word文件与html文件互转

一、使用poi完成docx转html

1. 引入maven依赖

   <dependency>
               <groupId>fr.opensagres.xdocreport</groupId>
               <artifactId>fr.opensagres.xdocreport.document</artifactId>
               <version>2.0.1</version>
           </dependency>
           <dependency>
               <groupId>fr.opensagres.xdocreport</groupId>
               <artifactId>fr.opensagres.poi.xwpf.converter.xhtml</artifactId>
               <version>2.0.1</version>
           </dependency>
   

   还有poi、poi-ooxml、poi-scratchpad、poi-ooxml-schemas这些，一定要避免jar包冲突。在我的项目中有用到elasticsearch(org.elasticsearch)，它其中就已经囊括了这些jar包，所以我再在pom文件中加入依赖后一直因为冲突报错。

   

2. 代码部分

   import org.apache.poi.xwpf.usermodel.XWPFDocument;
   import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLOptions;
   import fr.opensagres.poi.xwpf.converter.xhtml.XHTMLConverter;
   
   public static void docx2Html(String fileName, String outPutFile) throws TransformerException, IOException, ParserConfigurationException, XmlException {
           String fileOutName = outPutFile;
           XWPFDocument document = new XWPFDocument(new FileInputStream(fileName));
           XHTMLOptions options = XHTMLOptions.create().indent(4);
           // 导出图片
           File imageFolder = new File(tempPath);
           options.setExtractor(new FileImageExtractor(imageFolder));
           // URI resolver
           options.URIResolver(new FileURIResolver(imageFolder));
           File outFile = new File(fileOutName);
           outFile.getParentFile().mkdirs();
           OutputStream out = new FileOutputStream(outFile);
           XHTMLConverter.getInstance().convert(document, out, options);
       }
   public static void main(String argv[]) throws Exception {
       docx2Html("E:\\aaaaaa.docx", "E:\\aaaaaa.html");
   }
   

3. 注意

   我是通过hutool中的类Word07Writer生成的docx文件，会报styles no found和与页眉页脚nullpoint相关的错误（通过打断点进原始类发现）。最后是通过以下方式解决的。

   //设置样式
   writer.getDoc().createStyles();
   //设置页眉页脚
   createDefaultHeader(writer.getDoc(), "这是页眉内容");
   
   private static void createDefaultHeader(final XWPFDocument docx, final String text){
           CTP ctp = CTP.Factory.newInstance();
           XWPFParagraph paragraph = new XWPFParagraph(ctp, docx);
           ctp.addNewR().addNewT().setStringValue(text);
           ctp.addNewR().addNewT().setSpace(SpaceAttribute.Space.PRESERVE);
           CTSectPr sectPr = docx.getDocument().getBody().isSetSectPr() ? docx.getDocument().getBody().getSectPr() : docx.getDocument().getBody().addNewSectPr();
           XWPFHeaderFooterPolicy policy = new XWPFHeaderFooterPolicy(docx, sectPr);
           XWPFHeader header = policy.createHeader(STHdrFtr.DEFAULT, new XWPFParagraph[] { paragraph });
           header.setXWPFDocument(docx);
       }
   

二、通过docx4j将html转docx

1. 引入依赖

   <dependency>
               <groupId>org.docx4j</groupId>
               <artifactId>docx4j-ImportXHTML</artifactId>
               <version>3.0.0</version>
   </dependency>
   

2. 代码部分

   public static void main(String argv[]) throws Exception {
   //        String xhtml =
   //                "<table border=\"1\" cellpadding=\"1\" cellspacing=\"1\" style=\"width:100%;\"><tbody><tr><td>test</td><td>test</td></tr><tr><td>test</td><td>test</td></tr><tr><td>test</td><td>test</td></tr></tbody></table>";
           Document document = Jsoup.parse(new File("E:\\report.html"), "UTF-8");
       //html body体    
       String xhtml =document.body().outerHtml();
           // To docx, with content controls
           WordprocessingMLPackage wordMLPackage = WordprocessingMLPackage.createPackage();
   
           XHTMLImporterImpl XHTMLImporter = new XHTMLImporterImpl(wordMLPackage);
           //XHTMLImporter.setDivHandler(new DivToSdt());
   
           wordMLPackage.getMainDocumentPart().getContent().addAll(
                   XHTMLImporter.convert(xhtml, null));
   
           System.out.println(XmlUtils.marshaltoString(wordMLPackage
                   .getMainDocumentPart().getJaxbElement(), true, true));
   
   		wordMLPackage.save(new java.io.File("E:\\aaaaaa.docx"));