Dom4j的简单使用

要使用dom4j读写XML文档,需要先下载dom4j包,dom4j官方网站在 http://www.dom4j.org/
目前最新dom4j包下载地址:http://nchc.dl.sourceforge.net/sourceforge/dom4j/dom4j-1.6.1.zip

解开后有两个包,仅操作XML文档的话把dom4j-1.6.1.jar加入工程就可以了,如果需要使用XPath的话还需要加入包jaxen-1.1-beta-7.jar.

以下是相关操作:

一.Document对象相关

1.读取XML文件,获得document对象.
            SAXReader reader = new SAXReader();
            Document  document = reader.read(new File("input.xml"));

2.解析XML形式的文本,得到document对象.
            String text = "<members></members>";
            Document document = DocumentHelper.parseText(text);
3.主动创建document对象.
            Document document = DocumentHelper.createDocument();
            Element root = document.addElement("members");// 创建根节点
二.节点相关

1.获取文档的根节点.
Element rootElm = document.getRootElement();
2.取得root节点下子节点名字为member的节点.
Element memberElm=root.element("member");// "member"是节点名
3.取得节点的文字
String text=memberElm.getText();
也可以用:
String text=root.elementText("name");这个是取得根节点下的name字节点的文字.

4.取得某节点下名为"member"的所有子节点并进行遍历.
List nodes = rootElm.elements("member");

for (Iterator it = nodes.iterator(); it.hasNext();) {
   Element elm = (Element) it.next();
   // do something
}
5.对某节点下的所有子节点进行遍历.
            for(Iterator it=root.elementIterator();it.hasNext();){
                Element element = (Element) it.next();
                // do something
            }
6.在某节点下添加子节点.
Element ageElm = newMemberElm.addElement("age");
7.设置节点文字.
ageElm.setText("29");
8.删除某节点.
parentElm.remove(childElm);// childElm是待删除的节点,parentElm是其父节点
三.属性相关.
1.取得某节点下的某属性
            Element root=document.getRootElement();    
            Attribute attribute=root.attribute("size");// 属性名name
2.取得属性的文字
            String text=attribute.getText();
也可以用:
String text2=root.element("name").attributeValue("firstname");这个是取得根节点下name字节点的属性firstname的值.

3.遍历某节点的所有属性
            Element root=document.getRootElement();    
            for(Iterator it=root.attributeIterator();it.hasNext();){
                Attribute attribute = (Attribute) it.next();
                String text=attribute.getText();
                System.out.println(text);
            }
4.设置某节点的属性和文字.
newMemberElm.addAttribute("name", "sitinspring");
5.设置属性的文字
            Attribute attribute=root.attribute("name");
            attribute.setText("sitinspring");
6.删除某属性
            Attribute attribute=root.attribute("size");// 属性名name
            root.remove(attribute);
四.将文档写入XML文件.
1.文档中全为英文,不设置编码,直接写入的形式.
XMLWriter writer = new XMLWriter(new FileWriter("output.xml"));
writer.write(document);
writer.close();
2.文档中含有中文,设置编码格式写入的形式.
            OutputFormat format = OutputFormat.createPrettyPrint();
            format.setEncoding("GBK");    // 指定XML编码        
            XMLWriter writer = new XMLWriter(new FileWriter("output.xml"),format);
            
            writer.write(document);
            writer.close();
五.字符串与XML的转换
1.将字符串转化为XML
String text = "<members> <member>sitinspring</member> </members>";
Document document = DocumentHelper.parseText(text);
2.将文档或节点的XML转化为字符串.
            SAXReader reader = new SAXReader();
            Document  document = reader.read(new File("input.xml"));            
            Element root=document.getRootElement();                
            String docXmlText=document.asXML();
            String rootXmlText=root.asXML();
            Element memberElm=root.element("member");
            String memberXmlText=memberElm.asXML();
六.使用XPath快速找到节点.
读取的XML文档示例
<?xml version="1.0" encoding="UTF-8"?>
<projectDescription>
  <name>MemberManagement</name>
  <comment></comment>
  <projects>
    <project>PRJ1</project>
    <project>PRJ2</project>
    <project>PRJ3</project>
    <project>PRJ4</project>
  </projects>
  <buildSpec>
    <buildCommand>
      <name>org.eclipse.jdt.core.javabuilder</name>
      <arguments>
      </arguments>
    </buildCommand>
  </buildSpec>
  <natures>
    <nature>org.eclipse.jdt.core.javanature</nature>
  </natures>
</projectDescription>

使用XPath快速找到节点project.
 public static void main(String[] args){
    SAXReader reader = new SAXReader();
    
    try{
      Document  doc = reader.read(new File("sample.xml"));
      
      List projects=doc.selectNodes("/projectDescription/projects/project");
      
      Iterator it=projects.iterator();
      
      while(it.hasNext()){
        Element elm=(Element)it.next();       
        System.out.println(elm.getText());
      }
      
    }
    catch(Exception ex){
       ex.printStackTrace();
    }

package com.ctrip.search.dom;

import java.io.File;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

public class ElementDemo {

	public static void main(String[] args) throws Exception {
		Document doc = getDocument();
        //testElementApi(doc);
		Element root = doc.getRootElement();
		StringBuilder result = printElement(root);
		System.out.println(result.toString());
	}
	
	public static Document getDocument() throws Exception{
		SAXReader reader = new SAXReader();
		//采用文件的方式读取文件
//        File file = new File("D:/lqteng/Dom4jDemo/file/request.xml");
//        Document doc = reader.read(file); 
		//以类加载的路径为根路径，所以这个地方要写成绝对路径
        InputStream in = ElementDemo.class.getResourceAsStream("/request.xml");
        //这个是采用类加载器的方式读取，只要写出类加载器要加载的文件名称即可
//        InputStream in2 = ElementDemo.class.getClassLoader().getResourceAsStream("request.xml");
        Document doc = reader.read(in);
        
        return doc;
	}
	
	public static void testElementApi(Document doc) throws Exception{
        //获取这个文档的根元素
        Element requestsNode = doc.getRootElement();
        List<Element> requestNodes = new ArrayList<Element>();
        
        if("Requests".equalsIgnoreCase(requestsNode.getName())){
//        	 List<Element> subNodes = requestsNode.elements();
//        	 for(Element sub : subNodes){
//        		 if("Request".equalsIgnoreCase(sub.getName())){
//        	         requestNodes.add(sub);		 
//        		 }
//        	 }
        	Iterator<Element> subNodes = (Iterator<Element>)requestsNode.elementIterator();
        	for(;subNodes.hasNext();){
        		Element sub = subNodes.next();
       		    if("Request".equalsIgnoreCase(sub.getName())){
   	                requestNodes.add(sub);		 
       		 	}
        	}
        }else if("Request".equalsIgnoreCase(requestsNode.getName())){
        	requestNodes.add(requestsNode);
        }
        
        if(requestNodes != null && requestNodes.size() > 0){
        	Element firstRequest = requestNodes.get(0);
        	Element statNode = firstRequest.element("stat");
            if(statNode.isTextOnly()){
            	System.out.println("statNode text:"+statNode.getTextTrim());
            }else{
            	List<Element> statNodes = firstRequest.elements("query");
            	for(Element statE : statNodes){
            		System.out.println(statE.getName());
            		//如果没有子元素那么就为true
            		System.out.println(statE.isTextOnly());
            	}
            }
            
            //打印出所有sort元素下的name和asc，如果为内容为公式则取出公式
            //获取firstRequest元素下的sort元素，如果firstRequest元素下面有多个sort元素，那么就应该使用elements("sort")
            Element sortE = firstRequest.element("sort");
            //获取sortE元素的所有子元素
            List<Element> sortSubEs = sortE.elements();
            for(Element sortSubE : sortSubEs){
            	String name = sortSubE.getName();
//            	String asc = sortSubE.getTextTrim();
            	//获取sortE元素下的name元素的text
            	String asc = sortE.elementTextTrim(name);
            	Pattern pattern = Pattern.compile("\\$\\{(([a-z]|[A-Z]|\\.|\\s)+)\\}");
            	Matcher matcher = pattern.matcher(asc);
            	if(matcher.find()){
            		name = asc;
            		//获取sortSubE元素的order属性的值
            		asc = sortSubE.attributeValue("order");
            	}
                System.out.println("name: "+ name +",asc: "+("desc".equalsIgnoreCase(asc) ? false : true));
            }
        }
	}
	
	public static StringBuilder printElement(Element e){
		if(e == null){
			return new StringBuilder("");
		}
		
		StringBuilder str = new StringBuilder();
		str.append("<"+e.getName());
	    Iterator attrIterator = e.attributeIterator();
	    for(;attrIterator.hasNext();){
	    	Attribute attr = (Attribute)attrIterator.next();
	    	str.append(" "+attr.getName()+"='"+ attr.getValue() +"'");
	    }
	    str.append(">");
	    
	    if(e.isTextOnly()){
	    	str.append(e.getText());
	    }else{
	    	List<Element> subs = e.elements();
	    	for(Element sub : subs){
	    		str.append("\n");
	    		str.append(printElement(sub));
	    	}
	    	str.append("\n");
	    }
	    str.append("</"+ e.getName() +">");
		
		
		return str;
	}
}