javaapplication1.utils.MyWordToHtml.java Source code

Introduction

Here is the source code for javaapplication1.utils.MyWordToHtml.java

Source

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package javaapplication1.utils;

import java.io.BufferedWriter;
import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStreamWriter;
import java.util.List;
import javax.xml.parsers.DocumentBuilderFactory;
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 org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.w3c.dom.Document;

/**
 *
 * @author NMoldabe
 */
public class MyWordToHtml {

    public static void convert(String path, String file) throws Throwable {
        InputStream input = new FileInputStream(path + file);
        HWPFDocument wordDocument = new HWPFDocument(input);
        WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(
                DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());
        MyPictureManager pictureManager = new MyPictureManager();
        wordToHtmlConverter.setPicturesManager(pictureManager);

        wordToHtmlConverter.processDocument(wordDocument);
        List<?> pics = wordDocument.getPicturesTable().getAllPictures();
        File dir = new File("D:\\pics");
        dir.mkdir();
        if (pics != null) {
            for (int i = 0; i < pics.size(); i++) {
                Picture pic = (Picture) pics.get(i);
                try {
                    pic.writeImageContent(new FileOutputStream(path + "pics/" + pic.suggestFullFileName()));
                } catch (FileNotFoundException e) {
                    e.printStackTrace();
                }
            }
        }
        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());

        writeFile(content, path + "result.html", "UTF-8");
    }

    /**
     * The write file
     *
     * @param content
     * @param path
     * @param encode
     */
    public static void writeFile(String content, String path, String encode) {
        FileOutputStream fos = null;
        BufferedWriter bw = null;
        try {
            File file = new File(path);
            fos = new FileOutputStream(file);
            bw = new BufferedWriter(new OutputStreamWriter(fos, encode));
            bw.write(content);
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            try {
                if (bw != null) {
                    bw.close();
                }
                if (fos != null) {
                    fos.close();
                }
            } catch (IOException ie) {
                ie.printStackTrace();
            }
        }
    }
}