s; 571 start = i + 1; 572 } 573 break; 574 } 575 } 576 577 // Only use our context if the protocols match. 578 protocol = newProtocol; 579 if ((context != null) && ((newProtocol == null) || 580 newProtocol.equalsIgnoreCase(context.protocol))) { 581 // inherit the protocol handler from the context 582 // if not specified to the constructor 583 if (handler == null) { 584 handler = context.handler; 585 } 586 587 // If the context is a hierarchical URL scheme and the spec 588 // contains a matching scheme then maintain backwards 589 // compatibility and treat it as if the spec didn't contain 590 // the scheme; see 5.2.3 of RFC2396 591 if (context.path != null && context.path.startsWith("/")) 592 newProtocol = null; 593 594 if (newProtocol == null) { 595 protocol = context.protocol; 596 authority = context.authority; 597 userInfo = context.userInfo; 598 host = context.host; 599 port = context.port; 600 file = context.file; 601 path = context.path; 602 isRelative = true; 603 } 604 } 605 606 if (protocol == null) { 607 throw new MalformedURLException("no protocol: "+original); 608 } 609 610 // Get the protocol handler if not specified or the protocol 611 // of the context could not be used 612 if (handler == null && 613 (handler = getURLStreamHandler(protocol)) == null) { 614 throw new MalformedURLException("unknown protocol: "+protocol); 615 } 616 617 this.handler = handler; 618 619 i = spec.indexOf('#', start); 620 if (i >= 0) { 621 ref = spec.substring(i + 1, limit); 622 limit = i; 623 } 624 625 /* 626 * Handle special case inheritance of query and fragment 627 * implied by RFC2396 section 5.2.2. 628 */ 629 if (isRelative && start == limit) { 630 query = context.query; 631 if (ref == null) { 632 ref = context.ref; 633 } 634 } 635 636 handler.parseURL(this, spec, start, limit); 637 638 } catch(MalformedURLException e) { 639 throw e; 640 } catch(Exception e) { 641 MalformedURLException exception = new MalformedURLException(e.getMessage()); 642 exception.initCause(e); 643 throw exception; 644 } 645 } 646 647 /* 648 * Returns true if specified string is a valid protocol name. 649 */ 650 private boolean isValidProtocol(String protocol) { 651 int len = protocol.length(); 652 if (len < 1) 653 return false; 654 char c = protocol.charAt(0); 655 if (!Character.isLetter(c)) 656 return false; 657 for (int i = 1; i < len; i++) { 658 c = protocol.charAt(i); 659 if (!Character.isLetterOrDigit(c) && c != '.' && c != '+' && 660 c != '-') { 661 return false; 662 } 663 } 664 return true; 665 } 666 667 /* 668 * Checks for permission to specify a stream handler. 669 */ 670 private void checkSpecifyHandler(SecurityManager sm) { 671 sm.checkPermission(SecurityConstants.SPECIFY_HANDLER_PERMISSION); 672 } 673 674 /** 675 * Sets the fields of the URL. This is not a public method so that 676 * only URLStreamHandlers can modify URL fields. URLs are 677 * otherwise constant. 678 * 679 * @param protocol the name of the protocol to use 680 * @param host the name of the host 681 @param port the port number on the host 682 * @param file the file on the host 683 * @param ref the internal reference in the URL 684 */ 685 void set(String protocol, String host, int port, 686 String file, String ref) { 687 synchronized (this) { 688 this.protocol = protocol; 689 this.host = host; 690 authority = port == -1 ? host : host + ":" + port; 691 this.port = port; 692 this.file = file; 693 this.ref = ref; 694 /* This is very important. We must recompute this after the 695 * URL has been changed. */ 696 hashCode = -1; 697 hostAddress = null; 698 int q = file.lastIndexOf('?'); 699 if (q != -1) { 700 query = file.substring(q+1); 701 path = file.substring(0, q); 702 } else 703 path = file; 704 } 705 } 706 707 /** 708 * Sets the specified 8 fields of the URL. This is not a public method so 709 * that only URLStreamHandlers can modify URL fields. URLs are otherwise 710 * constant. 711 * 712 * @param protocol the name of the protocol to use 713 * @param host the name of the host 714 * @param port the port number on the host 715 * @param authority the authority part for the url 716 * @param userInfo the username and password 717 * @param path the file on the host 718 * @param ref the internal reference in the URL 719 * @param query the query part of this URL 720 * @since 1.3 721 */ 722 void set(String protocol, String host, int port, 723 String authority, String userInfo, String path, 724 String query, String ref) { 725 synchronized (this) { 726 this.protocol = protocol; 727 this.host = host; 728 this.port = port; 729 this.file = query == null ? path : path + "?" + query; 730 this.userInfo = userInfo; 731 this.path = path; 732 this.ref = ref; 733 /* This is very important. We must recompute this after the 734 * URL has been changed. */ 735 hashCode = -1; 736 hostAddress = null; 737 this.query = query; 738 this.authority = authority; 739 } 740 } 741 742 /** 743 * Gets the query part of this {@code URL}. 744 * 745 * @return the query part of this {@code URL}, 746 * or <CODE>null</CODE> if one does not exist 747 * @since 1.3 748 */ 749 public String getQuery() { 750 return query; 751 } 752 753 /** 754 * Gets the path part of this {@code URL}. 755 * 756 * @return the path part of this {@code URL}, or an 757 * empty string if one does not exist 758 * @since 1.3 759 */ 760 public String getPath() { 761 return path; 762 } 763 764 /** 765 * Gets the userInfo part of this {@code URL}. 766 * 767 * @return the userInfo part of this {@code URL}, or 768 * <CODE>null</CODE> if one does not exist 769 * @since 1.3 770 */ 771 public String getUserInfo() { 772 return userInfo; 773 } 774 775 /** 776 * Gets the authority part of this {@code URL}. 777 * 778 * @return the authority part of this {@code URL} 779 * @since 1.3 780 */ 781 public String getAuthority() { 782 return authority; 783 } 784 785 /** 786 * Gets the port number of this {@code URL}. 787 * 788 * @return the port number, or -1 if the port is not set 789 */ 790 public int getPort() { 791 return port; 792 } 793 794 /** 795 * Gets the default port number of the protocol associated 796 * with this {@code URL}. If the URL scheme or the URLStreamHandler 797 * for the URL do not define a default port number, 798 * then -1 is returned. 799 * 800 * @return the port number 801 * @since 1.4 802 */ 803 public int getDefaultPort() { 804 return handler.getDefaultPort(); 805 } 806 807 /** 808 * Gets the protocol name of this {@code URL}. 809 * 810 * @return the protocol of this {@code URL}. 811 */ 812 public String getProtocol() { 813 return protocol; 814 } 815 816 /** 817 * Gets the host name of this {@code URL}, if applicable. 818 * The format of the host conforms to RFC 2732, i.e. for a 819 * literal IPv6 address, this method will return the IPv6 address 820 * enclosed in square brackets ({@code '['} and {@code ']'}). 821 * 822 * @return the host name of this {@code URL}. 823 */ 824 public String getHost() { 825 return host; 826 } 827 828 /** 829 * Gets the file name of this {@code URL}. 830 * The returned file portion will be 831 * the same as <CODE>getPath()</CODE>, plus the concatenation of 832 * the value of <CODE>getQuery()</CODE>, if any. If there is 833 * no query portion, this method and <CODE>getPath()</CODE> will 834 * return identical results. 835 * 836 * @return the file name of this {@code URL}, 837 * or an empty string if one does not exist 838 */ 839 public String getFile() { 840 return file; 841 } 842 843 /** 844 * Gets the anchor (also known as the "reference") of this 845 * {@code URL}. 846 * 847 * @return the anchor (also known as the "reference") of this 848 * {@code URL}, or <CODE>null</CODE> if one does not exist 849 */ 850 public String getRef() { 851 return ref; 852 } 853 854 /** 855 * Compares this URL for equality with another object.<p> 856 * 857 * If the given object is not a URL then this method immediately returns 858 * {@code false}.<p> 859 * 860 * Two URL objects are equal if they have the same protocol, reference 861 * equivalent hosts, have the same port number on the host, and the same 862 * file and fragment of the file.<p> 863 * 864 * Two hosts are considered equivalent if both host names can be resolved 865 * into the same IP addresses; else if either host name can't be 866 * resolved, the host names must be equal without regard to case; or both 867 * host names equal to null.<p> 868 * 869 * Since hosts comparison requires name resolution, this operation is a 870 * blocking operation. <p> 871 * 872 * Note: The defined behavior for {@code equals} is known to 873 * be inconsistent with virtual hosting in HTTP. 874 * 875 * @param obj the URL to compare against. 876 * @return {@code true} if the objects are the same; 877 * {@code false} otherwise. 878 */ 879 public boolean equals(Object obj) { 880 if (!(obj instanceof URL)) 881 return false; 882 URL u2 = (URL)obj; 883 884 return handler.equals(this, u2); 885 } 886 887 /** 888 * Creates an integer suitable for hash table indexing.<p> 889 * 890 * The hash code is based upon all the URL components relevant for URL 891 * comparison. As such, this operation is a blocking operation. 892 * 893 * @return a hash code for this {@code URL}. 894 */ 895 public synchronized int hashCode() { 896 if (hashCode != -1) 897 return hashCode; 898 899 hashCode = handler.hashCode(this); 900 return hashCode; 901 } 902 903 /** 904 * Compares two URLs, excluding the fragment component.<p> 905 * 906 * Returns {@code true} if this {@code URL} and the 907 * {@code other} argument are equal without taking the 908 * fragment component into consideration. 909 * 910 * @param other the {@code URL} to compare against. 911 * @return {@code true} if they reference the same remote object; 912 * {@code false} otherwise. 913 */ 914 public boolean sameFile(URL other) { 915 return handler.sameFile(this, other); 916 } 917 918 /** 919 * Constructs a string representation of this {@code URL}. The 920 * string is created by calling the {@code toExternalForm} 921 * method of the stream protocol handler for this object. 922 * 923 * @return a string representation of this object. 924 * @see java.net.URL#URL(java.lang.String, java.lang.String, int, 925 * java.lang.String) 926 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL) 927 */ 928 public String toString() { 929 return toExternalForm(); 930 } 931 932 /** 933 * Constructs a string representation of this {@code URL}. The 934 * string is created by calling the {@code toExternalForm} 935 * method of the stream protocol handler for this object. 936 * 937 * @return a string representation of this object. 938 * @see java.net.URL#URL(java.lang.String, java.lang.String, 939 * int, java.lang.String) 940 * @see java.net.URLStreamHandler#toExternalForm(java.net.URL) 941 */ 942 public String toExternalForm() { 943 return handler.toExternalForm(this); 944 } 945 946 /** 947 * Returns a {@link java.net.URI} equivalent to this URL. 948 * This method functions in the same way as {@code new URI (this.toString())}. 949 * <p>Note, any URL instance that complies with RFC 2396 can be converted 950 * to a URI. However, some URLs that are not strictly in compliance 951 * can not be converted to a URI. 952 * 953 * @exception URISyntaxException if this URL is not formatted strictly according to 954 * to RFC2396 and cannot be converted to a URI. 955 * 956 * @return a URI instance equivalent to this URL. 957 * @since 1.5 958 */ 959 public URI toURI() throws URISyntaxException { 960 return new URI (toString()); 961 } 962 963 /** 964 * Returns a {@link java.net.URLConnection URLConnection} instance that 965 * represents a connection to the remote object referred to by the 966 * {@code URL}. 967 * 968 * <P>A new instance of {@linkplain java.net.URLConnection URLConnection} is 969 * created every time when invoking the 970 * {@linkplain java.net.URLStreamHandler#openConnection(URL) 971 * URLStreamHandler.openConnection(URL)} method of the protocol handler for 972 * this URL.</P> 973 * 974 * <P>It should be noted that a URLConnection instance does not establish 975 * the actual network connection on creation. This will happen only when 976 * calling {@linkplain java.net.URLConnection#connect() URLConnection.connect()}.</P> 977 * 978 * <P>If for the URL's protocol (such as HTTP or JAR), there 979 * exists a public, specialized URLConnection subclass belonging 980 * to one of the following packages or one of their subpackages: 981 * java.lang, java.io, java.util, java.net, the connection 982 * returned will be of that subclass. For example, for HTTP an 983 * HttpURLConnection will be returned, and for JAR a 984 * JarURLConnection will be returned.</P> 985 * 986 * @return a {@link java.net.URLConnection URLConnection} linking 987 * to the URL. 988 * @exception IOException if an I/O exception occurs. 989 * @see java.net.URL#URL(java.lang.String, java.lang.String, 990 * int, java.lang.String) 991 */ 992 public URLConnection openConnection() throws java.io.IOException { 993 return handler.openConnection(this); 994 } 995 996 /** 997 * Same as {@link #openConnection()}, except that the connection will be 998 * made through the specified proxy; Protocol handlers that do not 999 * support proxing will ignore the proxy parameter and make a 1000 * normal connection. 1001 * 1002 * Invoking this method preempts the system's default 1003 * {@link java.net.ProxySelector ProxySelector} settings. 1004 * 1005 * @param proxy the Proxy through which this connection 1006 * will be made. If direct connection is desired, 1007 * Proxy.NO_PROXY should be specified. 1008 * @return a {@code URLConnection} to the URL. 1009 * @exception IOException if an I/O exception occurs. 1010 * @exception SecurityException if a security manager is present 1011 * and the caller doesn't have permission to connect 1012 * to the proxy. 1013 * @exception IllegalArgumentException will be thrown if proxy is null, 1014 * or proxy has the wrong type 1015 * @exception UnsupportedOperationException if the subclass that 1016 * implements the protocol handler doesn't support 1017 * this method. 1018 * @see java.net.URL#URL(java.lang.String, java.lang.String, 1019 * int, java.lang.String) 1020 * @see java.net.URLConnection 1021 * @see java.net.URLStreamHandler#openConnection(java.net.URL, 1022 * java.net.Proxy) 1023 * @since 1.5 1024 */ 1025 public URLConnection openConnection(Proxy proxy) 1026 throws java.io.IOException { 1027 if (proxy == null) { 1028 throw new IllegalArgumentException("proxy can not be null"); 1029 } 1030 1031 // Create a copy of Proxy as a security measure 1032 Proxy p = proxy == Proxy.NO_PROXY ? Proxy.NO_PROXY : sun.net.ApplicationProxy.create(proxy); 1033 SecurityManager sm = System.getSecurityManager(); 1034 if (p.type() != Proxy.Type.DIRECT && sm != null) { 1035 InetSocketAddress epoint = (InetSocketAddress) p.address(); 1036 if (epoint.isUnresolved()) 1037 sm.checkConnect(epoint.getHostName(), epoint.getPort()); 1038 else 1039 sm.checkConnect(epoint.getAddress().getHostAddress(), 1040 epoint.getPort()); 1041 } 1042 return handler.openConnection(this, p); 1043 } 1044 1045 /** 1046 * Opens a connection to this {@code URL} and returns an 1047 * {@code InputStream} for reading from that connection. This 1048 * method is a shorthand for: 1049 * <blockquote><pre> 1050 * openConnection().getInputStream() 1051 * </pre></blockquote> 1052 * 1053 * @return an input stream for reading from the URL connection. 1054 * @exception IOException if an I/O exception occurs. 1055 * @see java.net.URL#openConnection() 1056 * @see java.net.URLConnection#getInputStream() 1057 */ 1058 public final InputStream openStream() throws java.io.IOException { 1059 return openConnection().getInputStream(); 1060 } 1061 1062 /** 1063 * Gets the contents of this URL. This method is a shorthand for: 1064 * <blockquote><pre> 1065 * openConnection().getContent() 1066 * </pre></blockquote> 1067 * 1068 * @return the contents of this URL. 1069 * @exception IOException if an I/O exception occurs. 1070 * @see java.net.URLConnection#getContent() 1071 */ 1072 public final Object getContent() throws java.io.IOException { 1073 return openConnection().getContent(); 1074 } 1075 1076 /** 1077 * Gets the contents of this URL. This method is a shorthand for: 1078 * <blockquote><pre> 1079 * openConnection().getContent(classes) 1080 * </pre></blockquote> 1081 * 1082 * @param classes an array of Java types 1083 * @return the content object of this URL that is the first match of 1084 * the types specified in the classes array. 1085 * null if none of the requested types are supported. 1086 * @exception IOException if an I/O exception occurs. 1087 * @see java.net.URLConnection#getContent(Class[]) 1088 * @since 1.3 1089 */ 1090 public final Object getContent(Class<?>[] classes) 1091 throws java.io.IOException { 1092 return openConnection().getContent(classes); 1093 } 1094 1095 /** 1096 * The URLStreamHandler factory. 1097 */ 1098 private static volatile URLStreamHandlerFactory factory; 1099 1100 /** 1101 * Sets an application's {@code URLStreamHandlerFactory}. 1102 * This method can be called at most once in a given Java Virtual 1103 * Machine. 1104 * 1105 *<p> The {@code URLStreamHandlerFactory} instance is used to 1106 *construct a stream protocol handler from a protocol name. 1107 * 1108 * <p> If there is a security manager, this method first calls 1109 * the security manager's {@code checkSetFactory} method 1110 * to ensure the operation is allowed. 1111 * This could result in a SecurityException. 1112 * 1113 * @param fac the desired factory. 1114 * @exception Error if the application has already set a factory. 1115 * @exception SecurityException if a security manager exists and its 1116 * {@code checkSetFactory} method doesn't allow 1117 * the operation. 1118 * @see java.net.URL#URL(java.lang.String, java.lang.String, 1119 * int, java.lang.String) 1120 * @see java.net.URLStreamHandlerFactory 1121 * @see SecurityManager#checkSetFactory 1122 */ 1123 public static void setURLStreamHandlerFactory(URLStreamHandlerFactory fac) { 1124 synchronized (streamHandlerLock) { 1125 if (factory != null) { 1126 throw new Error("factory already defined"); 1127 } 1128 SecurityManager security = System.getSecurityManager(); 1129 if (security != null) { 1130 security.checkSetFactory(); 1131 } 1132 handlers.clear(); 1133 1134 // safe publication of URLStreamHandlerFactory with volatile write 1135 factory = fac; 1136 } 1137 } 1138 1139 private static final URLStreamHandlerFactory defaultFactory = new DefaultFactory(); 1140 1141 private static class DefaultFactory implements URLStreamHandlerFactory { 1142 private static String PREFIX = "sun.net.www.protocol"; 1143 1144 public URLStreamHandler createURLStreamHandler(String protocol) { 1145 String name = PREFIX + "." + protocol + ".Handler"; 1146 try { 1147 Class<?> c = Class.forName(name); 1148 return (URLStreamHandler)c.newInstance(); 1149 } catch (ClassNotFoundException x) { 1150 // ignore 1151 } catch (Exception e) { 1152 // For compatibility, all Exceptions are ignored. 1153 // any number of exceptions can get thrown here 1154 } 1155 return null; 1156 } 1157 } 1158 1159 private static URLStreamHandler lookupViaProperty(String protocol) { 1160 String packagePrefixList = java.security.AccessController.doPrivileged( 1161 new PrivilegedAction<>() { 1162 public String run() { 1163 return System.getProperty(protocolPathProp, ""); 1164 } 1165 }); 1166 String[] packagePrefixes = packagePrefixList.split("\\|"); 1167 1168 URLStreamHandler handler = null; 1169 for (int i=0; handler == null && i<packagePrefixes.length; i++) { 1170 String packagePrefix = packagePrefixes[i].trim(); 1171 try { 1172 String clsName = packagePrefix + "." + protocol + ".Handler"; 1173 Class<?> cls = null; 1174 try { 1175 cls = Class.forName(clsName); 1176 } catch (ClassNotFoundException e) { 1177 ClassLoader cl = ClassLoader.getSystemClassLoader(); 1178 if (cl != null) { 1179 cls = cl.loadClass(clsName); 1180 } 1181 } 1182 if (cls != null) { 1183 handler = (URLStreamHandler)cls.newInstance(); 1184 } 1185 } catch (Exception e) { 1186 // any number of exceptions can get thrown here 1187 } 1188 } 1189 return handler; 1190 } 1191 1192 private static Iterator<URLStreamHandlerProvider> providers() { 1193 return new Iterator<>() { 1194 1195 ClassLoader cl = ClassLoader.getSystemClassLoader(); 1196 ServiceLoader<URLStreamHandlerProvider> sl = 1197 ServiceLoader.load(URLStreamHandlerProvider.class, cl); 1198 Iterator<URLStreamHandlerProvider> i = sl.iterator(); 1199 1200 URLStreamHandlerProvider next = null; 1201 1202 private boolean getNext() { 1203 while (next == null) { 1204 try { 1205 if (!i.hasNext()) 1206 return false; 1207 next = i.next(); 1208 } catch (ServiceConfigurationError sce) { 1209 if (sce.getCause() instanceof SecurityException) { 1210 // Ignore security exceptions 1211 continue; 1212 } 1213 throw sce; 1214 } 1215 } 1216 return true; 1217 } 1218 1219 public boolean hasNext() { 1220 return getNext(); 1221 } 1222 1223 public URLStreamHandlerProvider next() { 1224 if (!getNext()) 1225 throw new NoSuchElementException(); 1226 URLStreamHandlerProvider n = next; 1227 next = null; 1228 return n; 1229 } 1230 }; 1231 } 1232 1233 // Thread-local gate to prevent recursive provider lookups 1234 private static ThreadLocal<Object> gate = new ThreadLocal<>(); 1235 1236 private static URLStreamHandler lookupViaProviders(final String protocol) { 1237 if (!sun.misc.VM.isBooted()) 1238 return null; 1239 1240 if (gate.get() != null) 1241 throw new Error("Circular loading of URL stream handler providers detected"); 1242 1243 gate.set(gate); 1244 try { 1245 return AccessController.doPrivileged( 1246 new PrivilegedAction<>() { 1247 public URLStreamHandler run() { 1248 Iterator<URLStreamHandlerProvider> itr = providers(); 1249 while (itr.hasNext()) { 1250 URLStreamHandlerProvider f = itr.next(); 1251 URLStreamHandler h = f.createURLStreamHandler(protocol); 1252 if (h != null) 1253 return h; 1254 } 1255 return null; 1256 } 1257 }); 1258 } finally { 1259 gate.set(null); 1260 } 1261 } 1262 1263 private static final String[] NON_OVERRIDEABLE_PROTOCOLS = {"file", "jrt"}; 1264 private static boolean isOverrideable(String protocol) { 1265 for (String p : NON_OVERRIDEABLE_PROTOCOLS) 1266 if (protocol.equalsIgnoreCase(p)) 1267 return false; 1268 return true; 1269 } 1270 1271 /** 1272 * A table of protocol handlers. 1273 */ 1274 static Hashtable<String,URLStreamHandler> handlers = new Hashtable<>(); 1275 private static final Object streamHandlerLock = new Object(); 1276 1277 /** 1278 * Returns the Stream Handler. 1279 * @param protocol the protocol to use 1280 */ 1281 static URLStreamHandler getURLStreamHandler(String protocol) { 1282 1283 URLStreamHandler handler = handlers.get(protocol); 1284 1285 if (handler != null) { 1286 return handler; 1287 } 1288 1289 URLStreamHandlerFactory fac; 1290 boolean checkedWithFactory = false; 1291 1292 if (isOverrideable(protocol)) { 1293 // Use the factory (if any). Volatile read makes 1294 // URLStreamHandlerFactory appear fully initialized to current thread. 1295 fac = factory; 1296 if (fac != null) { 1297 handler = fac.createURLStreamHandler(protocol); 1298 checkedWithFactory = true; 1299 } 1300 1301 if (handler == null && !protocol.equalsIgnoreCase("jar")) { 1302 handler = lookupViaProviders(protocol); 1303 } 1304 1305 if (handler == null) { 1306 handler = lookupViaProperty(protocol); 1307 } 1308 } 1309 1310 synchronized (streamHandlerLock) { 1311 if (handler == null) { 1312 // Try the built-in protocol handler 1313 handler = defaultFactory.createURLStreamHandler(protocol); 1314 } else { 1315 URLStreamHandler handler2 = null; 1316 1317 // Check again with hashtable just in case another 1318 // thread created a handler since we last checked 1319 handler2 = handlers.get(protocol); 1320 1321 if (handler2 != null) { 1322 return handler2; 1323 } 1324 1325 // Check with factory if another thread set a 1326 // factory since our last check 1327 if (!checkedWithFactory && (fac = factory) != null) { 1328 handler2 = fac.createURLStreamHandler(protocol); 1329 } 1330 1331 if (handler2 != null) { 1332 // The handler from the factory must be given more 1333 // importance. Discard the default handler that 1334 // this thread created. 1335 handler = handler2; 1336 } 1337 } 1338 1339 // Insert this handler into the hashtable 1340 if (handler != null) { 1341 handlers.put(protocol, handler); 1342 } 1343 } 1344 1345 return handler; 1346 } 1347 1348 /** 1349 * WriteObject is called to save the state of the URL to an 1350 * ObjectOutputStream. The handler is not saved since it is 1351 * specific to this system. 1352 * 1353 * @serialData the default write object value. When read back in, 1354 * the reader must ensure that calling getURLStreamHandler with 1355 * the protocol variable returns a valid URLStreamHandler and 1356 * throw an IOException if it does not. 1357 */ 1358 private synchronized void writeObject(java.io.ObjectOutputStream s) 1359 throws IOException 1360 { 1361 s.defaultWriteObject(); // write the fields 1362 } 1363 1364 /** 1365 * readObject is called to restore the state of the URL from the 1366 * stream. It reads the components of the URL and finds the local 1367 * stream handler. 1368 */ 1369 private synchronized void readObject(java.io.ObjectInputStream s) 1370 throws IOException, ClassNotFoundException 1371 { 1372 s.defaultReadObject(); // read the fields 1373 if ((handler = getURLStreamHandler(protocol)) == null) { 1374 throw new IOException("unknown protocol: " + protocol); 1375 } 1376 1377 // Construct authority part 1378 if (authority == null && 1379 ((host != null && host.length() > 0) || port != -1)) { 1380 if (host == null) 1381 host = ""; 1382 authority = (port == -1) ? host : host + ":" + port; 1383 1384 // Handle hosts with userInfo in them 1385 int at = host.lastIndexOf('@'); 1386 if (at != -1) { 1387 userInfo = host.substring(0, at); 1388 host = host.substring(at+1); 1389 } 1390 } else if (authority != null) { 1391 // Construct user info part 1392 int ind = authority.indexOf('@'); 1393 if (ind != -1) 1394 userInfo = authority.substring(0, ind); 1395 } 1396 1397 // Construct path and query part 1398 path = null; 1399 query = null; 1400 if (file != null) { 1401 // Fix: only do this if hierarchical? 1402 int q = file.lastIndexOf('?'); 1403 if (q != -1) { 1404 query = file.substring(q+1); 1405 path = file.substring(0, q); 1406 } else 1407 path = file; 1408 } 1409 } 1410 } 1411 1412 class Parts { 1413 String path, query, ref; 1414 1415 Parts(String file) { 1416 int ind = file.indexOf('#'); 1417 ref = ind < 0 ? null: file.substring(ind + 1); 1418 file = ind < 0 ? file: file.substring(0, ind); 1419 int q = file.lastIndexOf('?'); 1420 if (q != -1) { 1421 query = file.substring(q+1); 1422 path = file.substring(0, q); 1423 } else { 1424 path = file; 1425 } 1426 } 1427 1428 String getPath() { 1429 return path; 1430 } 1431 1432 String getQuery() { 1433 return query; 1434 } 1435 1436 String getRef() { 1437 return ref; 1438 } 1439 }