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

org.docx4j.openpackaging.parts.WordprocessingML.MainDocumentPart Maven / Gradle / Ivy

Go to download 

/*
 *  Copyright 2007-2008, 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.WordprocessingML;



import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;

import javax.xml.bind.JAXBException;

import org.docx4j.TraversalUtil;
import org.docx4j.TraversalUtil.CallbackImpl;
import org.docx4j.XmlUtils;
import org.docx4j.fonts.CJKToEnglish;
import org.docx4j.fonts.RunFontSelector;
import org.docx4j.fonts.RunFontSelector.RunFontActionType;
import org.docx4j.fonts.RunFontSelector.RunFontCharacterVisitor;
import org.docx4j.jaxb.Context;
import org.docx4j.jaxb.McIgnorableNamespaceDeclarator;
import org.docx4j.model.PropertyResolver;
import org.docx4j.model.styles.StyleTree;
import org.docx4j.openpackaging.exceptions.Docx4JException;
import org.docx4j.openpackaging.exceptions.InvalidFormatException;
import org.docx4j.openpackaging.packages.WordprocessingMLPackage;
import org.docx4j.openpackaging.parts.Part;
import org.docx4j.openpackaging.parts.PartName;
import org.docx4j.openpackaging.parts.relationships.Namespaces;
import org.docx4j.openpackaging.parts.relationships.RelationshipsPart;
import org.docx4j.relationships.Relationship;
import org.docx4j.wml.Body;
import org.docx4j.wml.Br;
import org.docx4j.wml.CTEndnotes;
import org.docx4j.wml.CTFootnotes;
import org.docx4j.wml.Comments;
import org.docx4j.wml.ContentAccessor;
import org.docx4j.wml.Ftr;
import org.docx4j.wml.Hdr;
import org.docx4j.wml.Lvl;
import org.docx4j.wml.Numbering;
import org.docx4j.wml.P;
import org.docx4j.wml.P.Hyperlink;
import org.docx4j.wml.PPr;
import org.docx4j.wml.R;
import org.docx4j.wml.RPr;
import org.docx4j.wml.RStyle;
import org.docx4j.wml.SdtElement;
import org.docx4j.wml.SdtPr;
import org.docx4j.wml.Style;
import org.docx4j.wml.Styles;
import org.docx4j.wml.Text;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.Document;


/**
 * @author jharrop
 *
 */
public class MainDocumentPart extends DocumentPart implements ContentAccessor  {
	
	private static Logger log = LoggerFactory.getLogger(MainDocumentPart.class);
		
	
	public MainDocumentPart(PartName partName) throws InvalidFormatException {
		super(partName);
		init();
	}
	public MainDocumentPart() throws InvalidFormatException {
		super(new PartName("/word/document.xml"));
		init();
	}
		
	public void init() {
		// Used if this Part is added to [Content_Types].xml 
		setContentType(new  org.docx4j.openpackaging.contenttype.ContentType( 
				org.docx4j.openpackaging.contenttype.ContentTypes.WORDPROCESSINGML_DOCUMENT));
		
		/*
		 * From [MS-OE376]
		 * 
		 * 2.1.8 Part 1 Section 11.3.10, Main Document Part
		 * 
		 * a. The standard states that the content type for the Main Document part is: 
		 * 
		 *        application/vnd.openxmlformats-officedocument.wordprocessingml.main+xml.
		 *        
		 *    Office uses the following content type for the Main Document part: 
		 *    
		 *        application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml.
		 *        
		 * This note applies to the following products: 2007, 2007 SP1, 2007 SP2.
		 */

		// Used when this Part is added to a rels 
		setRelationshipType(Namespaces.DOCUMENT);
	}	
	
	@Override
    protected void setMceIgnorable(McIgnorableNamespaceDeclarator namespacePrefixMapper) {

		// NB it is up to you to jaxbElement.setIgnorable; see further McIgnorableNamespaceDeclarator
		
//		MainDocumentPartMceIgnorableHelper helper = new MainDocumentPartMceIgnorableHelper();
//		this.jaxbElement.setIgnorable(
//				helper.getMceIgnorable(this.getJaxbElement().getBody()));
		
		namespacePrefixMapper.setMcIgnorable(
				this.getJaxbElement().getIgnorable() );
	}

	@Override
	public String getMceIgnorable() {
    	return this.getJaxbElement().getIgnorable();
    }
	
    
    

    /**
     * Convenience method to getJaxbElement().getBody().getContent()
     * @since 2.7
     */
    public List getContent() {
    	
    	if (this.getJaxbElement()==null) {    		
    		this.setJaxbElement( Context.getWmlObjectFactory().createDocument() );
    	}
    	if (this.getJaxbElement().getBody()==null) {
    		this.getJaxbElement().setBody(
    				Context.getWmlObjectFactory().createBody() );
    	}
    	
    	return this.getJaxbElement().getContent();
    }	
	
    private PropertyResolver propertyResolver;
	public PropertyResolver getPropertyResolver() {
		if (propertyResolver==null) {
			try {
				propertyResolver = new PropertyResolver( (WordprocessingMLPackage)this.pack);
			} catch (Docx4JException e) {
				e.printStackTrace();
			}			
		}
		return propertyResolver;
	}
	
	private StyleTree styleTree;
	public StyleTree getStyleTree() {
		return getStyleTree(false); // preserve existing behaviour
	}
	
	public StyleTree getStyleTree(boolean refresh) {
		// refresh is post 2.7.1
		
		if (refresh || styleTree==null) {
			
			log.debug("Preparing StyleTree");

//		    try {
//				getStyleDefinitionsPart().createVirtualStylesForDocDefaults();
//			} catch (Docx4JException e) {
//				// Shouldn't happen, so catch here
//				log.error(e.getMessage(), e);
//			}
	    	
//			// Get these first, so we can be sure they are defined... 
//			Style defaultParagraphStyle = getStyleDefinitionsPart().getDefaultParagraphStyle();
//			Style defaultCharacterStyle = getStyleDefinitionsPart().getDefaultCharacterStyle();
			
			// Styles defined in StyleDefinitionsPart
			Map allStyles = new HashMap();
			Styles styles = getStyleDefinitionsPart().getJaxbElement();		
			for ( org.docx4j.wml.Style s : styles.getStyle() ) {				
				allStyles.put(s.getStyleId(), s);	
				//log.debug("live style: " + s.getStyleId() );
			}
			styleTree = new StyleTree(getStylesInUse(), allStyles,
					getStyleDefinitionsPart().getJaxbElement().getDocDefaults(), 
					getStyleDefinitionsPart().getDefaultParagraphStyle());
				
		}
		return styleTree;
		
	}
	
		
    
    /**
     * Traverse the document, looking for fonts which have been applied, either
     * directly, or via a style. 
     * 
     * @return
     */
    public Set fontsInUse() {
    	
    	log.debug("fontsInUse..");
    	
    	getPropertyResolver();  // this inits our virtual DocDefaults style
    	
    // Setup 
    	
    	Set fontsDiscovered = new java.util.HashSet();
    	
//    	// Keep track of styles we encounter, so we can
//    	// inspect these for fonts
//    	Set stylesInUse = new java.util.HashSet();
//
//		org.docx4j.wml.Styles styles = null;
//		if (this.getStyleDefinitionsPart()!=null) {
//			styles = (org.docx4j.wml.Styles)this.getStyleDefinitionsPart().getJaxbElement();			
//		}
//		// It is convenient to have a HashMap of styles
//		Map stylesDefined = new java.util.HashMap();
//		if (styles!=null) {
//		     for (Iterator