dom4j中XPath用法

大家经常运用DOM4J操作XML文档,如果XML文档存在namespace的话,读写XML经常不工作。下面是一个简单的例子，例子中需要用到的两个xml文件：a.xml与book.xml见附件。代码如下：

import java.io.FileInputStream;
import java.io.InputStream;
import java.util.HashMap;
import java.util.List;

import javax.xml.parsers.DocumentBuilder;   
import javax.xml.parsers.DocumentBuilderFactory;   
import javax.xml.xpath.XPath;   
import javax.xml.xpath.XPathConstants;   
import javax.xml.xpath.XPathExpression;   
import javax.xml.xpath.XPathFactory;   
  
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.io.SAXReader;

import org.w3c.dom.Document;
import org.w3c.dom.NodeList;

  
public class XpathTest {   
		/**
	     * 已知命名空间，获得该命名空间下节点
	     * @throws Exception
	     */
	    public static void test1() throws Exception {
	     	SAXReader reader = new SAXReader();
	     	String uri = "http://WebXml.com.cn/";//命名空间
	     	HashMap map = new HashMap();//将uri存入map中
	     	map.put("xx", uri);
	     	reader.getDocumentFactory().setXPathNamespaceURIs(map);
	     	
	     	InputStream is = new FileInputStream("src/a.xml");
				org.dom4j.Document document = reader.read(is);
				
	     	org.dom4j.XPath xpath = DocumentHelper.createXPath("//xx:string");
	     	
	     	List list = xpath.selectNodes(document);//等价List list = document.selectNodes("//xx:string");
	     	for(int i=0; i<list.size(); i++){
	     		Node node = (Node)list.get(i);//转型为Node
	     		System.out.println("hah====="+node.getText());
	     		
	     		Element e = (Element)list.get(i);//转型为Element
	     		System.out.println(e.getText());
	     	}
	    }
	
        /**
         * 先通过document获得命名空间，再获得该命名空间下节点
         * @throws Exception
         */
        public static void test2()  throws Exception {
        	SAXReader reader = new SAXReader();
        	InputStream is = new FileInputStream("src/a.xml");
			org.dom4j.Document document = reader.read(is);
			
			//获得节点的命名空间
        	String uri = document.getRootElement().element("Body")
					.element("getWeatherbyCityNameResponse").getNamespaceURI();
        	//将uri存入map中
        	HashMap map = new HashMap();
        	map.put("xx", uri);
        	
        	org.dom4j.XPath xpath = DocumentHelper.createXPath("//xx:string");
        	xpath.setNamespaceURIs(map);
        	
        	List list = xpath.selectNodes(document);
        	for(int i=0; i<list.size(); i++){
        		Node node = (Node)list.get(i);//转型为Node
        		System.out.println("hah====="+node.getText());
        		
        		Element e = (Element)list.get(i);//转型为Element
        		System.out.println(e.getText());
        	}
       }
       
       /**
        * 运用jdk中自带包javax.xml.xpath包
        * @throws Exception
        */
       public static void test3()  throws Exception {
       	//将XML文档加载到DOM Document对象中
           DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();   
           factory.setNamespaceAware(true); // never forget this!   
           DocumentBuilder builder = factory.newDocumentBuilder();   
           org.w3c.dom.Document doc = builder.parse("src/books.xml");   
           //创建 XPathFactory
           XPathFactory pathFactory = XPathFactory.newInstance();   
           //使用XPathFactory工厂创建 XPath 对象
           XPath xpath = pathFactory.newXPath();   
           //使用XPath对象编译XPath表达式
           XPathExpression pathExpression = xpath   
                           .compile("//book[author='TEST']/title/text()");   
           //计算 XPath 表达式得到结果
           Object result = pathExpression.evaluate(doc, XPathConstants.NODESET);   
           //节点集node-set转化为NodeList
           //将结果强制转化成 DOM NodeList 
           org.w3c.dom.NodeList nodes = (NodeList) result;   
           for (int i = 0; i < nodes.getLength(); i++) {   
                   System.out.println(nodes.item(i).getNodeValue());   
           }
           //查找所有图书的 XPath 查询非常简单:
           //book[author="TEST"]   
           //book代表节点的名称,author属性的名称,后面是要查询的值  
           
           //为了找出这些图书的标题(title),只要增加一步,表达式就变成了:
           //book[author="TEST"]/title   
           //title代表要取元素的名称  
           
           //最后,真正需要的是 title 元素的文本节点内容.这就要求再增加一步,完整的表达式就是:
           //book[author="TEST"]/title/text()   
           //text()该节点的内容  
       }
       
       public static void main(String[] args) throws Exception{
    	   test1();
    	   //test2();
    	   //test3();
       }   
}

以下是几个XPath讲解的资料：
dom4j中XPath的使用： http://nieli.iteye.com/blog/540720
xpath的数据和节点类型以及XPath中节点匹配的基本方法： http://www.iteye.com/topic/258109
编写简单的XPath程序： http://www.iteye.com/topic/153252