一、XML解析

• XML解析共有4种方式,分别是DOM,SAX,DOM4J,JDOM,以下只介绍DOM和DOM4J的两种方式

二、DOM

• 新建一个xml文件stus.xml:

  <students>
    <student>
        <sid>1</sid>
        <name>AAA</name>
        <addr>AA</addr>
    </student>
    <student>
        <sid>2</sid>
        <name>BBB</name>
        <addr>BB</addr>
    </student>
    <student>
        <sid>3</sid>
        <name>CCC</name>
        <addr>CC</addr>
    </student>
    <student>
        <sid>4</sid>
        <name>DDD</name>
        <addr>DD</addr>
    </student>
  </students>
  

• 新增一个与xml匹配的pojo Student的类

  @Data
  public class Student {
      private int sid;
      private String name;
      private String addr;
  }
  

• 新增类实现对于给定的xml进行解析

  public class TestStudent {
    public List<Student> parseXml(String xmlFile){
        List<Student> list = new ArrayList<>();
        //  1.  创建DocumentBuilderFactory对象
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        try {
              //  2.  使用DocumentBuilderFactory对象的newDocumentBuilder（）方法创建一个DocumentBuilder对象
              DocumentBuilder builder = dbf.newDocumentBuilder();
              //  3.  使用DocumentBuilder的parse（file）方法来对于指定文件来进行解析，得到一个document对象
              Document document = builder.parse(xmlFile);
              //  4.  通过document对象的getElementsByTagName(tagName)来获取指定标签的节点
              NodeList nodeList = document.getElementsByTagName("student");
              Student stu = null;
              for (int i = 0; i < nodeList.getLength(); i++) {
                  stu = new Student();
                  Node node = nodeList.item(i);
                  NodeList nodes = node.getChildNodes();
                  //  遍历每个student节点中的每个sid，name，addr节点
                  for (int j = 0; j < nodes.getLength(); j++) {
                      Node item = nodes.item(j);
                      //System.out.println(item);
                      switch (item.getNodeName()){
                          case "sid":
                              String ssid = item.getTextContent();
                              int sid = ssid == null ? 0 : Integer.parseInt(ssid);
                              stu.setSid(sid);
                              break;
                          case "name":
                              String name = item.getTextContent();
                              stu.setName(name);
                              break;
                          case "addr":
                              String addr = item.getTextContent();
                              stu.setAddr(addr);
                              break;
                      }
                  }
                  list.add(stu);
              }
              //System.out.println(document);
          } catch (ParserConfigurationException e) {
              e.printStackTrace();
          } catch (SAXException e) {
              e.printStackTrace();
          } catch (IOException e) {
              e.printStackTrace();
          }
          return list;
      }
      @Test
      public void testParse(){
          System.out.println(parseXml("stus.xml"));
      }
  }
  

• 运行结果:

  [Student(sid=1, name=AAA, addr=AA), 
  Student(sid=2, name=BBB, addr=BB), 
  Student(sid=3, name=CCC, addr=CC), 
  Student(sid=4, name=DDD, addr=DD)]
  

三、DOM4J

• 在pom文件中新增一个依赖

  <dependency>
      <groupId>dom4j</groupId>
      <artifactId>dom4j</artifactId>
      <version>1.6.1</version>
  </dependency>
  

• 新增一个XML文件

  <students>
    <student>
        <sid>1</sid>
        <name>AAA</name>
        <addr>AA</addr>
    </student>
    <student>
        <sid>2</sid>
        <name>BBB</name>
        <addr>BB</addr>
    </student>
    <student>
        <sid>3</sid>
        <name>CCC</name>
        <addr>CC</addr>
    </student>
    <student>
        <sid>4</sid>
        <name>DDD</name>
        <addr>DD</addr>
    </student>
  </students>
  

• Student.java

  @Data
  public class Student {
      private int sid;
      private String name;
      private String addr;
  }
  

• TestStudentXMLDom4j.java

  public class TestStudentXMLDom4j {
      public List<Student> parseXml(String xmlFile){
          List<Student> list = new ArrayList<>();
          //  1.  创建SAXReader对象
          SAXReader reader = new SAXReader();
          try {
              //  2.  使用SAXReader对象读取给定的xml文件得到一个Document对象
              Document document = reader.read(xmlFile);
              //  3.  通过Document对象的getRootElement（）方法得到xml的跟节点元素
              Element root = document.getRootElement();
              //System.out.println(size());
              //  4.  通过root（"根元素"）顺藤摸瓜找到所有的子元素节点
              List<Element> elements = root.elements();
              Student stu = null;
              for (Element el : elements) {
                  List<Element> list2 = el.elements();
                  //System.out.println(list2);
                  stu = new Student();
                  for (Element e : list2) {
                      switch (e.getName()){
                          case "sid":
                              String ssid = e.getText();
                              int sid = ssid == null ? 0 : Integer.parseInt(ssid);
                              stu.setSid(sid);
                              break;
                          case "name":
                              String name = e.getText();
                              stu.setName(name);
                              break;
                          case "addr":
                              String addr = e.getText();
                              stu.setAddr(addr);
                              break;
                      }
                  }
                  list.add(stu);
              }
          } catch (DocumentException e) {
              e.printStackTrace();
          }
          return list;
      }
      @Test
      public void testParseXml(){
          System.out.println(parseXml("stus.xml"));
      }
  }
  

• 运行结果

  [Student(sid=1, name=AAA, addr=AA), 
  Student(sid=2, name=BBB, addr=BB), 
  Student(sid=3, name=CCC, addr=CC), 
  Student(sid=4, name=DDD, addr=DD)]