这两天在整理Word、Excel、Cad在线预览的问题。刚花了点时间写了下word转化成html的工具。不过貌似这种显示处理稍稍有点问题，可能不会在项目中使用。可能转化成pdf再预览会更好一点。但是，既然工具已经写好了，那么还是先记录下好了，留着备用。

package com.nemo.utils;

import org.apache.commons.io.FileUtils;
import org.apache.poi.hwpf.HWPFDocument;
import org.apache.poi.hwpf.converter.PicturesManager;
import org.apache.poi.hwpf.converter.WordToHtmlConverter;
import org.apache.poi.hwpf.usermodel.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.apache.poi.xwpf.converter.core.FileImageExtractor;
import org.apache.poi.xwpf.converter.core.FileURIResolver;
import org.apache.poi.xwpf.converter.xhtml.XHTMLConverter;
import org.apache.poi.xwpf.converter.xhtml.XHTMLOptions;
import org.apache.poi.xwpf.usermodel.XWPFDocument;
import org.w3c.dom.Document;

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 java.io.*;
import java.util.List;

/**
 * Doc或者Docx文档转化成HTML的工具类
 * Created by nemo on 16-10-27.
 */
public class Doc2HTMLUtils {

    final static String _HTML_DIR="html/"; //HTML存放位置
    final static String _IMG_DIR="pic/"; //图片存储位置

    /**
     * 处理docx文件
     * @param path 文件路径
     * @param file 文件名称
     * @throws Exception
     */
    public static void dealDocx(String path,String file) throws Exception {
        File f = new File(path+file);

        //读入文件
        InputStream in = new FileInputStream(f);
        XWPFDocument document = new XWPFDocument(in);

        //图片处理，图片存储路径根据文件名称单独存储，防止覆盖
        File imageFolderFile = new File(path+_HTML_DIR+_IMG_DIR+file+"/");
        XHTMLOptions options = XHTMLOptions.create().URIResolver(
                new FileURIResolver(imageFolderFile));
        options.setExtractor(new FileImageExtractor(imageFolderFile));

        //输出到HTML，路径为 当前docx文件路径+html+文件名称.html
        OutputStream out = new FileOutputStream(new File(
                path+_HTML_DIR+file+".html"));
        XHTMLConverter.getInstance().convert(document, out, options);
    }

    /**
     * 处理doc文件
     * @param path 文件路径
     * @param file 文件名称
     * @throws Exception
     */
    private static void dealDoc(String path,String file) throws Exception{

            //读入doc文件
            InputStream input = new FileInputStream(path + file);
            HWPFDocument wordDocument = new HWPFDocument(input);

            //图片处理，图片存储路径根据文件名称单独存储，防止覆盖
            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) {
                    return _IMG_DIR + file + "/" + suggestedName;
                }
            });
            wordToHtmlConverter.processDocument(wordDocument);
            List pics = wordDocument.getPicturesTable().getAllPictures();
            if (pics != null) {
                for (int i = 0; i < pics.size(); i++) {
                    Picture pic = (Picture) pics.get(i);
                    try {
                        pic.writeImageContent(new FileOutputStream(path + _HTML_DIR + _IMG_DIR + file + "/"
                                + pic.suggestFullFileName()));
                    } catch (FileNotFoundException e) {
                        e.printStackTrace();
                    }
                }
            }

            //输出到html
            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());
            FileUtils.writeStringToFile(new File(path + _HTML_DIR + file + ".html"), content, "utf-8");
    }

    public static FileInputStream dealWord(String path,String file) throws Exception{

        File f = new File(path+file);
        if (!f.exists()) { //如果文件不存在
            throw new Exception();
        } else {
            String outPutFile = path+_HTML_DIR+file+".html"; //输出html的路径
            File mFile = new File(outPutFile);
            if (mFile.exists()) { //优先本地文件读取，如果已经找到这个文件，直接返回
                return new FileInputStream(outPutFile);
            } else {

                //穿件一些必要目录
                mFile = new File(path + _HTML_DIR + _IMG_DIR + file + "/");
                if (!mFile.exists()) {
                    mFile.mkdirs();
                }

                //开始处理
                if (file != null) {
                    if (file.toLowerCase().endsWith("doc")) {
                        dealDoc(path, file);
                    } else if (file.toLowerCase().endsWith("docx")) {
                        dealDocx(path, file);
                    }
                    return new FileInputStream(outPutFile);
                }

                return null;
            }
        }
    }

    public static void main(String args[]) {
        try {
            dealWord("/home/nemo/","t.doc");
        } catch (Exception e) {
            e.printStackTrace();
        }
    }
}