JAVA 解析XML

解析XML常见的四种方法分别是：

Dom4j、SAX、DOM、JDOM ，个人对四种方式的理解中Dom4j是比较常用性能也比较高的解析方式，如常见框架解析的XML配置文件也多为DOM4j方式。DOM方式需要对将整个XML文档调入内存生成DOM树驻留在内存中，耗费内存空间，但比较适合需要频繁更改XML文档的情况，而SAX方式不需要将XML一次性读进内存在进行解析，而是类似边读边解析，对内存要求较小。 

一、Dom4j

使用Dom4j 将List<Person>对象生成XML文件

public class DOM4jTest {public static void main(String[] args) throws Exception {List<Person> list = new ArrayList<Person>();Person person1=new Person(11, "张三1", "女", "北京", 20);Person person2=new Person(12, "张三2", "女", "上海", 21);Person person3=new Person(13, "张三3", "女", "广州", 22);Person person4=new Person(21, "李四1", "男", "北京", 20);Person person5=new Person(22, "李四2", "男", "上海", 21);Person person6=new Person(23, "李四3", "男", "广州", 22);person1.setMate(person4);//增加配偶person2.setMate(person5);//增加配偶person3.setMate(person6);//增加配偶list.add(person1);list.add(person2);list.add(person3);Element root = DocumentHelper.createElement("Persons");// 创建根节点PersonsDocument document = DocumentHelper.createDocument(root);for (Person person : list) {Element element = root.addElement("Person");//创建子节点Personelement.addAttribute("num", person.getNum()+"");//加入属性numElement name=element.addElement("name");//person创建子节点namename.setText(person.getName());Element sex=element.addElement("sex");sex.setText(person.getSex());Element age=element.addElement("age");age.setText(person.getAge()+"");Element mate=element.addElement("mate");Element num=mate.addElement("num");num.setText(person.getMate().getNum()+"");Element name_mate=mate.addElement("name");name_mate.setText(person.getMate().getName());Element sex_mate=mate.addElement("sex");sex_mate.setText(person.getMate().getSex());Element age_mate=mate.addElement("age");age_mate.setText(person.getMate().getAge()+"");} OutputFormat format = new OutputFormat("\r", true); XMLWriter xmlWriter = new XMLWriter(new OutputStreamWriter(new FileOutputStream("d:\\Persons.xml"),"UTF-8") ,format); xmlWriter.write(document); xmlWriter.close();}

结果：

使用Dom4j解析该XML 

public class DOM4jTest {public static void main(String[] args) throws Exception {SAXReader saxReader = new SAXReader();Document document = saxReader.read(new File("D:\\Persons.xml"));Element root = document.getRootElement(); // 获取根节点readElement(root);}private static void readElement(Element root) {// TODO Auto-generated method stubList<Attribute> attrlist=root.attributes();for (Attribute attribute : attrlist) {System.out.println(attribute.getName()+" "+attribute.getValue()); }List<Element> elementlist=root.elements();for (Element element : elementlist) { System.out.println(element.getName()+" "+element.getTextTrim());readElement(element);}}}

结果：

二、SAX

解析XML，需要传入一个继承了DefaultHandler并复习其主要方法的类，或直接传入匿名内部类。startDocument()和endDocument()方法分别是开始读取和读取完毕执行，读取XML方法顺序是Element相关方法（读取节点名和Attributes ）-->characters相关方法读取两结点之间的Text

package XML;import java.io.File;import javax.xml.parsers.SAXParser;import javax.xml.parsers.SAXParserFactory;import org.xml.sax.Attributes;import org.xml.sax.SAXException;import org.xml.sax.helpers.DefaultHandler;public class SAXTest {public static void main(String[] args) throws Exception {SAXParserFactory factory = SAXParserFactory.newInstance();// step2: 获得SAX解析器实例SAXParser parser = factory.newSAXParser();// step3: 开始进行解析parser.parse(new File("D:\\Persons.xml"), new DefaultHandler() {//传入匿名内部类  复写DefaultHandler主要方法@Overridepublic void startDocument() throws SAXException {// System.out.println("parse began");}@Overridepublic void endDocument() throws SAXException {// System.out.println("parse finished");}@Overridepublic void startElement(String uri, String localName,String qName, Attributes attributes) throws SAXException {System.out.print(qName);for (int i = 0; i < attributes.getLength(); i++) {System.out.println(attributes.getQName(i) + "=" + attributes.getValue(i));}}@Overridepublic void characters(char[] ch, int start, int length)throws SAXException {// TODO Auto-generated method stub// super.characters(ch, start, length);读取Text部分System.out.println(new String(ch, start, length).trim());}@Overridepublic void endElement(String uri, String localName, String qName)throws SAXException {// System.out.println("finish element");}});}}

结果：

三、JDom

生成Xml

public class JDomTest {public static void main(String[] args) throws Exception {Document document = new Document();Element root = new Element("Persons");document.addContent(root);// comment 注释Comment comment = new Comment("可以添加注释");root.addContent(comment);Element person = new Element("Person");person.setAttribute("id", "201501");root.addContent(person);Element name = new Element("name");name.setText("liuli");Element age = new Element("age");age.setText("25");person.addContent(name).addContent(age);Format format = Format.getPrettyFormat();// format.setIndent("\r");format.setEncoding("UTF-8");XMLOutputter out = new XMLOutputter(format);out.output(document, new OutputStreamWriter(new FileOutputStream("jdom.xml"), "UTF-8"));}}

结果：

读取XML

public class JDomTest {public static void main(String[] args) throws Exception {SAXBuilder builder = new SAXBuilder();Document doc = builder.build(new File("Persons.xml"));Element root = doc.getRootElement();System.out.println(root.getName());List<Element> elements = root.getChildren();readXml(elements);XMLOutputter out = new XMLOutputter(Format.getPrettyFormat().setIndent(""));out.output(doc, new FileOutputStream("newPerson.xml"));}private static void readXml(List<Element> elements) {for (Element element : elements) {System.out.println(element.getName()+element.getTextTrim());List<Attribute> attribute = element.getAttributes();for (Attribute attr : attribute) {System.out.println(attr.getName() + "=" + attr.getValue());}readXml(element.getChildren());}}}

打印结果：

四、DOM

public class DOMTest {public static void main(String[] args) throws Exception {DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();DocumentBuilder db = dbf.newDocumentBuilder();Document doc = db.parse(new File("Persons.xml"));// 获得根元素结点Element root = doc.getDocumentElement();readXml(root);}static void readXml(Element element) {String tagName = element.getNodeName();NodeList children = element.getChildNodes();System.out.print(tagName);// element元素的所有属性所构成的NamedNodeMap对象，需要对其进行判断NamedNodeMap map = element.getAttributes();// 如果该元素存在属性if (null != map) {for (int i = 0; i < map.getLength(); i++) {// 获得该元素的每一个属性Attr attr = (Attr) map.item(i);String attrName = attr.getName();String attrValue = attr.getValue();System.out.print(attrName + "=" + attrValue );}}for (int i = 0; i < children.getLength(); i++) {Node node = children.item(i);// 获得结点的类型short nodeType = node.getNodeType();if (nodeType == Node.ELEMENT_NODE) {// 是元素，递归readXml((Element) node);} else if (nodeType == Node.TEXT_NODE) { System.out.print(node.getNodeValue());} else if (nodeType == Node.COMMENT_NODE) {Comment comment = (Comment) node;// 注释内容String data = comment.getData();System.out.println(data);}}}}

结果：