Java解析XML的四种方法

• 一、DOM解析

 * 为 XML 文档的已解析版本定义了一组接口。
 * 解析器读入整个文档，然后构建一个驻留内存的树结构，
 * 然后代码就可以使用 DOM接口来操作这个树结构。
 * 优点：整个文档树在内存中，便于操作；支持删除、修改、重新排列等多种功能；
 * 缺点：将整个文档调入内存（包括无用的节点），浪费时间和空间；
 * 使用场合：一旦解析了文档还需多次访问这些数据；硬件资源充足（内存、CPU）。

公用接口：

package xml;

/**
 *定义XML文档建立与解析的接口 
 **/
public interface XmlDocument {

	/**
	 * 建立XML文档 
	 * @param fileName文件全路径名称 
	 */
	public void createXml(String fileName);
	
	/**
	 * 解析XML文档 
	 * @param fileName文件全路径名称 
	 */
	public void parserXml(String fileName);

}

DOM解析用例：

package xml;

public class Dom_xml implements XmlDocument {
	private Document document;
	private static String fileName="d:/Dom_xml.xml";

	public void init() {
		try {
			DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
			DocumentBuilder builder = factory.newDocumentBuilder();
			this.document = builder.newDocument();
		} catch (ParserConfigurationException e) {
			System.out.println(e.getMessage());
		}
	}

	public  void createXml(String fileName) {
		this.init();
		Element root = this.document.createElement("employees");
		this.document.appendChild(root);
		
		Element employee = this.document.createElement("employee");
		Element name = this.document.createElement("name");
		name.appendChild(this.document.createTextNode("杨过"));
		employee.appendChild(name);
		
		Element sex = this.document.createElement("sex");
		sex.appendChild(this.document.createTextNode("男"));
		employee.appendChild(sex);
		
		Element age = this.document.createElement("age");
		age.appendChild(this.document.createTextNode("26"));
		employee.appendChild(age);
		
		root.appendChild(employee);
		
		Element employee1 = this.document.createElement("employee");
		Element name1 = this.document.createElement("name");
		name1.appendChild(this.document.createTextNode("小龙女"));
		employee1.appendChild(name1);
		
		Element sex1 = this.document.createElement("sex");
		sex1.appendChild(this.document.createTextNode("女"));
		employee1.appendChild(sex1);
		
		Element age1 = this.document.createElement("age");
		age1.appendChild(this.document.createTextNode("28"));
		employee1.appendChild(age1);
		
		root.appendChild(employee1);
		
		TransformerFactory tf = TransformerFactory.newInstance();
		try {
			Transformer transformer = tf.newTransformer();
			DOMSource source = new DOMSource(document);
			transformer.setOutputProperty(OutputKeys.ENCODING, "gb2312");
			transformer.setOutputProperty(OutputKeys.INDENT, "yes");
			
			PrintWriter pw = new PrintWriter(new FileOutputStream(fileName));
			StreamResult result = new StreamResult(pw);
			transformer.transform(source, result);
			System.out.println("生成XML文件成功:"+fileName);
			
		} catch (TransformerConfigurationException e) {
			System.out.println(e.getMessage());
		} catch (IllegalArgumentException e) {
			System.out.println(e.getMessage());
		} catch (FileNotFoundException e) {
			System.out.println(e.getMessage());
		} catch (TransformerException e) {
			System.out.println(e.getMessage());
		}
	}

	public void parserXml(String fileName) {
		try {
			DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
			DocumentBuilder db = dbf.newDocumentBuilder();
			Document document = db.parse(fileName);
			
			NodeList employees = document.getChildNodes();
			for (int i = 0; i < employees.getLength(); i++) {
				//employees节点
				Node employee = employees.item(i);
				//employees节点下的子节点
				NodeList employeeInfo = employee.getChildNodes();
				
				for (int j = 0; j < employeeInfo.getLength(); j++) {
					//employee节点
					Node node = employeeInfo.item(j);
					//employee节点下的子节点
					NodeList employeeMeta = node.getChildNodes();
										
					for (int k = 0; k < employeeMeta.getLength(); k++) {
						System.out.println(k+": "+employeeMeta.item(k).getNodeName()
								+ ":" + employeeMeta.item(k).getTextContent());
					}
				}
			}
			System.out.println("解析完毕!");
			
		} catch (FileNotFoundException e) {
			System.out.println(e.getMessage());
		} catch (ParserConfigurationException e) {
			System.out.println(e.getMessage());
		} catch (SAXException e) {
			System.out.println(e.getMessage());
		} catch (IOException e) {
			System.out.println(e.getMessage());
		}
	}
	
	public static void main(String[] arg){
		Dom_xml dom_xml=new Dom_xml();
		dom_xml.createXml(fileName);
		dom_xml.parserXml(fileName);
	}
}

• 二、SAM解析

 * 为解决DOM的问题，出现了SAX，SAX为事件驱动。
 * 当解析器发现元素开始、元素结束、文本、文档的开始或结束等时，发送事件，
 * 程序员编写响应这些事件的代码，保存数据。
 * 优点：不用事先调入整个文档，占用资源少；
 * SAX解析器代码比DOM解析器代码小，适于Applet，下载。
 * 缺点：不是持久的；事件过后，若没保存数据，那么数据就丢了； 无状态性；
 * 从事件中只能得到文本，但不知该文本属于哪个元素；
 * 使用场合：Applet;只需XML文档的少量内容，很少回头访问；机器内存少。

SAM解析用例：

package xml;

public class Sam_xml implements XmlDocument {
	private static String fileName="d:/Sam_xml.xml";
	
	public void createXml(String fileName) {
		
	}

	public void parserXml(String fileName) {
		SAXParserFactory saxfac = SAXParserFactory.newInstance();
		try {
			
			SAXParser saxparser = saxfac.newSAXParser();
			InputStream is = new FileInputStream(fileName);
			saxparser.parse(is, new MySAXHandler());
			
		} catch (ParserConfigurationException e) {
			e.printStackTrace();
		} catch (SAXException e) {
			e.printStackTrace();
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	public static void main(String[] arg){
		Sam_xml sam_xml=new Sam_xml();
		sam_xml.createXml(fileName);
		sam_xml.parserXml(fileName);
	}
}

class MySAXHandler extends DefaultHandler {
	boolean hasAttribute = false;
	Attributes attributes = null;

	public void startDocument() throws SAXException {
		System.out.println("parsing start");
	}

	public void endDocument() throws SAXException {
		System.out.println("parsing end");
	}

	public void startElement(String uri, String localName, String qName,
			Attributes attributes) throws SAXException {
		if (qName.equals("employees")) {
			return;
		}
		if (qName.equals("employee")) {
			System.out.println(qName);
		}
		if (attributes.getLength() > 0) {
			this.attributes = attributes;
			this.hasAttribute = true;
		}
	}

	public void endElement(String uri, String localName, String qName)
			throws SAXException {
		if (hasAttribute && (attributes != null)) {
			for (int i = 0; i < attributes.getLength(); i++) {
				System.out.println(attributes.getQName(0)
						+ attributes.getValue(0));
			}
		}
	}

	public void characters(char[] ch, int start, int length)
			throws SAXException {
		System.out.println(new String(ch, start, length));
	}
	
}

• 三、JDOM解析

 * 为解决DOM的问题，出现了SAX，SAX为事件驱动。
 * 当解析器发现元素开始、元素结束、文本、文档的开始或结束等时，发送事件，
 * 程序员编写响应这些事件的代码，保存数据。
 * 优点：不用事先调入整个文档，占用资源少；
 * SAX解析器代码比DOM解析器代码小，适于Applet，下载。
 * 缺点：不是持久的；事件过后，若没保存数据，那么数据就丢了； 无状态性；
 * 从事件中只能得到文本，但不知该文本属于哪个元素；
 * 使用场合：Applet;只需XML文档的少量内容，很少回头访问；机器内存少。

【注:JDOM解析需要jdom.jar包】

JDOM解析用例：

package xml;

import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.List;
import org.jdom.Document;
import org.jdom.Element;
import org.jdom.JDOMException;
import org.jdom.input.SAXBuilder;
import org.jdom.output.Format;
import org.jdom.output.XMLOutputter;

public class Jdom_xml {
	private Document document;
	private static String fileName="d:/Jdom_xml.xml";
	/**
	 * 生产xml	
	 * @param fileName
	 */
	public void createXml(String fileName) {
		Element root;
		root = new Element("employees");
		this.document = new Document(root);
		
		Element employee = new Element("employee");
		root.addContent(employee);
		Element name = new Element("name");
		name.setText("杨过");
		employee.addContent(name);	
		Element sex = new Element("sex");
		sex.setText("男");
		employee.addContent(sex);
		Element age = new Element("age");
		age.setText("26");
		employee.addContent(age);
		
		Element employee1 = new Element("employee");
		root.addContent(employee1);
		Element name1 = new Element("name");
		name1.setText("小龙女");
		employee1.addContent(name1);	
		Element sex1 = new Element("sex");
		sex1.setText("女");
		employee1.addContent(sex1);
		Element age1 = new Element("age");
		age1.setText("28");
		employee1.addContent(age1);
		
		//设置xml编码
		XMLOutputter XMLOut = new XMLOutputter();
		Format format=XMLOut.getFormat();
		format.setEncoding("gb2312");
		XMLOut.setFormat(format);
		try {
			XMLOut.output(document, new FileOutputStream(fileName));
			System.out.println("生产xml成功："+fileName);
		} catch (FileNotFoundException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
    /**
     * 解析xml
     * @param fileName
     */
	@SuppressWarnings("rawtypes")
	public void parserXml(String fileName) {
		SAXBuilder builder = new SAXBuilder(false);
		try {
			Document document = builder.build(fileName);
			Element employees = document.getRootElement();
			List employeeList = employees.getChildren("employee");

			for (int i = 0; i < employeeList.size(); i++) {
				Element employee = (Element) employeeList.get(i);
				List employeeInfo = employee.getChildren();
				
				for (int j = 0; j < employeeInfo.size(); j++) {
					System.out.println(((Element) employeeInfo.get(j)).getName()
							+ ":"
							+ ((Element) employeeInfo.get(j)).getValue());
				}
			}

		} catch (JDOMException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
	
	public static void main(String[] arg){
		Jdom_xml jdom_xml=new Jdom_xml();
		jdom_xml.createXml(fileName);
		jdom_xml.parserXml(fileName);
	}
}

• 四、DOM4J解析

 * DOM4J 是一个非常优秀的Java XML API，
 * 具有性能优异、功能强大和极端易用使用的特点，
 * 同时它也是一个开放源代码的软件。
 * 如今你可以看到越来越多的 Java 软件都在使用 DOM4J 来读写XML，
 * 特别值得一提的是连 Sun 的 JAXM 也在用 DOM4J。

【注:JDOM解析需要dom4j-1.6.1.jar包】

DOM4J解析用例：

package xml;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.Iterator;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

public class Dom4j_xml implements XmlDocument {
	private Document document;
	private static String fileName="d:/Dom4j_xml.xml";
	
	/**
	 * 生产xml
	 */
	public void createXml(String fileName) {
		this.document = DocumentHelper.createDocument();
		Element employees = document.addElement("employees");
		Element employee = employees.addElement("employee");
		Element name = employee.addElement("name");
		name.setText("杨过");
		Element sex = employee.addElement("sex");
		sex.setText("男");
		Element age = employee.addElement("age");
		age.setText("26");
		
		Element employee1 = employees.addElement("employee");
		Element name1 = employee1.addElement("name");
		name1.setText("小龙女");
		Element sex1 = employee1.addElement("sex");
		sex1.setText("女");
		Element age1 = employee1.addElement("age");
		age1.setText("28");
		
		try {
			//设置XML编码
			OutputFormat format = OutputFormat.createPrettyPrint(); 
			format.setEncoding("gb2312"); 
			
			//使用字节流
			XMLWriter xmlWriter = new XMLWriter(new FileOutputStream(new File(fileName)));
			xmlWriter.write(document);
			xmlWriter.flush();
			xmlWriter.close();
			System.out.println("生成xml成功："+fileName);
		} catch (IOException e) {
			System.out.println(e.getMessage());
		}
	}

	/**
	 * 解析xml
	 */
	@SuppressWarnings("rawtypes")
	public void parserXml(String fileName) {
		File inputXml = new File(fileName);
		SAXReader saxReader = new SAXReader();
		try {
			Document document = saxReader.read(inputXml);
			Element employees = document.getRootElement();
			for (Iterator i = employees.elementIterator(); i.hasNext();) {
				Element employee = (Element) i.next();
				for (Iterator j = employee.elementIterator(); j.hasNext();) {
					Element node = (Element) j.next();
					System.out.println(node.getName() + ":" + node.getText());
				}
			}
		} catch (DocumentException e) {
			System.out.println(e.getMessage());
		}
	}
	
	public static void main(String[] arg){
		Dom4j_xml dom4j_xml=new Dom4j_xml();
		dom4j_xml.createXml(fileName);
		dom4j_xml.parserXml(fileName);
	}
}

参考：

http://developer.51cto.com/art/200903/117512.htm