poi3.17 html转word,poi 3.17 word 转 html（带图片格式）

项目中需要用到word文档在线预览的功能，之前在网上找了一些demo，但都poi版本都是 3.14以下的，而项目中已经集成了poi3.17，且其他模块中有用到3.17的包，所以不得不重新研究。目前可以将word转换为html，并且支持图片格式，表格样式还没有调完，调好了再更新上来。现在整理的工具类demo分享一下，希望对初学者学习交流有所帮助，写的不好的地方欢迎留言指正，哪位高人有更好的想法欢迎交流。

直接上代码吧

import java.io.ByteArrayInputStream;

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 java.util.HashMap;

import java.util.Map;

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.commons.lang3.StringUtils;

import org.apache.poi.hwpf.HWPFDocument;

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

import org.apache.poi.xwpf.usermodel.XWPFDocument;

import org.slf4j.Logger;

import org.slf4j.LoggerFactory;

import org.w3c.dom.Document;

import fr.opensagres.poi.xwpf.converter.core.BasicURIResolver;

import fr.opensagres.poi.xwpf.converter.core.FileImageExtractor;

import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLConverter;

import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLOptions;

public class POIUtils {

private static final Logger log = LoggerFactory.getLogger(POIUtils.class.getName());

/**

* docx to html

*

* @param in 输入流

* @return

* @throws IOException

*/

public static InputStream docxToHtml(InputStream in, String filePath) {

XWPFDocument document = null;

try {

document = new XWPFDocument(in);

XHTMLOptions options = XHTMLOptions.create();

options.setIgnoreStylesIfUnused(false);

options.setFragment(true);

filePath = filePath+"image"+File.separator;

options.setExtractor(new FileImageExtractor(new File(filePath)));

options.URIResolver(new BasicURIResolver("image"));

ByteArrayOutputStream out = new ByteArrayOutputStream();

XHTMLConverter.getInstance().convert(document, out, options);

return new ByteArrayInputStream(out.toByteArray());

} catch (IOException e) {

log.error(e.getMessage(), e);

}

return in;

}

/**

* doc to html

*

* @param in

* @return

* @throws Exception

*/

public static InputStream docToHtml(InputStream in) {

try {

HWPFDocument wordDocument = new HWPFDocument(in);

WordToHtmlConverter wordToHtmlConverter = new WordToHtmlConverter(

DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument());

wordToHtmlConverter.processDocument(wordDocument);

Document htmlDocument = wordToHtmlConverter.getDocument();

ByteArrayOutputStream outStream = new ByteArrayOutputStream();

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 new ByteArrayInputStream(outStream.toByteArray());

} catch (Exception e) {

log.error(e.getMessage(), e);

}

return in;

}

public static InputStream docToHtml(Maprequest, InputStream in) {

String fileName = (String) request.get("name");

if (StringUtils.isEmpty(fileName)) {

return in;

}

String extensionName = fileName.substring(fileName.lastIndexOf(".") + 1, fileName.length());

String prevName = fileName.substring(0, fileName.lastIndexOf("."));

if ("html".equalsIgnoreCase(extensionName)) {

return in;

}

if (extensionName.equalsIgnoreCase("doc")) {

request.put("name", prevName + ".html");

return docToHtml(in);

}

if (extensionName.equalsIgnoreCase("docx")) {

request.put("name", prevName + ".html");

return docxToHtml(in, (String)request.get("filePath"));

}

return in;

}

public static void inputStreamToFile(InputStream inputStream, String newPath) {

//InputStream inputStream = null;

OutputStream outputStream = null;

try {

/**

String userDir = System.getProperty("user.dir");

String path = userDir + "/bin/file.xml";

inputStream = new FileInputStream(path);

*/

//String newPath = userDir + "/bin/file-new.xml";

File file = new File(newPath);

outputStream = new FileOutputStream(file);

int bytesWritten = 0;

int byteCount = 0;

byte[] bytes = new byte[1024];

while ((byteCount = inputStream.read(bytes)) != -1) {

outputStream.write(bytes, bytesWritten, byteCount);

//bytesWritten += byteCount;

}

System.out.println("Done!");

} catch (IOException e) {

e.printStackTrace();

} finally {

if (inputStream != null) {

try {

inputStream.close();

} catch (IOException e) {

e.printStackTrace();

}

}

if (outputStream != null) {

try {

outputStream.close();

} catch (IOException e) {

e.printStackTrace();

}

}

}

}

public static void main(String[] args) {

try {

String fileName = "展示型网站开发培训方案.docx";

String newfileName = "展示型网站开发培训方案.html";

String filePath = "D:\\Temp\\";

Maprequest = new HashMap();

request.put("name", fileName);

request.put("filePath", filePath);

InputStream in = new FileInputStream(filePath + fileName);// 读取文件的数据。

InputStream result = docToHtml(request, in);

inputStreamToFile(result, filePath+newfileName);

} catch (FileNotFoundException e) {

e.printStackTrace();

}

}

}

依懒的maven库

org.apache.poi

poi

3.17

org.apache.poi

poi-scratchpad

3.17

org.apache.poi

poi-ooxml

3.17

fr.opensagres.xdocreport

xdocreport

2.0.1

org.apache.poi

poi-ooxml-schemas

3.17

org.apache.poi

ooxml-schemas

1.4

org.apache.commons

commons-lang3

3.7

org.slf4j

slf4j-api

1.8.0-beta2