使用Dom4j操做XML

時間 2019-11-18

標籤使用 dom4j dom xml 欄目 Java開源简体版

原文原文鏈接

使用Dom4j操做XML

Dom4j也能夠很方便完成XML文檔的建立、元素的修改、文檔的查詢遍歷等，但dom4j稍比jdom複雜一點，不過在大片文檔的狀況下dom4j的性能要不jdom好。

# 準備

首先，提供相關的jar包

Dom4j jar包下載：

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

jaxen jar下載：

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

和dom4j依賴或相關的jar：

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

Junit-jar下載：

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

其次，準備測試案例的部分代碼：

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;

/**
* function: 使用Dom4j操做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);
}
}

# 建立一篇XML文檔

文檔格式以下：

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

建立文檔代碼以下：

/**
* function:建立文檔
* @author hoojo
* @createDate 2011-8-5 下午06:18:18
*/
@Test
public void createDocument() {
//建立一篇文檔
Document doc = DocumentHelper.createDocument();

//添加一個元素
Element root = doc.addElement("catalog");
//爲root元素添加註釋
root.addComment("An XML Catalog");
//添加標記
root.addProcessingInstruction("target", "instruction");

//建立元素
Element journalEl = new BaseElement("journal");
//添加屬性
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");
//設置文本內容
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");

//能夠使用 addDocType() 方法添加文檔類型說明。
doc.addDocType("catalog", null,"file://c:/Dtds/catalog.dtd");

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

//將xml轉換成文本
fail(doc.asXML());

//寫入到文件
/*XMLWriter output;
try {
output = new XMLWriter(new FileWriter(new File("file/catalog.xml")));
output.write(doc);
output.close();
} catch (IOException e) {
e.printStackTrace();
}*/
}
* DocumentHelper是一個文檔助手類（工具類），它能夠完成文檔、元素、文本、屬性、註釋、CDATA、Namespace、XPath的建立，以及利用XPath完成文檔的遍歷和將文本轉換成Document；

parseText完成將xml字符串轉換成Doc的功能

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

createDocument建立一個文檔

Document doc = DocumentHelper.createDocument();
若是帶參數就會建立一個帶有根元素的文檔

createElement建立一個元素

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

* Document的addElement方法能夠給當前文檔添加一個子元素

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

* addComment方法能夠添加一段註釋

root.addComment("An XML Catalog");
爲root元素添加一段註釋

* addProcessingInstruction添加一個標記

root.addProcessingInstruction("target", "instruction");
爲root元素添加一個標記

* new BaseElement能夠建立一個元素

Element journalEl = new BaseElement("journal");

* addAttribute添加屬性

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

* add添加一個元素

root.add(journalEl);
將journalEl元素添加到root元素中

* addElement添加一個元素，並返回當前元素

Element articleEl = journalEl.addElement("article");
給journalEl元素添加一個子元素article

* setText、addText能夠設置元素的文本

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

* addDocType能夠設置文檔的DOCTYPE

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

* asXML能夠將文檔或元素轉換成一段xml字符串

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

* XMLWriter類能夠把文檔寫入到文件中

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

# 修改XML文檔內容

/**
* function: 修改XML內容
* @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"));

//修改屬性內容
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())) {
//修改屬性值
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())) {
//修改屬性值
attr.setValue("December-2011");
fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
}
}

//修改節點內容
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());
}
}
}

//修改節點子元素內容
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());
}
}

//寫入到文件
/*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"));讀取指定xml文件內容到文檔中；

* selectNodes是XPath的查詢方法，完成xml文檔的查詢，傳遞xpath路徑。其使用方法能夠參考jdom的xpath的使用方法：

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

* getName獲取元素標籤名稱、getValue、getText獲取值、文本內容；

* elementIterator("title");獲取當前節點下全部的title元素，返回Iterator；

* elements獲取下面全部的子元素，返回的是一個集合List；

# 顯示文檔相關信息

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

/**
* function:遞歸顯示文檔內容
* @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());
}
}
}

/**
* function:顯示文檔相關信息
* @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());
}

# 刪除文檔內容

/**
* function: 刪除節點內容
* @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()"));
//刪除註釋
doc.getRootElement().remove(doc.selectSingleNode("//comment()"));

Element node = (Element) doc.selectSingleNode("//article");
//刪除屬性
node.remove(new DOMAttribute(QName.get("level"), "Introductory"));
//刪除元素節點
node.remove(doc.selectSingleNode("//title"));

//只能刪除下一級節點，不能超過一級；（須要在父元素的節點上刪除子元素）
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()"));

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

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

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

* 刪除註釋

doc.getRootElement().remove(doc.selectSingleNode("//comment()"));
刪除root元素下面的註釋

* 刪除屬性

node.remove(new DOMAttribute(QName.get("level"), "Introductory"));
刪除node節點中的名稱爲level，其值爲Introductory的屬性

* 刪除元素

node.remove(doc.selectSingleNode("//title"));
刪除node節點下的title元素

* 刪除文本

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