poi的word转html，怎么显示修订内容的最终状态

0 0

poi的word转html，怎么显示修订内容的最终状态0

问题描述：使用poi将.doc转换成html时，发现其将修订前的内容也显示出来了，而且html的标题无法控制，有时候会出现乱码，操作如下

编辑测试文档：修订状态（附件中可以下载该doc文档）

期望显示效果：最终状态

转换成html的效果：在修订中删除的内容会显示出来，而且导航栏，也就是html的title显示内容不是我想要的

实现代码：

public class Word2Html {

	public static void main(String argv[]) {
		try {
			//word 路径       html输出路径
			convert2Html("D:/doctohtml/1.doc","D:/doctohtml/1.html");
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	public static void writeFile(String content, String path) {
		FileOutputStream fos = null;
		BufferedWriter bw = null;
		try {
			File file = new File(path);
			fos = new FileOutputStream(file);
			bw = new BufferedWriter(new OutputStreamWriter(fos,"utf-8"));
			bw.write(content);
		} catch (FileNotFoundException fnfe) {
			fnfe.printStackTrace();
		} catch (IOException ioe) {
			ioe.printStackTrace();
		} finally {
			try {
				if (bw != null)
					bw.close();
				if (fos != null)
					fos.close();
			} catch (IOException ie) {
			}
		}
	}

	public static void convert2Html(String fileName, String outPutFile)
			throws TransformerException, IOException,
			ParserConfigurationException {
		HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(fileName));//WordToHtmlUtils.loadDoc(new FileInputStream(inputFile));
		WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
				DocumentBuilderFactory.newInstance().newDocumentBuilder()
						.newDocument());
		 wordToHtmlConverter.setPicturesManager( new PicturesManager()
         {
             public String savePicture( byte[] content,
                     PictureType pictureType, String suggestedName,
                     float widthInches, float heightInches )
             {
                 //html 中  图片标签中 显示的图片路路径  <img src="d:/test/0.jpg"/>
                 return "d:/doctohtml/"+suggestedName;
             }
         } );
		wordToHtmlConverter.processDocument(wordDocument);
		//save pictures
		List pics=wordDocument.getPicturesTable().getAllPictures();
		if(pics!=null){
			for(int i=0;i<pics.size();i++){
				Picture pic = (Picture)pics.get(i);
				System.out.println();
				try {
					//word中图片的存储路径
					pic.writeImageContent(new FileOutputStream("D:/doctohtml/"
							+ pic.suggestFullFileName()));
				} catch (FileNotFoundException e) {
					e.printStackTrace();
				}  
			}
		}
		Document htmlDocument = wordToHtmlConverter.getDocument();
		ByteArrayOutputStream out = new ByteArrayOutputStream();
		DOMSource domSource = new DOMSource(htmlDocument);
		StreamResult streamResult = new StreamResult(out);

		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer serializer = tf.newTransformer();
		serializer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
		serializer.setOutputProperty(OutputKeys.INDENT, "yes");
		serializer.setOutputProperty(OutputKeys.METHOD, "html");
		serializer.transform(domSource, streamResult);
		out.close();
		writeFile(new String(out.toByteArray()), outPutFile);
	}
}