java实现word文件转html文件

最近在项目开发中用户提出要在电脑上没有装office时在浏览器中打开word文件，最后确定的逻辑：用户选择想要查看的文件，页面js判断文件是否为word。不是执行下载，是后端根据word文件后缀访问对应转换方法。文件已存在对应html文件直接返回html文件地址，不存在先生成对应html文件再返回地址。js直接通过open()打开新的页签，展示word文件内容。新人一枚，如果代码中存在错误或有更好的实现万望指正！

相关jar包

代码

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.outputstream;

import javax.xml.parsers.documentbuilderfactory;
import javax.xml.parsers.parserconfigurationexception;
import javax.xml.transform.outputkeys;
import javax.xml.transform.transformer;
import javax.xml.transform.transformerexception;
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.picturesmanager;
import org.apache.poi.hwpf.converter.wordtohtmlconverter;
import org.apache.poi.hwpf.usermodel.picturetype;
import org.apache.poi.xwpf.converter.core.basicuriresolver;
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;

/**
 * word 转换成html 2017-2-27 
 */
public class wordtohtml {
  
  
  /**
   * 将word2003转换为html文件 2017-2-27 
   * @param wordpath word文件路径
   * @param wordname word文件名称无后缀
   * @param suffix  word文件后缀
   * @throws ioexception
   * @throws transformerexception
   * @throws parserconfigurationexception
   */
  public string word2003tohtml(string wordpath,string wordname,string suffix) throws ioexception, transformerexception, parserconfigurationexception {
    string htmlpath = wordpath + file.separator + wordname + "_show" + file.separator;
    string htmlname = wordname + ".html";
    final string imagepath = htmlpath + "image" + file.separator;
    
    //判断html文件是否存在
    file htmlfile = new file(htmlpath + htmlname);
    if(htmlfile.exists()){ 
      return htmlfile.getabsolutepath();
    }
    
    //原word文档
    final string file = wordpath + file.separator + wordname + suffix;
    inputstream input = new fileinputstream(new file(file));
    
    hwpfdocument worddocument = new hwpfdocument(input);
    wordtohtmlconverter wordtohtmlconverter = new wordtohtmlconverter(documentbuilderfactory.newinstance().newdocumentbuilder().newdocument());
    //设置图片存放的位置
    wordtohtmlconverter.setpicturesmanager(new picturesmanager() {
      public string savepicture(byte[] content, picturetype picturetype, string suggestedname, float widthinches, float heightinches) {
        file imgpath = new file(imagepath);
        if(!imgpath.exists()){//图片目录不存在则创建
          imgpath.mkdirs();
        }
        file file = new file(imagepath + suggestedname);
        try {
          outputstream os = new fileoutputstream(file);
          os.write(content);
          os.close();
        } catch (filenotfoundexception e) {
          e.printstacktrace();
        } catch (ioexception e) {
          e.printstacktrace();
        }
        //图片在html文件上的路径 相对路径
        return "image/" + suggestedname;
      }
    });
    
    //解析word文档
    wordtohtmlconverter.processdocument(worddocument);
    document htmldocument = wordtohtmlconverter.getdocument();
    
    //生成html文件上级文件夹
    file folder = new file(htmlpath);
    if(!folder.exists()){ 
      folder.mkdirs(); 
    }
    
    //生成html文件地址
    outputstream outstream = new fileoutputstream(htmlfile);

    domsource domsource = new domsource(htmldocument);
    streamresult streamresult = new streamresult(outstream);

    transformerfactory factory = transformerfactory.newinstance();
    transformer serializer = factory.newtransformer();
    serializer.setoutputproperty(outputkeys.encoding, "utf-8");
    serializer.setoutputproperty(outputkeys.indent, "yes");
    serializer.setoutputproperty(outputkeys.method, "html");
    
    serializer.transform(domsource, streamresult);

    outstream.close();
    
    return htmlfile.getabsolutepath();
  }
  
  /**
   * 2007版本word转换成html 2017-2-27
   * @param wordpath word文件路径
   * @param wordname word文件名称无后缀
   * @param suffix  word文件后缀
   * @return
   * @throws ioexception
   */
  public string word2007tohtml(string wordpath,string wordname,string suffix) throws ioexception {
    string htmlpath = wordpath + file.separator + wordname + "_show" + file.separator;
    string htmlname = wordname + ".html";
    string imagepath = htmlpath + "image" + file.separator;
    
    //判断html文件是否存在
    file htmlfile = new file(htmlpath + htmlname);
    if(htmlfile.exists()){ 
      return htmlfile.getabsolutepath();
    }
        
    //word文件
    file wordfile = new file(wordpath + file.separator + wordname + suffix); 
    
    // 1) 加载word文档生成 xwpfdocument对象 
    inputstream in = new fileinputstream(wordfile); 
    xwpfdocument document = new xwpfdocument(in); 

    // 2) 解析 xhtml配置 (这里设置iuriresolver来设置图片存放的目录) 
    file imgfolder = new file(imagepath);
    xhtmloptions options = xhtmloptions.create();
    options.setextractor(new fileimageextractor(imgfolder));
    //html中图片的路径 相对路径 
    options.uriresolver(new basicuriresolver("image"));
    options.setignorestylesifunused(false); 
    options.setfragment(true); 
    
    // 3) 将 xwpfdocument转换成xhtml
    //生成html文件上级文件夹
    file folder = new file(htmlpath);
    if(!folder.exists()){ 
      folder.mkdirs(); 
    }
    outputstream out = new fileoutputstream(htmlfile); 
    xhtmlconverter.getinstance().convert(document, out, options);
    
    return htmlfile.getabsolutepath(); 
  } 
}

文件目录：

以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持。