Java的XML创建、解析文档

1、使用DOM

优点：可以在内存直接操作节点。

缺点：当文档较大时，消耗内存大。

/**
 * 
 */
package com.ee.xml;

import java.io.File;
import java.io.IOException;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.SAXException;

/**
 * <pre>
 * 使用DOM来创建文档，读取文档等。
 * </pre>
 * @author ps
 *
 */
public class XmlDocument {
	private Document document;
	/**
	 * 创建文档
	 */
	public void createXmlDocument(){
		try {
			//使用工厂类创建
			DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
			DocumentBuilder builder = builderFactory.newDocumentBuilder();
			document = builder.newDocument();
		} catch (ParserConfigurationException e) {
			e.printStackTrace();;
		}
	}
	
	/**
	 * <pre>
	 * 创建XML文档
	 * 生成的内容如下：
	 * <?xml version="1.0" encoding="utf-8" standalone="no"?>
	 * <employees>
	 * <employee>
	 * <name>pansen</name>
	 * <sex>男</sex>
	 * <age>26</age>
	 * </employee>
	 * </employees>
	 * </pre>
	 */
	public void createXml(){
		Element element = document.createElement("employee");
		Element name = document.createElement("name");
		Node node = document.createTextNode("pansen");
		name.appendChild(node);
		element.appendChild(name);
		
		Element sex = document.createElement("sex");
		Node sexText = document.createTextNode("男");
		sex.appendChild(sexText);
		element.appendChild(sex);
		
		
		Element age = document.createElement("age");
		Node ageText = document.createTextNode("26");
		age.appendChild(ageText);
		element.appendChild(age);
		
		Element root = document.createElement("employees");
		root.appendChild(element);
		document.appendChild(root);
		
		try {
			TransformerFactory transformerFactory = TransformerFactory.newInstance();
			Transformer transformer = transformerFactory.newTransformer();
			
			DOMSource domSource = new DOMSource(document);
			
			//设置文档的编码
			transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
			transformer.setOutputProperty(OutputKeys.INDENT, "yes");
			
			File file = new File("d:\\my.xml");//文件名
			
			StreamResult result = new StreamResult(file);
			transformer.transform(domSource, result);//生成XML文件
		} catch (TransformerConfigurationException e) {
			e.printStackTrace();
		} catch (TransformerException e) {
			e.printStackTrace();
		}
	}
	
	/**
	 * 解析XML文档
	 */
	public void parseXML(){
		try {
			DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
			DocumentBuilder builder = builderFactory.newDocumentBuilder();
			File file = new File("d:\\my.xml");
			Document document = builder.parse(file);//把XML文档转换为Document
			NodeList employees = document.getChildNodes();
			
			//遍历输出
			for (int i = 0; i < employees.getLength(); i++) {
				Node employe = employees.item(i);
				NodeList nodeList = employe.getChildNodes();
				for (int j = 0; j < nodeList.getLength(); j++) {
					Node node = nodeList.item(j);
					
					NodeList employeeMeta = node.getChildNodes();
					for (int k = 0; k < employeeMeta.getLength(); k++) { 
						System.out.println(employeeMeta.item(k).getNodeName() 
						+ ":" + employeeMeta.item(k).getTextContent()); 
					} 
				}
			}
		} catch (ParserConfigurationException e) {
			e.printStackTrace();
		} catch (SAXException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
}

2、使用SAX

优点：不必解析整个文档，消耗内存较小。

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。

例子：

/**
 * 
 */
package com.ee.xml;

import java.io.File;
import java.io.IOException;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.SAXException;

import com.ee.xml.handle.EmployeeHandler;


/**
 * <pre>
 * 使用SAX来创建文档，读取文档等。
 * </pre>
 * @author ps
 *
 */
public class SaxXmlDocument extends XmlDocument{
	/**
	 * 解析XML文档
	 */
	public void parseXML(){
		try {
			SAXParserFactory parserFactory = SAXParserFactory.newInstance();
			SAXParser saxParser = parserFactory.newSAXParser();
			File file = new File("d:\\my.xml");
			
			EmployeeHandler handler = new EmployeeHandler();
			saxParser.parse(file, handler);
		} catch (ParserConfigurationException e) {
			e.printStackTrace();
		} catch (SAXException e) {
			e.printStackTrace();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}
}

package com.ee.xml.handle;

import java.util.ArrayList;
import java.util.List;

import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.DefaultHandler;

import com.ee.xml.entity.Employee;
/**
 * 
 * @author ps
 *
 */
public class EmployeeHandler extends DefaultHandler{
	private Employee employee;
	private List<Employee> employeeLists;
	private String tagName;

	public Employee getEmployee() {
		return employee;
	}

	public void setEmployee(Employee employee) {
		this.employee = employee;
	}

	public List<Employee> getEmployeeLists() {
		return employeeLists;
	}

	public void setEmployeeLists(List<Employee> employeeLists) {
		this.employeeLists = employeeLists;
	}
	
	@Override
	public void startDocument() throws SAXException {
		//文档开始，可以做一些初始化的内容
		System.err.println("文档开始，可以做一些初始化的内容");
		employeeLists = new ArrayList<Employee>();
	}
	
	@Override
	public void startElement(String uri, String localName, String qName,
			Attributes attributes) throws SAXException {
		//开始节点调用
		System.err.println("开始节点调用");
		if("employee".equals(qName)){
			employee = new Employee();
			//在此可以用来判断获取tagName上的属性值
		}
		tagName = qName;
		System.err.println(qName);
	}
	
	@Override
	public void endElement(String uri, String localName, String qName)
			throws SAXException {
		//结束节点调用
		System.err.println("结束节点调用");
		employeeLists.add(employee);
		tagName = null;
	}
	
	@Override
	public void endDocument() throws SAXException {
		//文档结束
		System.err.println("文档结束");
	}
	
	@Override
	public void characters(char[] ch, int start, int length)
			throws SAXException {
		
		String val = new String(ch, start, length);
		System.err.println(val);
		if("name".equals(tagName)){
			employee.setName(val);
		}else if("sex".equals(tagName)){
			employee.setSex(val);
		}else if("age".equals(tagName)){
			employee.setAge(Integer.parseInt(val));
		}
		
	}
}

/**
 * 
 */
package com.ee.xml.entity;

/**
 * @author ps
 *
 */
public class Employee {
	private String name;
	private String sex;
	private int age;
	
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public String getSex() {
		return sex;
	}
	public void setSex(String sex) {
		this.sex = sex;
	}
	public int getAge() {
		return age;
	}
	public void setAge(int age) {
		this.age = age;
	}
}

3、使用DOM4J，需要导入dom4j-1.6.1.jar

DOM4J 是一个非常非常优秀的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

/**
 * 
 */
package com.ee.xml;

import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.IOException;
import java.io.OutputStream;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.Iterator;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

/**
 * @author ps
 *
 */
public class Dom4jXmlDocument {
	
	public void createXml(){
		Document document = DocumentHelper.createDocument();
		Element employees = document.addElement("employees");
		Element employee = employees.addElement("employee");
		Element name = employee.addElement("name");
		name.setText("pansen");
		Element sex = employee.addElement("sex");
		sex.setText("男");
		Element age = employee.addElement("age");
		age.setText("26");
		
		try {
			File file = new File("d:\\dom4j.xml");
			OutputStream out = new FileOutputStream(file);
			Writer writer = new OutputStreamWriter(out, "utf-8");
			//Writer writer = new FileWriter(file);//2 字节的 UTF-8 序列的字节 2 无效。
			XMLWriter xmlWriter = new XMLWriter(writer);
			
			xmlWriter.write(document);
			xmlWriter.close();
		} catch (IOException e) {
			e.printStackTrace();
		}
		
	}
	
	public void parseXml(){
		File file = new File("d:\\dom4j.xml");
		SAXReader saxReader = new SAXReader();
		
		try {
			Document document = saxReader.read(file);
			
			Element employees = document.getRootElement();
			
			Iterator<Element> iterator = employees.elementIterator();
			
			while(iterator.hasNext()){
				Element employee = iterator.next();
				
				Iterator<Element> iter = employee.elementIterator();
				while(iter.hasNext()){
					Element node = iter.next();
					
					System.err.println(node.getName() + "||" + node.getText());
				}
			}
		} catch (DocumentException e) {
			e.printStackTrace();
		}
	}
}