Java Docx4J类代码示例

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * docx文档转换为PDF
 *
 * @param wordMLPackage
 * @param pdfPath       PDF文档存储路径
 * @throws Exception
 */
public static void convertDocxToPDF(WordprocessingMLPackage wordMLPackage,
                                    String pdfPath)
        throws Exception {
    //HashSet<String> features = new HashSet<>();
    //features.add(PP_PDF_APACHEFOP_DISABLE_PAGEBREAK_LIST_ITEM);
    //WordprocessingMLPackage process = Preprocess.process(wordMLPackage, features);

    FileOutputStream fileOutputStream = new FileOutputStream(pdfPath);
    Docx4J.toPDF(wordMLPackage, fileOutputStream);
    fileOutputStream.flush();
    fileOutputStream.close();

    /*FOSettings foSettings = Docx4J.createFOSettings();
    foSettings.setWmlPackage(wordMLPackage);
    Docx4J.toFO(foSettings, fileOutputStream, Docx4J.FLAG_EXPORT_PREFER_XSL);*/
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * 将 {@link org.docx4j.openpackaging.packages.WordprocessingMLPackage} 存为 pdf
 *
 * @param wordMLPackage
 * @return
 * @throws Exception
 */
public File savePdf(WordprocessingMLPackage wordMLPackage) throws Exception {

    File file = new File(genFilePath() + ".pdf");

    OutputStream os = new java.io.FileOutputStream(file);

    Docx4J.toPDF(wordMLPackage, os);

    os.flush();
    os.close();

    if (logger.isDebugEnabled()) {
        logger.debug("Save to [.pdf]: {}", file.getAbsolutePath());
    }
    return file;
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
@Override
public InputStream convert(InputStream fromInputSource, String toMimeType) {
	try {
		WordprocessingMLPackage pkg = WordprocessingMLPackage.load(fromInputSource);

		// Refresh the values of DOCPROPERTY fields 
		FieldUpdater updater = new FieldUpdater(pkg);
		updater.update(true);
		
		AbstractHtmlExporter exporter = new HtmlExporterNG2();
		HTMLSettings htmlSettings= Docx4J.createHTMLSettings();
    	htmlSettings.setImageDirPath("/tmp/sample-docx.html_files");
    	htmlSettings.setImageTargetUri("/tmp/_files");
    	htmlSettings.setWmlPackage(pkg);
    	
    	Docx4jProperties.setProperty("docx4j.Convert.Out.HTML.OutputMethodXML", true);
 
		OutputStream os = new FileOutputStream("/tmp/temp.html");
		Docx4J.toHTML(htmlSettings, os, Docx4J.FLAG_EXPORT_PREFER_XSL);
		IOUtils.closeQuietly(os);

		if (pkg.getMainDocumentPart().getFontTablePart()!=null) {
			pkg.getMainDocumentPart().getFontTablePart().deleteEmbeddedFontTempFiles();
		}		
		// This would also do it, via finalize() methods
		htmlSettings = null;
		pkg = null;

		return new FileInputStream("/tmp/temp.html");
	} catch (Exception e) {
		
	}
	
	return null;
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
@Override
public File convertPDF(File theFile, String md5UploadedFile) throws PDFConverterException {
	try {
		WordprocessingMLPackage wordMLPckg = Docx4J.load(theFile);
		FOSettings foSettings = Docx4J.createFOSettings();
		foSettings.setWmlPackage(wordMLPckg);
		String outFileName = this.getOutputFileName(md5UploadedFile);
		File outputFile = new File(Config.getString("application.staticFiles"), outFileName);
		FileOutputStream pdfStream = new FileOutputStream(outputFile);
		Docx4J.toFO(foSettings, pdfStream, Docx4J.FLAG_EXPORT_PREFER_XSL);
		pdfStream.close();
		return outputFile;
	} catch (Exception e) {
		log.error("Fail to create PDF in DOC4J Converter", e);
		throw new PDFConverterException("Fail to create PDF in DOC4J Converter", e);
	}
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * 将 {@link org.docx4j.openpackaging.packages.WordprocessingMLPackage} 存为 docx
 */
public void writeToDocx(WordprocessingMLPackage wmlPackage,OutputStream output) throws IOException, Docx4JException {
	Assert.notNull(wmlPackage, " wmlPackage is not specified!");
	Assert.notNull(output, " output is not specified!");
       try {
       	wmlPackage.save(output , Docx4J.FLAG_SAVE_ZIP_FILE );//保存到 docx 文件
	} finally{
		IOUtils.closeQuietly(output);
       }
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * 将 {@link org.docx4j.openpackaging.packages.WordprocessingMLPackage} 存为 pdf
 */
public void writeToPDF(WordprocessingMLPackage wmlPackage,OutputStream output) throws IOException, Docx4JException {
	Assert.notNull(wmlPackage, " wmlPackage is not specified!");
	Assert.notNull(output, " output is not specified!");
       try {
		Docx4J.toPDF(wmlPackage, output); //保存到 pdf 文件
		output.flush();
	} finally{
		IOUtils.closeQuietly(output);
       }
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
@Override
	public InputStream convert(InputStream fromInputSource, String toMimeType) {
		try {
			// Font regex (optional)
			// Set regex if you want to restrict to some defined subset of fonts
			// Here we have to do this before calling createContent,
			// since that discovers fonts
			String regex = null;
			// Windows:
			// String
			// regex=".*(calibri|camb|cour|arial|symb|times|Times|zapf).*";
			//regex=".*(calibri|camb|cour|arial|times|comic|georgia|impact|LSANS|pala|tahoma|trebuc|verdana|symbol|webdings|wingding).*";
			// Mac
			// String
			// regex=".*(Courier New|Arial|Times New Roman|Comic Sans|Georgia|Impact|Lucida Console|Lucida Sans Unicode|Palatino Linotype|Tahoma|Trebuchet|Verdana|Symbol|Webdings|Wingdings|MS Sans Serif|MS Serif).*";
			PhysicalFonts.setRegex(regex);
			
			WordprocessingMLPackage pkg = WordprocessingMLPackage.load(fromInputSource);
	
			// Refresh the values of DOCPROPERTY fields 
			FieldUpdater updater = new FieldUpdater(pkg);
			updater.update(true);
			
			// FO exporter setup (required)
			// .. the FOSettings object
	    	FOSettings foSettings = Docx4J.createFOSettings();
//			if (false) {
//				foSettings.setFoDumpFile(new java.io.File("/tmp/test.fo"));
//			}
			foSettings.setWmlPackage(pkg);
			
			//ByteArrayOutputStream os = new ByteArrayOutputStream();
			
			String outputfilepath;
			outputfilepath = "/tmp/temp.pdf";
			OutputStream os = new java.io.FileOutputStream(outputfilepath);
	
			// Specify whether PDF export uses XSLT or not to create the FO
			// (XSLT takes longer, but is more complete).
			
			// Don't care what type of exporter you use
			Docx4J.toFO(foSettings, os, Docx4J.FLAG_EXPORT_PREFER_XSL);
			
			if (pkg.getMainDocumentPart().getFontTablePart()!=null) {
				pkg.getMainDocumentPart().getFontTablePart().deleteEmbeddedFontTempFiles();
			}
			
			return new FileInputStream(outputfilepath);
		} catch (Exception e) {
			
		}
		
		return null;
	}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
	 * "fo:table" content model is: (marker*,table-column*,table-header?,table-footer?,table-body+)
	 * 
	 * so a table with just a table header should have
	 * that converted to table-body row.
	 */
	@Test
	public  void testTblHeaderOne() throws Exception {
		
		String inputfilepath = System.getProperty("user.dir") + "/src/test/resources/tables/tblHeaderTestOne.docx";
		WordprocessingMLPackage wordMLPackage= WordprocessingMLPackage.load(new java.io.File(inputfilepath));	
		
    	FOSettings foSettings = Docx4J.createFOSettings();
		foSettings.setWmlPackage(wordMLPackage);
		
		// want the fo document as the result.
		foSettings.setApacheFopMime(FOSettings.INTERNAL_FO_MIME);
		
		// exporter writes to an OutputStream.		
		ByteArrayOutputStream baos = new ByteArrayOutputStream(); 
    	

		//Don't care what type of exporter you use
//		Docx4J.toFO(foSettings, os, Docx4J.FLAG_NONE);
		//Prefer the exporter, that uses a xsl transformation
		Docx4J.toFO(foSettings, baos, Docx4J.FLAG_EXPORT_PREFER_XSL);

		byte[] bytes = baos.toByteArray();
//		System.out.println(new String(bytes, "UTF-8"));
	
		// Now use XPath to assert it has a table-body
		try {
			org.w3c.dom.Document domDoc = w3cDomDocumentFromByteArray( bytes);
			assertTrue(this.isAbsent(domDoc, "//fo:table-header"));
			assertTrue(this.isPresent(domDoc, "//fo:table-body"));
		} catch (SAXParseException e) {
			
			Assert.fail(e.getMessage());
			Assert.fail(new String(bytes, "UTF-8"));
		}
		
		
	}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
	 * "fo:table" content model is: (marker*,table-column*,table-header?,table-footer?,table-body+)
	 * 
	 * so a table with body rows before header rows should have
	 * those body rows converted to header rows.
	 */
	@Test
	public  void testTblHeaderTwo() throws Exception {
		
		String inputfilepath = System.getProperty("user.dir") + "/src/test/resources/tables/tblHeaderTestTwo.docx";
		WordprocessingMLPackage wordMLPackage= WordprocessingMLPackage.load(new java.io.File(inputfilepath));	
		
    	FOSettings foSettings = Docx4J.createFOSettings();
		foSettings.setWmlPackage(wordMLPackage);
		
		// want the fo document as the result.
		foSettings.setApacheFopMime(FOSettings.INTERNAL_FO_MIME);
		
		// exporter writes to an OutputStream.		
		ByteArrayOutputStream baos = new ByteArrayOutputStream(); 
    	

		//Don't care what type of exporter you use
//		Docx4J.toFO(foSettings, os, Docx4J.FLAG_NONE);
		//Prefer the exporter, that uses a xsl transformation
		Docx4J.toFO(foSettings, baos, Docx4J.FLAG_EXPORT_PREFER_XSL);

		byte[] bytes = baos.toByteArray();
//		System.out.println(new String(bytes, "UTF-8"));
	
		// Now use XPath to assert it has a table-body
		try {
			org.w3c.dom.Document domDoc = w3cDomDocumentFromByteArray( bytes);
			assertTrue(this.isAbsent(domDoc, "//fo:table-body[following-sibling::fo:table-header]"));
			assertTrue(this.isPresent(domDoc, "//fo:table-header[following-sibling::fo:table-body]"));
		} catch (SAXParseException e) {
			
			Assert.fail(e.getMessage());
			Assert.fail(new String(bytes, "UTF-8"));
		}
		
		
		
	}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
private static void execute(WordprocessingMLPackage wordMLPackage) throws Docx4JException, IOException {
	
   	// Pretty print the main document part
	System.out.println(
			XmlUtils.marshaltoString(wordMLPackage.getMainDocumentPart().getJaxbElement(), true, true) );
	
	// Optionally save it
	if (save) {
		String filename = System.getProperty("user.dir") + "/OUT_CreateWordprocessingMLDocument.docx";
		wordMLPackage.save(new File(filename) );
		System.out.println("Saved " + filename);
	}
	
	// FO
	if (fo) {
		
		OutputStream baos = new ByteArrayOutputStream();
		Exporter<FOSettings> exporter = FOExporterVisitor.getInstance();
		FOSettings settings = new FOSettings();
		settings.setWmlPackage(wordMLPackage);
		settings.setApacheFopMime(FOSettings.INTERNAL_FO_MIME);
		exporter.export(settings, baos);
		
		System.out.println( ((ByteArrayOutputStream) baos).toString("UTF-8"));
		
	} else {
		
		Docx4J.toPDF(wordMLPackage, 
				FileUtils.openOutputStream(new File(System.getProperty("user.dir") + "/OUT_textbox.pdf")));
		
	}		
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
public static void convertToDocXThenPdf(File html, File pdf) throws IOException, Docx4JException, JAXBException {

        // Create an empty docx package
        WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage.createPackage();

        NumberingDefinitionsPart ndp = new NumberingDefinitionsPart();
        wordMLPackage.getMainDocumentPart().addTargetPart(ndp);
        ndp.unmarshalDefaultNumbering();

        XHTMLImporterImpl xHTMLImporter = new XHTMLImporterImpl(wordMLPackage);
        xHTMLImporter.setHyperlinkStyle("Hyperlink");

        // Convert the XHTML, and add it into the empty docx we made
        wordMLPackage.getMainDocumentPart().getContent().addAll(xHTMLImporter.convert(html, null));

        //wordMLPackage.save( docx );

        String regex = null;
        PhysicalFonts.setRegex(regex);

        try {
            wordMLPackage.setFontMapper(new IdentityPlusMapper());
        } catch (Exception e) {
            e.printStackTrace();
        }

        // All methods write to an output stream
        OutputStream os = new java.io.FileOutputStream(pdf);


        // Refresh the values of DOCPROPERTY fields
        FieldUpdater updater = new FieldUpdater(wordMLPackage);
        updater.update(true);


        Docx4J.toPDF(wordMLPackage, os);
        System.out.println("Saved: " + pdf.getAbsolutePath());

        // Clean up, so any ObfuscatedFontPart temp files can be deleted
        if (wordMLPackage.getMainDocumentPart().getFontTablePart() != null) {
            wordMLPackage.getMainDocumentPart().getFontTablePart().deleteEmbeddedFontTempFiles();
        }
    }
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * Writes this document as PDF to a OutputStream and closed the stream in
 * any case.
 * 
 * @param out
 *            - the Outputstream to write the document.
 * @throws IOException
 */
public void writeAsPDF(OutputStream out) throws IOException {

       WordprocessingMLPackage mlPackage = getWordMLPackage();
       
       try {
           FOSettings foSettings = Docx4J.createFOSettings();
           foSettings.setWmlPackage(mlPackage);
           Docx4J.toFO(foSettings, out, Docx4J.FLAG_EXPORT_PREFER_XSL);
       } catch (Exception e) {
       	throw new WteException("Unable to create PDF Document", e);
       } finally {
       	out.close();
       }
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * Export the items in the given output
 * 
 * @param document W3C XML DOM document
 * @param personBean current user
 * @param locale
 *            current locale
 * @param parameters
 *            the directory of the DOCX template enriched with special placeholders
 * @param os
 *            the output stream to write to
 * @param contextMap
 * @param description
 */
@Override
public void exportReport(Document document, 
		                 TPersonBean personBean,
		                 Locale locale, 
		                 Map<String, Object> parameters, 
		                 OutputStream os,
		                 Map<String, Object> contextMap, 
		                 Map<String, Object> description)
				throws ReportExportException {

	String format= (String) description.get(IDescriptionAttributes.FORMAT);

	if (format == null || !format.equals(FORMAT_DOCX)) {
		throw new ReportExportException(ERROR_UNKNOWN_FORMAT);
	}

	/* Caution! Because the me
	 * based on the template file name, the template has to be uploaded in the wiki!
	 */
	String docxTemplatePath = null;
	URL completeURL = (URL)parameters.get(JasperReportExporter.REPORT_PARAMETERS.COMPLETE_URL);
	if (completeURL!=null) {
		docxTemplatePath = completeURL.getFile();
		WordprocessingMLPackage wpMLP = AssembleWordprocessingMLPackage.getWordMLPackage(
				MeetingDatasource.WORK_ITEM_BEAN, MeetingDatasource.REPORT_BEANS, 
				docxTemplatePath, personBean.getObjectID(), locale);
		try {
			Docx4J.save(wpMLP, os, Docx4J.FLAG_NONE);
		} catch (Exception e) {
			LOGGER.error("Exporting the docx failed with throwable " + e.getMessage());
			LOGGER.debug(ExceptionUtils.getStackTrace(e));
		}
	}

}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * 将 {@link org.docx4j.openpackaging.packages.WordprocessingMLPackage} 存为 pdf
 */
public void writeToPDFWhithFo(WordprocessingMLPackage wmlPackage,OutputStream output) throws IOException, Docx4JException {
	Assert.notNull(wmlPackage, " wmlPackage is not specified!");
	Assert.notNull(output, " output is not specified!");
       try {
       	
		// Font regex (optional)
		// Set regex if you want to restrict to some defined subset of fonts
		// Here we have to do this before calling createContent,
		// since that discovers fonts
		//String regex = null;
		
		// Refresh the values of DOCPROPERTY fields 
		FieldUpdater updater = new FieldUpdater(wmlPackage);
		updater.update(true);
		
		// .. example of mapping font Times New Roman which doesn't have certain Arabic glyphs
		// eg Glyph "ي" (0x64a, afii57450) not available in font "TimesNewRomanPS-ItalicMT".
		// eg Glyph "ج" (0x62c, afii57420) not available in font "TimesNewRomanPS-ItalicMT".
		// to a font which does
		PhysicalFonts.get("Arial Unicode MS"); 

		// FO exporter setup (required)
		// .. the FOSettings object
	    FOSettings foSettings = Docx4J.createFOSettings();
	    
		foSettings.setWmlPackage(wmlPackage);
        foSettings.setApacheFopMime("application/pdf");
            
		// Document format: 
		// The default implementation of the FORenderer that uses Apache Fop will output
		// a PDF document if nothing is passed via 
		// foSettings.setApacheFopMime(apacheFopMime)
		// apacheFopMime can be any of the output formats defined in org.apache.fop.apps.MimeConstants eg org.apache.fop.apps.MimeConstants.MIME_FOP_IF or
		// FOSettings.INTERNAL_FO_MIME if you want the fo document as the result.
		//foSettings.setApacheFopMime(FOSettings.INTERNAL_FO_MIME);
		
		// Specify whether PDF export uses XSLT or not to create the FO
		// (XSLT takes longer, but is more complete).
		
		// Don't care what type of exporter you use
		Docx4J.toFO(foSettings, output, Docx4J.FLAG_EXPORT_PREFER_XSL);
		
		// Prefer the exporter, that uses a xsl transformation
		// Docx4J.toFO(foSettings, os, Docx4J.FLAG_EXPORT_PREFER_XSL);
		
		// Prefer the exporter, that doesn't use a xsl transformation (= uses a visitor)
		// faster, but not yet at feature parity
		// Docx4J.toFO(foSettings, os, Docx4J.FLAG_EXPORT_PREFER_NONXSL);
		   
		// Clean up, so any ObfuscatedFontPart temp files can be deleted 
		// if (wordMLPackage.getMainDocumentPart().getFontTablePart()!=null) {
		// 	wordMLPackage.getMainDocumentPart().getFontTablePart().deleteEmbeddedFontTempFiles();
		// } 
		// This would also do it, via finalize() methods
		updater = null;
		foSettings = null;
		wmlPackage = null;
	} finally{
		IOUtils.closeQuietly(output);
       }
}
 

import org.docx4j.Docx4J; //导入依赖的package包/类
/**
 * 保存当前Docx文件
 */
private static void saveDocx(WordprocessingMLPackage wordMLPackage,
                             String savePath)
        throws FileNotFoundException, Docx4JException {
    Docx4J.save(wordMLPackage, new File(savePath), Docx4J.FLAG_SAVE_ZIP_FILE);
}