org.apache.html.dom.HTMLBuilder Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of xercesImpl Show documentation

Xerces2 is the next generation of high performance, fully compliant XML parsers in the Apache Xerces family. This new version of Xerces introduces the Xerces Native Interface (XNI), a complete framework for building parser components and configurations that is extremely modular and easy to program. The Apache Xerces2 parser is the reference implementation of XNI but other parser components, configurations, and parsers can be written using the Xerces Native Interface. For complete design and implementation documents, refer to the XNI Manual. Xerces2 is a fully conforming XML Schema 1.0 processor. A partial experimental implementation of the XML Schema 1.1 Structures and Datatypes Working Drafts (December 2009) and an experimental implementation of the XML Schema Definition Language (XSD): Component Designators (SCD) Candidate Recommendation (January 2010) are provided for evaluation. For more information, refer to the XML Schema page. Xerces2 also provides a complete implementation of the Document Object Model Level 3 Core and Load/Save W3C Recommendations and provides a complete implementation of the XML Inclusions (XInclude) W3C Recommendation. It also provides support for OASIS XML Catalogs v1.1. Xerces2 is able to parse documents written according to the XML 1.1 Recommendation, except that it does not yet provide an option to enable normalization checking as described in section 2.13 of this specification. It also handles namespaces according to the XML Namespaces 1.1 Recommendation, and will correctly serialize XML 1.1 documents if the DOM level 3 load/save APIs are in use.

The newest version!

/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You under the Apache License, Version 2.0
 * (the "License"); you may not use this file except in compliance with
 * the License.  You may obtain a copy of the License at
 * 
 *      http://www.apache.org/licenses/LICENSE-2.0
 * 
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License is distributed on an "AS IS" BASIS,
 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 * See the License for the specific language governing permissions and
 * limitations under the License.
 */
package org.apache.html.dom;


import java.util.Vector;

import org.apache.xerces.dom.ElementImpl;
import org.apache.xerces.dom.ProcessingInstructionImpl;
import org.w3c.dom.Node;
import org.w3c.dom.html.HTMLDocument;
import org.xml.sax.AttributeList;
import org.xml.sax.DocumentHandler;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;


/**
 * This is a SAX document handler that is used to build an HTML document.
 * It can build a document from any SAX parser, but is specifically tuned
 * for working with the OpenXML HTML parser.
 * 
 * 
 * @version $Revision: 1029415 $ $Date: 2010-10-31 18:02:22 +0100 (Sun, 31 Oct 2010) $
 * @author Assaf Arkin
 */
public class HTMLBuilder
    implements DocumentHandler
{


    /**
     * The document that is being built.
     */
    protected HTMLDocumentImpl    _document;
    
    
    /**
     * The current node in the document into which elements, text and
     * other nodes will be inserted. This starts as the document itself
     * and reflects each element that is currently being parsed.
     */
    protected ElementImpl        _current;


    /**
     * Applies only to whitespace appearing between element tags in element content,
     * as per the SAX definition, and true by default.
     */
    private boolean         _ignoreWhitespace = true;


    /**
     * Indicates whether finished building a document. If so, can start building
     * another document. Must be initially true to get the first document processed.
     */
    private boolean         _done = true;


    /**    
     * The document is only created the same time as the document element, however, certain
     * nodes may precede the document element (comment and PI), and they are accumulated
     * in this vector.
     */
    protected Vector         _preRootNodes;

    
    public void startDocument()
        throws SAXException
    {
        if ( ! _done )
	    throw new SAXException( "HTM001 State error: startDocument fired twice on one builder." );
	_document = null;
	_done = false;
    }


    public void endDocument()
        throws SAXException
    {
        if ( _document == null )
            throw new SAXException( "HTM002 State error: document never started or missing document element." );
	if ( _current != null )
	    throw new SAXException( "HTM003 State error: document ended before end of document element." );
        _current = null;
	_done = true;
    }


    public synchronized void startElement( String tagName, AttributeList attrList )
        throws SAXException
    {
        ElementImpl elem;
        int         i;
        
	if ( tagName == null )
	    throw new SAXException( "HTM004 Argument 'tagName' is null." );

	// If this is the root element, this is the time to create a new document,
	// because only know we know the document element name and namespace URI.
	if ( _document == null )
	{
	    // No need to create the element explicitly.
	    _document = new HTMLDocumentImpl();
	    elem = (ElementImpl) _document.getDocumentElement();
	    _current = elem;
	    if ( _current == null )
		throw new SAXException( "HTM005 State error: Document.getDocumentElement returns null." );

	    // Insert nodes (comment and PI) that appear before the root element.
	    if ( _preRootNodes != null )
	    {
		for ( i = _preRootNodes.size() ; i-- > 0 ; )
		    _document.insertBefore( (Node) _preRootNodes.elementAt( i ), elem );
		_preRootNodes = null;
	    }
	     
	}
	else
	{
	    // This is a state error, indicates that document has been parsed in full,
	    // or that there are two root elements.
	    if ( _current == null )
		throw new SAXException( "HTM006 State error: startElement called after end of document element." );
	    elem = (ElementImpl) _document.createElement( tagName );
	    _current.appendChild( elem );
	    _current = elem;
	}

	// Add the attributes (specified and not-specified) to this element.
        if ( attrList != null )
        {
            for ( i = 0 ; i < attrList.getLength() ; ++ i )
                elem.setAttribute( attrList.getName( i ), attrList.getValue( i ) );
        }
    }

    
    public void endElement( String tagName )
        throws SAXException
    {
        if ( _current == null )
            throw new SAXException( "HTM007 State error: endElement called with no current node." );
	if ( ! _current.getNodeName().equalsIgnoreCase( tagName ))
	    throw new SAXException( "HTM008 State error: mismatch in closing tag name " + tagName + "\n" + tagName);

	// Move up to the parent element. When you reach the top (closing the root element).
	// the parent is document and current is null.
	if ( _current.getParentNode() == _current.getOwnerDocument() )
	    _current = null;
	else
	    _current = (ElementImpl) _current.getParentNode();
    }


    public void characters( String text )
        throws SAXException
    {
	if ( _current == null )
            throw new SAXException( "HTM009 State error: character data found outside of root element." );
        _current.appendChild( _document.createTextNode(text) );
    }

    
    public void characters( char[] text, int start, int length )
        throws SAXException
    {
	if ( _current == null )
            throw new SAXException( "HTM010 State error: character data found outside of root element." );
        _current.appendChild( _document.createTextNode(new String(text, start, length)) );
    }
    
    
    public void ignorableWhitespace( char[] text, int start, int length )
        throws SAXException
    {        
        if ( ! _ignoreWhitespace )
            _current.appendChild( _document.createTextNode(new String(text, start, length)) );
     }
    
    
    public void processingInstruction( String target, String instruction )
        throws SAXException
    {        
	// Processing instruction may appear before the document element (in fact, before the
	// document has been created, or after the document element has been closed.
        if ( _current == null && _document == null )
	{
	    if ( _preRootNodes == null )
		_preRootNodes = new Vector();
	    _preRootNodes.addElement( new ProcessingInstructionImpl( null, target, instruction ) );
	}
	else
        if ( _current == null && _document != null )
            _document.appendChild( _document.createProcessingInstruction(target, instruction) );
	else
        _current.appendChild( _document.createProcessingInstruction(target, instruction) );
    }
    
    
    public HTMLDocument getHTMLDocument()
    {
        return _document;
    }

    
    public void setDocumentLocator( Locator locator )
    {
        // ignored
    }


}