org.docx4j.samples.XhtmlToDocxAndBack Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of docx4j-ImportXHTML-samples Show documentation
docx4j-ImportXHTML converts XHTML to OpenXML WordML (docx) using docx4j
The newest version!
/*
 *  This file is part of the docx4j-ImportXHTML library.
 *
 *  Copyright 2011-2013, Plutext Pty Ltd, and contributors.
 *  Portions contributed before 15 July 2013 formed part of docx4j 
 *  and were contributed under ASL v2 (a copy of which is incorporated
 *  herein by reference and applies to those portions). 
 *   
 *  This library as a whole is licensed under the GNU Lesser General 
 *  Public License as published by the Free Software Foundation; 
    version 2.1.
    
    This library is free software; you can redistribute it and/or
    modify it under the terms of the GNU Lesser General Public
    License as published by the Free Software Foundation; either
    version 2.1 of the License, or (at your option) any later version.

    This library is distributed in the hope that it will be useful,
    but WITHOUT ANY WARRANTY; without even the implied warranty of
    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
    Lesser General Public License for more details.

    You should have received a copy of the GNU Lesser General Public
    License along with this library (see legals/LICENSE); if not, 
    see http://www.gnu.org/licenses/lgpl-2.1.html
    
 */
package org.docx4j.samples;

import java.io.ByteArrayOutputStream;
import java.io.IOException;
import java.io.OutputStream;
import java.util.HashMap;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.TransformerException;

import org.docx4j.Docx4J;
import org.docx4j.Docx4jProperties;
import org.docx4j.XmlUtils;
import org.docx4j.convert.in.xhtml.DivToSdt;
import org.docx4j.convert.in.xhtml.XHTMLImporterImpl;
import org.docx4j.convert.out.HTMLSettings;
import org.docx4j.convert.out.html.SdtTagHandler;
import org.docx4j.convert.out.html.SdtWriter;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.wml.SdtPr;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.Document;
import org.w3c.dom.DocumentFragment;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.traversal.NodeIterator;
import org.xml.sax.SAXException;

/**
 * Round-trip XHTML to docx and back to XHTML.
 */
public class XhtmlToDocxAndBack {
	
	private static Logger log = LoggerFactory.getLogger(XhtmlToDocxAndBack.class);		
	

    public static void main(String[] args) throws Exception {
        

    	String xhtml= 
    			"test test
test test
test test";    	
    	
    	// To docx, with content controls
		WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage.createPackage();
		
        XHTMLImporterImpl XHTMLImporter = new XHTMLImporterImpl(wordMLPackage);
        //XHTMLImporter.setDivHandler(new DivToSdt());
		
		wordMLPackage.getMainDocumentPart().getContent().addAll( 
				XHTMLImporter.convert( xhtml, null) );

		System.out.println(XmlUtils.marshaltoString(wordMLPackage
				.getMainDocumentPart().getJaxbElement(), true, true));

//		wordMLPackage.save(new java.io.File(System.getProperty("user.dir")
//				+ "/OUT_from_XHTML.docx"));

		// Back to XHTML

		HTMLSettings htmlSettings = Docx4J.createHTMLSettings();
		htmlSettings.setWmlPackage(wordMLPackage);

	
		// output to an OutputStream.
		OutputStream os = new ByteArrayOutputStream();

		// If you want XHTML output
		Docx4jProperties.setProperty("docx4j.Convert.Out.HTML.OutputMethodXML",
				true);
		Docx4J.toHTML(htmlSettings, os, Docx4J.FLAG_EXPORT_PREFER_XSL);

		System.out.println(((ByteArrayOutputStream) os).toString());	
	
  }
    
    
	
}