XML SAX解析xml文件

SAX解析xml文件

一、student.xml（解析的文件）

<?xml version="1.0" encoding="utf-8" ?><!--xml文档声明-->
<!--DTD约束-->
<!DOCTYPE class [
        <!ELEMENT student (name,age,sex,height)>
        <!ELEMENT name (#PCDATA)>
        <!ELEMENT age (#PCDATA)>
        <!ELEMENT sex (#PCDATA)>
        <!ELEMENT height (#PCDATA)>
        ]>

<!--只能有一个根标签-->
<class>
    <!--设置属性-->
    <student id="1" user="lisi">
        <name>李四</name>
        <age>18</age>
        <sex>男</sex>
        <height>182</height>
    </student>
    <student id="2" user="wangwu">
        <name>王五</name>
        <age>19</age>
        <sex>男</sex>
        <height>172</height>
    </student>
</class>

二、解析代码（SAXParseMain.java）

package com.xml.main;

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

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import java.io.IOException;
import java.util.ArrayList;

public class SAXParseMain {
    public static void main(String[] args) {
        try {
            //步骤一：创建SAX解析工厂实例
            SAXParserFactory factory = SAXParserFactory.newInstance();
            //步骤二：通过工厂创建一个SAX解析器
            SAXParser sax = factory.newSAXParser();
            MyHandler myHandler = new MyHandler();
            //步骤三：指定用相应的解析器开始解析XML文档
            sax.parse("student.xml", myHandler);
            ArrayList<Student> list = myHandler.getList();
            for (int i = 0; i < list.size(); i++) {
                Student student = list.get(i);
                System.out.println(student.toString());
            }
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
        }
    }
}

//指定解析处理器，编写解析规则
class MyHandler extends DefaultHandler {
    ArrayList<Student> list = new ArrayList<>();

    public ArrayList<Student> getList() {
        return list;
    }

    private Student student;
    private String target = "";

    //    解析到文档的开始
    @Override
    public void startDocument() throws SAXException {
    }

//    解析到开始的元素节点（包括根节点）

    /**
     * @param uri        命名空间
     * @param localName  元素名称【不支持了】
     * @param qName      [前缀:]元素名称（没有命名空间就不存在前缀）
     * @param attributes 属性集
     * @throws SAXException 异常
     */
    @Override
    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
        if ("student".equals(qName)) {
            student = new Student();
            String id = attributes.getValue("id");
            String user = attributes.getValue("user");
            student.setId(Integer.parseInt(id));
            student.setUser(user);
        }
        target = qName;
    }

    /**
     * 解析到文本内容（包括回车，空格，换行）
     *
     * @param ch     SAX并不是把整个文档加载到内存中，SAX会把解析到的内容缓存起来（缓存8192字节），char[] ch就是解析到的缓存内容
     * @param start  遇到文本的开始字符位置
     * @param length 当前整个文本从一个标签到下一个标签的长度
     * @throws SAXException
     */
    @Override
    public void characters(char[] ch, int start, int length) throws SAXException {
        String content = new String(ch, start, length);
        switch (target) {
            case "name":
                student.setName(content);
                break;
            case "age":
                student.setAge(Integer.parseInt(content));
                break;
            case "sex":
                student.setSex(content);
                break;
            case "height":
                student.setHeight(Double.parseDouble(content));
                break;
        }

    }

    /**
     * 解析到结束的元素节点
     *
     * @param uri
     * @param localName
     * @param qName
     * @throws SAXException
     */
    @Override
    public void endElement(String uri, String localName, String qName) throws SAXException {
        if ("student".equals(qName)) {
            list.add(student);
        }
        target = "";
    }

    /**
     * 解析到文档的结束
     *
     * @throws SAXException
     */
    @Override
    public void endDocument() throws SAXException {
    }

}

三、Student.java

package com.xml.main;

public class Student {
    private int id;
    private String user;
    private String name;
    private String sex;
    private int age;
    private double height;

    public Student() {
    }

    public Student(int id, String user, String name, String sex, int age, double height) {
        this.id = id;
        this.user = user;
        this.name = name;
        this.sex = sex;
        this.age = age;
        this.height = height;
    }

    public int getId() {
        return id;
    }

    public void setId(int id) {
        this.id = id;
    }

    public String getUser() {
        return user;
    }

    public void setUser(String user) {
        this.user = user;
    }

    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;
    }

    public double getHeight() {
        return height;
    }

    public void setHeight(double height) {
        this.height = height;
    }

    @Override
    public String toString() {
        return "Student{" +
                "id=" + id +
                ", user='" + user + '\'' +
                ", name='" + name + '\'' +
                ", sex='" + sex + '\'' +
                ", age=" + age +
                ", height=" + height +
                '}';
    }
}

四、解析结果

注：读边解析，应用于大型XML文档