一、环境准备
1.jdk:1.8
2.maven:3.6
3.springboot:2.2.2
二、maven主要依赖
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi</artifactId>
<version>4.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-scratchpad</artifactId>
<version>4.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml</artifactId>
<version>4.1.0</version>
</dependency>
<dependency>
<groupId>fr.opensagres.xdocreport</groupId>
<artifactId>xdocreport</artifactId>
<version>2.0.2</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>poi-ooxml-schemas</artifactId>
<version>4.1.0</version>
</dependency>
<dependency>
<groupId>org.apache.poi</groupId>
<artifactId>ooxml-schemas</artifactId>
<version>1.4</version>
</dependency>
三、具体实现
1.docToHtml
@RequestMapping("/wordToHtml")
public void wordToHtml(HttpServletResponse response){
final String path = "C:\\usr\\local\\";
final String file = "5页.doc";
try{
InputStream input = new FileInputStream(path + file);
docToHtml(input, response);
}catch (Exception e){
e.printStackTrace();
}
}
public void docToHtml(InputStream input, HttpServletResponse response) throws Exception{
HWPFDocumentCore wordDocument = WordToHtmlUtils.loadDoc(input);
WordToHtmlConverter wordToHtmlConverter = new ImageConverter(
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 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();
// 清空response
response.reset();
OutputStream toClient = new BufferedOutputStream(response.getOutputStream());
response.setContentType("text/html");
response.setCharacterEncoding("UTF-8");
toClient.write(outStream.toByteArray());
toClient.flush();
toClient.close();
}
//图片处理
public class ImageConverter extends WordToHtmlConverter{
public ImageConverter(Document document) {
super(document);
}
@Override
protected void processImageWithoutPicturesManager(Element currentBlock, boolean inlined, Picture picture){
Element imgNode = currentBlock.getOwnerDocument().createElement("img");
StringBuffer sb = new StringBuffer();
sb.append(Base64.getMimeEncoder().encodeToString(picture.getRawContent()));
sb.insert(0, "data:" + picture.getMimeType() + ";base64,");
imgNode.setAttribute("src", sb.toString());
currentBlock.appendChild(imgNode);
}
}
预览效果:

2.docxToHtml
@RequestMapping("/wordToHtml")
public void wordToHtml(HttpServletResponse response){
final String path = "C:\\usr\\local\\";
final String file = "3.docx";
try{
InputStream input = new FileInputStream(path + file);
docxToHtml(input, response);
}catch (Exception e){
e.printStackTrace();
}
}
public void docxToHtml(InputStream inputStream, HttpServletResponse response) throws IOException {
XWPFDocument docxDocument = new XWPFDocument(inputStream);
XHTMLOptions options = XHTMLOptions.create();
//图片转base64
options.setImageManager(new Base64EmbedImgManager());
// 转换htm1
ByteArrayOutputStream htmlStream = new ByteArrayOutputStream();
XHTMLConverter.getInstance().convert(docxDocument, htmlStream, options);
// 清空response
response.reset();
OutputStream toClient = new BufferedOutputStream(response.getOutputStream());
response.setContentType("text/html");
response.setCharacterEncoding("UTF-8");
toClient.write(htmlStream.toByteArray());
toClient.flush();
toClient.close();
}
预览效果:

四、总结
1.主要几个maven包的依赖版本需要一致
2.文档需要标准的word文档,举个例子,从boss直聘上下载下来的简历不能预览,因为里面内容实际是html格式,会出现异常:
Docment is really HTML File,需要把文件另存为标准word格式
3.不能直接修改文件后缀名预览,虽然office能打开,但是不是标准word格式,需要另存为你想要的格式(doc,docx),否则会出现异常java.lang.IllegalArgumentException: The document is really a OOXML file
4.尝试过spire.doc,用的是免费版,文档超过三页不能预览,这一方面官网给出了解释,最终选定poi这个方案
4083



被折叠的 条评论
为什么被折叠?



