saxreader.java

解决如何把XML应用到JAVA里问题

/*
 * Copyright 2001-2005 (C) MetaStuff, Ltd. All Rights Reserved.
 *
 * This software is open source.
 * See the bottom of this file for the licence.
 */

package org.dom4j.io;

import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.InputStream;
import java.io.Reader;
import java.io.Serializable;
import java.net.URL;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentFactory;
import org.dom4j.ElementHandler;

import org.xml.sax.EntityResolver;
import org.xml.sax.ErrorHandler;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.XMLFilter;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;
import org.xml.sax.helpers.XMLReaderFactory;

/**
 * <p>
 * <code>SAXReader</code> creates a DOM4J tree from SAX parsing events.
 * </p>
 * 
 * <p>
 * The actual SAX parser that is used by this class is configurable so you can
 * use your favourite SAX parser if you wish. DOM4J comes configured with its
 * own SAX parser so you do not need to worry about configuring the SAX parser.
 * </p>
 * 
 * <p>
 * To explicitly configure the SAX parser that is used via Java code you can use
 * a constructor or use the {@link #setXMLReader(XMLReader)}or {@link
 * #setXMLReaderClassName(String)} methods.
 * </p>
 * 
 * <p>
 * If the parser is not specified explicitly then the standard SAX policy of
 * using the <code>org.xml.sax.driver</code> system property is used to
 * determine the implementation class of {@link XMLReader}.
 * </p>
 * 
 * <p>
 * If the <code>org.xml.sax.driver</code> system property is not defined then
 * JAXP is used via reflection (so that DOM4J is not explicitly dependent on the
 * JAXP classes) to load the JAXP configured SAXParser. If there is any error
 * creating a JAXP SAXParser an informational message is output and then the
 * default (Aelfred) SAX parser is used instead.
 * </p>
 * 
 * <p>
 * If you are trying to use JAXP to explicitly set your SAX parser and are
 * experiencing problems, you can turn on verbose error reporting by defining
 * the system property <code>org.dom4j.verbose</code> to be "true" which will
 * output a more detailed description of why JAXP could not find a SAX parser
 * </p>
 * 
 * <p>
 * For more information on JAXP please go to <a
 * href="http://java.sun.com/xml/">Sun's Java &amp; XML site </a>
 * </p>
 * 
 * @author <a href="mailto:[e-mail]">James Strachan </a>
 * @version $Revision: 1.58 $
 */
public class SAXReader {
    private static final String SAX_STRING_INTERNING = 
            "http://xml.org/sax/features/string-interning";
    private static final String SAX_NAMESPACE_PREFIXES = 
            "http://xml.org/sax/features/namespace-prefixes";
    private static final String SAX_NAMESPACES = 
            "http://xml.org/sax/features/namespaces";
    private static final String SAX_DECL_HANDLER = 
            "http://xml.org/sax/properties/declaration-handler";
    private static final String SAX_LEXICAL_HANDLER = 
            "http://xml.org/sax/properties/lexical-handler";
    private static final String SAX_LEXICALHANDLER = 
            "http://xml.org/sax/handlers/LexicalHandler";

    /** <code>DocumentFactory</code> used to create new document objects */
    private DocumentFactory factory;

    /** <code>XMLReader</code> used to parse the SAX events */
    private XMLReader xmlReader;

    /** Whether validation should occur */
    private boolean validating;

    /** DispatchHandler to call when each <code>Element</code> is encountered */
    private DispatchHandler dispatchHandler;

    /** ErrorHandler class to use */
    private ErrorHandler errorHandler;

    /** The entity resolver */
    private EntityResolver entityResolver;

    /** Should element & attribute names and namespace URIs be interned? */
    private boolean stringInternEnabled = true;

    /** Should internal DTD declarations be expanded into a List in the DTD */
    private boolean includeInternalDTDDeclarations = false;

    /** Should external DTD declarations be expanded into a List in the DTD */
    private boolean includeExternalDTDDeclarations = false;

    /** Whether adjacent text nodes should be merged */
    private boolean mergeAdjacentText = false;

    /** Holds value of property stripWhitespaceText. */
    private boolean stripWhitespaceText = false;

    /** Should we ignore comments */
    private boolean ignoreComments = false;

    /** Encoding of InputSource - null means system default encoding */
    private String encoding = null;

    // private boolean includeExternalGeneralEntities = false;
    // private boolean includeExternalParameterEntities = false;

    /** The SAX filter used to filter SAX events */
    private XMLFilter xmlFilter;

    public SAXReader() {
    }

    public SAXReader(boolean validating) {
        this.validating = validating;
    }

    public SAXReader(DocumentFactory factory) {
        this.factory = factory;
    }

    public SAXReader(DocumentFactory factory, boolean validating) {
        this.factory = factory;
        this.validating = validating;
    }

    public SAXReader(XMLReader xmlReader) {
        this.xmlReader = xmlReader;
    }

    public SAXReader(XMLReader xmlReader, boolean validating) {
        this.xmlReader = xmlReader;
        this.validating = validating;
    }

    public SAXReader(String xmlReaderClassName) throws SAXException {
        if (xmlReaderClassName != null) {
            this.xmlReader = XMLReaderFactory
                    .createXMLReader(xmlReaderClassName);
        }
    }

    public SAXReader(String xmlReaderClassName, boolean validating)
            throws SAXException {
        if (xmlReaderClassName != null) {
            this.xmlReader = XMLReaderFactory
                    .createXMLReader(xmlReaderClassName);
        }

        this.validating = validating;
    }

    /**
     * Allows a SAX property to be set on the underlying SAX parser. This can be
     * useful to set parser-specific properties such as the location of schema
     * or DTD resources. Though use this method with caution as it has the
     * possibility of breaking the standard behaviour. An alternative to calling
     * this method is to correctly configure an XMLReader object instance and
     * call the {@link #setXMLReader(XMLReader)}method
     * 
     * @param name
     *            is the SAX property name
     * @param value
     *            is the value of the SAX property
     * 
     * @throws SAXException
     *             if the XMLReader could not be created or the property could
     *             not be changed.
     */
    public void setProperty(String name, Object value) throws SAXException {
        getXMLReader().setProperty(name, value);
    }

    /**
     * Sets a SAX feature on the underlying SAX parser. This can be useful to
     * set parser-specific features. Though use this method with caution as it
     * has the possibility of breaking the standard behaviour. An alternative to
     * calling this method is to correctly configure an XMLReader object
     * instance and call the {@link #setXMLReader(XMLReader)}method
     * 
     * @param name
     *            is the SAX feature name
     * @param value
     *            is the value of the SAX feature
     * 
     * @throws SAXException
     *             if the XMLReader could not be created or the feature could
     *             not be changed.
     */
    public void setFeature(String name, boolean value) throws SAXException {
        getXMLReader().setFeature(name, value);
    }

    /**
     * <p>
     * Reads a Document from the given <code>File</code>
     * </p>
     * 
     * @param file
     *            is the <code>File</code> to read from.
     * 
     * @return the newly created Document instance
     * 
     * @throws DocumentException
     *             if an error occurs during parsing.
     */
    public Document read(File file) throws DocumentException {
        try {
            /*
             * We cannot convert the file to an URL because if the filename
             * contains '#' characters, there will be problems with the URL in
             * the InputSource (because a URL like
             * http://myhost.com/index#anchor is treated the same as
             * http://myhost.com/index) Thanks to Christian Oetterli
             */
            InputSource source = new InputSource(new FileInputStream(file));
            if (this.encoding != null) {
                source.setEncoding(this.encoding);
            }
            String path = file.getAbsolutePath();

            if (path != null) {
                // Code taken from Ant FileUtils
                StringBuffer sb = new StringBuffer("file://");

                // add an extra slash for filesystems with drive-specifiers
                if (!path.startsWith(File.separator)) {
                    sb.append("/");
                }

                path = path.replace('\\', '/');
                sb.append(path);

                source.setSystemId(sb.toString());
            }

            return read(source);
        } catch (FileNotFoundException e) {
            throw new DocumentException(e.getMessage(), e);
        }
    }

    /**
     * <p>
     * Reads a Document from the given <code>URL</code> using SAX
     * </p>
     * 
     * @param url
     *            <code>URL</code> to read from.
     * 
     * @return the newly created Document instance
     * 
     * @throws DocumentException
     *             if an error occurs during parsing.
     */
    public Document read(URL url) throws DocumentException {
        String systemID = url.toExternalForm();

        InputSource source = new InputSource(systemID);
        if (this.encoding != null) {
            source.setEncoding(this.encoding);
        }

        return read(source);
    }

    /**
     * <p>
     * Reads a Document from the given URL or filename using SAX.
     * </p>
     * 
     * <p>
     * If the systemId contains a <code>':'</code> character then it is
     * assumed to be a URL otherwise its assumed to be a file name. If you want
     * finer grained control over this mechansim then please explicitly pass in
     * either a {@link URL}or a {@link File}instance instead of a {@link
     * String} to denote the source of the document.
     * </p>
     * 
     * @param systemId
     *            is a URL for a document or a file name.
     * 
     * @return the newly created Document instance
     * 
     * @throws DocumentException
     *             if an error occurs during parsing.
     */
    public Document read(String systemId) throws DocumentException {
        InputSource source = new InputSource(systemId);
        if (this.encoding != null) {
            source.setEncoding(this.encoding);
        }

        return read(source);
    }

    /**
     * <p>
     * Reads a Document from the given stream using SAX
     * </p>
     * 
     * @param in
     *            <code>InputStream</code> to read from.
     * 
     * @return the newly created Document instance
     * 
     * @throws DocumentException
     *             if an error occurs during parsing.
     */
    public Document read(InputStream in) throws DocumentException {
        InputSource source = new InputSource(in);
        if (this.encoding != null) {
            source.setEncoding(this.encoding);
        }

        return read(source);
    }

    /**
     * <p>
     * Reads a Document from the given <code>Reader</code> using SAX