Java (POI) 解析不同版本的word（doc、docx）

所需依赖

<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi</artifactId>
    <version>3.17</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-ooxml</artifactId>
    <version>3.17</version>
</dependency>
<dependency>
    <groupId>org.apache.poi</groupId>
    <artifactId>poi-scratchpad</artifactId>
    <version>3.17</version>
</dependency>

创建工具类

public void analysisFile(HttpServletRequest request) {
        MultipartHttpServletRequest multipartRequest = (MultipartHttpServletRequest) request;
        MultipartFile multipartFile = entity.getValue();// 获取上传文件对象
        //获取文件头判断版本
        byte[] b = new byte[4];
        multipartFile.getInputStream().read(b, 0, b.length);
        String value = bytesToHexString(b);
       //2003版本的word
       if ("d0cf11e0".equals(value )) {
          HWPFDocument document = new HWPFDocument(inputStream);
          String txt = document.getText().toString();
          for (String string : txt.split("\r")) {
              stringList = new ArrayList<String>();
              if (!StringUtils.isEmpty(string) || "\\n".equals(string)) {
                stringList.add(string.split(",")[0]);
                stringList.add(string.split(",")[1]);
                list.add(stringList);
              }
         }
      } else {
         XWPFDocument doc = new XWPFDocument(inputStream);
         XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
         //获取文件内容
         for (String string : extractor.getText().split("\\n")) {
              stringList = new ArrayList<String>();
              if (!StringUtils.isEmpty(string) || "\\n".equals(string)) {
                   stringList.add(string.split(",")[0]);
                   stringList.add(string.split(",")[1]);
                   list.add(stringList);
              }
        }
    } 		
}

因为2003版本的word需要用不同的类去解析，所以使用头部信息来判断word是什么版本