htmlserializer.java

uPortal是开放源码的Portal门户产品

/*
 * The Apache Software License, Version 1.1
 *
 *
 * Copyright (c) 1999 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) 1999, International
 * Business Machines, Inc., http://www.apache.org.  For more
 * information on the Apache Software Foundation, please see
 * <http://www.apache.org/>.
 */


// Sep 14, 2000:
//  Fixed serializer to report IO exception directly, instead at
//  the end of document processing.
//  Reported by Patrick Higgins <[e-mail]>
// Aug 21, 2000:
//  Fixed bug in startDocument not calling prepare.
//  Reported by Mikael Staldal <[e-mail]>
// Aug 21, 2000:
//  Added ability to omit DOCTYPE declaration.
// Sep 1, 2000:
//   If no output format is provided the serializer now defaults
//   to ISO-8859-1 encoding. Reported by Mikael Staldal
//   <[e-mail]>


package org.jasig.portal.serialize;


import java.io.IOException;
import java.io.OutputStream;
import java.io.Writer;
import java.util.Enumeration;

import org.jasig.portal.IAnchoringSerializer;
import org.w3c.dom.Attr;
import org.w3c.dom.Element;
import org.w3c.dom.NamedNodeMap;
import org.w3c.dom.Node;
import org.xml.sax.AttributeList;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;


/**
 * Implements an HTML/XHTML serializer supporting both DOM and SAX
 * pretty serializing. HTML/XHTML mode is determined in the
 * constructor.  For usage instructions see {@link Serializer}.
 * <p>
 * If an output stream is used, the encoding is taken from the
 * output format (defaults to <tt>UTF-8</tt>). If a writer is
 * used, make sure the writer uses the same encoding (if applies)
 * as specified in the output format.
 * <p>
 * The serializer supports both DOM and SAX. DOM serializing is done
 * by calling {@link #serialize(Element)} and SAX serializing is done by firing
 * SAX events and using the serializer as a document handler.
 * <p>
 * If an I/O exception occurs while serializing, the serializer
 * will not throw an exception directly, but only throw it
 * at the end of serializing (either DOM or SAX's {@link
 * org.xml.sax.DocumentHandler#endDocument}.
 * <p>
 * For elements that are not specified as whitespace preserving,
 * the serializer will potentially break long text lines at space
 * boundaries, indent lines, and serialize elements on separate
 * lines. Line terminators will be regarded as spaces, and
 * spaces at beginning of line will be stripped.
 * <p>
 * XHTML is slightly different than HTML:
 * <ul>
 * <li>Element/attribute names are lower case and case matters
 * <li>Attributes must specify value, even if empty string
 * <li>Empty elements must have '/' in empty tag
 * <li>Contents of SCRIPT and STYLE elements serialized as CDATA
 * </ul>
 *
 *
 * @version $Revision: 1.6.2.1 $ $Date: 2004/11/02 20:41:47 $
 * @author <a href="mailto:[e-mail]">Assaf Arkin</a>
 * @see Serializer
 */
public class HTMLSerializer extends BaseMarkupSerializer implements IAnchoringSerializer {


    /**
     * True if serializing in XHTML format.
     */
    private static boolean _xhtml;


    public static String XHTMLNamespace = "";

    private String anchorId = null;


    /**
     * Constructs a new HTML/XHTML serializer depending on the value of
     * <tt>xhtml</tt>. The serializer cannot be used without calling
     * init() first.
     *
     * @param xhtml True if XHTML serializing
     */
    protected HTMLSerializer( boolean xhtml, OutputFormat format )
    {
        super( format );
        _xhtml = xhtml;
    }


    /**
     * Constructs a new serializer. The serializer cannot be used without
     * calling {@link #setOutputCharStream(Writer)} or {@link #setOutputByteStream(OutputStream)}
     * first.
     */
    public HTMLSerializer()
    {
        this( false, new OutputFormat( Method.HTML, "ISO-8859-1", false ) );
    }


    /**
     * Constructs a new serializer. The serializer cannot be used without
     * calling {@link #setOutputCharStream(Writer)} or {@link #setOutputByteStream(OutputStream)}
     * first.
     */
    public HTMLSerializer( OutputFormat format )
    {
        this( false, format != null ? format : new OutputFormat( Method.HTML, "ISO-8859-1", false ) );
    }



    /**
     * Constructs a new serializer that writes to the specified writer
     * using the specified output format. If <tt>format</tt> is null,
     * will use a default output format.
     *
     * @param writer The writer to use
     * @param format The output format to use, null for the default
     */
    public HTMLSerializer( Writer writer, OutputFormat format )
    {
        this( false, format != null ? format : new OutputFormat( Method.HTML, "ISO-8859-1", false ) );
        setOutputCharStream( writer );
    }


    /**
     * Constructs a new serializer that writes to the specified output
     * stream using the specified output format. If <tt>format</tt>
     * is null, will use a default output format.
     *
     * @param output The output stream to use
     * @param format The output format to use, null for the default
     */
    public HTMLSerializer( OutputStream output, OutputFormat format )
    {
        this( false, format != null ? format : new OutputFormat( Method.HTML, "ISO-8859-1", false ) );
        setOutputByteStream( output );
    }


    public void setOutputFormat( OutputFormat format )
    {
        super.setOutputFormat( format != null ? format : new OutputFormat( Method.HTML, "ISO-8859-1", false ) );
    }


    //-----------------------------------------//
    // SAX content handler serializing methods //
    //-----------------------------------------//


    public void startElement( String namespaceURI, String localName,
                              String rawName, Attributes attrs )
        throws SAXException
    {
        int          i;
        boolean      preserveSpace;
        ElementState state;
        String       name;
        String       value;
        String       htmlName;
        boolean      addNSAttr = false;

        try {
            if ( _printer == null )
                throw new IllegalStateException( "SER002 No writer supplied for serializer" );

            state = getElementState();
            if ( isDocumentState() ) {
                // If this is the root element handle it differently.
                // If the first root element in the document, serialize
                // the document's DOCTYPE. Space preserving defaults
                // to that of the output format.
                if ( ! _started )
                    startDocument( localName == null ? rawName : localName );
            } else {
                // For any other element, if first in parent, then
                // close parent's opening tag and use the parnet's
                // space preserving.
                if ( state.empty )
                    _printer.printText( '>' );
                // Indent this element on a new line if the first
                // content of the parent element or immediately
                // following an element.
                if ( _indenting && ! state.preserveSpace &&
                     ( state.empty || state.afterElement ) )
                    _printer.breakLine();
            }
            preserveSpace = state.preserveSpace;

            // Do not change the current element state yet.
            // This only happens in endElement().

            if ( rawName == null ) {
                rawName = localName;
                if ( namespaceURI != null ) {
                    String prefix;
                    prefix = getPrefix( namespaceURI );
                    if ( prefix.length() > 0 )
                        rawName = prefix + ":" + localName;
                }
                addNSAttr = true;
            }
            if ( namespaceURI == null )
                htmlName = rawName;
            else {
                if ( namespaceURI.equals( XHTMLNamespace ) )
                    htmlName = localName;
                else
                    htmlName = null;
            }

            // XHTML: element names are lower case, DOM will be different
            _printer.printText( '<' );
            if ( _xhtml )
                _printer.printText( rawName.toLowerCase() );
            else
                _printer.printText( rawName );
            _printer.indent();

            // For each attribute serialize it's name and value as one part,
            // separated with a space so the element can be broken on
            // multiple lines.
            if ( attrs != null ) {
                for ( i = 0 ; i < attrs.getLength() ; ++i ) {
                    _printer.printSpace();
                    name = attrs.getQName( i ).toLowerCase();;
                    value = attrs.getValue( i );
                    if ( _xhtml || namespaceURI != null ) {
                        // XHTML: print empty string for null values.
                        if ( value == null ) {