url.java

来自「《移动Agent技术》一书的所有章节源代码。」· Java 代码 · 共 719 行 · 第 1/2 页

/*
 * @(#)URL.java	1.43 97/09/29
 * 
 * Copyright (c) 1995, 1996 Sun Microsystems, Inc. All Rights Reserved.
 * 
 * This software is the confidential and proprietary information of Sun
 * Microsystems, Inc. ("Confidential Information").  You shall not
 * disclose such Confidential Information and shall use it only in
 * accordance with the terms of the license agreement you entered into
 * with Sun.
 * 
 * SUN MAKES NO REPRESENTATIONS OR WARRANTIES ABOUT THE SUITABILITY OF THE
 * SOFTWARE, EITHER EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR
 * PURPOSE, OR NON-INFRINGEMENT. SUN SHALL NOT BE LIABLE FOR ANY DAMAGES
 * SUFFERED BY LICENSEE AS A RESULT OF USING, MODIFYING OR DISTRIBUTING
 * THIS SOFTWARE OR ITS DERIVATIVES.
 * 
 * CopyrightVersion 1.1_beta
 * 
 */

package java.net;

import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;
import java.util.Hashtable;
import java.util.StringTokenizer;

/**
 * Class <code>URL</code> represents a Uniform Resource 
 * Locator, a pointer to a "resource" on the World 
 * Wide Web. A resource can be something as simple as a file or a 
 * directory, or it can be a reference to a more complicated object, 
 * such as a query to a database or to a search engine. More 
 * information on the types of URLs and their formats can be found at:
 * <ul><code>
 *     http://www.ncsa.uiuc.edu/demoweb/url-primer.html
 * </code></ul>
 * <p>
 * In general, a URL can be broken into several parts. The previous 
 * example of a URL indicates that the protocol to use is 
 * <code>http</code> (HyperText Transport Protocol) and that the 
 * information resides on a host machine named 
 * <code>www.ncsa.uiuc.edu</code>. The information on that host 
 * machine is named <code>demoweb/url-primer.html</code>. The exact 
 * meaning of this name on the host machine is both protocol 
 * dependent and host dependent. The information normally resides in 
 * a file, but it could be generated on the fly. This component of 
 * the URL is called the <i>file</i> component, even though the 
 * information is not necessarily in a file. 
 * <p>
 * A URL can optionally specify a "port", which is the 
 * port number to which the TCP connection is made on the remote host 
 * machine. If the port is not specified, the default port for 
 * the protocol is used instead. For example, the default port for 
 * <code>http</code> is <code>80</code>. An alternative port could be 
 * specified as: 
 * <ul><code>
 *     http://www.ncsa.uiuc.edu:8080/demoweb/url-primer.html
 * </code></ul>
 * <p>
 * A URL may have appended to it an "anchor", also known 
 * as a "ref" or a "reference". The anchor is 
 * indicated by the sharp sign character "#" followed by 
 * more characters. For example, 
 * <ul><code>
 *     http://java.sun.com/index.html#chapter1
 * </code></ul>
 * <p>
 * This anchor is not technically part of the URL. Rather, it 
 * indicates that after the specified resource is retrieved, the 
 * application is specifically interested in that part of the 
 * document that has the tag <code>chapter1</code> attached to it. The 
 * meaning of a tag is resource specific. 
 * <p>
 * An application can also specify a "relative URL", 
 * which contains only enough information to reach the resource 
 * relative to another URL. Relative URLs are frequently used within 
 * HTML pages. For example, if the contents of the URL:
 * <ul><code>
 *     http://java.sun.com/index.html
 * </code></ul>
 * contained within it the relative URL:
 * <ul><code>
 *     FAQ.html
 * </code></ul>
 * it would be a shorthand for:
 * <ul><code>
 *     http://java.sun.com/FAQ.html
 * </code></ul>
 * <p>
 * The relative URL need not specify all the components of a URL. If 
 * the protocol, host name, or port number is missing, the value is 
 * inherited from the fully specified URL. The file component must be 
 * specified. The optional anchor is not inherited. 
 *
 * @author  James Gosling
 * @version 1.43, 09/29/97
 * @since   JDK1.0
 */
public final class URL implements java.io.Serializable {
    /**
     * The property which specifies the package prefix list to be scanned
     * for protocol handlers.  The value of this property (if any) should
     * be a vertical bar delimited list of package names to search through
     * for a protocol handler to load.  The policy of this class is that
     * all protocol handlers will be in a class called <protocolname>.Handler,
     * and each package in the list is examined in turn for a matching
     * handler.  If none are found (or the property is not specified), the
     * default package prefix, sun.net.www.protocol, is used.  The search
     * proceeds from the first package in the last to the last and stops
     * when a match is found.
     */
    private static final String protocolPathProp = "java.protocol.handler.pkgs";

    /** 
     * The protocol to use (ftp, http, nntp, ... etc.) . 
     */
    private String protocol;

    /** 
     * The host name in which to connect to. 
     */
    private String host;

    /** 
     * The protocol port to connect to. 
     */
    private int port = -1;

    /** 
     * The specified file name on that host. 
     */
    private String file;

    /** 
     * # reference. 
     */
    private String ref;

    /**
     * The URLStreamHandler for this URL.
     */
    transient URLStreamHandler handler;

    /* Our hash code */
    private int hashCode = -1;

    /** 
     * Creates a <code>URL</code> object from the specified 
     * <code>protocol</code>, <code>host</code>, <code>port</code> 
     * number, and <code>file</code>. Specifying a <code>port</code> 
     * number of <code>-1</code> indicates that the URL should use 
     * the default port for the protocol. 
     * <p>
     * If this is the first URL object being created with the specified 
     * protocol, a <i>stream protocol handler</i> object, an instance of 
     * class <code>URLStreamHandler</code>, is created for that protocol:
     * <ol>
     * <li>If the application has previously set up an instance of
     *     <code>URLStreamHandlerFactory</code> as the stream handler factory,
     *     then the <code>createURLStreamHandler</code> method of that instance
     *     is called with the protocol string as an argument to create the
     *     stream protocol handler.
     * <li>If no <code>URLStreamHandlerFactory</code> has yet been set up,
     *     or if the factory's <code>createURLStreamHandler</code> method
     *     returns <code>null</code>, then the constructor finds the 
     *     value of the system property:
     *     <ul><code>
     *         java.handler.protol.pkgs
     *     </code></ul>
     *     If the value of that system property is not <code>null</code>,
     *     it is interpreted as a list of packages separated by a vertical
     *     slash character '<code>|</code>'. The constructor tries to load 
     *     the class named:
     *     <ul><code>
     *         &lt;<i>package</i>&gt;.&lt;<i>protocol</i>&gt;.Handler
     *     </code></ul>
     *     where &lt;<i>package</i>&gt; is replaced by the name of the package
     *     and &lt;<i>protocol</i>&gt; is replaced by the name of the protocol.
     *     If this class does not exist, or if the class exists but it is not
     *     a subclass of <code>URLStreamHandler</code>, then the next package
     *     in the list is tried.
     * <li>If the previous step fails to find a protocol handler, then the
     *     constructor tries to load the class named:
     *     <ul><code>
     *         sun.net.www.protocol.&lt;<i>protocol</i>&gt;.Handler
     *     </code></ul>
     *     If this class does not exist, or if the class exists but it is not a
     *     subclass of <code>URLStreamHandler</code>, then a
     *     <code>MalformedURLException</code> is thrown.
     * </ol>
     *
     * @param      protocol   the name of the protocol.
     * @param      host       the name of the host.
     * @param      port       the port number.
     * @param      file       the host file.
     * @exception  MalformedURLException  if an unknown protocol is specified.
     * @see        java.lang.System#getProperty(java.lang.String)
     * @see        java.net.URL#setURLStreamHandlerFactory(java.net.URLStreamHandlerFactory)
     * @see        java.net.URLStreamHandler
     * @see        java.net.URLStreamHandlerFactory#createURLStreamHandler(java.lang.String)
     * @since      JDK1.0
     */
    public URL(String protocol, String host, int port, String file)
	throws MalformedURLException {
	this.protocol = protocol;
	this.host = host;
	this.port = port;
	int ind = file.indexOf('#');
	this.file = ind < 0 ? file: file.substring(0, ind);
	this.ref = ind < 0 ? null: file.substring(ind + 1);
	if ((handler = getURLStreamHandler(protocol)) == null) {
	    throw new MalformedURLException("unknown protocol: " + protocol);
	}
    }

    /** 
     * Creates an absolute URL from the specified <code>protocol</code> 
     * name, <code>host</code> name, and <code>file</code> name. The 
     * default port for the specified protocol is used. 
     * <p>
     * This method is equivalent to calling the four-argument 
     * constructor with the arguments being <code>protocol</code>, 
     * <code>host</code>, <code>-1</code>, and <code>file</code>. 
     *
     * @param      protocol   the protocol to use.
     * @param      host       the host to connect to.
     * @param      file       the file on that host.
     * @exception  MalformedURLException  if an unknown protocol is specified.
     * @see        java.net.URL#URL(java.lang.String, java.lang.String, int, java.lang.String)
     * @since      JDK1.0
     */
    public URL(String protocol, String host, String file) throws MalformedURLException {
	this(protocol, host, -1, file);
    }

    /**
     * Creates a <code>URL</code> object from the <code>String</code> 
     * representation. 
     * <p>
     * This constructor is equivalent to a call to the two-argument 
     * constructor with a <code>null</code> first argument. 
     *
     * @param      spec   the <code>String</code> to parse as a URL.
     * @exception  MalformedURLException  If the string specifies an
     *               unknown protocol.
     * @see        java.net.URL#URL(java.net.URL, java.lang.String)
     * @since      JDK1.0
     */
    public URL(String spec) throws MalformedURLException {
	this(null, spec);
    }

    /** 
     * Creates a URL by parsing the specification <code>spec</code> 
     * within a specified context. If the <code>context</code> argument 
     * is not <code>null</code> and the <code>spec</code> argument is a 
     * partial URL specification, then any of the strings missing 
     * components are inherited from the <code>context</code> argument. 
     * <p>
     * The specification given by the <code>String</code> argument is 
     * parsed to determine if it specifies a protocol. If the 
     * <code>String</code> contains an ASCII colon '<code>:</code>'
     * character before the first occurrence of an ASCII slash character 
     * '<code>/</code>', then the characters before the colon comprise 
     * the protocol. 
     * <ul>
     * <li>If the <code>spec</code> argument does not specify a protocol:
     *     <ul>
     *     <li>If the context argument is not <code>null</code>, then the
     *         protocol is copied from the context argument.
     *     <li>If the context argument is <code>null</code>, then a
     *         <code>MalformedURLException</code> is thrown.
     *     </ul>
     * <li>If the <code>spec</code> argument does specify a protocol:
     *     <ul>
     *     <li>If the context argument is <code>null</code>, or specifies a
     *         different protocol than the specification argument, the context
     *         argument is ignored.
     *     <li>If the context argument is not <code>null</code> and specifies
     *         the same protocol as the specification, the <code>host</code>,
     *         <code>port</code> number, and <code>file</code> are copied from
     *         the context argument into the newly created <code>URL</code>.
     *     </ul>
     * </ul>
     * <p>
     * The constructor then searches for an appropriate stream protocol 
     * handler of type <code>URLStreamHandler</code> as outlined for:
     * <ul><code>
     *     java.net.URL#URL(java.lang.String, java.lang.String, int,
     *                      java.lang.String)
     * </code></ul>
     * The stream protocol handler's 
     * <code>parseURL</code> method is called to parse the remaining 
     * fields of the specification that override any defaults set by the 
     * context argument. 

     * @param      context   the context in which to parse the specification.
     * @param      spec      a <code>String</code> representation of a URL.
     * @exception  MalformedURLException  if no protocol is specified, or an
     *               unknown protocol is found.
     * @see        java.net.URL#URL(java.lang.String, java.lang.String, int, java.lang.String)
     * @see        java.net.URLStreamHandler
     * @see        java.net.URLStreamHandler#parseURL(java.net.URL, java.lang.String, int, int)
     * @since   JDK1.0
     */
    public URL(URL context, String spec) throws MalformedURLException {
	String original = spec;
	int i, limit, c;
	int start = 0;
	String newProtocol = null;
	boolean aRef=false;

	try {
	    limit = spec.length();
	    while ((limit > 0) && (spec.charAt(limit - 1) <= ' ')) {
		limit--;	//eliminate trailing whitespace
	    }
	    while ((start < limit) && (spec.charAt(start) <= ' ')) {
		start++;	// eliminate leading whitespace
	    }

	    if (spec.regionMatches(true, start, "url:", 0, 4)) {
		start += 4;
	    }
	    if (start < spec.length() && spec.charAt(start) == '#') {
		/* we're assuming this is a ref relative to the context URL.
		 * This means protocols cannot start w/ '#', but we must parse
		 * ref URL's like: "hello:there" w/ a ':' in them.
		 */
		aRef=true;
	    }
	    for (i = start ; !aRef && (i < limit) && ((c = spec.charAt(i)) != '/') ; i++) {
		if (c == ':') {
		    newProtocol = spec.substring(start, i).toLowerCase();
		    start = i + 1;
		    break;
		}
	    }
	    // Only use our context if the protocols match.
	    if ((context != null) && ((newProtocol == null) ||
				    newProtocol.equals(context.protocol))) {
		protocol = context.protocol;
		host = context.host;
		port = context.port;
		file = context.file;
	    } else {
		protocol = newProtocol;
	    }

	    if (protocol == null) {
		throw new MalformedURLException("no protocol: "+original);
	    }

	    if ((handler = getURLStreamHandler(protocol)) == null) {
		throw new MalformedURLException("unknown protocol: "+protocol);
	    }