将 doc 转换为 html 图形或形状时未转换为 html 格式

Question

我们想在浏览器的对话框中显示 doc 文件。这就是我将其转换为html文件的原因。因此 doc 文件成功转换为 html，但如果 doc 文件有图形或任何形状，则它会转换为 html 文件。但是图形软件没有转换成任何 html 标签，如 img 等，也没有显示在 UI 上显示的文件中，

那么我们如何将具有图形或形状的doc文件转换为html。

InputStream input = new FileInputStream (baseDir + fileName);
HWPFDocument wordDocument = new HWPFDocument (input);
wordToHtmlConverter.processDocument (wordDocument);
wordToHtmlConverter.setPicturesManager (picmang=new PicturesManager() {
        public String savePicture (byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
            return suggestedName;
        }

    });
org.w3c.dom.Document htmlDocument = wordToHtmlConverter.getDocument();

    ByteArrayOutputStream outStream = new ByteArrayOutputStream();
    DOMSource domSource = new DOMSource (htmlDocument);
    StreamResult streamResult = new StreamResult (outStream);

    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);
    outStream.close();

    String content = new String (outStream.toByteArray() );
    FileOutputStream fos = null;
    String destinationHTMLFile = baseDir + fileName.replace(".docx", "").replace(".doc", "")+".html";
    BufferedWriter bw = null;

    File file = new File(destinationHTMLFile);
    fos = new FileOutputStream(file);
    bw = new BufferedWriter(new OutputStreamWriter(fos, "UTF-8"));
    bw.write(content);

所以请帮我在浏览器中显示 doc 文件。

Answer 1

AbstractWordConverter.setPicturesManager 必须在AbstractWordConverter.processDocument 之前完成。当然Interface PicturesManager中的PicturesManager.savePicture方法需要在实现该接口的类中填充保存图片的功能。

以下示例从我的主目录中获取 WordDocument.doc，并将其转换为包含图片的 HTML，并将生成的文件（HTML 文件和图像文件）放入新创建的目录 html。请注意，WordDocument.doc 中包含的图片必须为*.gif 或*.png 或*.jpg，因为Writing/Saving an Image 使用的方法仅支持这些类型。

import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.converter.PicturesManager;

import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.util.XMLHelper;
import org.w3c.dom.Document;

import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import java.io.StringWriter;
import java.io.FileInputStream;
import java.io.ByteArrayInputStream;
import java.io.File;

import java.awt.image.BufferedImage;
import javax.imageio.ImageIO;

public class TestWordToHtmlConverter {

 private static void convertDocToHTML(String docFilePathAndName, String htmlPath, String htmlFileName) throws Exception {

  new File(htmlPath).mkdir();

  HWPFDocument hwpfDocument = new HWPFDocument(new FileInputStream(docFilePathAndName));

  Document newDocument = XMLHelper.getDocumentBuilderFactory().newDocumentBuilder().newDocument();
  WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(newDocument);

  wordToHtmlConverter.setPicturesManager(
   new PicturesManager() {
    public String savePicture(byte[] content, PictureType pictureType, String suggestedName, float widthInches, float heightInches) {
     /*
     System.out.println(content);
     System.out.println(pictureType);
     System.out.println(suggestedName);
     System.out.println(widthInches);
     System.out.println(heightInches);
     */
     try {
      BufferedImage image = ImageIO.read(new ByteArrayInputStream(content));
      ImageIO.write(image, pictureType.getExtension(), new File(htmlPath, suggestedName));
     } catch (Exception e) {
      e.printStackTrace();
     }
     return suggestedName;
    }
   }
  );

  wordToHtmlConverter.processDocument(hwpfDocument);

  Transformer transformer = TransformerFactory.newInstance().newTransformer();
  transformer.setOutputProperty(OutputKeys.INDENT, "yes");
  transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
  transformer.setOutputProperty(OutputKeys.METHOD, "html");
  transformer.transform(new DOMSource(wordToHtmlConverter.getDocument()),
                        new StreamResult(new File(htmlPath, htmlFileName)));

 }

 public static void main(String[] args) throws Exception {

  convertDocToHTML("/home/axel/Dokumente/WordDocument.doc", "/home/axel/Dokumente/html", "WordDocument.html");

 }

}