使用dom4j生成和解析XML文档

虽然Java中已经有了Dom和Sax这两种标准解析方式
但其操作起来并不轻松，对于我这么一个初学者来说，其中部分代码是活生生的恶心
为此，伟大的第三方开发组开发出了Jdom和Dom4j等工具
鉴于目前的趋势，我们这里来讲讲Dom4j的基本用法，不涉及递归等复杂操作
Dom4j的用法很多，官网上的示例有那么点儿晦涩，这里就不写了
首先我们需要出创建一个xml文档，然后才能对其解析

参考资料：
http://developer.51cto.com/art/200903/117512.htm
http://www.jb51.net/article/42323.htm

<?xml version="1.0" encoding="UTF-8"?>
<books> 
   <book id="001"> 
      <title>Harry Potter</title> 
      <author>J K. Rowling</author> 
   </book> 
   <book id="002"> 
      <title>Learning XML</title> 
      <author>Erik T. Ray</author> 
   </book> 
</books> 

示例一：用List列表的方式来解析xml

import java.io.File;
import java.util.List;

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

public class Demo {
    public static void main(String[] args) throws Exception {
        SAXReader reader = new SAXReader();
        File file = new File("books.xml");
        Document document = reader.read(file);
        //获取根目录
        Element root = document.getRootElement();
        System.out.println("根目录是:"+root.getName());

        List<Element> childElements = root.elements();
        for (Element child : childElements) {
            // 未知属性名情况下
            List<Attribute> attributeList = child.attributes();
            for (Attribute attr : attributeList) {
                System.out.println(attr.getName() + ": " + attr.getValue());
            }

            //已知属性名情况下
            // System.out.println("id: " + child.attributeValue("id"));

            // 未知子元素名情况下
            List<Element> elementList = child.elements();
            for (Element ele : elementList) {
                System.out.println(ele.getName() + ": " + ele.getText());
            }
            System.out.println();

            // 已知子元素名的情况下
//          System.out.println("title: " + child.elementText("title"));
//          System.out.println("author: " + child.elementText("author"));

            // 这行是为了格式化美观而存在
            System.out.println();
        }
    }
}

示例二：使用Iterator迭代器的方式来解析xml

import java.io.File;
import java.util.Iterator;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.Element;
import org.dom4j.io.SAXReader;

public class Demo1 {
    public static void main(String[] args) throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read(new File("books.xml"));
        Element root = document.getRootElement();

        Iterator it = root.elementIterator();
        while (it.hasNext()) {
            Element element = (Element) it.next();

            // 未知属性名称情况下
            Iterator attrIt = element.attributeIterator(); 
            while(attrIt.hasNext()) {
                Attribute a = (Attribute) attrIt.next();
                System.out.println(a.getValue()); 
            }


            // 已知属性名称情况下
//          System.out.println("id: " + element.attributeValue("id"));

            // 未知元素名情况下
            Iterator eleIt = element.elementIterator(); 
            while(eleIt.hasNext()) { 
                Element e = (Element) eleIt.next();
                System.out.println(e.getName() + ": " + e.getText()); 
            }
            System.out.println();


            // 已知元素名情况下
//          System.out.println("title: " + element.elementText("title"));
//          System.out.println("author: " + element.elementText("author"));

            System.out.println();
        }
    }
}

运行结果：

根目录是:books
id: 001
title: Harry Potter
author: J K. Rowling


id: 002
title: Learning XML
author: Erik T. Ray

示例三：创建xml文档并输出到文件

import java.io.File;
import java.io.FileOutputStream;
import org.dom4j.Document;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.XMLWriter;

public class CreateXML {
    public static void main(String[] args) throws Exception {
        Document doc = DocumentHelper.createDocument();
        // 增加根节点
        Element books = doc.addElement("books");
        // 增加子元素
        Element book1 = books.addElement("book");
        Element title1 = book1.addElement("title");
        Element author1 = book1.addElement("author");

        Element book2 = books.addElement("book");
        Element title2 = book2.addElement("title");
        Element author2 = book2.addElement("author");

        // 为子节点添加属性
        book1.addAttribute("id", "001");
        // 为元素添加内容
        title1.setText("Harry Potter");
        author1.setText("J K. Rowling");

        book2.addAttribute("id", "002");
        title2.setText("Learning XML");
        author2.setText("Erik T. Ray");

        // 实例化输出格式对象
        OutputFormat format = OutputFormat.createPrettyPrint();
        // 设置输出编码
        format.setEncoding("UTF-8");
        // 创建需要写入的File对象
        File file = new File("newBooks.xml");
        // 生成XMLWriter对象，构造函数中的参数为需要输出的文件流和格式
        XMLWriter writer = new XMLWriter(new FileOutputStream(file), format);
        // 开始写入，write方法中包含上面创建的Document对象
        writer.write(doc);
    }
}

运行结果:

<?xml version="1.0" encoding="UTF-8"?>

<books>
  <book id="001">
    <title>Harry Potter</title>
    <author>J K. Rowling</author>
  </book>
  <book id="002">
    <title>Learning XML</title>
    <author>Erik T. Ray</author>
  </book>
</books>