dom4j 操作总结

在官网https://dom4j.github.io/下载最新的dom4j的jar包，以及配合xpath解析的http://central.maven.org/maven2/jaxen/jaxen/1.1.6/的jaxen.jar包。

总的来说其实要掌握的是，node和element和attribute的使用，以及一些迭代器配合。下面展示示例代码。具体演示了xml的增删改查的操作。

package Day04;

import java.io.FileOutputStream;
import java.io.OutputStreamWriter;
import java.util.Iterator;
import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;
import org.junit.Test;

public class XmlDemo {
    private void documentToFile(Document doucument,String charsetName) throws Exception {
        FileOutputStream fileWiter = new FileOutputStream("src/book.xml");
        OutputFormat format = OutputFormat.createPrettyPrint();
        XMLWriter writer = new XMLWriter(new OutputStreamWriter(fileWiter,charsetName), format);
        writer.write( doucument );
        writer.close();
    }
    @Test
    public void CreateXml() {
        Document document = DocumentHelper.createDocument();
        Element root = document.addElement("书店");
        Element cateGrayElement1 =  root.addElement("分类").addAttribute("descript", "童话故事");
        Element cateGrayElement2 =  root.addElement("分类").addAttribute("descript", "IT技术刊");

        Element bookElement1 = cateGrayElement1.addElement("书");
        bookElement1.addElement("书名").addText("格林童话");
        bookElement1.addElement("国家").addText("非中");
        Element bookElement2 = cateGrayElement1.addElement("书");
        bookElement2.addElement("书名").addText("愚公移山");
        bookElement2.addElement("国家").addText("中国");
        Element bookElement3 = cateGrayElement2.addElement("书");
        bookElement3.addElement("书名").addText("Tcp/ip 详解");
        bookElement3.addElement("国家").addText("非中");
        Element bookElement4 = cateGrayElement2.addElement("书");
        bookElement4.addElement("书名").addText("c语言入门");
        bookElement4.addElement("国家").addText("中国");
        try {
            documentToFile(document,"UTF-8");
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
    public void treeWalk(Document document) {
        treeWalk(document.getRootElement());
    }

    public void treeWalk(Element element) {
        for (int i = 0, size = element.nodeCount(); i < size; i++) {
            Node node = element.node(i);
            if (node instanceof Element) {
                String name = node.getName();
                switch(name) {
                    case "分类":System.out.println(name+"(descript="+((Element) node).attributeValue("descript")+")");break;
                    case "书":System.out.println("\t"+name);break;
                    default:System.out.println("\t\t"+name+" "+node.getText());
                }
                treeWalk((Element) node);
            }
            else {
                // do something…
            }
        }
    }
    /*
     * 递归输出xml
     */
    @Test
    public void loopXml() throws Exception {
         SAXReader reader = new SAXReader();
         Document document = reader.read("src/book.xml");
         treeWalk(document);
    }

    /**
     * 利用xpath语法 获取属性和节点
     */
    @Test
    public void xpath() throws Exception {
         SAXReader reader = new SAXReader();
         Document document = reader.read("src/book.xml");
         System.out.println("----------------------获取属性---------------------------------");
         List<Node> attrlists = document.selectNodes("//@descript");
         Iterator<Node> attrIt = attrlists.iterator();
         while(attrIt.hasNext()) {
             Attribute attr = (Attribute)attrIt.next();
             System.out.println("分类的"+(attr).getName()+"="+attr.getData());
         }
         System.out.println("----------------------获取节点---------------------------------");
         List<Node> lists = document.selectNodes("//书");
         Iterator<Node> it = lists.iterator();
         while(it.hasNext()) {
             //获取子类值
             Node node = it.next();
             for (Iterator<Element> bookIt = ((Element)node).elementIterator(); bookIt.hasNext();) {
                    Element element = bookIt.next();
                    System.out.println(element.getName()+":"+element.getText());
                    // do something
             }
         }

         System.out.println("-----------------------获取属性的节点--------------------------------");
         List<Node> attrlists1 = document.selectNodes("//分类[@descript=\"童话故事\"]");
         Iterator<Node> attrIt1 = attrlists1.iterator();
         while(attrIt1.hasNext()) {
             //获取子类值
             Element cateElement = (Element)attrIt1.next();
             System.out.println(cateElement.getName()+"attributes:descript="+cateElement.attribute("descript").getValue());
         }
    }

    /**
     * 演示插入,在愚公移山书名后加一个简介(指定位置插入)
     */
    @Test
    public void insert() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read("src/book.xml");
        //找到第二本书//分类[@descript="童话故事"]/书[2]
        Node pNode = document.selectSingleNode("//分类[@descript=\"童话故事\"]/书[2]");
        List<Element> list = ((Element)pNode).elements();
        Element addNode = DocumentHelper.createElement("简介");
        addNode.addText("《愚公移山》是战国时期思想家列子创作的一篇寓言小品文。文章叙述了愚公不畏艰难，坚持不懈，挖山不止，最终感动天帝而将山挪走的故事。");
        list.add(1, addNode);
        System.out.println(list.toArray());
        try {
            documentToFile(document,"UTF-8");
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    /**
     * 修改xml元素
     */
    @Test
    public void update() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read("src/book.xml");
        //找到要修改的节点，比如我现在想给愚公移山这个书名加上书名号
        Node pNode = document.selectSingleNode("//分类[@descript=\"童话故事\"]/书[2]/书名");
        pNode.setText(new StringBuffer().append("《").append(pNode.getText()).append("》").toString());
        try {
            documentToFile(document,"UTF-8");
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }

    /**
     * 删除，刚刚添加的愚公移山的简介
     */
    @Test
    public void delete() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read("src/book.xml");
        //找到要修改的节点，比如我现在想给愚公移山这个书名加上书名号
        Node pNode = document.selectSingleNode("//分类[@descript=\"童话故事\"]/书[2]/简介");
        ((Element)pNode).getParent().remove(pNode);
        try {
            documentToFile(document,"UTF-8");
        } catch (Exception e) {
            // TODO Auto-generated catch block
            e.printStackTrace();
        }
    }
}