POI实现word文档转html文件

[b]POI word文件转html[/b]

package com.feiruo.officeConvert;

import java.io.BufferedWriter;
import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.util.List;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.TransformerException;

import org.apache.poi.hwpf.usermodel.Picture;

public abstract class OfficeConvert {

// 图片的存放地址
private String imgPath = null;
// 文件存放的地址
private String parentPath = null;
// 文件内容
private String fileContent = null;
private String encode = "UTF-8";

/**
* 将指定的doc文档进行格式转换
*
* @param docPath
*            *.doc文档地址
*
* @throws FileNotFoundException
* @throws IOException
* @throws ParserConfigurationException
* @throws TransformerException
*/
public abstract void convert(String docPath) throws FileNotFoundException,
IOException, ParserConfigurationException, TransformerException;

/**
* 将文件内容写入到磁盘
*
* @param filepath
*            保存转换文件的地址
*/
public void writeFile(String filepath) {
FileOutputStream fos = null;
BufferedWriter bw = null;
File f=new File(this.parentPath);

if(!f.exists()){
f.mkdirs();
}
try {
File file = new File(filepath);
fos = new FileOutputStream(file);
bw = new BufferedWriter(new OutputStreamWriter(fos, encode));
bw.write(fileContent);
} 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 String checkSetPath(String path){
path=path.trim();
if(path.lastIndexOf("/")<path.length()-1) path+="/";
if(path.indexOf("\"")>0)path=path.replaceAll("\"", "");
if(path.indexOf(">")>0)path=path.replaceAll(">", ">");
if(path.indexOf("<")>0)path=path.replaceAll("<", "<");
//TODO if(path.indexOf("*")>0)path=path.replaceAll("/*", "");
return path;
}
public String getEncode() {
return encode;
}

public void setEncode(String encode) {
this.encode = encode;
}

/**
* 获取图片存放地址
*
* @return <strong>java.lang.String</strong>
*/
public String getImgPath() {
return imgPath;
}

/**
* 设置图片的存放地址文件夹路径
*
* @param imgPath
*            设置图片的存放文件夹名称
*/
public void setImgPath(String imgPath) {
this.imgPath = checkSetPath(imgPath);
}

/**
* 获取存放文件的目录地址
*
* @return <strong>java.lang.String</strong>
*/
public String getParentPath() {
return parentPath;
}

/**
* 设置文件存放的路径
*
* @param parentPath
*            文件地址
*/
public void setParentPath(String parentPath) {
this.parentPath = checkSetPath(parentPath);
}

/**
* 获取文件内容
*
* @return <strong>java.lang.String</strong>
*/
public String getFileContent() {
return fileContent;
}
public void setFileContent(String content){
this.fileContent=content;
}
}

package com.feiruo.officeConvert;

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.util.List;

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.Picture;
import org.apache.poi.hwpf.usermodel.PictureType;
import org.w3c.dom.Document;

/**
* 将*.doc文档转换为*.html文件格式
*
* @author Jdk.feiruo.
* @since JDK 1.7 POI 3.8
* @version 1.0
*/
public class DocToHtml extends OfficeConvert implements IOfficeConvert {
private List<Picture> pics = null;

/**
* @param parentPath
*            html文件存放地址
* @param imageppth
*            html图片存放地址
* @param encoding
*            设置html的编码格式
*/
public DocToHtml(String parentPath, String imageppth, String encoding) {
setParentPath(checkSetPath(parentPath));
setImgPath(checkSetPath(imageppth));
this.setEncode(encoding);
}

public DocToHtml() {

}

/**
* 将*doc文档转为*html文件
*
* @param docPath
*            *doc文档的所在地址
*
* @throws FileNotFoundException
* @throws IOException
* @throws ParserConfigurationException
* @throws TransformerException
*/
public void convert(String docPath) throws FileNotFoundException,
IOException, ParserConfigurationException, TransformerException {
HWPFDocument wordDocument = new HWPFDocument(new FileInputStream(
docPath));
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 suggestedName;
}
});
wordToHtmlConverter.processDocument(wordDocument);
pics = wordDocument.getPicturesTable().getAllPictures();

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, this.getEncode());
serializer.setOutputProperty(OutputKeys.INDENT, "yes");
serializer.setOutputProperty(OutputKeys.METHOD, "html");
serializer.transform(domSource, streamResult);

out.close();

String htmlContent = new String(out.toByteArray());
if(htmlContent.indexOf("<img src=\"") > 0){
htmlContent=htmlContent.replaceAll("<img src=\"", "<img src=\"" + getImgPath());
}
setFileContent(htmlContent);
}

@Override
public void writeWithName(String fileName) {
// 先保存文档中的图片
if (pics != null) {
File imgfile = new File(this.getParentPath() + this.getImgPath());
// 如果当前文件夹不存在，则创建新文件夹
if (!imgfile.exists())
imgfile.mkdirs();
for (int i = 0; i < pics.size(); i++) {
Picture pic = (Picture) pics.get(i);
try {
pic.writeImageContent(new FileOutputStream(imgfile + "//"
+ pic.suggestFullFileName()));
} catch (IOException e) {
e.printStackTrace();
}
}
}
// 保存html源码文件
this.writeFile(getParentPath()+fileName+".html");
}
}

package com.feiruo.Test;

import java.io.FileNotFoundException;
import java.io.IOException;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.TransformerException;

import com.yinhai.officeConvert.DocToHtml;

public class Test{
public static void main(String[] args) {
Test t=new Test();
}
public Test(){
DocToHtml dth=new DocToHtml("C://test", "f", "UTF-8");
try {
dth.convert("D://test//test.doc");
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (TransformerException e) {
e.printStackTrace();
}
dth.writeWithName("feiruo");
}
}

package com.feiruo.officeConvert;

public interface IOfficeConvert {
/**
* 将文件写入到磁盘
* @param fileName 要写入文件的名称
*/
public void writeWithName(String fileName);
}