使用Dom4j操作XML

Dom4j也可以很方便完成XML文档的创建、元素的修改、文档的查询遍历等，但dom4j稍比jdom复杂一点，不过在大片文档的情况下dom4j的性能要不jdom好。

# 准备

首先，提供相关的jar包

Dom4j jar包下载：

http://sourceforge.net/projects/dom4j/files/dom4j-2.0.0-ALPHA-2/

jaxen jar下载：

http://repo1.maven.org/maven2/jaxen/jaxen/1.1.1/jaxen-1.1.1.jar

和dom4j依赖或相关的jar：

http://dom4j.sourceforge.net/dependencies.html

Junit-jar下载：

http://ebr.springsource.com/repository/app/bundle/version/download?name=com.springsource.org.junit&version=4.8.1&type=binary

 

其次，准备测试案例的部分代码：

package com.hoo.test;

import java.io.File;
import java.util.Iterator;
import java.util.List;
import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.Node;
import org.dom4j.QName;
import org.dom4j.dom.DOMAttribute;
import org.dom4j.io.SAXReader;
import org.dom4j.tree.BaseElement;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

/**
 * <b>function:</b> 使用Dom4j操作XML
 * @author hoojo
 * @createDate 2011-8-5 下午06:15:40
 * @file DocumentTest.java
 * @package com.hoo.test
 * @project Dom4jTest
 * @blog http://blog.csdn.net/IBM_hoojo
 * @email hoojo_@126.com
 * @version 1.0
 */
public class DocumentTest {

    private SAXReader reader = null;

    @Before
    public void init() {
        reader = new SAXReader();
    }

    @After
    public void destory() {
        reader = null;
        System.gc();
    }

    public void fail(Object o) {
        if (o != null)
            System.out.println(o);
    }
}

 

# 创建一篇XML文档

文档格式如下：

<?xml version="1.0" encoding="UTF-8"?>
<catalog>
    <!--An XML Catalog-->
    <?target instruction?>
    <journal title="XML Zone" publisher="IBM developerWorks">
         <article level="Intermediate" date="December-2001">
             <title>Java configuration with XML Schema</title>
             <author>
                 <firstname>Marcello</firstname>
                 <lastname>Vitaletti</lastname>
             </author>
           </article>
    </journal>
</catalog>

 

创建文档代码如下：

/**
 * <b>function:</b>创建文档
 * @author hoojo
 * @createDate 2011-8-5 下午06:18:18
 */
@Test
public void createDocument() {
    //创建一篇文档
    Document doc = DocumentHelper.createDocument();

    //添加一个元素
    Element root = doc.addElement("catalog");
    //为root元素添加注释
    root.addComment("An XML Catalog");
    //添加标记
    root.addProcessingInstruction("target", "instruction");

    //创建元素
    Element journalEl = new BaseElement("journal");
    //添加属性
    journalEl.addAttribute("title", "XML Zone");
    journalEl.addAttribute("publisher", "IBM developerWorks");
    root.add(journalEl);

    //添加元素
    Element articleEl = journalEl.addElement("article");
    articleEl.addAttribute("level", "Intermediate");
    articleEl.addAttribute("date", "December-2001");

    Element titleEl = articleEl.addElement("title");
    //设置文本内容
    titleEl.setText("Java configuration with XML Schema");
    //titleEl.addText("Java configuration with XML Schema");

    Element authorEl = articleEl.addElement("author");
    authorEl.addElement("firstname").setText("Marcello");
    authorEl.addElement("lastname").addText("Vitaletti");

    //可以使用 addDocType() 方法添加文档类型说明。
    doc.addDocType("catalog", null,"file://c:/Dtds/catalog.dtd");

    fail(doc.getRootElement().getName());

    //将xml转换成文本
    fail(doc.asXML());

    //写入到文件
    /*XMLWriter output;
    try {
        output = new XMLWriter(new FileWriter(new File("file/catalog.xml")));
        output.write(doc);
        output.close();
    } catch (IOException e) {
        e.printStackTrace();
    }*/
}

* DocumentHelper是一个文档助手类（工具类），它可以完成文档、元素、文本、属性、注释、CDATA、Namespace、XPath的创建，以及利用XPath完成文档的遍历和将文本转换成Document；

parseText完成将xml字符串转换成Doc的功能

Document doc = DocumentHelper.parseText("<root></root>");

createDocument创建一个文档

Document doc = DocumentHelper.createDocument();

如果带参数就会创建一个带有根元素的文档

 

createElement创建一个元素

Element el = DocumentHelper.createElement("el");

* Document的addElement方法可以给当前文档添加一个子元素

Element root = doc.addElement("catalog");

* addComment方法可以添加一段注释

root.addComment("An XML Catalog");

为root元素添加一段注释

 

* addProcessingInstruction添加一个标记

root.addProcessingInstruction("target", "instruction");

为root元素添加一个标记

 

* new BaseElement可以创建一个元素

Element journalEl = new BaseElement("journal");

 

* addAttribute添加属性

journalEl.addAttribute("title", "XML Zone");

* add添加一个元素

root.add(journalEl);

将journalEl元素添加到root元素中

 

* addElement添加一个元素，并返回当前元素

Element articleEl = journalEl.addElement("article");

给journalEl元素添加一个子元素article

 

* setText、addText可以设置元素的文本

authorEl.addElement("firstname").setText("Marcello");
authorEl.addElement("lastname").addText("Vitaletti");

* addDocType可以设置文档的DOCTYPE

doc.addDocType("catalog", null,file://c:/Dtds/catalog.dtd);

* asXML可以将文档或元素转换成一段xml字符串

doc.asXML();
root.asXML();

* XMLWriter类可以把文档写入到文件中

output = new XMLWriter(new FileWriter(new File("file/catalog.xml")));
output.write(doc);
output.close();

 

# 修改XML文档内容

/**
 * <b>function:</b> 修改XML内容
 * @author hoojo
 * @createDate 2011-8-9 下午03:37:04
 */
@SuppressWarnings("unchecked")
@Test
public void modifyDoc() {
    try {
        Document doc = reader.read(new File("file/catalog.xml"));

        //修改属性内容
        List list = doc.selectNodes("//article/@level");
        Iterator<Attribute> iter = list.iterator();
        while (iter.hasNext()) {
            Attribute attr = iter.next();
            fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
            if ("Intermediate".equals(attr.getValue())) {
                //修改属性值
                attr.setValue("Introductory");
                fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
            }
        }

        list = doc.selectNodes("//article/@date");
        iter = list.iterator();
        while (iter.hasNext()) {
            Attribute attr = iter.next();
            fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
            if ("December-2001".equals(attr.getValue())) {
                //修改属性值
                attr.setValue("December-2011");
                fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
            }
        }

        //修改节点内容
        list = doc.selectNodes("//article");
        Iterator<Element> it = list.iterator();
        while (it.hasNext()) {
            Element el = it.next();
            fail(el.getName() + "#" + el.getText() + "#" + el.getStringValue());
            //修改title元素
            Iterator<Element> elIter = el.elementIterator("title");
            while(elIter.hasNext()) {
                Element titleEl = elIter.next();
                fail(titleEl.getName() + "#" + titleEl.getText() + "#" + titleEl.getStringValue());
                if ("Java configuration with XML Schema".equals(titleEl.getTextTrim())) {
                    //修改元素文本值
                    titleEl.setText("Modify the Java configuration with XML Schema");
                    fail(titleEl.getName() + "#" + titleEl.getText() + "#" + titleEl.getStringValue());
                }
            }
        }

        //修改节点子元素内容
        list = doc.selectNodes("//article/author");
        it = list.iterator();
        while (it.hasNext()) {
            Element el = it.next();
            fail(el.getName() + "#" + el.getText() + "#" + el.getStringValue());
            List<Element> childs = el.elements();
            for (Element e : childs) {
                fail(e.getName() + "#" + e.getText() + "#" + e.getStringValue());
                if ("Marcello".equals(e.getTextTrim())) {
                    e.setText("Ayesha");
                } else if ("Vitaletti".equals(e.getTextTrim())) {
                    e.setText("Malik");
                }
                fail(e.getName() + "#" + e.getText() + "#" + e.getStringValue());
            }
        }

        //写入到文件
        /*XMLWriter output = new XMLWriter(new FileWriter(new File("file/catalog-modified.xml")));
        output.write(doc);
        output.close();*/
    } catch (DocumentException e) {
        e.printStackTrace();
    } catch (Exception e) {
        e.printStackTrace();
    }
}

* reader.read(new File("file/catalog.xml"));读取指定xml文件内容到文档中；

* selectNodes是XPath的查询方法，完成xml文档的查询，传递xpath路径。其使用方法可以参考jdom的xpath的使用方法：

     http://www.cnblogs.com/hoojo/archive/2011/08/11/2134638.html

* getName获取元素标签名称、getValue、getText获取值、文本内容；

* elementIterator("title");获取当前节点下所有的title元素，返回Iterator；

* elements获取下面所有的子元素，返回的是一个集合List；

 

# 显示文档相关信息

private String format(int i) {
    String temp = "";
    while (i > 0) {
        temp += "--";
        i--;
    }
    return temp;
}

/**
 * <b>function:</b>递归显示文档内容
 * @author hoojo
 * @createDate 2011-8-9 下午03:43:45
 * @param i
 * @param els
 */
private void print(int i, List<Element> els) {
    i++;
    for (Element el : els) {
        fail(format(i) + "##" + el.getName() + "#" + el.getTextTrim());
        if (el.hasContent()) {
            print(i, el.elements());
        }
    }
}

/**
 * <b>function:</b>显示文档相关信息
 * @author hoojo
 * @createDate 2011-8-9 下午03:44:10
 */
@Test
public void printInfo() {
    try {
        Document doc = reader.read(new File("file/catalog.xml"));
        fail("asXML: " + doc.asXML());

        fail(doc.asXPathResult(new BaseElement("article")));
        List<Node> list = doc.content();
        for (Node node : list) {
            fail("Node: " + node.getName() + "#" + node.getText() + "#" + node.getStringValue());
        }

        fail("-----------------------------");
        print(0, doc.getRootElement().elements());

        fail("getDocType: " + doc.getDocType());
        fail("getNodeTypeName: " + doc.getNodeTypeName());
        fail("getPath: " + doc.getRootElement().getPath());
        fail("getPath: " + doc.getRootElement().getPath(new BaseElement("journal")));
        fail("getUniquePath: " + doc.getRootElement().getUniquePath());
        fail("getXMLEncoding: " + doc.getXMLEncoding());
        fail("hasContent: " + doc.hasContent());
        fail("isReadOnly: " + doc.isReadOnly());
        fail("nodeCount: " + doc.nodeCount());
        fail("supportsParent: " + doc.supportsParent());
    } catch (DocumentException e) {
        e.printStackTrace();
    }
    fail("getEncoding: " + reader.getEncoding());
    fail("isIgnoreComments: " + reader.isIgnoreComments());
    fail("isMergeAdjacentText: " + reader.isMergeAdjacentText());
    fail("isStringInternEnabled: " + reader.isStringInternEnabled());
    fail("isStripWhitespaceText: " + reader.isStripWhitespaceText());
    fail("isValidating: " + reader.isValidating());
}

 

# 删除文档内容

/**
 * <b>function:</b> 删除节点内容
 * @author hoojo
 * @createDate 2011-8-9 下午03:47:44
 */
@Test
public void removeNode() {
    try {
        Document doc = reader.read(new File("file/catalog-modified.xml"));
        fail("comment: " + doc.selectSingleNode("//comment()"));
        //删除注释
        doc.getRootElement().remove(doc.selectSingleNode("//comment()"));

        Element node = (Element) doc.selectSingleNode("//article");
        //删除属性
        node.remove(new DOMAttribute(QName.get("level"), "Introductory"));
        //删除元素 节点
        node.remove(doc.selectSingleNode("//title"));

        //只能删除下一级节点，不能超过一级；（需要在父元素的节点上删除子元素）
        Node lastNameNode = node.selectSingleNode("//lastname");
        lastNameNode.getParent().remove(lastNameNode);

        fail("Text: " + doc.selectObject("//*[text()='Ayesha']"));
        Element firstNameEl = (Element)doc.selectObject("//firstname");
        fail("Text: " + firstNameEl.selectSingleNode("text()"));

        //删除text文本
        //firstNameEl.remove(firstNameEl.selectSingleNode("text()"));
        //firstNameEl.remove(doc.selectSingleNode("//firstname/text()"));
        firstNameEl.remove(doc.selectSingleNode("//*[text()='Ayesha']/text()"));

        //删除子元素author
        //node.remove(node.selectSingleNode("//author"));

        fail(doc.asXML());
    } catch (Exception e) {
        e.printStackTrace();
    }
}

 

* 删除注释

doc.getRootElement().remove(doc.selectSingleNode("//comment()"));

删除root元素下面的注释

 

* 删除属性

node.remove(new DOMAttribute(QName.get("level"), "Introductory"));

删除node节点中的名称为level，其值为Introductory的属性

 

* 删除元素

node.remove(doc.selectSingleNode("//title"));

删除node节点下的title元素

 

* 删除文本

firstNameEl.remove(firstNameEl.selectSingleNode("text()"));
firstNameEl.remove(doc.selectSingleNode("//firstname/text()"));
firstNameEl.remove(doc.selectSingleNode("//*[text()='Ayesha']/text()"));

删除firstNameEl的文本内容