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:
其次,准备测试案例的部分代码:
1 package com.hoo.test;
2
3 import java.io.File;
4 import java.util.Iterator;
5 import java.util.List;
6 import org.dom4j.Attribute;
7 import org.dom4j.Document;
8 import org.dom4j.DocumentException;
9 import org.dom4j.DocumentHelper;
10 import org.dom4j.Element;
11 import org.dom4j.Node;
12 import org.dom4j.QName;
13 import org.dom4j.dom.DOMAttribute;
14 import org.dom4j.io.SAXReader;
15 import org.dom4j.tree.BaseElement;
16 import org.junit.After;
17 import org.junit.Before;
18 import org.junit.Test;
19
20 /**
21 * <b>function:</b> 使用Dom4j操作XML
22 * @author hoojo
23 * @createDate 2011-8-5 下午06:15:40
24 * @file DocumentTest.java
25 * @package com.hoo.test
26 * @project Dom4jTest
27 * @blog http://blog.csdn.net/IBM_hoojo
28 * @email hoojo_@126.com
29 * @version 1.0
30 */
31 public class DocumentTest {
32
33 private SAXReader reader = null;
34
35 @Before
36 public void init() {
37 reader = new SAXReader();
38 }
39
40 @After
41 public void destory() {
42 reader = null;
43 System.gc();
44 }
45
46 public void fail(Object o) {
47 if (o != null)
48 System.out.println(o);
49 }
50 }
# 创建一篇XML文档
文档格式如下:
1 <?xml version="1.0" encoding="UTF-8"?>
2 <catalog>
3 <!--An XML Catalog-->
4 <?target instruction?>
5 <journal title="XML Zone" publisher="IBM developerWorks">
6 <article level="Intermediate" date="December-2001">
7 <title>Java configuration with XML Schema</title>
8 <author>
9 <firstname>Marcello</firstname>
10 <lastname>Vitaletti</lastname>
11 </author>
12 </article>
13 </journal>
14 </catalog>
创建文档代码如下:
1 /**
2 * <b>function:</b>创建文档
3 * @author hoojo
4 * @createDate 2011-8-5 下午06:18:18
5 */
6 @Test
7 public void createDocument() {
8 //创建一篇文档
9 Document doc = DocumentHelper.createDocument();
10
11 //添加一个元素
12 Element root = doc.addElement("catalog");
13 //为root元素添加注释
14 root.addComment("An XML Catalog");
15 //添加标记
16 root.addProcessingInstruction("target", "instruction");
17
18 //创建元素
19 Element journalEl = new BaseElement("journal");
20 //添加属性
21 journalEl.addAttribute("title", "XML Zone");
22 journalEl.addAttribute("publisher", "IBM developerWorks");
23 root.add(journalEl);
24
25 //添加元素
26 Element articleEl = journalEl.addElement("article");
27 articleEl.addAttribute("level", "Intermediate");
28 articleEl.addAttribute("date", "December-2001");
29
30 Element titleEl = articleEl.addElement("title");
31 //设置文本内容
32 titleEl.setText("Java configuration with XML Schema");
33 //titleEl.addText("Java configuration with XML Schema");
34
35 Element authorEl = articleEl.addElement("author");
36 authorEl.addElement("firstname").setText("Marcello");
37 authorEl.addElement("lastname").addText("Vitaletti");
38
39 //可以使用 addDocType() 方法添加文档类型说明。
40 doc.addDocType("catalog", null,"file://c:/Dtds/catalog.dtd");
41
42 fail(doc.getRootElement().getName());
43
44 //将xml转换成文本
45 fail(doc.asXML());
46
47 //写入到文件
48 /*XMLWriter output;
49 try {
50 output = new XMLWriter(new FileWriter(new File("file/catalog.xml")));
51 output.write(doc);
52 output.close();
53 } catch (IOException e) {
54 e.printStackTrace();
55 }*/
56 }
* 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
1 /**
2 * <b>function:</b> 修改XML内容
3 * @author hoojo
4 * @createDate 2011-8-9 下午03:37:04
5 */
6 @SuppressWarnings("unchecked")
7 @Test
8 public void modifyDoc() {
9 try {
10 Document doc = reader.read(new File("file/catalog.xml"));
11
12 //修改属性内容
13 List list = doc.selectNodes("//article/@level");
14 Iterator<Attribute> iter = list.iterator();
15 while (iter.hasNext()) {
16 Attribute attr = iter.next();
17 fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
18 if ("Intermediate".equals(attr.getValue())) {
19 //修改属性值
20 attr.setValue("Introductory");
21 fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
22 }
23 }
24
25 list = doc.selectNodes("//article/@date");
26 iter = list.iterator();
27 while (iter.hasNext()) {
28 Attribute attr = iter.next();
29 fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
30 if ("December-2001".equals(attr.getValue())) {
31 //修改属性值
32 attr.setValue("December-2011");
33 fail(attr.getName() + "#" + attr.getValue() + "#" + attr.getText());
34 }
35 }
36
37 //修改节点内容
38 list = doc.selectNodes("//article");
39 Iterator<Element> it = list.iterator();
40 while (it.hasNext()) {
41 Element el = it.next();
42 fail(el.getName() + "#" + el.getText() + "#" + el.getStringValue());
43 //修改title元素
44 Iterator<Element> elIter = el.elementIterator("title");
45 while(elIter.hasNext()) {
46 Element titleEl = elIter.next();
47 fail(titleEl.getName() + "#" + titleEl.getText() + "#" + titleEl.getStringValue());
48 if ("Java configuration with XML Schema".equals(titleEl.getTextTrim())) {
49 //修改元素文本值
50 titleEl.setText("Modify the Java configuration with XML Schema");
51 fail(titleEl.getName() + "#" + titleEl.getText() + "#" + titleEl.getStringValue());
52 }
53 }
54 }
55
56 //修改节点子元素内容
57 list = doc.selectNodes("//article/author");
58 it = list.iterator();
59 while (it.hasNext()) {
60 Element el = it.next();
61 fail(el.getName() + "#" + el.getText() + "#" + el.getStringValue());
62 List<Element> childs = el.elements();
63 for (Element e : childs) {
64 fail(e.getName() + "#" + e.getText() + "#" + e.getStringValue());
65 if ("Marcello".equals(e.getTextTrim())) {
66 e.setText("Ayesha");
67 } else if ("Vitaletti".equals(e.getTextTrim())) {
68 e.setText("Malik");
69 }
70 fail(e.getName() + "#" + e.getText() + "#" + e.getStringValue());
71 }
72 }
73
74 //写入到文件
75 /*XMLWriter output = new XMLWriter(new FileWriter(new File("file/catalog-modified.xml")));
76 output.write(doc);
77 output.close();*/
78 } catch (DocumentException e) {
79 e.printStackTrace();
80 } catch (Exception e) {
81 e.printStackTrace();
82 }
83 }
* 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
1 private String format(int i) {
2 String temp = "";
3 while (i > 0) {
4 temp += "--";
5 i--;
6 }
7 return temp;
8 }
9
10 /**
11 * <b>function:</b>递归显示文档内容
12 * @author hoojo
13 * @createDate 2011-8-9 下午03:43:45
14 * @param i
15 * @param els
16 */
17 private void print(int i, List<Element> els) {
18 i++;
19 for (Element el : els) {
20 fail(format(i) + "##" + el.getName() + "#" + el.getTextTrim());
21 if (el.hasContent()) {
22 print(i, el.elements());
23 }
24 }
25 }
26
27 /**
28 * <b>function:</b>显示文档相关信息
29 * @author hoojo
30 * @createDate 2011-8-9 下午03:44:10
31 */
32 @Test
33 public void printInfo() {
34 try {
35 Document doc = reader.read(new File("file/catalog.xml"));
36 fail("asXML: " + doc.asXML());
37
38 fail(doc.asXPathResult(new BaseElement("article")));
39 List<Node> list = doc.content();
40 for (Node node : list) {
41 fail("Node: " + node.getName() + "#" + node.getText() + "#" + node.getStringValue());
42 }
43
44 fail("-----------------------------");
45 print(0, doc.getRootElement().elements());
46
47 fail("getDocType: " + doc.getDocType());
48 fail("getNodeTypeName: " + doc.getNodeTypeName());
49 fail("getPath: " + doc.getRootElement().getPath());
50 fail("getPath: " + doc.getRootElement().getPath(new BaseElement("journal")));
51 fail("getUniquePath: " + doc.getRootElement().getUniquePath());
52 fail("getXMLEncoding: " + doc.getXMLEncoding());
53 fail("hasContent: " + doc.hasContent());
54 fail("isReadOnly: " + doc.isReadOnly());
55 fail("nodeCount: " + doc.nodeCount());
56 fail("supportsParent: " + doc.supportsParent());
57 } catch (DocumentException e) {
58 e.printStackTrace();
59 }
60 fail("getEncoding: " + reader.getEncoding());
61 fail("isIgnoreComments: " + reader.isIgnoreComments());
62 fail("isMergeAdjacentText: " + reader.isMergeAdjacentText());
63 fail("isStringInternEnabled: " + reader.isStringInternEnabled());
64 fail("isStripWhitespaceText: " + reader.isStripWhitespaceText());
65 fail("isValidating: " + reader.isValidating());
66 }
# 删除文档内容
1 /**
2 * <b>function:</b> 删除节点内容
3 * @author hoojo
4 * @createDate 2011-8-9 下午03:47:44
5 */
6 @Test
7 public void removeNode() {
8 try {
9 Document doc = reader.read(new File("file/catalog-modified.xml"));
10 fail("comment: " + doc.selectSingleNode("//comment()"));
11 //删除注释
12 doc.getRootElement().remove(doc.selectSingleNode("//comment()"));
13
14 Element node = (Element) doc.selectSingleNode("//article");
15 //删除属性
16 node.remove(new DOMAttribute(QName.get("level"), "Introductory"));
17 //删除元素 节点
18 node.remove(doc.selectSingleNode("//title"));
19
20 //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)
21 Node lastNameNode = node.selectSingleNode("//lastname");
22 lastNameNode.getParent().remove(lastNameNode);
23
24 fail("Text: " + doc.selectObject("//*[text()='Ayesha']"));
25 Element firstNameEl = (Element)doc.selectObject("//firstname");
26 fail("Text: " + firstNameEl.selectSingleNode("text()"));
27
28 //删除text文本
29 //firstNameEl.remove(firstNameEl.selectSingleNode("text()"));
30 //firstNameEl.remove(doc.selectSingleNode("//firstname/text()"));
31 firstNameEl.remove(doc.selectSingleNode("//*[text()='Ayesha']/text()"));
32
33 //删除子元素author
34 //node.remove(node.selectSingleNode("//author"));
35
36 fail(doc.asXML());
37 } catch (Exception e) {
38 e.printStackTrace();
39 }
40 }
* 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()"));