基于POI的Word解析成HTML（base64图片）

 @PostMapping("/upload/{menuId}/{space}") 
 public ResponseResult uploadDocument(@PathVariable("menuId") String menuId, @PathVariable("space") String space, @RequestParam("file") MultipartFile file) { 
 FileProperties properties = fileService.storeFile(file); 
 Document document = new Document(); 
 String title; 
 String content; 
 String originName = properties.getFileName(); 
 try { 
 if (originName.endsWith(".doc")) { 
                title = originName.substring(0, originName.indexOf(".doc")); 
                content = fileService.docToHtml(properties); 
 } else { 
                title = originName.substring(0, originName.indexOf(".docx")); 
                content = fileService.docxToHtml(properties); 
 } 
 } catch (Exception e) { 
            e.printStackTrace(); 
 return ResponseResult.FAILED(GlobalTipMsg.DOC_UPLOAD_FAILTURE); 
 } 
        document.setTitle(title); 
        document.setContent(content); 
 return docService.addDocument(space, menuId, document); 
 } 

 <dependency> 
 <groupId>fr.opensagres.xdocreport</groupId> 
 <artifactId>xdocreport</artifactId> 
 <version>2.0.2</version> 
 </dependency> 
 <dependency> 
 <groupId>org.apache.poi</groupId> 
 <artifactId>poi</artifactId> 
 <version>4.1.2</version> 
 </dependency> 
 <dependency> 
 <groupId>org.apache.poi</groupId> 
 <artifactId>poi-ooxml</artifactId> 
 <version>4.1.2</version> 
 </dependency> 
 <dependency> 
 <groupId>org.apache.poi</groupId> 
 <artifactId>poi-scratchpad</artifactId> 
 <version>4.1.2</version> 
 </dependency> 
 <dependency> 
 <groupId>org.apache.poi</groupId> 
 <artifactId>poi-ooxml-schemas</artifactId> 
 <version>4.1.2</version> 
 </dependency> 
 <dependency> 
 <groupId>org.apache.poi</groupId> 
 <artifactId>ooxml-schemas</artifactId> 
 <version>1.4</version> 
 </dependency> 
 <dependency> 
 <groupId>org.jsoup</groupId> 
 <artifactId>jsoup</artifactId> 
 <version>1.13.1</version> 
 </dependency> 

@Service 
@Slf4j 
public class FileService { 
 private final Path fileStorageLocation; 
 @Autowired 
 public FileService(FileProperties fileProperties) { 
 this.fileStorageLocation = Paths.get(fileProperties.getUploadDir()).toAbsolutePath().normalize(); 
 try { 
 Files.createDirectories(this.fileStorageLocation); 
 } catch (Exception ex) { 
            log.error(ex.toString()); 
 } 
 } 
 public FileProperties storeFile(MultipartFile file) { 
 // Normalize file name 
 FileProperties properties = new FileProperties(); 
 String fileName = StringUtils.cleanPath(file.getOriginalFilename()); 
 try { 
 // Check if the file's name contains invalid characters 
 if (fileName.contains("..")) { 
                log.error("Sorry! Filename contains invalid path sequence " + fileName); 
 } 
 System.out.println(this.fileStorageLocation + fileName); 
 // Copy file to the target location (Replacing existing file with the same name) 
 InputStream input = file.getInputStream(); 
 Path targetLocation = this.fileStorageLocation.resolve(fileName); 
 Files.copy(input, targetLocation, StandardCopyOption.REPLACE_EXISTING); 
            properties.setFileDir(this.fileStorageLocation + "\\" + fileName); 
            properties.setUploadDir(this.fileStorageLocation.toString()); 
            properties.setFileName(fileName); 
            input.close(); 
 return properties; 
 } catch (IOException ex) { 
            log.error(ex.toString()); 
 } 
 return properties; 
 } 
 public static String docxToHtml(FileProperties properties) throws Exception { 
 FileInputStream fileInputStream = new FileInputStream(properties.getFileDir()); 
 XWPFDocument docxDocument = new XWPFDocument(fileInputStream); 
 XHTMLOptions options = XHTMLOptions.create(); 
 //图片转base64 
        options.setImageManager(new Base64EmbedImgManager()); 
 // 转换html 
 ByteArrayOutputStream htmlStream = new ByteArrayOutputStream(); 
 XHTMLConverter.getInstance().convert(docxDocument, htmlStream, options); 
 String htmlStr = htmlStream.toString(); 
        htmlStream.close(); 
        fileInputStream.close(); 
 return htmlStr; 
 } 
 public String docToHtml(FileProperties properties)throws IOException, ParserConfigurationException, TransformerException { 
 HWPFDocumentCore wordDocument = WordToHtmlUtils.loadDoc(new FileInputStream(properties.getFileDir())); 
 WordToHtmlConverter wordToHtmlConverter = new ImageConverter( 
 DocumentBuilderFactory.newInstance().newDocumentBuilder().newDocument() 
 ); 
        wordToHtmlConverter.processDocument(wordDocument); 
 Document htmlDocument = wordToHtmlConverter.getDocument(); 
 ByteArrayOutputStream out = new ByteArrayOutputStream(); 
 DOMSource domSource = new DOMSource(htmlDocument); 
 StreamResult streamResult = new StreamResult(out); 
 TransformerFactory transformerFactory = TransformerFactory.newInstance(); 
 Transformer serializer = transformerFactory.newTransformer(); 
        serializer.setOutputProperty(OutputKeys.ENCODING, "UTF-8"); 
        serializer.setOutputProperty(OutputKeys.INDENT, "yes"); 
        serializer.setOutputProperty(OutputKeys.METHOD, "html"); 
        serializer.transform(domSource, streamResult); 
        out.close(); 
 String htmlStr = new String(out.toByteArray()); 
 return htmlStr; 
 } 
}