xmlserializer.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 problem with namespace handling. Contributed by
//  David Blondeau <[e-mail]>
// 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.


package org.jasig.portal.serialize;


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

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;
import org.xml.sax.helpers.AttributesImpl;


/**
 * Implements an XML serializer supporting both DOM and SAX pretty
 * serializing. 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.ContentHandler#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.
 *
 *
 * @version $Revision: 1.3 $ $Date: 2004/09/10 17:17:27 $
 * @author <a href="mailto:[e-mail]">Assaf Arkin</a>
 * @see Serializer
 */
public class XMLSerializer
    extends BaseMarkupSerializer
{


    /**
     * Constructs a new serializer. The serializer cannot be used without
     * calling {@link #setOutputCharStream(Writer)} or {@link #setOutputByteStream(OutputStream)}
     * first.
     */
    public XMLSerializer()
    {
        super( new OutputFormat( Method.XML, null, false ) );
    }


    /**
     * Constructs a new serializer. The serializer cannot be used without
     * calling {@link #setOutputCharStream(Writer)} or {@link #setOutputByteStream(OutputStream)}
     * first.
     */
    public XMLSerializer( OutputFormat format )
    {
        super( format != null ? format : new OutputFormat( Method.XML, null, false ) );
        _format.setMethod( Method.XML );
    }


    /**
     * 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 XMLSerializer( Writer writer, OutputFormat format )
    {
        super( format != null ? format : new OutputFormat( Method.XML, null, false ) );
        _format.setMethod( Method.XML );
        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 XMLSerializer( OutputStream output, OutputFormat format )
    {
        super( format != null ? format : new OutputFormat( Method.XML, null, false ) );
        _format.setMethod( Method.XML );
        setOutputByteStream( output );
    }


    public void setOutputFormat( OutputFormat format )
    {
        super.setOutputFormat( format != null ? format : new OutputFormat( Method.XML, null, 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;
        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 || localName.length() == 0 ) ? 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( '>' );
            // Must leave CData section first
            if ( state.inCData )
            {
                _printer.printText( "]]>" );
                state.inCData = false;
            }
            // Indent this element on a new line if the first
            // content of the parent element or immediately
            // following an element or a comment
            if ( _indenting && ! state.preserveSpace &&
                 ( state.empty || state.afterElement || state.afterComment) )
                _printer.breakLine();
        }
        preserveSpace = state.preserveSpace;

            //We remove the namespaces from the attributes list so that they will
            //be in _prefixes
            attrs = extractNamespaces(attrs);

        // Do not change the current element state yet.
        // This only happens in endElement().
            if ( rawName == null || rawName.length() == 0 ) {
                if ( localName == null )
                    throw new SAXException( "No rawName and localName is null" );
                if ( namespaceURI != null && ! namespaceURI.equals( "" ) ) {
                String prefix;
                prefix = getPrefix( namespaceURI );
                    if ( prefix != null && prefix.length() > 0 )
                    rawName = prefix + ":" + localName;
                    else
                        rawName = localName;
                } else
                    rawName = localName;
            addNSAttr = true;
        }

        _printer.printText( '<' );
        _printer.printText( rawName );
        _printer.indent();

        // For each attribute print 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 );
                    if ( name != null && name.length() == 0 ) {
                    String prefix;
                    String attrURI;

                    name = attrs.getLocalName( i );
                    attrURI = attrs.getURI( i );
                        if ( ( attrURI != null && attrURI.length() != 0 ) &&
                             ( namespaceURI == null || namespaceURI.length() == 0 ||
                                              ! attrURI.equals( namespaceURI ) ) ) {
                        prefix = getPrefix( attrURI );
                        if ( prefix != null && prefix.length() > 0 )
                            name = prefix + ":" + name;
                    }
                }

                value = attrs.getValue( i );
                if ( value == null )
                    value = "";
                _printer.printText( name );
                _printer.printText( "=\"" );
                printEscaped( value );
                _printer.printText( '"' );

                // If the attribute xml:space exists, determine whether
                // to preserve spaces in this and child nodes based on
                // its value.
                if ( name.equals( "xml:space" ) ) {
                    if ( value.equals( "preserve" ) )
                        preserveSpace = true;
                    else
                        preserveSpace = _format.getPreserveSpace();
                }
            }
        }

            if ( _prefixes != null ) {
            Enumeration enum;

            enum = _prefixes.keys();
            while ( enum.hasMoreElements() ) {
                _printer.printSpace();
                value = (String) enum.nextElement();
                name = (String) _prefixes.get( value );
                if ( name.length() == 0 ) {
                    _printer.printText( "xmlns=\"" );
                    printEscaped( value );
                    _printer.printText( '"' );
                } else {
                    _printer.printText( "xmlns:" );
                    _printer.printText( name );
                    _printer.printText( "=\"" );
                    printEscaped( value );
                    _printer.printText( '"' );
                }
            }
        }

        // Now it's time to enter a new element state
        // with the tag name and space preserving.
        // We still do not change the curent element state.
        state = enterElementState( namespaceURI, localName, rawName, preserveSpace );
            name = ( localName == null || localName.length() == 0 ) ? rawName : namespaceURI + "^" + localName;
            state.doCData = _format.isCDataElement( name );
            state.unescaped = _format.isNonEscapingElement( name );
        } catch ( IOException except ) {
            throw new SAXException( except );
        }
    }


    public void endElement( String namespaceURI, String localName,
                            String rawName )
        throws SAXException
    {
        try {
            endElementIO( namespaceURI, localName, rawName );
        } catch ( IOException except ) {
            throw new SAXException( except );
        }
    }


    public void endElementIO( String namespaceURI, String localName,
                            String rawName )
        throws IOException
    {
        ElementState state;

        // Works much like content() with additions for closing
        // an element. Note the different checks for the closed
        // element's state and the parent element's state.
        _printer.unindent();
        state = getElementState();
        if ( state.empty ) {
            _printer.printText( "/>" );
        } else {
            // Must leave CData section first
            if ( state.inCData )
                _printer.printText( "]]>" );
            // This element is not empty and that last content was
            // another element, so print a line break before that
            // last element and this element's closing tag.
            if ( _indenting && ! state.preserveSpace && (state.afterElement || state.afterComment) )
                _printer.breakLine();
            _printer.printText( "</" );
            _printer.printText( state.rawName );
            _printer.printText( '>' );
        }
        // Leave the element state and update that of the parent
        // (if we're not root) to not empty and after element.
        state = leaveElementState();
        state.afterElement = true;
        state.afterComment = false;
        state.empty = false;
        if ( isDocumentState() )