Java操作XML(2)--SAX方式处理XML

SAX是一个用于处理XML事件驱动的“推”模型，虽然它不是W3C标准，但它却是一个得到了广泛认可的API。本文主要介绍Java SAX方式处理XML，文中所使用到的软件版本：Java 1.8.0_191。

1、SAX简介

      SAX的全称是Simple APIs for XML，也即XML简单应用程序接口。与DOM不同，SAX提供的访问模式是一种顺序模式，这是一种快速读写XML数据的方式。当使用SAX分析器对XML文档进行分析时，会触发一系列事件，并激活相应的事件处理函数，应用程序通过这些事件处理函数实现对XML文档的访问，因而SAX接口也被称作事件驱动接口。

1.1、SAX的优点

1、顺序读入文档并产生相应事件，可以处理任何大小的XML文档。
2、适用于只需要文档的部分内容，或者只需要从文档中得到特定信息。

1.2、SAX的缺点

1、只能对文档按顺序解析一遍，不支持对文档的随意访问。
2、只能读取XML文档内容，而不能修改。
3、开发上比较复杂，需要自己来实现事件处理器。

2、Java SAX方式操作XML

2.1、XML文件

<?xml version="1.0" encoding="utf-8" ?>
<school:class xmlns:school="http://www.w3.org/TR/html4/school/">
    <school:student rollno="1" school:testattr="test">
        <school:firstname>cxx1</school:firstname>
        <lastname>Bob1</lastname>
        <nickname>stars1</nickname>
        <marks>85</marks>
    </school:student>
    <student rollno="2">
        <firstname>cxx2</firstname>
        <lastname>Bob2</lastname>
        <nickname>stars2</nickname>
        <marks>85</marks>
    </student>
    <student rollno="3">
        <firstname>cxx3</firstname>
        <lastname>Bob3</lastname>
        <nickname>stars3</nickname>
        <marks>85</marks>
    </student>
</school:class>

2.2、Java代码例子

该例子演示如何使用SAX方式解析XML以及使用SAX方式来生成XML。

package com.abc.demo.general.xml;

import org.junit.Test;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.xml.sax.Attributes;
import org.xml.sax.SAXException;
import org.xml.sax.helpers.AttributesImpl;
import org.xml.sax.helpers.DefaultHandler;

import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;
import javax.xml.transform.OutputKeys;
import javax.xml.transform.Transformer;
import javax.xml.transform.sax.SAXTransformerFactory;
import javax.xml.transform.sax.TransformerHandler;
import javax.xml.transform.stream.StreamResult;
import java.io.ByteArrayOutputStream;

public class SaxCase {
    private static Logger logger = LoggerFactory.getLogger(DomCase.class);

    /**
     * 解析xml
     * @throws Exception
     */
    @Test
    public void parse() throws Exception {
        SAXParserFactory factory = SAXParserFactory.newInstance();
        SAXParser parser = factory.newSAXParser();
        SaxHandler handler = new SaxHandler(logger);
        parser.parse(DomCase.class.getResourceAsStream("student.xml"), handler);
    }

    /**
     * 生成xml
     * @throws Exception
     */
    @Test
    public void toXml() throws Exception {
        //创建SAX转换工厂
        SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
        TransformerHandler handler = factory.newTransformerHandler();

        //创建handler转换器
        Transformer transformer = handler.getTransformer();
        //换行
        transformer.setOutputProperty(OutputKeys.INDENT, "yes");
        transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");

        ByteArrayOutputStream out = new ByteArrayOutputStream();
        StreamResult streamResult = new StreamResult(out);
        handler.setResult(streamResult);

        AttributesImpl attributes = new AttributesImpl();
        //打开doc对象
        handler.startDocument();
        handler.startElement("http://www.w3.org/TR/html4/school/", "", "school:class", null);

        //第一个学生
        attributes.clear();
        attributes.addAttribute("", "", "rollno", "", "1");
        attributes.addAttribute("", "", "school:testattr", "", "test");
        handler.startElement("", "", "student", attributes);
        handler.startElement("", "", "school:firstname", null);
        handler.characters("cxx1".toCharArray(), 0, 4);
        handler.endElement("", "", "school:firstname");
        handler.startElement("", "", "lastname", null);
        handler.characters("Bob1".toCharArray(), 0, 4);
        handler.endElement("", "", "lastname");
        handler.startElement("", "", "nickname", null);
        handler.characters("stars1".toCharArray(), 0, 6);
        handler.endElement("", "", "nickname");
        handler.startElement("", "", "marks", null);
        handler.characters("85".toCharArray(), 0, 2);
        handler.endElement("", "", "marks");
        handler.endElement("", "", "student");
        //第二个学生
        attributes.clear();
        attributes.addAttribute("", "", "rollno", "", "2");
        handler.startElement("", "", "student", attributes);
        handler.startElement("", "", "firstname", null);
        handler.characters("cxx2".toCharArray(), 0, 4);
        handler.endElement("", "", "firstname");
        handler.startElement("", "", "lastname", null);
        handler.characters("Bob2".toCharArray(), 0, 4);
        handler.endElement("", "", "lastname");
        handler.startElement("", "", "nickname", null);
        handler.characters("stars2".toCharArray(), 0, 6);
        handler.endElement("", "", "nickname");
        handler.startElement("", "", "marks", null);
        handler.characters("85".toCharArray(), 0, 2);
        handler.endElement("", "", "marks");
        handler.endElement("", "", "student");
        //第三个学生
        attributes.clear();
        attributes.addAttribute("", "", "rollno", "", "3");
        handler.startElement("", "", "student", attributes);
        handler.startElement("", "", "firstname", null);
        handler.characters("cxx3".toCharArray(), 0, 4);
        handler.endElement("", "", "firstname");
        handler.startElement("", "", "lastname", null);
        handler.characters("Bob3".toCharArray(), 0, 4);
        handler.endElement("", "", "lastname");
        handler.startElement("", "", "nickname", null);
        handler.characters("stars3".toCharArray(), 0, 6);
        handler.endElement("", "", "nickname");
        handler.startElement("", "", "marks", null);
        handler.characters("85".toCharArray(), 0, 2);
        handler.endElement("", "", "marks");
        handler.endElement("", "", "student");

        handler.endElement("", "", "school:class");

        handler.endDocument();
        logger.info(out.toString());
    }
}

class SaxHandler extends DefaultHandler {
    private String value;

    private Logger logger;
    public SaxHandler(Logger logger) {
        this.logger = logger;
    }

    @Override
    public void startDocument() throws SAXException {
        super.startDocument();
        logger.info("SAX解析开始");
    }

    @Override
    public void endDocument() throws SAXException {
        super.endDocument();
        logger.info("SAX解析结束");
    }

    @Override
    public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
        super.startElement(uri, localName, qName, attributes);
        if (qName.equals("student") || qName.equals("school:student")) {
            logger.info("学生编号" + attributes.getValue("rollno"));
            if (attributes.getValue("school:testattr") != null) {
                logger.info("testattr=" + attributes.getValue("school:testattr"));
            }
        } else if (qName.equals("firstname") || qName.equals("lastname") || qName.equals("nickname") || qName.equals("marks")) {
            //logger.info(qName + "开始");
        }
    }

    @Override
    public void endElement(String uri, String localName, String qName)
            throws SAXException {
        super.endElement(uri, localName, qName);
        if (qName.equals("firstname") || qName.equals("school:firstname") || qName.equals("lastname") || qName.equals("nickname") || qName.equals("marks")) {
            logger.info(qName + ":" + value);
        }
    }

    @Override
    public void characters(char[] ch, int start, int length) throws SAXException {
        super.characters(ch, start, length);
        value = new String(ch, start, length);
        if (!value.trim().equals("")) {
//            logger.info("节点值是：" + value);
        }
    }
}