dom4j解析XML

dom4j解析XML

dom4j 是一种解析 XML 文档的开放源代码 XML 框架,与 W3C DOM API 相比,使用 dom4j 所包含的解析器的好处是 dom4j 拥有本地的 XPath 支持.DOM 解析器不支持使用 XPath 选择节点.

  该解析器可以从 http://dom4j.org/ 获取.
java 代码

java 代码

  package  com.nikee.dom4j;
 import  org.dom4j.Document;
 import  org.dom4j.DocumentHelper;
 import  org.dom4j.Element;
 import  org.dom4j.io.OutputFormat;
 import  org.dom4j.io.XMLWriter;
 import  java.io.*;

 public   class  XmlDom4J{
   public   void  generateDocument(){
    //使用 DocumentHelper 类创建一个文档实例。 DocumentHelper 是生成 XML 文档节点的 dom4j API 工厂类
   Document document = DocumentHelper.createDocument();

    //使用 addElement()方法创建根元素catalog , addElement()用于向 XML 文档中增加元素
   Element catalogElement = document.addElement( "catalog" );

    //在 catalog 元素中使用 addComment() 方法添加注释"An XML catalog"
   catalogElement.addComment( "An XML Catalog" );

    //在 catalog 元素中使用 addProcessingInstruction() 方法增加一个处理指令
   catalogElement.addProcessingInstruction( "target" , "text" );

    //在 catalog 元素中使用 addElement() 方法增加 journal 元素
   Element journalElement = catalogElement.addElement( "journal" );
    //使用 addAttribute() 方法向 journal 元素添加 title 和 publisher 属性
   journalElement.addAttribute( "title" ,  "XML Zone" );
   journalElement.addAttribute( "publisher" ,  "IBM developerWorks" );


   Element articleElement=journalElement.addElement( "article" );
   articleElement.addAttribute( "level" ,  "Intermediate" );
   articleElement.addAttribute( "date" ,  "December-2001" );

   Element titleElement=articleElement.addElement( "title" );
   titleElement.setText( "Java configuration with XML Schema" );

   Element authorElement=articleElement.addElement( "author" );
   Element firstNameElement=authorElement.addElement( "firstname" );
   firstNameElement.setText( "Marcello" );
   Element lastNameElement=authorElement.addElement( "lastname" );
   lastNameElement.setText( "Vitaletti" );

    //可以使用 addDocType() 方法添加文档类型说明
    //这样就向 XML 文档中增加文档类型说明：
   document.addDocType( "catalog" , "nikee" , "file://c:/Dtds/catalog.dtd" );
    try {
     //XMLWriter output = new XMLWriter(new FileWriter( new File("D:/eclipse3.2/workspace/WebServices/src/com/nikee/dom4j/catalog.xml")));
     FileOutputStream fos= new  FileOutputStream( "D:/eclipse3.2/workspace/WebServices/src/com/nikee/dom4j/catalog.xml" );
        OutputFormat of= new  OutputFormat( "    " ,  true );
        XMLWriter xw= new  XMLWriter(fos, of);
        xw.write( document );
        xw.close();
   }
    catch (IOException e)
   {
    System.out.println(e.getMessage());
   }
  }

   public   static   void  main(String[] argv){
   XmlDom4J dom4j= new  XmlDom4J();
   dom4j.generateDocument();
  }
 }

xml 代码

  <!--sp--> xml  version = "1.0"   encoding = "UTF-8" ?>
 <!--CTYPE catalog PUBLIC "nikee" "file://c:/Dtds/catalog.dtd"</sp--> >

   < catalog >
      <!--An XML Catalog--><!--sp--> target text ?>

      < journal   title = "XML Zone"   publisher = "IBM developerWorks" >
       < article   level = "Intermediate"   date = "December-2001" >
           < title > Java configuration with XML Schematitle >
           < author >
               < firstname > Marcellofirstname >
               < lastname > Vitalettilastname >
          author >
      article >
     journal >
  catalog >

XmlDom4J.java 用于创建 XML 文档 catalog.xml

java 代码

java 代码

package com.nikee.dom4j;

import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.Attribute;
import java.util.List;
import java.util.Iterator;

import org.dom4j.io.OutputFormat;
import org.dom4j.io.XMLWriter;
import java.io.*;

import org.dom4j.DocumentException;
import org.dom4j.io.SAXReader;

public class Dom4Jparser{
    public Dom4Jparser(){
        //construction
    }

    public void modifyDocument(File inputXml){
        try{
            //使用 SAXReader 解析 XML 文档 catalog.xml
            SAXReader saxReader = new SAXReader();
            Document document = saxReader.read(inputXml);

            //使用 XPath 表达式从 article 元素中获得 level 节点列表。如果 level 属性值是"Intermediate"则改为"Introductory"
            List list = document.selectNodes("//article/@level");
            Iterator iter=list.iterator();
            while(iter.hasNext()){
                Attribute attribute=(Attribute)iter.next();
                if(attribute.getValue().equals("Intermediate"))
                    attribute.setValue("Introductory");
            }

            list = document.selectNodes("//article/@date" );
            iter=list.iterator();
            while(iter.hasNext()){
                Attribute attribute=(Attribute)iter.next();
                if(attribute.getValue().equals("December-2001"))
                    attribute.setValue("October-2002");
            }

            //获取 article 元素列表，从 article 元素中的 title 元素得到一个迭代器，并修改 title 元素的文本
            list = document.selectNodes("//article" );
            iter=list.iterator();
            while(iter.hasNext()){
                Element element=(Element)iter.next();
                Iterator iterator=element.elementIterator("title");
                while(iterator.hasNext()){
                    Element titleElement=(Element)iterator.next();
                    if(titleElement.getText().equals("Java configuration with XML Schema"))
                        titleElement.setText("Create flexible and extensible XML schema");
                }
            }


            list = document.selectNodes("//article/author" );
            iter=list.iterator();
            while(iter.hasNext()){
                Element element=(Element)iter.next();
                Iterator iterator=element.elementIterator("firstname");
                while(iterator.hasNext()){
                    Element firstNameElement=(Element)iterator.next();
                    if(firstNameElement.getText().equals("Marcello"))
                        firstNameElement.setText("Ayesha");
                }
            }

            list = document.selectNodes("//article/author" );
            iter=list.iterator();
            while(iter.hasNext()){
                Element element=(Element)iter.next();
                Iterator iterator=element.elementIterator("lastname");
                while(iterator.hasNext()){
                    Element lastNameElement=(Element)iterator.next();
                    if(lastNameElement.getText().equals("Vitaletti"))
                        lastNameElement.setText("Malik");
                }
            }

            FileOutputStream fos=new FileOutputStream("D:/eclipse3.2/workspace/WebServices/src/com/nikee/dom4j/catalog-modified.xml");
            OutputFormat of=new OutputFormat("   ",true);
            XMLWriter xw=new XMLWriter(fos, of);
            xw.write( document );
            xw.close();
        }
        catch(DocumentException e)
        {
            e.printStackTrace();
        }
        catch(IOException e){
            e.printStackTrace();
        }
    }

    public static void main(String argv[]){
        Dom4Jparser dom4jParser=new Dom4Jparser();
        dom4jParser.modifyDocument(new File("D:/eclipse3.2/workspace/WebServices/src/com/nikee/dom4j/catalog.xml"));
    }
}

xml 代码

xml 代码

Dom4Jparser.java用于修改 XML 文档 catalog.xml为catalog-modified.xml

问题总结:

1.当catalog.xml有<!--CTYPE catalog PUBLIC "nikee" "file://c:/Dtds/catalog.dt-->这一句,Dom4Jparser.java修改 XML 文档 catalog.xml为catalog-modified.xml时,发生异常org.dom4j.DocumentException: c Nested exception: c.

原因:我自己没有此 file://c:/Dtds/catalog.dtd .

解决办法:删掉此行.

2.除了加入dom4j.jar包外,必须加入jaxen.jar包,否则会发生异常.jaxen包可在 http://jaxen.org/ 下载.