XML文件解析的四种方式

XML文件解析有四种方式:SAX、DOM、JDOM和DOM4J。

XML文件

<?xml version="1.0" encoding="UTF-8" ?>
<people>
   <person personid="E01">
      <name>Tony Blair</name>
      <address>10 Downing Street,London,UK</address>
      <tel>(061) 98765</tel>
      <fax>(061) 98765</fax>
      <email>blair@enerywhere.com</email>
   </person>
   <person personid="E02">
      <name>Bill Clinton</name>
      <address>White House,USA</address>
      <tel>(001) 6400 98765</tel>
      <fax>(001) 6400 98765</fax>
      <email>bill@everywhere.com</email>
   </person>
</people>

Person类

public class Person {
    private String personid;
    private String name;
    private String address;
    private String tel;
    private String fax;
    private String email;

    public Person() {
    }

    public Person(String personid, String name, String address, String tel, String fax, String email) {
        this.personid = personid;
        this.name = name;
        this.address = address;
        this.tel = tel;
        this.fax = fax;
        this.email = email;
    }

    @Override
    public String toString() {
        return "Person{" +
                "personid='" + personid + '\'' +
                ", name='" + name + '\'' +
                ", address='" + address + '\'' +
                ", tel='" + tel + '\'' +
                ", fax='" + fax + '\'' +
                ", email='" + email + '\'' +
                '}';
    }

    public String getPersonid() {
        return personid;
    }

    public void setPersonid(String personid) {
        this.personid = personid;
    }

    public String getName() {
        return name;
    }

    public void setName(String name) {
        this.name = name;
    }

    public String getAddress() {
        return address;
    }

    public void setAddress(String address) {
        this.address = address;
    }

    public String getTel() {
        return tel;
    }

    public void setTel(String tel) {
        this.tel = tel;
    }

    public String getFax() {
        return fax;
    }

    public void setFax(String fax) {
        this.fax = fax;
    }

    public String getEmail() {
        return email;
    }

    public void setEmail(String email) {
        this.email = email;
    }
}

1.SAX方式:

编写数据处理器

public class PersonHandler extends DefaultHandler {
    private String tag; //用于记录当前正在解析的标签
    private Person person;
    private List<Person> ps = new ArrayList<>();

    public List<Person> getPersons() {
        return ps;
    }

    @Override
    public void startDocument() throws SAXException {
        super.startDocument();
        System.out.println("解析开始");
    }

    @Override
    public void endDocument() throws SAXException {
        super.endDocument();
        System.out.println("解析结束");
    }

    @Override
    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
        super.startElement(uri, localName, qName, attributes);
        if ("person".equals(qName)) {
            person = new Person();
            String personid = attributes.getValue("personid");
            person.setPersonid(personid);
        }
        tag = qName;
    }

    @Override
    public void endElement(String uri, String localName, String qName) throws SAXException {
        super.endElement(uri, localName, qName);
        if ("person".equals(qName)) {
            ps.add(person);
        }
        tag = null;
    }

    @Override
    public void characters(char[] ch, int start, int length) throws SAXException {
        super.characters(ch, start, length);
        if (tag != null) {
            if ("name".equals(tag)) {
                person.setName(new String(ch, start, length));
            } else if ("address".equals(tag)) {
                person.setAddress(new String(ch, start, length));
            } else if ("tel".equals(tag)) {
                person.setTel(new String(ch, start, length));
            } else if ("fax".equals(tag)) {
                person.setFax(new String(ch, start, length));
            } else if ("email".equals(tag)) {
                person.setEmail(new String(ch, start, length));
            }
        }
    }
}

执行最后SAX解析过程

/**
 * SAX解析的特点:
 * 1.基于事件驱动
 * 2.顺序读取,速度快
 * 3.不能任意读取节点(灵活性差)
 * 4.解析时占用的内存少
 * 5.SAX更适应于在性能要求更高的设备上使用(Android开发中)
 */
public class XMLDemo {
    @Test
    public void saxParseXML(){
        try {
            //创建一个SAX解析器工厂对象
            SAXParserFactory spf = SAXParserFactory.newInstance();
            //通过SAX工厂解析器对象创建一个SAX解析器
            SAXParser saxParser = spf.newSAXParser();
            //创建一个数据处理器(需要我们自己编写)
            PersonHandler ph = new PersonHandler();
            //开始解析
            InputStream resourceAsStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("com/clayfan/xml/person.xml");
            saxParser.parse(resourceAsStream,ph);
            List<Person> persons = ph.getPersons();
            for (Person person : persons) {
                System.out.println(person);
            }
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果

解析开始
解析结束
Person{personid='E01', name='Tony Blair', address='10 Downing Street,London,UK', tel='(061) 98765', fax='(061) 98765', email='blair@enerywhere.com'}
Person{personid='E02', name='Bill Clinton', address='White House,USA', tel='(001) 6400 98765', fax='(001) 6400 98765', email='bill@everywhere.com'}

2. DOM方式

/**
 * DOM解析XML
 * 1.基于树型结构,通过解析器一次性把文档加载到内存中,所以会比较占用内存,可以随机访问
 * 更加灵活,更适合在WEB开发中使用
 * @throws ParserConfigurationException
 * @throws IOException
 * @throws SAXException
 */
@Test
public void domParseXML() throws ParserConfigurationException, IOException, SAXException {
    //创建一个DOM解析器工厂对象
    DocumentBuilderFactory documentBuilderFactory = DocumentBuilderFactory.newInstance();
    //通过工厂对象创建解析器对象
    DocumentBuilder documentBuilder = documentBuilderFactory.newDocumentBuilder();
    //解析文档
    InputStream resourceAsStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("com/clayfan/xml/person.xml");
    Document document = documentBuilder.parse(resourceAsStream);
    //从内存中读取数据
    NodeList persons = document.getElementsByTagName("person");
    Person p = null;
    ArrayList<Person> people = new ArrayList<>();
    for (int i = 0; i < persons.getLength(); i++) {
        Node item = persons.item(i);
        //获取节点的属性值
        String personid = item.getAttributes().getNamedItem("personid").getNodeName();
        p = new Person();
        p.setPersonid(personid);
        //获取当前节点的所有子节点
        NodeList childNodes = item.getChildNodes();
        for (int j = 0; j < childNodes.getLength(); j++) {
            Node item1 = childNodes.item(j);
            String nodeName = item1.getNodeName();
            if ("name".equals(nodeName)) {
                p.setName(item1.getFirstChild().getNodeValue());
            }else if("address".equals(nodeName)){
                p.setAddress(item1.getFirstChild().getNodeValue());
            }else if("tel".equals(nodeName)){
                p.setTel(item1.getFirstChild().getNodeValue());
            }else if("fax".equals(nodeName)){
                p.setFax(item1.getFirstChild().getNodeValue());
            }else if("email".equals(nodeName)){
                p.setEmail(item1.getFirstChild().getNodeValue());
            }
        }
        people.add(p);
    }
    for(Person pp:people){
        System.out.println(pp);
    }
}

3.JDOM方式:

下载地址:http://www.jdom.org/downloads/index.html

/**
 * JDOM解析XML
 * 1.与DOM类似基于树型结构
 * 2.与DOM的区别
 *  第三方开源的组件
 *  实现使用JAVA的Collection接口
 *  效率比DOM更快
 * @throws JDOMException
 * @throws IOException
 */
@Test
public void jdomParseXML() throws JDOMException, IOException {
    SAXBuilder saxBuilder = new SAXBuilder();
    InputStream resourceAsStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("com/clayfan/xml/person.xml");
    org.jdom2.Document build = saxBuilder.build(resourceAsStream);
    Element rootElement = build.getRootElement();
    List<Person> list = new ArrayList<>();
    Person person = null;
    List<Element> children = rootElement.getChildren();
    for(Element element:children){
        person= new Person();
        String personid = element.getAttributeValue("personid");
        person.setPersonid(personid);
        List<Element> children1 = element.getChildren();
        for(Element e:children1){
            String tag = e.getName();
            if ("name".equals(tag)) {
                person.setName(e.getText());
            }else if("address".equals(tag)){
                person.setAddress(e.getText());
            }else if("tel".equals(tag)){
                person.setTel(e.getText());
            }else if("fax".equals(tag)){
                person.setFax(e.getText());
            }else if("email".equals(tag)){
                person.setEmail(e.getText());
            }
        }
        list.add(person);
    }
    for(Person pp:list){
        System.out.println(pp);
    }
}

4.DOM4J方式:

下载地址:https://dom4j.github.io/

 

/**
 * DOM4J解析XML
 * 基于树型结构,第三方组件
 * 解析速度快,效率更高,使用的JAVA中的迭代器实现数据读取,在WEB框架中使用较多(Hibernate)
 * 
 * @throws DocumentException
 */
@Test
public void dom4jParseXML() throws DocumentException {
    SAXReader reader = new SAXReader();
    InputStream resourceAsStream = Thread.currentThread().getContextClassLoader().getResourceAsStream("com/clayfan/xml/person.xml");
    org.dom4j.Document read = reader.read(resourceAsStream);
    org.dom4j.Element rootElement = read.getRootElement();
    Iterator<org.dom4j.Element> iterator = rootElement.elementIterator();
    ArrayList<Person> persons = new ArrayList<>();
    Person person = null;
    while(iterator.hasNext()){
        person = new Person();
        org.dom4j.Element element = iterator.next();
        person.setPersonid(element.attributeValue("personid"));
        Iterator<org.dom4j.Element> iterator1 = element.elementIterator();
        while(iterator1.hasNext()){
            org.dom4j.Element next = iterator1.next();
            String tag = next.getName();
            if ("name".equals(tag)) {
                person.setName(next.getText());
            }else if("address".equals(tag)){
                person.setAddress(next.getText());
            }else if("tel".equals(tag)){
                person.setTel(next.getText());
            }else if("fax".equals(tag)){
                person.setFax(next.getText());
            }else if("email".equals(tag)){
                person.setEmail(next.getText());
            }
        }
        persons.add(person);
    }
    for(Person pp:persons){
        System.out.println(pp);
    }
}