domparserimpl.java

来自「JAVA的一些源码 JAVA2 STANDARD EDITION DEVELO」· Java 代码 · 共 1,089 行 · 第 1/3 页

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 2000-2004 The Apache Software Foundation.  All rights
 * reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in
 *    the documentation and/or other materials provided with the
 *    distribution.
 *
 * 3. The end-user documentation included with the redistribution,
 *    if any, must include the following acknowledgment:
 *       "This product includes software developed by the
 *        Apache Software Foundation (http://www.apache.org/)."
 *    Alternately, this acknowledgment may appear in the software itself,
 *    if and wherever such third-party acknowledgments normally appear.
 *
 * 4. The names "Xerces" and "Apache Software Foundation" must
 *    not be used to endorse or promote products derived from this
 *    software without prior written permission. For written
 *    permission, please contact [e-mail].
 *
 * 5. Products derived from this software may not be called "Apache",
 *    nor may "Apache" appear in their name, without prior written
 *    permission of the Apache Software Foundation.
 *
 * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
 * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
 * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
 * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
 * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
 * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
 * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * ====================================================================
 *
 * This software consists of voluntary contributions made by many
 * individuals on behalf of the Apache Software Foundation and was
 * originally based on software copyright (c) 2001, International
 * Business Machines, Inc., http://www.apache.org.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */


package com.sun.org.apache.xerces.internal.parsers;

import java.io.StringReader;
import java.util.Locale;
import java.util.Stack;
import java.util.StringTokenizer;
import java.util.Vector;
import java.util.Locale;

import com.sun.org.apache.xerces.internal.dom.DOMErrorImpl;
import com.sun.org.apache.xerces.internal.dom.DOMMessageFormatter;
import com.sun.org.apache.xerces.internal.dom.DOMStringListImpl;
import org.w3c.dom.DOMError;
import com.sun.org.apache.xerces.internal.impl.Constants;
import com.sun.org.apache.xerces.internal.util.DOMEntityResolverWrapper;
import com.sun.org.apache.xerces.internal.util.DOMErrorHandlerWrapper;
import com.sun.org.apache.xerces.internal.util.SymbolTable;
import com.sun.org.apache.xerces.internal.xni.grammars.XMLGrammarPool;
import com.sun.org.apache.xerces.internal.xni.parser.XMLConfigurationException;
import com.sun.org.apache.xerces.internal.xni.parser.XMLEntityResolver;
import com.sun.org.apache.xerces.internal.xni.parser.XMLInputSource;
import com.sun.org.apache.xerces.internal.xni.parser.XMLParserConfiguration;
import org.w3c.dom.DOMConfiguration;
import org.w3c.dom.DOMErrorHandler;
import org.w3c.dom.DOMException;
import org.w3c.dom.Document;
import org.w3c.dom.DOMStringList;
import org.w3c.dom.Node;
import org.w3c.dom.ls.LSException;
import org.w3c.dom.ls.LSParser;
import org.w3c.dom.ls.LSParserFilter;
import org.w3c.dom.ls.LSResourceResolver;
import org.w3c.dom.ls.LSInput;


/**
 * This is Xerces DOM Builder class. It uses the abstract DOM
 * parser with a document scanner, a dtd scanner, and a validator, as
 * well as a grammar pool.
 *
 * @author Pavani Mukthipudi, Sun Microsystems Inc.
 * @author Elena Litani, IBM
 * @author Rahul Srivastava, Sun Microsystems Inc.
 * @version $Id: DOMParserImpl.java,v 1.25 2004/04/23 16:06:10 mrglavas Exp $
 */
public class DOMParserImpl
extends AbstractDOMParser implements LSParser, DOMConfiguration {



    // SAX & Xerces feature ids

    /** Feature identifier: namespaces. */
    protected static final String NAMESPACES =
    Constants.SAX_FEATURE_PREFIX + Constants.NAMESPACES_FEATURE;

    /** Feature id: validation. */
    protected static final String VALIDATION_FEATURE =
    Constants.SAX_FEATURE_PREFIX+Constants.VALIDATION_FEATURE;

    /** XML Schema validation */
    protected static final String XMLSCHEMA =
    Constants.XERCES_FEATURE_PREFIX + Constants.SCHEMA_VALIDATION_FEATURE;

    /** Dynamic validation */
    protected static final String DYNAMIC_VALIDATION =
    Constants.XERCES_FEATURE_PREFIX + Constants.DYNAMIC_VALIDATION_FEATURE;

    /** Feature identifier: expose schema normalized value */
    protected static final String NORMALIZE_DATA =
    Constants.XERCES_FEATURE_PREFIX + Constants.SCHEMA_NORMALIZED_VALUE;

    /** Feature identifier: disallow docType Decls. */
    protected static final String DISALLOW_DOCTYPE_DECL_FEATURE =
        Constants.XERCES_FEATURE_PREFIX + Constants.DISALLOW_DOCTYPE_DECL_FEATURE;

    // internal properties
    protected static final String SYMBOL_TABLE =
    Constants.XERCES_PROPERTY_PREFIX + Constants.SYMBOL_TABLE_PROPERTY;

    protected static final String PSVI_AUGMENT =
    Constants.XERCES_FEATURE_PREFIX +Constants.SCHEMA_AUGMENT_PSVI;
	Thread currentThread = null;

    //
    // Data
    //


    // REVISIT: this value should be null by default and should be set during creation of
    //          LSParser
    protected String fSchemaType = null;

    protected boolean fBusy = false;

    protected final static boolean DEBUG = false;

    private Vector fSchemaLocations = new Vector ();
    private String fSchemaLocation = null;
	private DOMStringList fRecognizedParameters;

	private boolean abortNow = false;

    //
    // Constructors
    //

    /**
     * Constructs a DOM Builder using the standard parser configuration.
     */
    public DOMParserImpl (String configuration, String schemaType) {
        this (
        (XMLParserConfiguration) ObjectFactory.createObject (
        "com.sun.org.apache.xerces.internal.xni.parser.XMLParserConfiguration",
        configuration));
        if (schemaType != null) {
            if (schemaType.equals (Constants.NS_DTD)) {
                fConfiguration.setFeature (
                Constants.XERCES_FEATURE_PREFIX + Constants.SCHEMA_VALIDATION_FEATURE,
                false);
                fConfiguration.setProperty (
                Constants.JAXP_PROPERTY_PREFIX + Constants.SCHEMA_LANGUAGE,
                Constants.NS_DTD);
                fSchemaType = Constants.NS_DTD;
            }
            else if (schemaType.equals (Constants.NS_XMLSCHEMA)) {
                // XML Schem validation
                fConfiguration.setProperty (
                Constants.JAXP_PROPERTY_PREFIX + Constants.SCHEMA_LANGUAGE,
                Constants.NS_XMLSCHEMA);
            }
        }

    }

    /**
     * Constructs a DOM Builder using the specified parser configuration.
     */
    public DOMParserImpl (XMLParserConfiguration config) {
        super (config);

        // add recognized features
        final String[] domRecognizedFeatures = {
            Constants.DOM_CANONICAL_FORM,
            Constants.DOM_CDATA_SECTIONS,
            Constants.DOM_CHARSET_OVERRIDES_XML_ENCODING,
            Constants.DOM_INFOSET,
            Constants.DOM_NAMESPACE_DECLARATIONS,
            Constants.DOM_SPLIT_CDATA,
            Constants.DOM_SUPPORTED_MEDIATYPES_ONLY,
            Constants.DOM_CERTIFIED,
            Constants.DOM_WELLFORMED,
            Constants.DOM_IGNORE_UNKNOWN_CHARACTER_DENORMALIZATIONS,
        };


        fConfiguration.addRecognizedFeatures (domRecognizedFeatures);

        // turn off deferred DOM
        fConfiguration.setFeature (DEFER_NODE_EXPANSION, false);

        // Set values so that the value of the
        // infoset parameter is true (its default value).
        //
        // true: namespace-declarations, well-formed,
        // element-content-whitespace, comments, namespaces
        //
        // false: validate-if-schema, entities,
        // datatype-normalization, cdata-sections

        fConfiguration.setFeature(Constants.DOM_NAMESPACE_DECLARATIONS, true);
        fConfiguration.setFeature(Constants.DOM_WELLFORMED, true);
        fConfiguration.setFeature(INCLUDE_COMMENTS_FEATURE, true);
        fConfiguration.setFeature(INCLUDE_IGNORABLE_WHITESPACE, true);
        fConfiguration.setFeature(NAMESPACES, true);

        fConfiguration.setFeature(DYNAMIC_VALIDATION, false);
        fConfiguration.setFeature(CREATE_ENTITY_REF_NODES, false);
        fConfiguration.setFeature(NORMALIZE_DATA, false);
        fConfiguration.setFeature(CREATE_CDATA_NODES_FEATURE, false);

        // set other default values
        fConfiguration.setFeature (Constants.DOM_CANONICAL_FORM, false);
        fConfiguration.setFeature (Constants.DOM_CHARSET_OVERRIDES_XML_ENCODING, true);
        fConfiguration.setFeature (Constants.DOM_SPLIT_CDATA, true);
        fConfiguration.setFeature (Constants.DOM_SUPPORTED_MEDIATYPES_ONLY, false);
        fConfiguration.setFeature (Constants.DOM_IGNORE_UNKNOWN_CHARACTER_DENORMALIZATIONS, true);

        // REVISIT: by default Xerces assumes that input is certified.
        //          default is different from the one specified in the DOM spec
        fConfiguration.setFeature (Constants.DOM_CERTIFIED, true);

        // Xerces datatype-normalization feature is on by default
        fConfiguration.setFeature( NORMALIZE_DATA, false );
    } // <init>(XMLParserConfiguration)

    /**
     * Constructs a DOM Builder using the specified symbol table.
     */
	public DOMParserImpl(SymbolTable symbolTable) {
		this(
			(XMLParserConfiguration) ObjectFactory.createObject(
				"com.sun.org.apache.xerces.internal.xni.parser.XMLParserConfiguration",
				"com.sun.org.apache.xerces.internal.parsers.XIncludeParserConfiguration"));
		fConfiguration.setProperty(
			Constants.XERCES_PROPERTY_PREFIX + Constants.SYMBOL_TABLE_PROPERTY,
			symbolTable);
	} // <init>(SymbolTable)


    /**
     * Constructs a DOM Builder using the specified symbol table and
     * grammar pool.
     */
	public DOMParserImpl(SymbolTable symbolTable, XMLGrammarPool grammarPool) {
		this(
			(XMLParserConfiguration) ObjectFactory.createObject(
				"com.sun.org.apache.xerces.internal.xni.parser.XMLParserConfiguration",
				"com.sun.org.apache.xerces.internal.parsers.XIncludeParserConfiguration"));
		fConfiguration.setProperty(
			Constants.XERCES_PROPERTY_PREFIX + Constants.SYMBOL_TABLE_PROPERTY,
			symbolTable);
		fConfiguration.setProperty(
			Constants.XERCES_PROPERTY_PREFIX
				+ Constants.XMLGRAMMAR_POOL_PROPERTY,
			grammarPool);
	}

    /**
     * Resets the parser state.
     *
     * @throws SAXException Thrown on initialization error.
     */
    public void reset() {
        super.reset();
        // DOM Filter
        if (fSkippedElemStack!=null) {
            fSkippedElemStack.removeAllElements();
        }
		fSchemaLocations.clear();
        fRejectedElement.clear();
        fFilterReject = false;
        fSchemaType = null;

    } // reset()

    //
    // DOMParser methods
    //

    public DOMConfiguration getDomConfig (){
        return this;
    }


    /**
     *  When the application provides a filter, the parser will call out to
     * the filter at the completion of the construction of each
     * <code>Element</code> node. The filter implementation can choose to
     * remove the element from the document being constructed (unless the
     * element is the document element) or to terminate the parse early. If
     * the document is being validated when it's loaded the validation
     * happens before the filter is called.
     */
    public LSParserFilter getFilter() {
        return fDOMFilter;
    }

    /**
     *  When the application provides a filter, the parser will call out to
     * the filter at the completion of the construction of each
     * <code>Element</code> node. The filter implementation can choose to
     * remove the element from the document being constructed (unless the
     * element is the document element) or to terminate the parse early. If
     * the document is being validated when it's loaded the validation
     * happens before the filter is called.
     */
    public void setFilter(LSParserFilter filter) {
        fDOMFilter = filter;
        if (fSkippedElemStack == null) {
            fSkippedElemStack = new Stack();
        }
    }

    /**
     * Set parameters and properties
     */
    public void setParameter (String name, Object value) throws DOMException {
        // set features
        if(value instanceof Boolean){
            boolean state = ((Boolean)value).booleanValue ();
            try {
                if (name.equalsIgnoreCase (Constants.DOM_COMMENTS)) {
                    fConfiguration.setFeature (INCLUDE_COMMENTS_FEATURE, state);
                }
                else if (name.equalsIgnoreCase (Constants.DOM_DATATYPE_NORMALIZATION)) {
                    fConfiguration.setFeature (NORMALIZE_DATA, state);
                }
                else if (name.equalsIgnoreCase (Constants.DOM_ENTITIES)) {
                    fConfiguration.setFeature (CREATE_ENTITY_REF_NODES, state);
                }
                else if (name.equalsIgnoreCase (Constants.DOM_DISALLOW_DOCTYPE)) {
                    fConfiguration.setFeature (DISALLOW_DOCTYPE_DECL_FEATURE, state);
                }
                else if (name.equalsIgnoreCase (Constants.DOM_SUPPORTED_MEDIATYPES_ONLY)