[转]详解Java解析XML的四种方法

XML现在已经成为一种通用的数据交换格式,它的平台无关性,语言无关性,系统无关性,给数据集成与交互带来了极大的方便。对于XML本身的语法知识与技术细节,需要阅读相关的技术文献,这里面包括的内容有DOM(Document Object Model),DTD(Document Type Definition),SAX(Simple API for XML),XSD(Xml Schema Definition),XSLT(Extensible Stylesheet Language Transformations),具体可参阅w3c官方网站文档http://www.w3.org获取更多信息。

XML在不同的语言里解析方式都是一样的,只不过实现的语法不同而已。基本的解析方式有两种,一种叫SAX，另一种叫DOM。SAX是基于事件流的解析,DOM是基于XML文档树结构的解析。假设我们XML的内容和结构如下: 

 

<?xml version="1.0" encoding="UTF-8"?> 
<employees> 
<employee> 
<name>ddviplinux</name> 
<sex>m</sex> 
<age>30</age> 
</employee> 
</employees>

 

本文使用JAVA语言来实现DOM与SAX的XML文档生成与解析。 
首先定义一个操作XML文档的接口XmlDocument 它定义了XML文档的建立与解析的接口。

 

package com.alisoft.facepay.framework.bean; /** * * @author hongliang.dinghl * 定义XML文档建立与解析的接口 */ 
public interface XmlDocument { /** * 建立XML文档 * @param fileName 文件全路径名称 */ 
public void createXml(String fileName); /** * 解析XML文档 * @param fileName 文件全路径名称 */ 
public void parserXml(String fileName); } 

 

1.DOM生成和解析XML文档

为 XML 文档的已解析版本定义了一组接口。解析器读入整个文档，然后构建一个驻留内存的树结构，然后代码就可以使用 DOM 接口来操作这个树结构。优点：整个文档树在内存中，便于操作；支持删除、修改、重新排列等多种功能；缺点：将整个文档调入内存（包括无用的节点），浪费时间和空间；使用场合：一旦解析了文档还需多次访问这些数据；硬件资源充足（内存、CPU）。 

 

package com.alisoft.facepay.framework.bean;  2 import java.io.FileInputStream;  3 import java.io.FileNotFoundException;  4 import java.io.FileOutputStream;  5 import java.io.IOException;  6 import java.io.InputStream;  7 import java.io.PrintWriter;  8 import javax.xml.parsers.DocumentBuilder;  9 import javax.xml.parsers.DocumentBuilderFactory;  10 import javax.xml.parsers.ParserConfigurationException;  11 import javax.xml.transform.OutputKeys;  12 import javax.xml.transform.Transformer;  13 import javax.xml.transform.TransformerConfigurationException;  14 import javax.xml.transform.TransformerException;  15 import javax.xml.transform.TransformerFactory;  16 import javax.xml.transform.dom.DOMSource;  17 import javax.xml.transform.stream.StreamResult;  18 import org.w3c.dom.Document;  19 import org.w3c.dom.Element;  20 import org.w3c.dom.Node;  21 import org.w3c.dom.NodeList;  22 import org.xml.sax.SAXException;  23 /** 
*  25 * @author hongliang.dinghl  26 * DOM生成与解析XML文档  27 */ 
public class DomDemo implements XmlDocument {  29 private Document document;  30 private String fileName;  31 public void init() {  32 try {  33 DocumentBuilderFactory factory = DocumentBuilderFactory  34 .newInstance();  35 DocumentBuilder builder = factory.newDocumentBuilder();  36 this.document = builder.newDocument();  37 } catch (ParserConfigurationException e) {  38 System.out.println(e.getMessage());  39 }  40 }  41 public void createXml(String fileName) {  42 Element root = this.document.createElement("employees");  43 this.document.appendChild(root);  44 Element employee = this.document.createElement("employee");  45 Element name = this.document.createElement("name");  46 name.appendChild(this.document.createTextNode("丁宏亮"));  47 employee.appendChild(name);  48 Element sex = this.document.createElement("sex");  49 sex.appendChild(this.document.createTextNode("m"));  50 employee.appendChild(sex);  51 Element age = this.document.createElement("age");  52 age.appendChild(this.document.createTextNode("30"));  53 employee.appendChild(age);  54 root.appendChild(employee);  55 TransformerFactory tf = TransformerFactory.newInstance();  56 try {  57 Transformer transformer = tf.newTransformer();  58 DOMSource source = new DOMSource(document);  59 transformer.setOutputProperty(OutputKeys.ENCODING, "gb2312");  60 transformer.setOutputProperty(OutputKeys.INDENT, "yes");  61 PrintWriter pw = new PrintWriter(new FileOutputStream(fileName));  62 StreamResult result = new StreamResult(pw);  63 transformer.transform(source, result);  64 System.out.println("生成XML文件成功!");  65 } catch (TransformerConfigurationException e) {  66 System.out.println(e.getMessage());  67 } catch (IllegalArgumentException e) {  68 System.out.println(e.getMessage());  69 } catch (FileNotFoundException e) {  70 System.out.println(e.getMessage());  71 } catch (TransformerException e) {  72 System.out.println(e.getMessage());  73 }  74 }  75 public void parserXml(String fileName) {  76 try {  77 DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();  78 DocumentBuilder db = dbf.newDocumentBuilder();  79 Document document = db.parse(fileName);  80 NodeList employees = document.getChildNodes();  81 for (int i = 0; i < employees.getLength(); i++) {  82 Node employee = employees.item(i);  83 NodeList employeeInfo = employee.getChildNodes();  84 for (int j = 0; j < employeeInfo.getLength(); j++) {  85 Node node = employeeInfo.item(j);  86 NodeList employeeMeta = node.getChildNodes();  87 for (int k = 0; k < employeeMeta.getLength(); k++) {  88 System.out.println(employeeMeta.item(k).getNodeName()  89 + ":" + employeeMeta.item(k).getTextContent());  90 }  91 }  92 }  93 System.out.println("解析完毕");  94 } catch (FileNotFoundException e) {  95 System.out.println(e.getMessage());  96 } catch (ParserConfigurationException e) {  97 System.out.println(e.getMessage());  98 } catch (SAXException e) {  99 System.out.println(e.getMessage()); 100 } catch (IOException e) { 101 System.out.println(e.getMessage()); 102 } 103 } 104 } 

 

 

2.SAX生成和解析XML文档

为解决DOM的问题，出现了SAX。SAX ，事件驱动。当解析器发现元素开始、元素结束、文本、文档的开始或结束等时，发送事件，程序员编写响应这些事件的代码，保存数据。优点：不用事先调入整个文档，占用资源少；SAX解析器代码比DOM解析器代码小，适于Applet，下载。缺点：不是持久的；事件过后，若没保存数据，那么数据就丢了；无状态性；从事件中只能得到文本，但不知该文本属于哪个元素；使用场合：Applet;只需XML文档的少量内容，很少回头访问；机器内存少；

Java代码

 

package com.alisoft.facepay.framework.bean;  2 import java.io.FileInputStream;  3 import java.io.FileNotFoundException;  4 import java.io.IOException;  5 import java.io.InputStream;  6 
import javax.xml.parsers.ParserConfigurationException;  8 import javax.xml.parsers.SAXParser;  9 import javax.xml.parsers.SAXParserFactory;  10 
import org.xml.sax.Attributes;  12 import org.xml.sax.SAXException;  13 import org.xml.sax.helpers.DefaultHandler;  14 /**  
*  16 * @author hongliang.dinghl  17 * SAX文档解析  18 */  
public class SaxDemo implements XmlDocument {  20 
public void createXml(String fileName) {  22 System.out.println("<<"+filename+">>");  23 }  24 
public void parserXml(String fileName) {  26 SAXParserFactory saxfac = SAXParserFactory.newInstance();  27 
try {  29 
SAXParser saxparser = saxfac.newSAXParser();  31 
InputStream is = new FileInputStream(fileName);  33 
saxparser.parse(is, new MySAXHandler());  35 
} catch (ParserConfigurationException e) {  37 
e.printStackTrace();  39 
} catch (SAXException e) {  41 
e.printStackTrace();  43 
} catch (FileNotFoundException e) {  45 
e.printStackTrace();  47 
} catch (IOException e) {  49 
e.printStackTrace();  51 
}  53 
}  55 
}  57 
class MySAXHandler extends DefaultHandler {  59 
boolean hasAttribute = false;  61 
Attributes attributes = null;  63 
public void startDocument() throws SAXException {  65 
System.out.println("文档开始打印了");  67 
}  69 
public void endDocument() throws SAXException {  71 
System.out.println("文档打印结束了");  73 
}  75 
public void startElement(String uri, String localName, String qName,  77 
Attributes attributes) throws SAXException {  79 
if (qName.equals("employees")) {  81 
return;  83 
}  85 
if (qName.equals("employee")) {  87 
System.out.println(qName);  89 
}  91 
if (attributes.getLength() > 0) {  93 
this.attributes = attributes;  95 
this.hasAttribute = true;  97 
}  99 
} 101 
public void endElement(String uri, String localName, String qName) 103 
throws SAXException { 105 
if (hasAttribute && (attributes != null)) { 107 
for (int i = 0; i < attributes.getLength(); i++) { 109 
System.out.println(attributes.getQName(0) 111 + attributes.getValue(0)); 112 
} 114 
} 116 
} 118 
public void characters(char[] ch, int start, int length) 120 
throws SAXException { 122 
System.out.println(new String(ch, start, length)); 124 
} 126 
} 128 package com.alisoft.facepay.framework.bean; 129 import java.io.FileInputStream; 130 import java.io.FileNotFoundException; 131 import java.io.IOException; 132 import java.io.InputStream; 133 import javax.xml.parsers.ParserConfigurationException; 134 import javax.xml.parsers.SAXParser; 135 import javax.xml.parsers.SAXParserFactory; 136 import org.xml.sax.Attributes; 137 import org.xml.sax.SAXException; 138 import org.xml.sax.helpers.DefaultHandler; 139 /** 
* 141 * @author hongliang.dinghl 142 * SAX文档解析 143 */ 
public class SaxDemo implements XmlDocument { 145 public void createXml(String fileName) { 146 System.out.println("<<"+filename+">>"); 147 } 148 public void parserXml(String fileName) { 149 SAXParserFactory saxfac = SAXParserFactory.newInstance(); 150 try { 151 SAXParser saxparser = saxfac.newSAXParser(); 152 InputStream is = new FileInputStream(fileName); 153 saxparser.parse(is, new MySAXHandler()); 154 } catch (ParserConfigurationException e) { 155 e.printStackTrace(); 156 } catch (SAXException e) { 157 e.printStackTrace(); 158 } catch (FileNotFoundException e) { 159 e.printStackTrace(); 160 } catch (IOException e) { 161 e.printStackTrace(); 162 } 163 } 164 } 165 class MySAXHandler extends DefaultHandler { 166 boolean hasAttribute = false; 167 Attributes attributes = null; 168 public void startDocument() throws SAXException { 169 System.out.println("文档开始打印了"); 170 } 171 public void endDocument() throws SAXException { 172 System.out.println("文档打印结束了"); 173 } 174 public void startElement(String uri, String localName, String qName, 175 Attributes attributes) throws SAXException { 176 if (qName.equals("employees")) { 177 return; 178 } 179 if (qName.equals("employee")) { 180 System.out.println(qName); 181 } 182 if (attributes.getLength() > 0) { 183 this.attributes = attributes; 184 this.hasAttribute = true; 185 } 186 } 187 public void endElement(String uri, String localName, String qName) 188 throws SAXException { 189 if (hasAttribute && (attributes != null)) { 190 for (int i = 0; i < attributes.getLength(); i++) { 191 System.out.println(attributes.getQName(0) 192 + attributes.getValue(0)); 193 } 194 } 195 } 196 public void characters(char[] ch, int start, int length) 197 throws SAXException { 198 System.out.println(new String(ch, start, length)); 199 } 200 } 

 

 

3.DOM4J生成和解析XML文档

DOM4J 是一个非常非常优秀的Java XML API，具有性能优异、功能强大和极端易用使用的特点，同时它也是一个开放源代码的软件。如今你可以看到越来越多的 Java 软件都在使用 DOM4J 来读写 XML，特别值得一提的是连 Sun 的 JAXM 也在用 DOM4J。

Java代码

 

package com.alisoft.facepay.framework.bean;  2 import java.io.File;  3 import java.io.FileWriter;  4 import java.io.IOException;  5 import java.io.Writer;  6 import java.util.Iterator;  7 
import org.dom4j.Document;  9 import org.dom4j.DocumentException; 10 import org.dom4j.DocumentHelper; 11 import org.dom4j.Element; 12 import org.dom4j.io.SAXReader; 13 import org.dom4j.io.XMLWriter; 14 /**  
* 16 * @author hongliang.dinghl 17 * Dom4j 生成XML文档与解析XML文档 18 */  
public class Dom4jDemo implements XmlDocument { 20 
public void createXml(String fileName) { 22 Document document = DocumentHelper.createDocument(); 23 Element employees=document.addElement("employees"); 24 Element employee=employees.addElement("employee"); 25 Element name= employee.addElement("name"); 26 name.setText("ddvip"); 27 Element sex=employee.addElement("sex"); 28 sex.setText("m"); 29 Element age=employee.addElement("age"); 30 age.setText("29"); 31 try { 32 Writer fileWriter=new FileWriter(fileName); 33 XMLWriter xmlWriter=new XMLWriter(fileWriter); 34 xmlWriter.write(document); 35 xmlWriter.close(); 36 } catch (IOException e) { 37 
System.out.println(e.getMessage()); 39 } 40 

} 43 

public void parserXml(String fileName) { 46 File inputXml=new File(fileName); 47 SAXReader saxReader = new SAXReader(); 48 try { 49 Document document = saxReader.read(inputXml); 50 Element employees=document.getRootElement(); 51 for(Iterator i = employees.elementIterator(); i.hasNext();){ 52 Element employee = (Element) i.next(); 53 for(Iterator j = employee.elementIterator(); j.hasNext();){ 54 Element node=(Element) j.next(); 55 System.out.println(node.getName()+":"+node.getText()); 56 } 57 
} 59 } catch (DocumentException e) { 60 System.out.println(e.getMessage()); 61 } 62 System.out.println("dom4j parserXml"); 63 } 64 }   

 

 

4.JDOM生成和解析XML  

为减少DOM、SAX的编码量，出现了JDOM；优点：20-80原则，极大减少了代码量。使用场合：要实现的功能简单，如解析、创建等，但在底层，JDOM还是使用SAX（最常用）、DOM、Xanan文档。

 

package com.alisoft.facepay.framework.bean;  2 
import java.io.FileNotFoundException;  4 import java.io.FileOutputStream;  5 import java.io.IOException;  6 import java.util.List;  7 
import org.jdom.Document;  9 import org.jdom.Element; 10 import org.jdom.JDOMException; 11 import org.jdom.input.SAXBuilder; 12 import org.jdom.output.XMLOutputter; 13 /**  
* 15 * @author hongliang.dinghl 16 * JDOM 生成与解析XML文档 17 * 18 */  
public class JDomDemo implements XmlDocument { 20 
public void createXml(String fileName) { 22 Document document; 23 Element root; 24 root=new Element("employees"); 25 document=new Document(root); 26 Element employee=new Element("employee"); 27 root.addContent(employee); 28 Element name=new Element("name"); 29 name.setText("ddvip"); 30 employee.addContent(name); 31 Element sex=new Element("sex"); 32 sex.setText("m"); 33 employee.addContent(sex); 34 Element age=new Element("age"); 35 age.setText("23"); 36 employee.addContent(age); 37 XMLOutputter XMLOut = new XMLOutputter(); 38 try { 39 XMLOut.output(document, new FileOutputStream(fileName)); 40 } catch (FileNotFoundException e) { 41 e.printStackTrace(); 42 } catch (IOException e) { 43 e.printStackTrace(); 44 } 45 
} 47 
public void parserXml(String fileName) { 49 SAXBuilder builder=new SAXBuilder(false); 50 try { 51 Document document=builder.build(fileName); 52 Element employees=document.getRootElement(); 53 List employeeList=employees.getChildren("employee"); 54 for(int i=0;iElement employee=(Element)employeeList.get(i); 55 List employeeInfo=employee.getChildren(); 56 for(int j=0;jSystem.out.println(((Element)employeeInfo.get(j)).getName()+":"+((Element)employeeInfo.get(j)).getValue()); 57 
} 59 } 60 } catch (JDOMException e) { 61 
e.printStackTrace(); 63 } catch (IOException e) { 64 
e.printStackTrace(); 66 } 67 
} 69 } 70   

 

原文链接：http://developer.51cto.com/art/200903/117512.htm