Sax解析xml文档

测试的xml数据：

<?xml version="1.0" encoding="utf-8" ?>

<note>

    <to>George</to>

    <from>John</from>

    <heading>Reminder</heading>

    <body>Don't forget the meeting!</body>

</note>

新建SaxTest类继承至DefaultHandle

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.SAXParserFactory;

import java.io.FileInputStream;

import java.io.IOException;

public class SaxTest extends DefaultHandler {

    @Override

    public void startDocument() throws SAXException {

        System.out.println("开始解析文档");

    }

    @Override

    public void endDocument() throws SAXException {

        System.out.println("解析文档结束");

    }

    @Override

    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {

        System.out.println(qName);//每个标签开始都会触发该事件,attributes是标签的属性

    }

    @Override

    public void endElement(String uri, String localName, String qName) throws SAXException {

        System.out.println(qName);//每个标签结束都会触发该事件

    }

    @Override

    public void characters(char[] ch, int start, int length) throws SAXException {

        System.out.println(new String(ch, start, length));//标签开始到标签结束之间的内容

    }

    static public void main(String[] args) throws IOException, ParserConfigurationException, SAXException {

        String textXml = SaxTest.class.getResource("/").getPath() + "test.xml";

        FileInputStream inputStream = new FileInputStream(textXml);

        SAXParserFactory.newInstance().newSAXParser().parse(inputStream, new SaxTest());

    }

}

解析结果截图：

其中characters方法需要特别注意，开始标签到结束标签的内容可能不止会触发一次characters事件，也就是说标签中的内容可能会多次触发characters事件，所以如果要获取标签内的完整内容需要特别小心，一般使用StringBuilder，如下代码。

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.SAXParserFactory;

import java.io.FileInputStream;

import java.io.IOException;

public class SaxTest extends DefaultHandler {

    StringBuilder stringBuilder = new StringBuilder();

    @Override

    public void startDocument() throws SAXException {

        System.out.println("开始解析文档");

    }

    @Override

    public void endDocument() throws SAXException {

        System.out.println("解析文档结束");

    }

    @Override

    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {

        System.out.println(qName);//每个标签开始都会触发该事件,attributes是标签的属性

    }

    @Override

    public void endElement(String uri, String localName, String qName) throws SAXException {

        System.out.println(stringBuilder.toString().trim());

        stringBuilder.delete(0, stringBuilder.length());//输出内容,并清空stringBuilder

        System.out.println(qName);//每个标签结束都会触发该事件

    }

    @Override

    public void characters(char[] ch, int start, int length) throws SAXException {

        stringBuilder.append(ch, start, length);

    }

    static public void main(String[] args) throws IOException, ParserConfigurationException, SAXException {

        String textXml = SaxTest.class.getResource("/").getPath() + "test.xml";

        FileInputStream inputStream = new FileInputStream(textXml);

        SAXParserFactory.newInstance().newSAXParser().parse(inputStream, new SaxTest());

    }

}

uo

Sax解析xml文档