SAX解析XML

下面是SAX解析XML的示例，包括三个文件employee.xml、Employee.java、SaxEmployee.java

1.被解析的employee.xml文件

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE employees [
	<!ELEMENT employees (employee*)>
	<!ELEMENT employee (name,age,gender,email,salary)>
	<!ATTLIST employee id  CDATA #IMPLIED> 
	<!ATTLIST employee depName CDATA #IMPLIED> 
	<!ELEMENT name (#PCDATA)>
	<!ELEMENT age (#PCDATA)>
	<!ELEMENT gender (#PCDATA)>
	<!ELEMENT email (#PCDATA)>
	<!ELEMENT salary (#PCDATA)>
]>
<employees>
	<employee id="1" depName="教学部">
		<name>tom</name>
		<age>20</age>
		<gender>male</gender>
		<email>[email protected]</email>
		<salary>10k</salary>
	</employee>
	<employee id="2" depName="教学部">
		<name>jack</name>
		<age>30</age>
		<gender>female</gender>
		<email>[email protected]</email>
		<salary>8k</salary>
	</employee>
	<employee id="3" depName="市场部">
		<name>rose</name>
		<age>25</age>
		<gender>female</gender>
		<email>[email protected]</email>
		<salary>5k</salary>
	</employee>
	<employee id="4" depName="教学管理部">
		<name>mark</name>
		<age>30</age>
		<gender>male</gender>
		<email>[email protected]</email>
		<salary>5k</salary>
	</employee>
</employees>

2.Employee.java文件

 

package exercise;

public class Employee {

	private int id;
	private String depName;
	private String name;
	private int age;
	private String gender;
	private String email;
	private String salary;
	
	public Employee() {
	}
	
	public Employee(int id, String depName, String name, int age, String gender, String email, String salary) {
		super();
		this.id = id;
		this.depName = depName;
		this.name = name;
		this.age = age;
		this.gender = gender;
		this.email = email;
		this.salary = salary;
	}
	
	@Override
	public String toString() {
		return "Employee [id=" + id + ", depName=" + depName + ", name=" + name + ", age=" + age + ", gender=" + gender
				+ ", email=" + email + ", salary=" + salary + "]";
	}
	
	public int getId() {
		return id;
	}
	public void setId(int id) {
		this.id = id;
	}
	public String getDepName() {
		return depName;
	}
	public void setDepName(String depName) {
		this.depName = depName;
	}
	public String getName() {
		return name;
	}
	public void setName(String name) {
		this.name = name;
	}
	public int getAge() {
		return age;
	}
	public void setAge(int age) {
		this.age = age;
	}
	public String getGender() {
		return gender;
	}
	public void setGender(String gender) {
		this.gender = gender;
	}
	public String getEmail() {
		return email;
	}
	public void setEmail(String email) {
		this.email = email;
	}
	public String getSalary() {
		return salary;
	}
	public void setSalary(String salary) {
		this.salary = salary;
	}
	
	
}

3.SaxEmployee.java实现解析

 

package exercise;

import java.io.File;
import java.util.ArrayList;
import java.util.List;

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;



/**
 * 利用SAX解析，将employee.xml中的employee对象存放到list中
 * @author Attention
 *
 */
public class SaxEmployee {

	public static void main(String[] args) throws Exception {
		//1.先创建解析器工厂
		SAXParserFactory factory = SAXParserFactory.newInstance();
		//2.利用工厂创建一个解析器
		SAXParser parser = factory.newSAXParser();
		//3.调用解析方法，解析文件,该方法有两个参数，第一个参数是你要解析的文件，第二个参数是处理类
		File file = new File("src/exercise/employee.xml");
		Handler handler = new Handler();
		parser.parse(file, handler);
	}
}

/**
 * 创建一个类继承默认处理类，实现里面具体的解析方法
 * 前面说过SAX是基于事件的解析，遇到开始标签、结束标签、文本，空文本会触发事件
 * 我们就是要写触发事件后具体的执行过程，这也是SAX比较复杂的地方
 * 里面有几个很关键的方法：
 * 1.startDocument()
 * 2.endDocument()
 * 3.startElement()
 * 4.endElement()
 * 5.characters()
 * 实现这几个方法就可以对xml文件进行解析了，当然1和2两个方法可以不实现
 */
class Handler extends DefaultHandler{

	//首先我们先创建一个List容器用来存放Employee对象，我们在startDocument()方法中进行初始化
	private List<Employee> list = null;
	//用来存放当前的标签名
	private String tagName = null;
	//定义一个Employee对象
	private Employee employee = null;
	@Override
	public void startDocument() throws SAXException {
		System.out.println("============开始解析文档============");
		list = new ArrayList<>();
	}

	@Override
	public void endDocument() throws SAXException {
		System.out.println("============解析文档结束============");
		//执行到这个方法，说明文档已经解析完毕，我们在这里将list容器中的内容打印出来，测试一下我们方法是否有误
		//当前也可以给List提供get()函数，在外面拿取
		for(Employee e : list) {
			System.out.println(e);
		}
	}

	//开始标签，当遇到开始标签会触发该方法
	@Override
	public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
		if(qName.equals("employee")) {                 //说明拿到一个Employee对象
			employee = new Employee();                 //我们就创建一个对象
			String id = attributes.getValue("id");     //获取到两个属性值
			String depName = attributes.getValue("depName");
			employee.setId(Integer.parseInt(id));      //将当前取到的值赋给当前对象
			employee.setDepName(depName);
		}else {
			tagName = qName;
		}
	}

	@Override
	public void endElement(String uri, String localName, String qName) throws SAXException {
		
		if(qName.equals("employee")) {    //此时说明一个对象已经解析完，我们就将当前对象存放到容器中
			list.add(employee);
		}else {
			//因为SAX解析也会识别空文本，所以每次遇到尾标签，需要将tagName值空，避免，将当前的值被空文本给覆盖掉
			tagName = null;
		}
	}
	//当前文本内容
	@Override
	public void characters(char[] ch, int start, int length) throws SAXException {
		//构建当前读取到文本内容
		String msg = new String(ch,start,length);
		//tagName存放这当前的qName，判断当前拿取到的是那个值
		if(tagName.equals("name")) {
			employee.setName(msg);
		}else if(tagName.equals("age")) {
			employee.setAge(Integer.parseInt(msg));
		}else if(tagName.equals("gender")) {
			employee.setGender(msg);
		}else if(tagName.equals("email")) {
			employee.setEmail(msg);
		}else if(tagName.equals("salary")) {
			employee.setSalary(msg);
		}
	}
	
}