android 网站项目源代码

// HTMLParser Library - A java-based parser for HTML // http://htmlparser.org // Copyright (C) 2006 Derrick Oswald // // Revision Control Information // // $URL: https://svn.sourceforge.net/svnroot/htmlparser/trunk/lexer/src/main/java/org/htmlparser/lexer/Lexer.java $ // $Author: derrickoswald $ // $Date: 2006-09-23 00:23:10 -0400 (Sat, 23 Sep 2006) $ // $Revision: 13 $ // // This library is free software; you can redistribute it and/or // modify it under the terms of the Common Public License; either // version 1.0 of the License, or (at your option) any later version. // // This library is distributed in the hope that it will be useful, // but WITHOUT ANY WARRANTY; without even the implied warranty of // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the // Common Public License for more details. // // You should have received a copy of the Common Public License // along with this library; if not, the license is available from // the Open Source Initiative (OSI) website: // http://opensource.org/licenses/cpl1.0.php package org.htmlparser.lexer; import java.io.Serializable; import java.net.MalformedURLException; import java.net.URLConnection; import java.util.Vector; import org.htmlparser.Node; import org.htmlparser.NodeFactory; import org.htmlparser.Remark; import org.htmlparser.Text; import org.htmlparser.Tag; import org.htmlparser.http.ConnectionManager; import org.htmlparser.nodes.RemarkNode; import org.htmlparser.nodes.TextNode; import org.htmlparser.nodes.TagNode; import org.htmlparser.util.ParserException; /** * This class parses the HTML stream into nodes. * There are three major types of nodes (lexemes): * <ul> * <li>Remark</li> * <li>Text</li> * <li>Tag</li> * </ul> * Each time <code>nextNode()</code> is called, another node is returned until * the stream is exhausted, and <code>null</code> is returned. */ public class Lexer implements Serializable, NodeFactory { // Please don't change the formatting of the version variables below. // This is done so as to facilitate ant script processing. /** * The floating point version number ({@value}). */ public static final double VERSION_NUMBER = 2.0 ; /** * The type of version ({@value}). */ public static final String VERSION_TYPE = "Release Build" ; /** * The date of the version ({@value}). */ public static final String VERSION_DATE = "Sep 17, 2006" ; // End of formatting /** * The display version ({@value}). */ public static final String VERSION_STRING = "" + VERSION_NUMBER + " (" + VERSION_TYPE + " " + VERSION_DATE + ")"; /** * Process remarks strictly flag. * If <code>true</code>, remarks are not terminated by ---$gt; * or --!$gt;, i.e. more than two dashes. If <code>false</code>, * a more lax (and closer to typical browser handling) remark parsing * is used. * Default <code>true</code>. */ public static boolean STRICT_REMARKS = true; /** * The page lexemes are retrieved from. */ protected Page mPage; /** * The current position on the page. */ protected Cursor mCursor; /** * The factory for new nodes. */ protected NodeFactory mFactory; /** * Line number to trigger on. * This is tested on each <code>nextNode()</code> call, as a debugging aid. * Alter this value and set a breakpoint on the guarded statement. * Remember, these line numbers are zero based, while most editors are * one based. * @see #nextNode */ protected static int mDebugLineTrigger = -1; // // Static methods // /** * Return the version string of this parser. * @return A string of the form: * <pre> * "[floating point number] ([build-type] [build-date])" * </pre> */ public static String getVersion () { return (VERSION_STRING); } // // Constructors // /** * Creates a new instance of a Lexer. */ public Lexer () { this (new Page ("")); } /** * Creates a new instance of a Lexer. * @param page The page with HTML text. */ public Lexer (Page page) { setPage (page); setCursor (new Cursor (page, 0)); setNodeFactory (this); } /** * Creates a new instance of a Lexer. * @param text The text to parse. */ public Lexer (String text) { this (new Page (text)); } /** * Creates a new instance of a Lexer. * @param connection The url to parse. * @exception ParserException If an error occurs opening the connection. */ public Lexer (URLConnection connection) throws ParserException { this (new Page (connection)); } // // Bean patterns // /** * Get the page this lexer is working on. * @return The page that nodes are being read from. */ public Page getPage () { return (mPage); } /** * Set the page this lexer is working on. * @param page The page that nodes will be read from. */ public void setPage (Page page) { if (null == page) throw new IllegalArgumentException ("page cannot be null"); // todo: sanity checks mPage = page; } /** * Get the current scanning position. * @return The lexer's cursor position. */ public Cursor getCursor () { return (mCursor); } /** * Set the current scanning position. * @param cursor The lexer's new cursor position. */ public void setCursor (Cursor cursor) { if (null == cursor) throw new IllegalArgumentException ("cursor cannot be null"); // todo: sanity checks mCursor = cursor; } /** * Get the current node factory. * @return The lexer's node factory. */ public NodeFactory getNodeFactory () { return (mFactory); } /** * Set the current node factory. * @param factory The node factory to be used by the lexer. */ public void setNodeFactory (NodeFactory factory) { if (null == factory) throw new IllegalArgumentException ("node factory cannot be null"); mFactory = factory; } /** * Get the current cursor position. * @return The current character offset into the source. */ public int getPosition () { return (getCursor ().getPosition ()); } /** * Set the current cursor position. * @param position The new character offset into the source. */ public void setPosition (int position) { // todo: sanity checks getCursor ().setPosition (position); } /** * Get the current line number. * @return The line number the lexer's working on. */ public int getCurrentLineNumber () { return (getPage ().row (getCursor ())); } /** * Get the current line. * @return The string the lexer's working on. */ public String getCurrentLine () { return (getPage ().getLine (getCursor ())); } // // Public methods // /** * Reset the lexer to start parsing from the beginning again. * The underlying components are reset such that the next call to * <code>nextNode()</code> will return the first lexeme on the page. */ public void reset () { getPage ().reset (); setCursor (new Cursor (getPage (), 0)); } /** * Get the next no