xml读写

miaoxiong_gavin

浏览: 70225 次
性别:
来自: 山西

最近访客更多访客>>

leimingchao

mengxiang.com

dong717

dongnandeday

博主相关

博客

微博

相册

留言

关于我

文章分类

社区版块

存档分类

参考文章：http://inotgaoshou.iteye.com/blog/1012188
一、xml解析常用的四种方式：
DOM(Document Object Model）文档对象模型;
SAX（Simple APIs for XML）XML简单应用程序接口;
JDOM(java-based Document Object Model）;
DOM4J（Document Object Model for Java）;

================================================================================
推荐用dom4j（大文档，或xml文档较多时候）和 dom （小文档，xml文档较少的时候）
================================================================================

参考文章：http://download.csdn.net/download/shizhending/4067649

二、四种方式的比较：
DOM：性能测试时表现不佳 .W3C的官方标准,允许应用程序对数据和结构做出更改，允许获取和操作文档的任意部分，
但需要加载整个文档，性能差，占内存多，小文件可以，据说超10M才溢出
由于它的遍历能力，DOM解析器常用于XML文档需要频繁的改变的服务中。
SAX：性能表现较好.类似于流媒体特点，分析能够立即开始，而不是等待所有的数据被处理。
只在读取数据时检查数据，不需要保存在内存中。可以在某个条件得到满足时停止解析，
不必解析整个文档。效率和性能较高，能解析大于系统内存的文档。
很难同时访问同一个文档中的多处不同数据，对内存的要求通常会比较低，
适用于大型文档。
DOM4j：DOM4J性能最好，DOM4J是一个非常非常优秀的Java XML API，具有性能优异、功能强大和极端易用使用的特点，
同时它也是一个开放源代码的软件。
JDOM：性能测试时表现不佳， JDOM的目的是成为Java特定文档模型，它简化与XML的交互并且比使用DOM实现更快。

三、使用举例

1.dom4j：

src/person.xml

<?xml version="1.0" encoding="UTF-8"?>
<persons>
	<person id="psn0001" >
		<name>gavin</name>
		<age>18</age>
		<address>
			<country>中国</country>
			<province>北京</province>
			<city>北京</city>
		</address>
		<zipcode>100000</zipcode>
		
	</person>
	<person2 id="psn0002" >
		<name>sophia</name>
		<age>18</age>
		<address>
			<country>中国</country>
			<province>钓鱼岛</province>
			<city>钓鱼岛</city>
		</address>
		<zipcode>100000</zipcode>
	</person2>
</persons>

dom4j读取：

package com.gavin.xmlparse.dom4j;

import java.io.File;
import java.io.InputStream;
import java.io.Reader;
import java.net.URL;
import java.util.Iterator;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.io.DOMReader;
import org.dom4j.io.SAXReader;
import org.xml.sax.InputSource;
/**
 * 用dom4j读取xml信息
 * @author gavin
 */
public class ParseXml {
	/**
	 * dom4j object model representation of a xml document. Note: We use the
	 * interface(!) not its implementation
	 */
	private Document doc;

	/**
	 * Loads a document from a file.
	 * @param aFile    the data source
	 * @throw a org.dom4j.DocumentExcepiton occurs on parsing failure.
	 */
	public void parseWithSAX(File aFile) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(aFile);
	}

	/**
	 * Loads a document from a file.
	 * 
	 * @param aURL
	 *            the data source
	 * @throw a org.dom4j.DocumentExcepiton occurs on parsing failure.
	 */
	public void parseWithSAX(URL aURL) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(aURL);
	}
	/**
	 * Reads a Document from the given InputSource using SAX
	 * @param inputSource
	 * @throws DocumentException
	 */
	public void parseWithSAX(InputSource inputSource) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(inputSource);
	}
	
	/**
	 * Reads a Document from the given stream using SAX
	 * @param in
	 * @throws DocumentException
	 */
	public void parseWithSAX(InputStream in) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(in);
	}
	/**
	 * Reads a Document from the given stream using SAX
	 * @param in
	 * @param systemId
	 * @throws DocumentException
	 */
	public void parseWithSAX(InputStream in, String systemId) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(in,systemId);
	}
	
	/**
	 * Reads a Document from the given Reader using SAX
	 * @param reader
	 * @throws DocumentException
	 */
	public void parseWithSAX(Reader reader) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(reader);
	}
	
	/**
	 * Reads a Document from the given URL or filename using SAX.
	 * @param systemId
	 * @throws DocumentException
	 */
	public void parseWithSAX(String systemId) throws DocumentException {
		SAXReader xmlReader = new SAXReader();
		this.doc = xmlReader.read(systemId);
	}
	
	/**
	 * converts a W3C DOM document into a dom4j document
	 * @param doc
	 */
	public void parseW3CDom2Dom4j(org.w3c.dom.Document doc){
		DOMReader domReader = new DOMReader();
		this.doc = domReader.read(doc);
	}
	

	public Document getDoc() {
		return doc;
	}
	
	/**
	 * 利用xpath读取属性值
	 * @param xpathExpression
	 * @return
	 */
	public String getAttributeValue(String xpathExpression){
		Node node = doc.selectSingleNode(xpathExpression);
		if(node == null){
			return null;
		}
		return node.valueOf("@id");
	}
	
	/**
	 * 利用xpath读取某元素的值
	 * @param xpathExpression
	 * @return
	 */
	public String getElementValue(String xpathExpression){
		Node node = doc.selectSingleNode(xpathExpression);
		if(node == null){
			return null;
		}
		return node.getText();
	}
	
	public static void main(String[] args) throws DocumentException {
		ParseXml parser = new ParseXml();
		File file = new File("D:\\workspace\\javaCoreSkill\\src\\person.xml");
		if(!file.exists()){
			return;
		}
		parser.parseWithSAX(file);
		Document document = parser.getDoc();

        Element root = document.getRootElement();

        // iterate through child elements of root
        for ( Iterator i = root.elementIterator(); i.hasNext(); ) {
            Element element = (Element) i.next();
            String psnId =  element.attributeValue("id");
            System.out.println(psnId);
            // iterate through attributes of root 
            for ( Iterator iter = element.attributeIterator(); iter.hasNext(); ) {
                Attribute attribute = (Attribute) iter.next();
                System.out.println(attribute.getValue());
            }	
        }

        // iterate through child elements of root with element name "person"
        for ( Iterator i = root.elementIterator( "person" ); i.hasNext(); ) {
            Element person = (Element) i.next();
            String psnId =  person.attributeValue("id");
            System.out.println(psnId);
            for(Iterator i2 = person.elementIterator(); i2.hasNext();){
            	Element el = (Element) i2.next();
            	if(el.isTextOnly()){
                	System.out.println(el.getName() + ":" +el.getText());
            	}else{
            		Node node1 = document.selectSingleNode( "/persons/person/address/country" );
            		Node node2 = document.selectSingleNode( "/persons/person/address/city" );
            		Node node3 = document.selectSingleNode( "/persons/person/address/province" );
            		String country = node1.getText();
            		String province = node2.getText();
            		String city = node3.getText();
            		System.out.println("country:"+country+"province:"+province+"city:"+city);
            				
            	}
            }
        }

        
        System.out.println("person2元素的id属性值为："+parser.getAttributeValue("//person2"));
        System.out.println("person2元素的id属性值为："+parser.getElementValue("//person2/address/province"));        
	}

}

参考文档：

xpath tutorial

w3cschool

待续..........

分享到：