dom4j学习总结
一、Dom4j介绍
二、dom4j API
DocumentHelper类中有：
(1)Document document = DocumentHelper.createDocument();//创建一个document对象，通常用于新建一个xml文档
(2)Element element = DocumentHelper.createElement();//创建一个element对象，即创建一个标签
(3)Document document = DocumentHelper.parseText(String xml);//将xml字符串转换成以document为根节点的DOM树
SAXReader类中有：
(1)SAXReader reader = new SAXReader();
(2)Document document = reader.read(new File("1.xml"));//读取并解析1.xml文档，并返回document
Document类中有：
(1)String text = document.asXML(Document); //将一颗DOM树转为XML字符串
(2)Element root = document.getRootElement(); //获得根节点
Element中有：
(1)Element newelem = elem.addElement("child"); //加入名为child的子标签，并返回此element
(2)newelem.addAttribute("name","value"); //标签添加一个属性
(3)newelem.addText("xxxx"); //为标签添加一个标签值
(4)newelem.getText(); //获得标签的标签值
(5)String value = newelem.attributeValue("name");//获得标签的属性值
(6)Iterator iter = newelem.attributeIterator() ;//标签的属性迭代器
(7)List childs = newelem.elements(); //获得标签的全部子元素
(8)Element child = newelem.element("name"); //获得标签的子标签中的多个<name>标签中的第一个元素
(9)List childs = newelem.elements("name"); //获得标签的子标签中的全部<name>标签
(10)newelem.remove(elem); //删除elem标签
XMLWriter类中有：
(1)XMLWriter writer = new XMLWriter(OutputStream out,OutputFormat format);
(2)writer.write(document); //输出document
(3)writer.close(); //关闭XMLWriter流
OutputFormat类中有：
(1)OutputFormat format = OutputFormat.createPrettyFormat();//输出时排版整齐
(2)OutputFormat format = OutputFormat.createCompactFormat();//输出时排版紧实
(3)format.setEncoding("UTF-8"); //设置<?xml ?>中的encoding属性，默认为UTF-8
Attribute类中有：
(1)attr.setValue("value"); //设置属性
(2)String value = attr.getValue();
三、dom4j中的CRUD
1.Create
创建一个文档：
private static void create() throws Exception {
Document document = DocumentHelper.createDocument();
Element person = DocumentHelper.createElement("person");
document.add(person);
Element name = person.addElement("name").addAttribute("a", "x").addText("xiazdong");
Element age = person.addElement("age").addText("20");
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("utf-8");
XMLWriter writer = new XMLWriter(new FileOutputStream("output.xml"),format);
writer.write(document);
writer.close();
}
插入：
private static void insert(Document document) throws Exception {
Element root = document.getRootElement();
List list = root.elements("person");
Element person = (Element)list.get(1);
Element tmpElement = person.addElement("tmpChild");
tmpElement.setText("tmp"); //添加标签值
tmpElement.addAttribute("tmpname", "tmpvalue"); //添加属性
Element tmp2 = DocumentHelper.createElement("tmpChild2");//创建一个element
tmp2.setText("tmp2");
list.add(1,tmp2); //在指定位置添加元素
XMLWriter writer = new XMLWriter(new FileOutputStream("1.xml"));
writer.write(document);
writer.close();
}
2.Read
private static void read(Document document) throws Exception{
Element root = document.getRootElement();
Element person = (Element) root.elements("person").get(1);
String value = person.element("name").getText();
String attri = person.element("name").attributeValue("a");
System.out.println(value);
System.out.println(attri);
}
3.Update
private static void update(Document document) throws Exception{
Element root = document.getRootElement();
Element name = root.element("person").element("name");
name.setText("xiazdong"); //更新标签值
name.attribute("a").setValue("bb"); //更新属性值
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("utf-8");
XMLWriter writer = new XMLWriter(new FileOutputStream("1.xml"),format);
writer.write(document);
writer.close();
}
4.Delete
private static void delete(Document document) throws Exception {
Element root = document.getRootElement();
Element name = root.element("person").element("name");
name.remove(name.attribute("a")); //删除attribute
name.getParent().remove(name); //删除element
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("utf-8");
XMLWriter writer = new XMLWriter(new FileOutputStream("1.xml"),format);
writer.write(document);
writer.close();
}
四、乱码问题
解决方法：
format.setEncoding("UTF-8");
并且用字节流输出
补充：dom4j处理大文件问题（比如100G）
因为dom方法是将整个XML文件读入内存，因此如果文件太大，会出现问题；
我们采用ElementHandler进行解决：每读一个分支节点，就处理一个分支节点。
SAXReader reader = new SAXReader();
reader.addHandler("/subwaycard/card", //当处理<subwaycard>元素下的<card>子元素时
new ElementHandler() {
public void onEnd(ElementPath arg0) { // 处理</card>时
Element card = arg0.getCurrent(); //获得<card>节点
card.getParent().remove(card);
card.detach(); //将dom树上的card节点剪枝
}
public void onStart(ElementPath arg0) {//处理<card>时
}
});
以上函数会在Document document = reader.read(new File("1.xml")); 调用。
以下代码可以实现大文件的删除操作：
package org.xiazdong.xml;
import java.io.File;
import java.io.FileOutputStream;
import java.util.List;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.Element;
import org.dom4j.ElementHandler;
import org.dom4j.ElementPath;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;
public class ElementHandlerTest {
public static void main(String[] args) throws Exception {
SAXReader reader = new SAXReader();
reader.addHandler("/subwaycard/card",
new ElementHandler() {
public void onEnd(ElementPath arg0) {
Element card = arg0.getCurrent();
card.getParent().remove(card);
card.detach();
}
public void onStart(ElementPath arg0) {
}
});
Document document = reader.read(new File("1.xml"));
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("GBK");
XMLWriter writer = new XMLWriter(new FileOutputStream("1.xml"),
format);
writer.write(document);
writer.close();
}
}