XML使用SAX方式解析

1. XML使用SAX方式解析

SAX的工作原理简单地说就是对文档进行顺序扫描，当扫描到文档(document)开始与结束、元素(element)开始与结束、文档(document)结束等地方时通知事件处理函数，由事件处理函数做相应动作，然后继续同样的扫描，直至文档结束。
优点：消耗资源比较少；适合大文件解析；
缺点：只能读取不能修改；开发复杂；

1.1 使用SAX方式读取XML文件

<?xml version="1.0" encoding="UTF-8"?>
<students>
    <student>
        <name id="001" xx="哈哈">张三</name>
        <sex>男</sex>
        <age>20</age>
    </student>
    <student>
        <name id="002">李四</name>
        <sex>女</sex>
        <age>21</age>
    </student>
</students>

package com.andrew.xml;
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 SAX01 extends DefaultHandler {
    @Override
    public void startDocument() throws SAXException {
        System.out.println("<?xml version=\"1.0\" encoding=\"UTF-8\"?>");
    }
    @Override
    public void endDocument() throws SAXException {
        System.out.print("\n 扫描文档结束");
    }
    @Override
    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
        System.out.print("<");
        System.out.print(qName);
        if (attributes != null) {
            for (int i = 0; i < attributes.getLength(); i++) {
                System.out.print(" " + attributes.getQName(i) + "=\"" + attributes.getValue(i) + "\"");
            }
        }
        System.out.print(">");
    }
    @Override
    public void endElement(String uri, String localName, String qName) throws SAXException {
        System.out.print("</");
        System.out.print(qName);
        System.out.print(">");
    }
    @Override
    public void characters(char[] ch, int start, int length) throws SAXException {
        System.out.print(new String(ch, start, length));
    }

    public static void main(String[] args) throws Exception {
        SAXParserFactory factory = SAXParserFactory.newInstance();
        SAXParser parser = factory.newSAXParser();
        parser.parse("src/students.xml", new SAX01());
    }
}
运行结果：
<?xml version="1.0" encoding="UTF-8"?>
<students>
    <student>
        <name id="001" xx="哈哈">张三</name>
        <sex>男</sex>
        <age>20</age>
    </student>
    <student>
        <name id="002">李四</name>
        <sex>女</sex>
        <age>21</age>
    </student>
</students>
 扫描文档结束

1.2 使用SAX方式读取XML数据到Bean

<?xml version="1.0" encoding="UTF-8"?>
<students>
    <student id="001">
        <name>张三</name>
        <sex>男</sex>
        <age>20</age>
    </student>
    <student id="002">
        <name>李四</name>
        <sex>女</sex>
        <age>21</age>
    </student>
</students>

package com.andrew.model;
public class Student {
    private String id;
    private String name;
    private String sex;
    private int age;
    @Override
    public String toString() {
        return "Student [id=" + id + ", name=" + name + ", sex=" + sex + ", age=" + age + "]";
    }
    // getter and setter
}

package com.andrew.xml;
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;
import com.andrew.model.Student;
public class SAX02 extends DefaultHandler {
    private List<Student> students = null;
    private Student student = null;
    private String preTag = null; // 标记上一个节点名称
    @Override
    public void startDocument() throws SAXException {
        System.out.println("开始读取学生信息");
        students = new ArrayList<Student>();
    }
    @Override
    public void endDocument() throws SAXException {
        System.out.println("学生信息读取完毕");
    }
    @Override
    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
        if ("student".equals(qName)) {
            student = new Student();
            student.setId(attributes.getValue(0));
        }
        preTag = qName;
    }
    @Override
    public void endElement(String uri, String localName, String qName) throws SAXException {
        if ("student".equals(qName)) {
            students.add(student);
            student = null;
        }
        preTag = null;
    }
    @Override
    public void characters(char[] ch, int start, int length) throws SAXException {
        if (preTag != null) {
            String content = new String(ch, start, length);
            if ("name".equals(preTag)) {
                student.setName(content);
            } else if ("sex".equals(preTag)) {
                student.setSex(content);
            } else if ("age".equals(preTag)) {
                student.setAge(Integer.parseInt(content));
            }
        }
    }
    public static void main(String[] args) throws Exception {
        SAXParserFactory factory = SAXParserFactory.newInstance();
        SAXParser parser = factory.newSAXParser();
        SAX02 sax02 = new SAX02();
        parser.parse("src/studentsSax.xml", sax02);
        for (Student s : sax02.students) {
            System.out.println(s);
        }
    }
}

运行结果：
开始读取学生信息
学生信息读取完毕
Student [id=001, name=张三, sex=男, age=20]
Student [id=002, name=李四, sex=女, age=21]