Java生成和解析XML格式文件和字符串

1、基础知识：

Java解析XML一般有四种方法：DOM、SAX、JDOM、DOM4J。

2、使用介绍

1)、DOM

(1)简介

由W3C(org.w3c.dom)提供的接口，它将整个XML文档读入内存，构建一个DOM树来对各个节点(Node)进行操作。优点就是整个文档都一直在内存中，我们可以随时访问任何节点，并且对树的遍历也是比较熟悉的操作；缺点则是耗内存，并且必须等到所有的文档都读入内存才能进行处理。

(2)示例代码：

<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<root>
<TelePhone>
<type name="nokia">
<price>599</price>
<operator>CMCC</operator>
</type>
<type name="xiaomi">
<price>699</price>
<operator>ChinaNet</operator>
</type>
</TelePhone>
</root>

import java.io.ByteArrayOutputStream;
import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.StringReader;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.Transformer;
import javax.xml.transform.TransformerConfigurationException;
import javax.xml.transform.TransformerException;
import javax.xml.transform.TransformerFactory;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

public class XMLHandler {
public XMLHandler(){

}

public String createXML(){
String xmlStr = null;
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder builder = factory.newDocumentBuilder();
Document document = builder.newDocument();
document.setXmlVersion("1.0");

Element root = document.createElement("root");
document.appendChild(root);

Element telephone = document.createElement("TelePhone");

Element nokia = document.createElement("type");
nokia.setAttribute("name", "nokia");

Element priceNokia = document.createElement("price");
priceNokia.setTextContent("599");
nokia.appendChild(priceNokia);

Element operatorNokia = document.createElement("operator");
operatorNokia.setTextContent("CMCC");
nokia.appendChild(operatorNokia);

telephone.appendChild(nokia);

Element xiaomi = document.createElement("type");
xiaomi.setAttribute("name", "xiaomi");

Element priceXiaoMi = document.createElement("price");
priceXiaoMi.setTextContent("699");
xiaomi.appendChild(priceXiaoMi);

Element operatorXiaoMi = document.createElement("operator");
operatorXiaoMi.setTextContent("ChinaNet");
xiaomi.appendChild(operatorXiaoMi);

telephone.appendChild(xiaomi);

root.appendChild(telephone);

TransformerFactory transFactory = TransformerFactory.newInstance();
Transformer transFormer = transFactory.newTransformer();
DOMSource domSource = new DOMSource(document);

//export string
ByteArrayOutputStream bos = new ByteArrayOutputStream();
transFormer.transform(domSource, new StreamResult(bos));
xmlStr = bos.toString();

//-------
//save as file
File file = new File("TelePhone.xml");
if(!file.exists()){
file.createNewFile();
}
FileOutputStream out = new FileOutputStream(file);
StreamResult xmlResult = new StreamResult(out);
transFormer.transform(domSource, xmlResult);
//--------
} catch (ParserConfigurationException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}catch (TransformerConfigurationException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}catch (TransformerException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}

return xmlStr;
}

public void parserXML(String strXML){
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder builder = factory.newDocumentBuilder();
StringReader sr = new StringReader(strXML);
InputSource is = new InputSource(sr);
Document doc = builder.parse(is);
Element rootElement = doc.getDocumentElement();
NodeList phones = rootElement.getElementsByTagName("type");
for (int i = 0; i < phones.getLength(); i++) {
Node type = phones.item(i);
String phoneName = ((Element)type).getAttribute("name");
System.out.println("Phone name = "+phoneName);
NodeList properties = type.getChildNodes();
for (int j = 0; j < properties.getLength(); j++) {
Node property = properties.item(j);
String nodeName = property.getNodeName();
if (nodeName.equals("price")) {
String price=property.getFirstChild().getNodeValue();
System.out.println("price="+price);
} else if (nodeName.equals("operator")) {
String operator=property.getFirstChild().getNodeValue();
System.out.println("operator="+operator);
}
}
}
} catch (ParserConfigurationException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}catch (SAXException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

public static void main(String[] args) {
XMLHandler handler = new XMLHandler();
String xml = handler.createXML();
System.out.println(xml);
handler.parserXML(xml);
}
}

(3)元素(Element)和结点(Node)的区别（org.w3c.dom）

Node对象是整个文档对象模型的主要数据类型，是DOM中最基本的对象，代表了文档树中的抽象节点。但在实际使用中很少会直接使用Node对象，而是使用Node对象的子对象Element,Attr,Text等。

Element对象表示HTML或XML文档中的一个元素，是Node类最主要的子对象，在元素中可以包含属性，因而Element中有存取其属性的方法。

Element是从Node继承而来的，元素是一个小范围的定义，必须是含有完整信息的结点才是一个元素，例如<div>...</div>。但是一个结点不一定是一个元素，而一个元素一定是一个结点。

node有几个子类型：Element,Text,Attribute,RootElement,Comment,Namespace等

2)、SAX

3)、JDOM

4)、DOM4J

(1)简介

dom4j是目前在xml解析方面是最优秀的(Hibernate、Sun的JAXM也都使用dom4j来解析XML)，它合并了许多超出基本XML文档表示的功能，包括集成的XPath支持、XML Schema支持以及用于大文档或流化文档的基于事件的处理。

在使用XPATH时要增加jaxen.jar，否则会出现如下错误：

Exception in thread "main" java.lang.NoClassDefFoundError: org/jaxen/JaxenException
at org.dom4j.DocumentFactory.createXPath(DocumentFactory.java:230)
at org.dom4j.tree.AbstractNode.createXPath(AbstractNode.java:207)
at org.dom4j.tree.AbstractNode.selectNodes(AbstractNode.java:164)

(2)示例代码：

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.StringReader;
import java.io.StringWriter;
import java.util.List;

import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.io.OutputFormat;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;
import org.xml.sax.InputSource;

public class XMLHandler {

public XMLHandler() {
// TODO Auto-generated constructor stub
}

public String createXML(){
String strXML = null;
Document document = DocumentHelper.createDocument();
Element root = document.addElement("root");

Element phone = root.addElement("TelePhone");

Element nokia = phone.addElement("type");
nokia.addAttribute("name", "nokia");
Element price_nokia = nokia.addElement("price");
price_nokia.addText("599");
Element operator_nokia = nokia.addElement("operator");
operator_nokia.addText("CMCC");

Element xiaomi = phone.addElement("type");
xiaomi.addAttribute("name", "xiaomi");
Element price_xiaomi = xiaomi.addElement("price");
price_xiaomi.addText("699");
Element operator_xiaomi = xiaomi.addElement("operator");
operator_xiaomi.addText("ChinaNet");

//--------
StringWriter strWtr = new StringWriter();
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("UTF-8");
XMLWriter xmlWriter =new XMLWriter(strWtr, format);
try {
xmlWriter.write(document);
} catch (IOException e1) {
// TODO Auto-generated catch block
e1.printStackTrace();
}
strXML = strWtr.toString();
//--------

//-------
//strXML=document.asXML();
//------

//-------------
File file = new File("TelePhone.xml");
if (file.exists()) {
file.delete();
}
try {
file.createNewFile();
XMLWriter out = new XMLWriter(new FileWriter(file));
out.write(document);
out.flush();
out.close();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
//--------------

return strXML;
}

public void parserXML(String strXML){
SAXReader reader = new SAXReader();
StringReader sr = new StringReader(strXML);
InputSource is = new InputSource(sr);
try {
Document document = reader.read(is);

Element root = document.getRootElement();

//get element
List<Element> phoneList = root.elements("TelePhone");
List<Element> typeList = phoneList.get(0).elements("type");
for (int i=0;i<typeList.size();i++){
Element element = typeList.get(i);
String phoneName = element.attributeValue("name");
System.out.println("phonename = "+phoneName);
//get all element
List<Element> childList = element.elements();
for (int j=0;j<childList.size();j++){
Element e = childList.get(j);
System.out.println(e.getName()+"="+e.getText());
}
}
} catch (DocumentException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

public void parserXMLbyXPath(String strXML){
SAXReader reader = new SAXReader();
StringReader sr = new StringReader(strXML);
InputSource is = new InputSource(sr);
try {
Document document = reader.read(is);
List list = document.selectNodes("/root/TelePhone/type");
for(int i=0;i<list.size();i++){
Element e = (Element) list.get(i);
System.out.println("phonename="+e.attributeValue("name"));
List list1 = e.selectNodes("./*");
for(int j=0;j<list1.size();j++){
Element e1 = (Element) list1.get(j);
System.out.println(e1.getName()+"="+e1.getText());
}
}
} catch (DocumentException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}

/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
XMLHandler handler = new XMLHandler();
String strXML=handler.createXML();
System.out.println(strXML);
handler.parserXML(strXML);
System.out.println("-----------");
handler.parserXMLbyXPath(strXML);
}

}

5)XPATH

(1)简介

XPath是一门在XML文档中查找信息的语言。XPath用于在XML文档中通过元素和属性进行导航。

具体语法介绍参考：http://w3school.com.cn/xpath/index.asp

(2)示例代码：

import java.io.IOException;
import java.io.StringReader;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.xpath.XPath;
import javax.xml.xpath.XPathConstants;
import javax.xml.xpath.XPathExpression;
import javax.xml.xpath.XPathExpressionException;
import javax.xml.xpath.XPathFactory;

import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

public class XMLHandler {

public XMLHandler() {
// TODO Auto-generated constructor stub
}

public void parserXML(String strXML){
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder builder = factory.newDocumentBuilder();
StringReader sr = new StringReader(strXML);
InputSource is = new InputSource(sr);
Document doc = builder.parse(is);

XPathFactory xFactory = XPathFactory.newInstance();
XPath xpath = xFactory.newXPath();
XPathExpression expr = xpath.compile("/root/TelePhone/type");
NodeList phones = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
for (int i = 0; i < phones.getLength(); i++) {
Node type = phones.item(i);
String phoneName = ((Element)type).getAttribute("name");
System.out.println("Phone name = "+phoneName);
XPathExpression expr1 = xpath.compile("./*");
NodeList list = (NodeList) expr1.evaluate(type, XPathConstants.NODESET);
for(int j =0;j<list.getLength();j++){
Element e1 = (Element) list.item(j);
System.out.println(e1.getNodeName()+"="+e1.getTextContent());
}

}
} catch (ParserConfigurationException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}catch (SAXException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}catch (XPathExpressionException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}

}
/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub
String strXML="<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>"+
"<root>"+
"<TelePhone>"+
"<type name=\"nokia\">"+
"<price>599</price>"+
"<operator>CMCC</operator>"+
"</type>"+
"<type name=\"xiaomi\">"+
"<price>699</price>"+
"<operator>ChinaNet</operator>"+
"</type>"+
"</TelePhone>"+
"</root>";
XMLHandler handler = new XMLHandler();
handler.parserXML(strXML);
}

}