解析XML之DOM4J

概述

DOM4J是dom4j.org出品的一个开源XML解析包,Dom4j是一个易用的,开源的库,用于XML,XPath和XSLT它应用于Java平台,采用了Java集合框架并完全支持DOM,SAX和JAXPDOM4J架包下载http://downloads.sourceforge.net/dom4j/dom4j-1.6.1.jarDOM4J在线APIhttp://www.javasoft.ch/dom4j-2.0.0-beta/apidocs/org/dom4j/package-summary.htmljaxen(对XPath的支持)http://dist.codehaus.org/jaxen/distributions/jaxen-1.1.1.zip

Dom4j的主要接口

Node为所有的dom4j中XML节点定义了多态行为Branch为能够包含子节点的节点,如XML元素(Element)和文档(Docuemnts)定义了一个公共的行为Element定义XML 元素Document定义了XML文档DocumentType定义XML DOCTYPE声明Entity定义 XML entityAttribute定义了XML的属性ProcessingInstruction定义 XML 处理指令CharacterData是一个标识接口,标识基于字符的节点,如CDATA,Comment,TextCDATA定义了XML CDATA区域Text定义XML文本节点Comment定义了XML注释的行为

创建XML文件的两种方法

<?xml version="1.0" encoding="UTF-8"?><!DOCTYPE student SYSTEM "dom4j.dtd"><students><student><name>lwc</name><sex>boy</sex><age>20</age></student><student><name>nxj</name><sex>girl</sex><age>18</age></student></students>

转换字符串创建

package com.itlwc;import java.io.File;import java.io.FileWriter;import org.dom4j.Document;import org.dom4j.DocumentHelper;import org.dom4j.io.OutputFormat;import org.dom4j.io.XMLWriter;public class Dom4jTest {public static void main(String[] args) {String xml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>"+"<!DOCTYPE student SYSTEM \"dom4j.dtd\">"+"<students>" +"<student>" +"<name>lwc</name>" +"<sex>boy</sex>" +"<age>20</age>" +"</student>" +"<student>" +"<name>nxj</name>" +"<sex>girl</sex>" +"<age>18</age>" +"</student>" +"</students>";try {//解析XML,得到文档Document document = DocumentHelper.parseText(xml);//创建默认漂亮输出格式OutputFormat format = OutputFormat.createPrettyPrint();File file = new File("output.xml");//将文档输出到文件保存,可指定字符编码,可指定格式化输出XMLWriter output = new XMLWriter(new FileWriter(file), format);output.write(document);output.close();} catch (Exception e) {e.printStackTrace();}}}

Dom4j的方法创建

package com.itlwc;import java.io.File;import java.io.FileWriter;import org.dom4j.Document;import org.dom4j.DocumentHelper;import org.dom4j.Element;import org.dom4j.io.OutputFormat;import org.dom4j.io.XMLWriter;public class Dom4jTest {public static void main(String[] args) {try {// 得到文档实例Document document = DocumentHelper.createDocument();document.addDocType("student", "", "dom4j.dtd");// 创建元素Element studentsElement = document.addElement("students");Element student1Element = studentsElement.addElement("student");Element name1Element = student1Element.addElement("name");name1Element.setText("lwc");Element sex1Element = student1Element.addElement("sex");sex1Element.setText("boy");Element age1Element = student1Element.addElement("age");age1Element.setText("20");Element student2Element = studentsElement.addElement("student");Element name2Element = student2Element.addElement("name");name2Element.setText("nxj");Element sex2Element = student2Element.addElement("sex");sex2Element.setText("girl");Element age2Element = student2Element.addElement("age");age2Element.setText("18");// 创建默认漂亮输出格式OutputFormat format = OutputFormat.createPrettyPrint();File file = new File("output.xml");// 将文档输出到文件保存,可指定字符编码,可指定格式化输出XMLWriter output = new XMLWriter(new FileWriter(file), format);output.write(document);output.close();} catch (Exception e) {e.printStackTrace();}}}

修改XML文件

package com.itlwc;import java.io.File;import java.io.FileWriter;import java.util.Iterator;import java.util.List;import org.dom4j.Document;import org.dom4j.Element;import org.dom4j.io.SAXReader;import org.dom4j.io.XMLWriter;public class Dom4jTest {public static void main(String[] args) {try {SAXReader saxReader = new SAXReader();File file = new File("output.xml");// 定位资源文件并获取document实例Document document = saxReader.read(file);// Document实例的selectNodes方法可以传入xpath,并返回一个List实例List list = document.selectNodes("//students/student");Iterator iter = list.iterator();while (iter.hasNext()) {Element element = (Element) iter.next();Iterator iterName = element.elementIterator("name");while (iterName.hasNext()) {Element nameElement = (Element) iterName.next();if ("lwc".equals(nameElement.getText())) {// 修改文本nameElement.setText("itlwc");}}}// 从新保存文件XMLWriter output = new XMLWriter(new FileWriter(new File("students-modified.xml")));output.write(document);output.close();} catch (Exception e) {e.printStackTrace();}}}/*output.xml<?xml version="1.0" encoding="UTF-8"?><students><student no="1001"><name>lwc</name><sex>boy</sex><age>20</age></student><student no="1002"><name>nxj</name><sex>girl</sex><age>18</age></student></students>students-modified.xml<?xml version="1.0" encoding="UTF-8"?><students><student no="1001"><name>itlwc</name><sex>boy</sex><age>20</age></student><student no="1002"><name>nxj</name><sex>girl</sex><age>18</age></student></students>*/

遍历XML文件

<?xml version="1.0" encoding="UTF-8"?><students><student no="1001"><name>lwc</name><sex>boy</sex><age>20</age></student><student no="1002"><name>nxj</name><sex>girl</sex><age>18</age></student></students> 

使用迭代遍历

package com.itlwc;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 Dom4jTest {public static void main(String[] args) {try {SAXReader saxReader = new SAXReader();File file = new File("output.xml");// 定位资源文件并获取document实例Document document = saxReader.read(file);// 获取根元素studentsElement root = document.getRootElement();System.out.println(root.getName());// 枚举根节点下所有子节点studentIterator iteStudent = root.elementIterator();while (iteStudent.hasNext()) {Element elementStudent = (Element) iteStudent.next();System.out.println(elementStudent.getName());// 枚举根节点下所有子节点student的子节点Iterator iteSonNode = elementStudent.elementIterator();while (iteSonNode.hasNext()) {Element elementSon = (Element) iteSonNode.next();System.out.println(elementSon.getName() + ":"+ elementSon.getText());}// 枚举根节点下所有子节点student的属性Iterator iteSonAttribute = elementStudent.attributeIterator();while (iteSonAttribute.hasNext()) {Attribute attribute = (Attribute) iteSonAttribute.next();System.out.println(attribute.getName() + ":"+ attribute.getData());}}} catch (Exception e) {e.printStackTrace();}}}/*打印结果:studentsstudentname:lwcsex:boyage:20no:1001studentname:nxjsex:girlage:18no:1002*/

使用观察者模式遍历

Visitor是GOF设计模式之一,其主要原理就是两种类互相保有对方的引用,并且一种作为Visitor去访问许多VisitableDOM4J中的Visitor模式只需要自定一个类实现Visitor接口即可public class MyVisitor extends VisitorSupport {    public void visit(Element element) {       System.out.println(element.getName());    }     public void visit(Attribute attr) {       System.out.println(attr.getName());    }}调用:root.accept(new MyVisitor())Visitor接口提供多种Visit()的重载,根据XML不同的对象,将采用不同的方式来访问上面是给出的Element和Attribute的简单实现,一般比较常用的就是这两个VisitorSupport是DOM4J提供的默认适配器,Visitor接口的Default Adapter模式,这个模式给出了各种visit(*)的空实现,以便简化代码注意,这个Visitor是自动遍历所有子节点的,如果是root.accept(MyVisitor),将遍历子节点

案例

package com.itlwc;import java.io.File;import org.dom4j.Attribute;import org.dom4j.Document;import org.dom4j.Element;import org.dom4j.ProcessingInstruction;import org.dom4j.VisitorSupport;import org.dom4j.io.SAXReader;/** * 定义自己的访问者类 */class MyVisitor extends VisitorSupport {// 对于属性节点,打印属性的名字和值public void visit(Attribute node) {System.out.println("attribute : " + node.getName() + " = "+ node.getValue());}// 对于处理指令节点,打印处理指令目标和数据public void visit(ProcessingInstruction node) {System.out.println("PI : " + node.getTarget() + " " + node.getText());}// 对于元素节点,判断是否只包含文本内容,如是,则打印标记的名字和 元素的内容,如果不是,则只打印标记的名字public void visit(Element node) {if (node.isTextOnly()) {System.out.println("element : " + node.getName() + " = "+ node.getText());} else {System.out.println("-----" + node.getName() + "-----");}}}public class Dom4jTest {public static void main(String[] args) {try {SAXReader saxReader = new SAXReader();File file = new File("output.xml");// 定位资源文件并获取document实例Document document = saxReader.read(file);document.accept(new MyVisitor());} catch (Exception e) {e.printStackTrace();}}}/* 打印结果:     -----students----------student-----attribute : no = 1001element : name = lwcelement : sex = boyelement : age = 20-----student-----attribute : no = 1002element : name = nxjelement : sex = girlelement : age = 18*/