使用dom4j解析xml字符串

package dom4j;
import java.util.Iterator;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;
/**
* 使用dom4j处理xml字符串；使用迭代器可以搞定一切；
* 附件是转成base64的字符串；便于webservice基于soap的传输；
* @author shuaisweet
*/
public class InfoXML
{
public void doInfoXML(String infoXML)
{
  System.out.println(infoXML);
  SAXReader reader = new SAXReader();
  Document document;
  try
  {
   document = DocumentHelper.parseText(infoXML);
   Element root = document.getRootElement();
   //信息条数；
   int info_count=root.elements().size();
   Iterator it =root.elements().iterator();
   while(it.hasNext())
   {
    Element info=(Element) it.next();
    System.out.println(info.elementText("info_title"));
    System.out.println(info.elementText("index_code"));
    System.out.println(info.elementText("content"));
    //在此处理信息
    System.out.println("附件开始");
     Element adjuncts= info.element("adjuncts");
     Iterator adjs=adjuncts.elements().iterator();
     while(adjs.hasNext())
     {
      Element adj=(Element) adjs.next();
      System.out.println(adj.elementText("file_name"));
      System.out.println(adj.elementText("adjunct_content"));
      //在此处理附件；
     }
    System.out.println("==============================");
   }
  } catch (DocumentException e1)
  {
   e1.printStackTrace();
  }
}
public static void main(String[] args)
{
  InfoXML xml=new InfoXML();
  String infoXML="<?xml version=\"1.0\" encoding=\"UTF-8\"?>"+
  "<infos>"+
   "<info>"+
    "<info_title><![CDATA[aaaaaaaaaa]]></info_title>"+
    "<index_code><![CDATA[bbbbbbbbbb]]></index_code>"+
    "<content><![CDATA[cccccccccc]]></content>"+
    "<adjuncts>"+      
    "</adjuncts>"+
   "</info>"+
   "<info>"+
    "<info_title><![CDATA[11111111111111]]></info_title>"+
    "<index_code><![CDATA[2222222222222]]></index_code>"+
    "<content><![CDATA[33333333333333]]></content>"+
    "<adjuncts>"+
     "<adjunct>"+
      "<file_name><![CDATA[44444444444]]></file_name>"+
      "<adjunct_content><![CDATA[5555555555555]]></adjunct_content>"+
     "</adjunct>"+
    "</adjuncts>"+
   "</info>"+
   "<info>"+
    "<info_title><![CDATA[xxxxxxxxxxxxxxxxx]]></info_title>"+
    "<index_code><![CDATA[yyyyyyyyyyyyyyyy]]></index_code>"+
    "<content><![CDATA[zzzzzzzzzzzzzzzzzz]]></content>"+
    "<adjuncts>"+
     "<adjunct>"+
      "<file_name><![CDATA[vvvvvvvvvvvvv]]></file_name>"+
      "<adjunct_content><![CDATA[rrrrrrrrrrrrrrrr]]></adjunct_content>"+
     "</adjunct>"+
     "<adjunct>"+
      "<file_name><![CDATA[ggggggggggggggggggggggg]]></file_name>"+
      "<adjunct_content><![CDATA[llllllllllllllllll]]></adjunct_content>"+
    "</adjunct>"+
    "</adjuncts>"+
   "</info>"+
  "</infos>";
  xml.doInfoXML(infoXML);
}
}

评论

2 楼 C_J 2009-04-19  

dom是把inputsource 作为参数转换为document

看到4jdom 的 document = DocumentHelper.parseText(infoXML);

不知道是不是也是把xml全部加载进来？
今天还在看dom

4jdom还没来得及，看到楼主的帖子 忍不住想问问了。

1 楼 yesorno01 2009-04-18  

如果 xml中少了一层 "<infos>"+
   "<info>"+
呢？

只有"<infos>" 该如何修改？