All Downloads are FREE. Search and download functionalities are using the official Maven repository.

org.docx4j.openpackaging.parts.JaxbXmlPartAltChunkHost Maven / Gradle / Ivy

Go to download

docx4j is a library which helps you to work with the Office Open XML file format as used in docx documents, pptx presentations, and xlsx spreadsheets.

There is a newer version: 6.1.2
Show newest version
/**
 *  Copyright 2012, Plutext Pty Ltd.
 *   
 *  This file is part of docx4j.

    docx4j is licensed 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.docx4j.openpackaging.parts;

import java.io.InputStream;
import java.io.UnsupportedEncodingException;
import java.lang.reflect.Constructor;
import java.lang.reflect.InvocationTargetException;
import java.lang.reflect.Method;
import java.nio.ByteBuffer;
import java.util.List;

import org.docx4j.TraversalUtil;
import org.docx4j.convert.in.xhtml.XHTMLImporter;
import org.docx4j.jaxb.Context;
import org.docx4j.openpackaging.exceptions.Docx4JException;
import org.docx4j.openpackaging.exceptions.InvalidFormatException;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.openpackaging.parts.WordprocessingML.AltChunkInterface;
import org.docx4j.openpackaging.parts.WordprocessingML.AltChunkType;
import org.docx4j.openpackaging.parts.WordprocessingML.AlternativeFormatInputPart;
import org.docx4j.openpackaging.parts.relationships.RelationshipsPart.AddPartBehaviour;
import org.docx4j.relationships.Relationship;
import org.docx4j.utils.AltChunkFinder;
import org.docx4j.utils.AltChunkFinder.LocatedChunk;
import org.docx4j.wml.CTAltChunk;
import org.docx4j.wml.ContentAccessor;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * @author jharrop
 * @since 3.0.0
 */
public abstract class JaxbXmlPartAltChunkHost extends JaxbXmlPartXPathAware implements AltChunkInterface {
	
	protected static Logger log = LoggerFactory.getLogger(JaxbXmlPartAltChunkHost.class);

	public JaxbXmlPartAltChunkHost(PartName partName)
			throws InvalidFormatException {
		super(partName);
		// TODO Auto-generated constructor stub
	}


	/* (non-Javadoc)
	 * @see org.docx4j.openpackaging.parts.WordprocessingML.AltChunkInterface#addAltChunkOfTypeHTML(byte[])
	 */
	@Override
	public AlternativeFormatInputPart addAltChunk(AltChunkType type, byte[] bytes)  throws Docx4JException {
		
		AlternativeFormatInputPart afiPart = new AlternativeFormatInputPart(type); 
		Relationship altChunkRel = this.addTargetPart(afiPart, AddPartBehaviour.RENAME_IF_NAME_EXISTS); 
		// now that its attached to the package ..
		afiPart.registerInContentTypeManager();
		
		afiPart.setBinaryData(bytes); 		
		
		// .. the bit in document body 
		CTAltChunk ac = Context.getWmlObjectFactory().createCTAltChunk(); 
		ac.setId(altChunkRel.getId() ); 
		if (this instanceof ContentAccessor) {
		 ((ContentAccessor)this).getContent().add(ac); 
		} else {
			throw new Docx4JException(this.getClass().getName() + " doesn't implement ContentAccessor");
		}
		
		return afiPart;
	}

	/* (non-Javadoc)
	 * @see org.docx4j.openpackaging.parts.WordprocessingML.AltChunkInterface#addAltChunkOfTypeHTML(java.io.InputStream)
	 */
	@Override
	public AlternativeFormatInputPart addAltChunk(AltChunkType type, InputStream is)   throws Docx4JException {
		
		AlternativeFormatInputPart afiPart = new AlternativeFormatInputPart(type); 
		Relationship altChunkRel = this.addTargetPart(afiPart, AddPartBehaviour.RENAME_IF_NAME_EXISTS); 
		// now that its attached to the package ..
		afiPart.registerInContentTypeManager();		
		
		afiPart.setBinaryData(is); 
		
		// .. the bit in document body 
		CTAltChunk ac = Context.getWmlObjectFactory().createCTAltChunk(); 
		ac.setId(altChunkRel.getId() ); 
		if (this instanceof ContentAccessor) {
		 ((ContentAccessor)this).getContent().add(ac); 
		} else {
			throw new Docx4JException(this.getClass().getName() + " doesn't implement ContentAccessor");
		}
		
		return afiPart;
	}

	/* (non-Javadoc)
	 * @see org.docx4j.openpackaging.parts.WordprocessingML.AltChunkInterface#addAltChunkOfTypeHTML(byte[], org.docx4j.wml.ContentAccessor)
	 */
	@Override
	public AlternativeFormatInputPart addAltChunk(AltChunkType type, byte[] bytes,
			ContentAccessor attachmentPoint)   throws Docx4JException {
		
		AlternativeFormatInputPart afiPart = new AlternativeFormatInputPart(type); 
		Relationship altChunkRel = this.addTargetPart(afiPart, AddPartBehaviour.RENAME_IF_NAME_EXISTS); 
		// now that its attached to the package ..
		afiPart.registerInContentTypeManager();
		
		afiPart.setBinaryData(bytes); 		
		
		// .. the bit in document body 
		CTAltChunk ac = Context.getWmlObjectFactory().createCTAltChunk(); 
		ac.setId(altChunkRel.getId() ); 
		attachmentPoint.getContent().add(ac);
					
		return afiPart;
	}

	/* (non-Javadoc)
	 * @see org.docx4j.openpackaging.parts.WordprocessingML.AltChunkInterface#addAltChunkOfTypeHTML(java.io.InputStream, org.docx4j.wml.ContentAccessor)
	 */
	@Override
	public AlternativeFormatInputPart addAltChunk(AltChunkType type, InputStream is,
			ContentAccessor attachmentPoint) throws Docx4JException {
		
		AlternativeFormatInputPart afiPart = new AlternativeFormatInputPart(type); 
		Relationship altChunkRel = this.addTargetPart(afiPart, AddPartBehaviour.RENAME_IF_NAME_EXISTS); 
		// now that its attached to the package ..
		afiPart.registerInContentTypeManager();		
		
		afiPart.setBinaryData(is); 
		
		// .. the bit in document body 
		CTAltChunk ac = Context.getWmlObjectFactory().createCTAltChunk(); 
		ac.setId(altChunkRel.getId() ); 
		attachmentPoint.getContent().add(ac);
					
		return afiPart;
	}

	/* (non-Javadoc)
	 * @see org.docx4j.openpackaging.parts.WordprocessingML.AltChunkInterface#processAltChunksOfTypeHTML()
	 */
	/**
	 * To convert an altChunk of type XHTML, this method requires docx4j-XHTMLImport.jar (LGPL) and its dependencies.
	 * */
	@Override
	public WordprocessingMLPackage convertAltChunks() throws Docx4JException {
		
		// TODO: Currently only processes AltChunks in main document part.

		if (!(this instanceof ContentAccessor)) {
				throw new Docx4JException(this.getClass().getName() + " doesn't implement ContentAccessor");
		}	
		PartName partName = this.getPartName();
				
		WordprocessingMLPackage clonePkg = (WordprocessingMLPackage)this.getPackage().clone(); // consistent with MergeDocx approach
		JaxbXmlPartAltChunkHost clonedPart = (JaxbXmlPartAltChunkHost)clonePkg.getParts().get(partName); 
				
		List contentList = ((ContentAccessor)clonedPart).getContent();
		
	    AltChunkFinder bf = new AltChunkFinder();
		new TraversalUtil(contentList, bf);

		CTAltChunk altChunk;
		boolean encounteredDocxAltChunk = false;
		for (LocatedChunk locatedChunk : bf.getAltChunks()) {
			
			altChunk = locatedChunk.getAltChunk();
			AlternativeFormatInputPart afip 
				=  (AlternativeFormatInputPart)clonedPart.getRelationshipsPart().getPart(
						altChunk.getId() );
			
			// Can we process it?
			AltChunkType type = afip.getAltChunkType();

			if (type.equals(AltChunkType.Xhtml) ) {
				
				XHTMLImporter xHTMLImporter= null;
			    try {
			    	Class xhtmlImporterClass = Class.forName("org.docx4j.convert.in.xhtml.XHTMLImporterImpl");
				    Constructor ctor = xhtmlImporterClass.getConstructor(WordprocessingMLPackage.class);
				    xHTMLImporter = (XHTMLImporter) ctor.newInstance(clonePkg);
			    } catch (Exception e) {
			        log.warn("docx4j-XHTMLImport jar not found. Please add this to your classpath.");
					log.warn(e.getMessage(), e);
					return null;
			    }		
				
	            List results = null;
				try {
					
					results = xHTMLImporter.convert(toString(afip.getBuffer()), null);
					
				} catch (Exception e) {
					log.error(e.getMessage(), e);
					// Skip this one
					continue;
				} 
				
				int index = locatedChunk.getIndex(); 
				locatedChunk.getContentList().remove(index); // handles case where it is nested eg in a tc
				locatedChunk.getContentList().addAll(index, results);	
				
				log.info("Converted altChunk of type XHTML ");
				
			} else if (type.equals(AltChunkType.Mht) ) {
				log.warn("Skipping altChunk of type MHT ");
				continue;
			} else if (type.equals(AltChunkType.Xml) ) {
				log.warn("Skipping altChunk of type XML "); // what does Word do??
				continue;
			} else if (type.equals(AltChunkType.TextPlain) ) {
				
				String result= null;
				try {
					result = toString(afip.getBuffer());
				} catch (UnsupportedEncodingException e) {
					log.error(e.getMessage(), e);
					// Skip this one
					continue;
				}
				
				if (result!=null) {
					int index = locatedChunk.getIndex();
					locatedChunk.getContentList().remove(index); // handles case where it is nested eg in a tc
					
					org.docx4j.wml.ObjectFactory factory = Context.getWmlObjectFactory();
					org.docx4j.wml.P  para = factory.createP();
					locatedChunk.getContentList().add(index, para);	
				
					org.docx4j.wml.R  run = factory.createR();
					para.getContent().add(run);

					org.docx4j.wml.Text  t = factory.createText();
					t.setValue(result);
					run.getContent().add(t);		
					
					
					log.info("Converted altChunk of type text ");
				}

			} else if (type.equals(AltChunkType.WordprocessingML)
					 || type.equals(AltChunkType.OfficeWordMacroEnabled)
					 || type.equals(AltChunkType.OfficeWordTemplate)
					 ||type.equals(AltChunkType.OfficeWordMacroEnabledTemplate) ) {
				encounteredDocxAltChunk = true;
				continue;
				
			} else if (type.equals(AltChunkType.Rtf) ) {
				log.warn("Skipping altChunk of type RTF ");
				continue;
			} else if (type.equals(AltChunkType.Html) ) {
				log.warn("Skipping altChunk of type HTML ");
				continue;
				// if there was a pretty printer on class path,
				// could use it via reflection?
			}
						
		}
		
		if (encounteredDocxAltChunk) {
			
			// Docx AltChunks are handled by MergeDocx, if available
			try {
				// Use reflection, so docx4j can be built
				// by users who don't have the MergeDocx utility
				Class documentBuilder = Class.forName("com.plutext.merge.altchunk.ProcessAltChunk");			
				//Method method = documentBuilder.getMethod("merge", wmlPkgList.getClass());			
				Method[] methods = documentBuilder.getMethods(); 
				Method method = null;
				for (int j=0; j    

    

    
            
    
            







    
© 2015 - 2024 Weber Informatics LLC | Privacy Policy