com.sun.org.apache.xml.internal.serialize.TextSerializer Maven / Gradle / Ivy
Show all versions of org.apache.servicemix.bundles.jaxp-ri
/*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS HEADER.
*
* Copyright (c) 1997-2010 Oracle and/or its affiliates. All rights reserved.
*
* The contents of this file are subject to the terms of either the GNU
* General Public License Version 2 only ("GPL") or the Common Development
* and Distribution License("CDDL") (collectively, the "License"). You
* may not use this file except in compliance with the License. You can
* obtain a copy of the License at
* https://glassfish.dev.java.net/public/CDDL+GPL_1_1.html
* or packager/legal/LICENSE.txt. See the License for the specific
* language governing permissions and limitations under the License.
*
* When distributing the software, include this License Header Notice in each
* file and include the License file at packager/legal/LICENSE.txt.
*
* GPL Classpath Exception:
* Oracle designates this particular file as subject to the "Classpath"
* exception as provided by Oracle in the GPL Version 2 section of the License
* file that accompanied this code.
*
* Modifications:
* If applicable, add the following below the License Header, with the fields
* enclosed by brackets [] replaced by your own identifying information:
* "Portions Copyright [year] [name of copyright owner]"
*
* Contributor(s):
* If you wish your version of this file to be governed by only the CDDL or
* only the GPL Version 2, indicate your decision by adding "[Contributor]
* elects to include this software in this distribution under the [CDDL or GPL
* Version 2] license." If you don't indicate a single choice of license, a
* recipient has the option to distribute your version of this file under
* either the CDDL, the GPL Version 2 or to extend the choice of license to
* its licensees as provided above. However, if you add GPL Version 2 code
* and therefore, elected the GPL Version 2 license, then the option applies
* only if the new code is made subject to such option by the copyright
* holder.
*
*
* This file incorporates work covered by the following copyright and
* permission notice:
*
* 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.
*/
// Sep 14, 2000:
// Fixed serializer to report IO exception directly, instead at
// the end of document processing.
// Reported by Patrick Higgins
package com.sun.org.apache.xml.internal.serialize;
import java.io.IOException;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.xml.sax.AttributeList;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
/**
* Implements a text serializer supporting both DOM and SAX
* serializing. For usage instructions see {@link Serializer}.
*
* If an output stream is used, the encoding is taken from the
* output format (defaults to UTF-8). If a writer is
* used, make sure the writer uses the same encoding (if applies)
* as specified in the output format.
*
* The serializer supports both DOM and SAX. DOM serializing is done
* by calling {@link #serialize} and SAX serializing is done by firing
* SAX events and using the serializer as a document handler.
*
* 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}.
*
*
* @version $Revision: 1.6 $ $Date: 2010-11-01 04:40:36 $
* @author Assaf Arkin
* @see Serializer
*/
public class TextSerializer
extends BaseMarkupSerializer
{
/**
* Constructs a new serializer. The serializer cannot be used without
* calling {@link #setOutputCharStream} or {@link #setOutputByteStream}
* first.
*/
public TextSerializer()
{
super( new OutputFormat( Method.TEXT, null, false ) );
}
public void setOutputFormat( OutputFormat format )
{
super.setOutputFormat( format != null ? format : new OutputFormat( Method.TEXT, null, false ) );
}
//-----------------------------------------//
// SAX content handler serializing methods //
//-----------------------------------------//
public void startElement( String namespaceURI, String localName,
String rawName, Attributes attrs )
throws SAXException
{
startElement( rawName == null ? localName : rawName, null );
}
public void endElement( String namespaceURI, String localName,
String rawName )
throws SAXException
{
endElement( rawName == null ? localName : rawName );
}
//------------------------------------------//
// SAX document handler serializing methods //
//------------------------------000---------//
public void startElement( String tagName, AttributeList attrs )
throws SAXException
{
boolean preserveSpace;
ElementState state;
try {
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( tagName );
}
// For any other element, if first in parent, then
// use the parnet's space preserving.
preserveSpace = state.preserveSpace;
// Do not change the current element state yet.
// This only happens in endElement().
// Ignore all other attributes of the element, only printing
// its contents.
// 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( null, null, tagName, preserveSpace );
} catch ( IOException except ) {
throw new SAXException( except );
}
}
public void endElement( String tagName )
throws SAXException
{
try {
endElementIO( tagName );
} catch ( IOException except ) {
throw new SAXException( except );
}
}
public void endElementIO( String tagName )
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.
state = getElementState();
// 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.empty = false;
if ( isDocumentState() )
_printer.flush();
}
public void processingInstructionIO( String target, String code ) throws IOException
{
}
public void comment( String text )
{
}
public void comment( char[] chars, int start, int length )
{
}
public void characters( char[] chars, int start, int length )
throws SAXException
{
ElementState state;
try {
state = content();
state.doCData = state.inCData = false;
printText( chars, start, length, true, true );
} catch ( IOException except ) {
throw new SAXException( except );
}
}
protected void characters( String text, boolean unescaped )
throws IOException
{
ElementState state;
state = content();
state.doCData = state.inCData = false;
printText( text, true, true );
}
//------------------------------------------//
// Generic node serializing methods methods //
//------------------------------------------//
/**
* Called to serialize the document's DOCTYPE by the root element.
*
* This method will check if it has not been called before ({@link #_started}),
* will serialize the document type declaration, and will serialize all
* pre-root comments and PIs that were accumulated in the document
* (see {@link #serializePreRoot}). Pre-root will be serialized even if
* this is not the first root element of the document.
*/
protected void startDocument( String rootTagName )
throws IOException
{
// Required to stop processing the DTD, even though the DTD
// is not printed.
_printer.leaveDTD();
_started = true;
// Always serialize these, even if not te first root element.
serializePreRoot();
}
/**
* Called to serialize a DOM element. Equivalent to calling {@link
* #startElement}, {@link #endElement} and serializing everything
* inbetween, but better optimized.
*/
protected void serializeElement( Element elem )
throws IOException
{
Node child;
ElementState state;
boolean preserveSpace;
String tagName;
tagName = elem.getTagName();
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( tagName );
}
// For any other element, if first in parent, then
// use the parnet's space preserving.
preserveSpace = state.preserveSpace;
// Do not change the current element state yet.
// This only happens in endElement().
// Ignore all other attributes of the element, only printing
// its contents.
// If element has children, then serialize them, otherwise
// serialize en empty tag.
if ( elem.hasChildNodes() ) {
// Enter an element state, and serialize the children
// one by one. Finally, end the element.
state = enterElementState( null, null, tagName, preserveSpace );
child = elem.getFirstChild();
while ( child != null ) {
serializeNode( child );
child = child.getNextSibling();
}
endElementIO( tagName );
} else {
if ( ! isDocumentState() ) {
// After element but parent element is no longer empty.
state.afterElement = true;
state.empty = false;
}
}
}
/**
* Serialize the DOM node. This method is unique to the Text serializer.
*
* @param node The node to serialize
*/
protected void serializeNode( Node node )
throws IOException
{
// Based on the node type call the suitable SAX handler.
// Only comments entities and documents which are not
// handled by SAX are serialized directly.
switch ( node.getNodeType() ) {
case Node.TEXT_NODE : {
String text;
text = node.getNodeValue();
if ( text != null )
characters( node.getNodeValue(), true );
break;
}
case Node.CDATA_SECTION_NODE : {
String text;
text = node.getNodeValue();
if ( text != null )
characters( node.getNodeValue(), true );
break;
}
case Node.COMMENT_NODE :
break;
case Node.ENTITY_REFERENCE_NODE :
// Ignore.
break;
case Node.PROCESSING_INSTRUCTION_NODE :
break;
case Node.ELEMENT_NODE :
serializeElement( (Element) node );
break;
case Node.DOCUMENT_NODE :
// !!! Fall through
case Node.DOCUMENT_FRAGMENT_NODE : {
Node child;
// By definition this will happen if the node is a document,
// document fragment, etc. Just serialize its contents. It will
// work well for other nodes that we do not know how to serialize.
child = node.getFirstChild();
while ( child != null ) {
serializeNode( child );
child = child.getNextSibling();
}
break;
}
default:
break;
}
}
protected ElementState content()
{
ElementState state;
state = getElementState();
if ( ! isDocumentState() ) {
// If this is the first content in the element,
// change the state to not-empty.
if ( state.empty )
state.empty = false;
// Except for one content type, all of them
// are not last element. That one content
// type will take care of itself.
state.afterElement = false;
}
return state;
}
protected String getEntityRef( int ch )
{
return null;
}
}