org.docx4j.model.datastorage.migration.FromMergeFields Maven / Gradle / Ivy

Show more of this group Show more artifacts with this name
Show all versions of docx4j Show documentation
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.
The newest version!
package org.docx4j.model.datastorage.migration;

import org.docx4j.TraversalUtil;
import org.docx4j.XmlUtils;
import org.docx4j.model.fields.ComplexFieldLocator;
import org.docx4j.model.fields.FieldRef;
import org.docx4j.model.fields.FieldsPreprocessor;
import org.docx4j.openpackaging.io.SaveToZipFile;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.wml.ContentAccessor;
import org.docx4j.wml.P;
import org.docx4j.wml.Text;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.util.ArrayList;
import java.util.List;

/**
 * This class will help you to migrate
 * from MERGEFIELDs
 * to use of content control data bindings.
 * 
 * After migrating, you'll be able to
 * use the OpenDoPE authoring tool to
 * add repeats, conditionals, and other
 * OpenDoPE features, if you need them.
 * 
 * Limitations: this first version
 * operates only on the main document part
 * (ie it won't process variables in
 *  headers/footers, footnotes/endnotes,
 *  or comments)
 *  
 * @author jharrop
 * @since 3.0.0
 */
public class FromMergeFields extends AbstractMigratorUsingAnswersFormat {
	
	private static Logger log = LoggerFactory.getLogger(FromMergeFields.class);
	
	public WordprocessingMLPackage migrate(WordprocessingMLPackage pkgIn) throws Exception {
		
		// TODO - test that OpenDoPE parts aren't already present
		// or if they are, that this docx is using our answer format
		// (since only that format is supported here)
		
		// Clone it
		WordprocessingMLPackage pkgOut = (WordprocessingMLPackage)pkgIn.clone();
				
		// Create the CustomXML parts
		createParts(pkgOut);
		
		FieldsPreprocessor.complexifyFields(pkgOut.getMainDocumentPart() );
        if(log.isDebugEnabled()) {
            log.debug("complexified: "
                    + XmlUtils.marshaltoString(pkgOut.getMainDocumentPart().getJaxbElement(), true));
        }
		
		// find fields
		ComplexFieldLocator fl = new ComplexFieldLocator();
		new TraversalUtil(pkgOut.getMainDocumentPart().getContent(), fl);
		log.info("Found " + fl.getStarts().size() + " fields ");
		
		
		// canonicalise and setup fieldRefs 
		List fieldRefs = new ArrayList();
		for( P p : fl.getStarts() ) {
			int index = ((ContentAccessor)p.getParent()).getContent().indexOf(p);
			P newP = FieldsPreprocessor.canonicalise(p, fieldRefs);
			((ContentAccessor)p.getParent()).getContent().set(index, newP);
			
			/*
			 *   
				    
				      Hallo, lower 
				    
				    
				      
				        
				      
				      
				       MERGEFIELD  kundenname  \* MERGEFORMAT  
				      
				    
				    
				      
				        
				      
				      «Kundenname»
				    
				    
				    
				      
				    
				  
			 */
		}
		
		// Populate
		for (FieldRef fr : fieldRefs) {
			
			if ( fr.getFldName().equals("MERGEFIELD") ) {
				String instr = extractInstr(fr.getInstructions() );

				// eg  MERGEFIELD  Kundenstrasse \* MERGEFORMAT 
				// or  MERGEFIELD  Kundenstrasse
				
				String tmp = instr.substring( instr.indexOf("MERGEFIELD") + 10);
				tmp = tmp.trim();
				String key  = tmp.indexOf(" ") >-1 ? tmp.substring(0, tmp.indexOf(" ")) : tmp ;
				log.info("Key: '" + key + "'");
								
				// Remove the field related runs
				int end = fr.getParent().getContent().indexOf(fr.getEndRun());
				int begin = fr.getParent().getContent().indexOf(fr.getBeginRun());
				for (int i = end; i>=begin; i--) {
					fr.getParent().getContent().remove(i);
				}
				
				// Now add a content control
				List