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(DocumentObjectModel),DTD(DocumentTypeDefinition),SAX(SimpleAPIforXML),XSD(XmlSchemaDefinition),XSLT(ExtensibleStylesheetLanguageTransformations),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:
<?xmlversion="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。
/**
*
*@authorhongliang.dinghl
*定义XML文档建立与解析的接口
*/
publicinterfaceXmlDocument{
/**
*建立XML文档
*@paramfileName文件全路径名称
*/
publicvoidcreateXml(StringfileName);
/**
*解析XML文档
*@paramfileName文件全路径名称
*/
publicvoidparserXml(StringfileName);
}
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）。
importjava.io.FileInputStream;
importjava.io.FileNotFoundException;
importjava.io.FileOutputStream;
importjava.io.IOException;
importjava.io.InputStream;
importjava.io.PrintWriter;
importjavax.xml.parsers.DocumentBuilder;
importjavax.xml.parsers.DocumentBuilderFactory;
importjavax.xml.parsers.ParserConfigurationException;
importjavax.xml.transform.OutputKeys;
importjavax.xml.transform.Transformer;
importjavax.xml.transform.TransformerConfigurationException;
importjavax.xml.transform.TransformerException;
importjavax.xml.transform.TransformerFactory;
importjavax.xml.transform.dom.DOMSource;
importjavax.xml.transform.stream.StreamResult;
importorg.w3c.dom.Document;
importorg.w3c.dom.Element;
importorg.w3c.dom.Node;
importorg.w3c.dom.NodeList;
importorg.xml.sax.SAXException;
/**
*
*@authorhongliang.dinghl
*DOM生成与解析XML文档
*/
publicclassDomDemoimplementsXmlDocument{
privateDocumentdocument;
privateStringfileName;
publicvoidinit(){
try{
DocumentBuilderFactoryfactory=DocumentBuilderFactory
.newInstance();
DocumentBuilderbuilder=factory.newDocumentBuilder();
this.document=builder.newDocument();
}catch(ParserConfigurationExceptione){
System.out.println(e.getMessage());
}
}
publicvoidcreateXml(StringfileName){
Elementroot=this.document.createElement("employees");
this.document.appendChild(root);
Elementemployee=this.document.createElement("employee");
Elementname=this.document.createElement("name");
name.appendChild(this.document.createTextNode("丁宏亮"));
employee.appendChild(name);
Elementsex=this.document.createElement("sex");
sex.appendChild(this.document.createTextNode("m"));
employee.appendChild(sex);
Elementage=this.document.createElement("age");
age.appendChild(this.document.createTextNode("30"));
employee.appendChild(age);
root.appendChild(employee);
TransformerFactorytf=TransformerFactory.newInstance();
try{
Transformertransformer=tf.newTransformer();
DOMSourcesource=newDOMSource(document);
transformer.setOutputProperty(OutputKeys.ENCODING,"gb2312");
transformer.setOutputProperty(OutputKeys.INDENT,"yes");
PrintWriterpw=newPrintWriter(newFileOutputStream(fileName));
StreamResultresult=newStreamResult(pw);
transformer.transform(source,result);
System.out.println("生成XML文件成功!");
}catch(TransformerConfigurationExceptione){
System.out.println(e.getMessage());
}catch(IllegalArgumentExceptione){
System.out.println(e.getMessage());
}catch(FileNotFoundExceptione){
System.out.println(e.getMessage());
}catch(TransformerExceptione){
System.out.println(e.getMessage());
}
}
publicvoidparserXml(StringfileName){
try{
DocumentBuilderFactorydbf=DocumentBuilderFactory.newInstance();
DocumentBuilderdb=dbf.newDocumentBuilder();
Documentdocument=db.parse(fileName);
NodeListemployees=document.getChildNodes();
for(inti=0;i<employees.getLength();i++){
Nodeemployee=employees.item(i);
NodeListemployeeInfo=employee.getChildNodes();
for(intj=0;j<employeeInfo.getLength();j++){
Nodenode=employeeInfo.item(j);
NodeListemployeeMeta=node.getChildNodes();
for(intk=0;k<employeeMeta.getLength();k++){
System.out.println(employeeMeta.item(k).getNodeName()
+":"+employeeMeta.item(k).getTextContent());
}
}
}
System.out.println("解析完毕");
}catch(FileNotFoundExceptione){
System.out.println(e.getMessage());
}catch(ParserConfigurationExceptione){
System.out.println(e.getMessage());
}catch(SAXExceptione){
System.out.println(e.getMessage());
}catch(IOExceptione){
System.out.println(e.getMessage());
}
}
}
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；
importjava.io.FileInputStream;
importjava.io.FileNotFoundException;
importjava.io.IOException;
importjava.io.InputStream;
importjavax.xml.parsers.ParserConfigurationException;
importjavax.xml.parsers.SAXParser;
importjavax.xml.parsers.SAXParserFactory;
importorg.xml.sax.Attributes;
importorg.xml.sax.SAXException;
importorg.xml.sax.helpers.DefaultHandler;
/**
*
*@authorhongliang.dinghl
*SAX文档解析
*/
publicclassSaxDemoimplementsXmlDocument{
publicvoidcreateXml(StringfileName){
System.out.println("<<"+filename+">>");
}
publicvoidparserXml(StringfileName){
SAXParserFactorysaxfac=SAXParserFactory.newInstance();
try{
SAXParsersaxparser=saxfac.newSAXParser();
InputStreamis=newFileInputStream(fileName);
saxparser.parse(is,newMySAXHandler());
}catch(ParserConfigurationExceptione){
e.printStackTrace();
}catch(SAXExceptione){
e.printStackTrace();
}catch(FileNotFoundExceptione){
e.printStackTrace();
}catch(IOExceptione){
e.printStackTrace();
}
}
}
classMySAXHandlerextendsDefaultHandler{
booleanhasAttribute=false;
Attributesattributes=null;
publicvoidstartDocument()throwsSAXException{
System.out.println("文档开始打印了");
}
publicvoidendDocument()throwsSAXException{
System.out.println("文档打印结束了");
}
publicvoidstartElement(Stringuri,StringlocalName,StringqName,
Attributesattributes)throwsSAXException{
if(qName.equals("employees")){
return;
}
if(qName.equals("employee")){
System.out.println(qName);
}
if(attributes.getLength()>0){
this.attributes=attributes;
this.hasAttribute=true;
}
}
publicvoidendElement(Stringuri,StringlocalName,StringqName)
throwsSAXException{
if(hasAttribute&&(attributes!=null)){
for(inti=0;i<attributes.getLength();i++){
System.out.println(attributes.getQName(0)
+attributes.getValue(0));
}
}
}
publicvoidcharacters(char[]ch,intstart,intlength)
throwsSAXException{
System.out.println(newString(ch,start,length));
}
}
packagecom.alisoft.facepay.framework.bean;
importjava.io.FileInputStream;
importjava.io.FileNotFoundException;
importjava.io.IOException;
importjava.io.InputStream;
importjavax.xml.parsers.ParserConfigurationException;
importjavax.xml.parsers.SAXParser;
importjavax.xml.parsers.SAXParserFactory;
importorg.xml.sax.Attributes;
importorg.xml.sax.SAXException;
importorg.xml.sax.helpers.DefaultHandler;
/**
*
*@authorhongliang.dinghl
*SAX文档解析
*/
publicclassSaxDemoimplementsXmlDocument{
publicvoidcreateXml(StringfileName){
System.out.println("<<"+filename+">>");
}
publicvoidparserXml(StringfileName){
SAXParserFactorysaxfac=SAXParserFactory.newInstance();
try{
SAXParsersaxparser=saxfac.newSAXParser();
InputStreamis=newFileInputStream(fileName);
saxparser.parse(is,newMySAXHandler());
}catch(ParserConfigurationExceptione){
e.printStackTrace();
}catch(SAXExceptione){
e.printStackTrace();
}catch(FileNotFoundExceptione){
e.printStackTrace();
}catch(IOExceptione){
e.printStackTrace();
}
}
}
classMySAXHandlerextendsDefaultHandler{
booleanhasAttribute=false;
Attributesattributes=null;
publicvoidstartDocument()throwsSAXException{
System.out.println("文档开始打印了");
}
publicvoidendDocument()throwsSAXException{
System.out.println("文档打印结束了");
}
publicvoidstartElement(Stringuri,StringlocalName,StringqName,
Attributesattributes)throwsSAXException{
if(qName.equals("employees")){
return;
}
if(qName.equals("employee")){
System.out.println(qName);
}
if(attributes.getLength()>0){
this.attributes=attributes;
this.hasAttribute=true;
}
}
publicvoidendElement(Stringuri,StringlocalName,StringqName)
throwsSAXException{
if(hasAttribute&&(attributes!=null)){
for(inti=0;i<attributes.getLength();i++){
System.out.println(attributes.getQName(0)
+attributes.getValue(0));
}
}
}
publicvoidcharacters(char[]ch,intstart,intlength)
throwsSAXException{
System.out.println(newString(ch,start,length));
}
}
3.DOM4J生成和解析XML文档
DOM4J是一个非常非常优秀的JavaXMLAPI，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。
importjava.io.File;
importjava.io.FileWriter;
importjava.io.IOException;
importjava.io.Writer;
importjava.util.Iterator;
importorg.dom4j.Document;
importorg.dom4j.DocumentException;
importorg.dom4j.DocumentHelper;
importorg.dom4j.Element;
importorg.dom4j.io.SAXReader;
importorg.dom4j.io.XMLWriter;
/**
*
*@authorhongliang.dinghl
*Dom4j生成XML文档与解析XML文档
*/
publicclassDom4jDemoimplementsXmlDocument{
publicvoidcreateXml(StringfileName){
Documentdocument=DocumentHelper.createDocument();
Elementemployees=document.addElement("employees");
Elementemployee=employees.addElement("employee");
Elementname=employee.addElement("name");
name.setText("ddvip");
Elementsex=employee.addElement("sex");
sex.setText("m");
Elementage=employee.addElement("age");
age.setText("29");
try{
WriterfileWriter=newFileWriter(fileName);
XMLWriterxmlWriter=newXMLWriter(fileWriter);
xmlWriter.write(document);
xmlWriter.close();
}catch(IOExceptione){
System.out.println(e.getMessage());
}
}
publicvoidparserXml(StringfileName){
FileinputXml=newFile(fileName);
SAXReadersaxReader=newSAXReader();
try{
Documentdocument=saxReader.read(inputXml);
Elementemployees=document.getRootElement();
for(Iteratori=employees.elementIterator();i.hasNext();){
Elementemployee=(Element)i.next();
for(Iteratorj=employee.elementIterator();j.hasNext();){
Elementnode=(Element)j.next();
System.out.println(node.getName()+":"+node.getText());
}
}
}catch(DocumentExceptione){
System.out.println(e.getMessage());
}
System.out.println("dom4jparserXml");
}
}
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。
importjava.io.FileNotFoundException;
importjava.io.FileOutputStream;
importjava.io.IOException;
importjava.util.List;
importorg.jdom.Document;
importorg.jdom.Element;
importorg.jdom.JDOMException;
importorg.jdom.input.SAXBuilder;
importorg.jdom.output.XMLOutputter;
/**
*
*@authorhongliang.dinghl
*JDOM生成与解析XML文档
*
*/
publicclassJDomDemoimplementsXmlDocument{
publicvoidcreateXml(StringfileName){
Documentdocument;
Elementroot;
root=newElement("employees");
document=newDocument(root);
Elementemployee=newElement("employee");
root.addContent(employee);
Elementname=newElement("name");
name.setText("ddvip");
employee.addContent(name);
Elementsex=newElement("sex");
sex.setText("m");
employee.addContent(sex);
Elementage=newElement("age");
age.setText("23");
employee.addContent(age);
XMLOutputterXMLOut=newXMLOutputter();
try{
XMLOut.output(document,newFileOutputStream(fileName));
}catch(FileNotFoundExceptione){
e.printStackTrace();
}catch(IOExceptione){
e.printStackTrace();
}
}
publicvoidparserXml(StringfileName){
SAXBuilderbuilder=newSAXBuilder(false);
try{
Documentdocument=builder.build(fileName);
Elementemployees=document.getRootElement();
ListemployeeList=employees.getChildren("employee");
for(inti=0;iElementemployee=(Element)employeeList.get(i);
ListemployeeInfo=employee.getChildren();
for(intj=0;jSystem.out.println(((Element)employeeInfo.get(j)).getName()+":"+((Element)employeeInfo.get(j)).getValue());
}
}
}catch(JDOMExceptione){
e.printStackTrace();
}catch(IOExceptione){
e.printStackTrace();
}
}
}
以上就是本文的全部内容，希望对大家的学习有所帮助，也希望大家多多支持毛票票。