代码即财富之我学XML
<?xml version="1.0" encoding="utf-8"?> <users> <user id="1"> <name>Andrea</name> <age>10</age> <gender>Male</gender> </user> <user id="2"> <name>Bell</name> <age>20</age> <gender>Male</gender> </user> <user id="3"> <name>Calinda</name> <age>30</age> <gender>Female</gender> </user> </users>
上面即使基本的XML文件，一个XML文件分为头信息和数据区，头信息即上述XML文件的第一行，<?xml version="1.0" encoding="utf-8" ?>该头信息指定XML文件的版本和字符编码。除去第一行之后的内容都属于本XML文件的数据区，即数据保存部分。其中根元素为users，又包含3个user元素，user元素有id属性和3个标签元素，分别是name,age和gender。
下面介绍XML文件的四种解析方式，DOM方式，SAX解析，JDOM方式以及DOM4J方式，以简单工厂设计模式，先定义一个基本的XML解析接口作为产品接口,包含解析xml，和生成xml文件两个抽象方法，再定义4个具体的产品类即4种XML解析方式，以枚举方式描述。定义解析工厂。
/**
* ParserMethod enum
*/
enum ParserMethod{
DOM,SAX,JDOM,DOM4J
}
/**
* HelperFactory to manufacture XmlHelper
* a static method is needed
*/
class XmlHelperFactory{
public static XmlHelper newInstance(ParserMethod method){
XmlHelper helper = null;
switch (method) {
case DOM:
helper = new DomHelper();
break;
case SAX:
helper = new SaxHelper();
break;
case JDOM:
helper = new JDomHelper();
break;
case DOM4J:
helper = new Dom4JHelper();
break;
default:
break;
}
return helper;
}
}
/**
* Base XmlHelper interface
*/
interface XmlHelper{
void parseXml(String fileName)throws Exception ;
void writeXml(String fileName) throws Exception ;
}
第一种即为W3C推荐的标准，DOM解析方式，以DOM树的形式将整个XML文件结构装载到内存中，要知道对于一个大而复杂的XML文件，在内存中建立它的DOM树形式是非常耗费空间的，因此DOM解析方式适合解析那些XML文件较小，内容需要经常修改，结构较为简单的。对于小XML文件，使用DOM解析方式，非常简单，且易于理解，由于DOM树存于内存中，支持随意读取，对于上述XML文件，只要将其想象成一颗树，根元素为users。解析代码如下：
/**
* DomHelper, a concrete XmlHelper product
*/
class DomHelper implements XmlHelper {
private DocumentBuilder builder = null;
public DomHelper(){
try{
DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
builder = factory.newDocumentBuilder();
}catch(Exception e){
}
}
public void parseXml(String fileName) throws Exception {
Document document = builder.parse(fileName);
NodeList nodes = document.getChildNodes();//document.getElementByTagName("users");
for(int i=0;i<nodes.getLength();i++){
Node users = nodes.item(i);
NodeList user = users.getChildNodes();
for(int j=0;j<user.getLength();j++){
Node userInfo = user.item(j);
NamedNodeMap userAttr = userInfo.getAttributes();
if(userAttr != null && userAttr.getLength() > 0){
for(int at=0;at<userAttr.getLength();at++){
System.out.print(userAttr.item(at).getNodeName() +
"=" + userAttr.item(at).getTextContent());
}
}
NodeList infoMeta = userInfo.getChildNodes();
for(int k=0;k<infoMeta.getLength();k++){
if(infoMeta.item(k).getNodeName() != "#text"){
System.out.print(infoMeta.item(k).getNodeName() +
":" + infoMeta.item(k).getTextContent());
}
System.out.print("\t");
}
System.out.println();
}
}
}
public void writeXml(String fileName) throws Exception{
Document document = builder.newDocument();
Node users = document.createElement("users");
Node user = document.createElement("user");
Node name = document.createElement("name");
Node age = document.createElement("age");
Node gender = document.createElement("gender");
name.appendChild(document.createTextNode("zhangsan"));
age.appendChild(document.createTextNode("20"));
gender.appendChild(document.createTextNode("Male"));
user.appendChild(name);
user.appendChild(age);
user.appendChild(gender);
users.appendChild(user);
document.appendChild(users);
TransformerFactory factory = TransformerFactory.newInstance();
Transformer transformer = factory.newTransformer();
transformer.setOutputProperty(OutputKeys.ENCODING,"utf-8");
DOMSource source = new DOMSource(document);
StreamResult result = new StreamResult(new File(fileName));
transformer.transform(source,result);
}
}
在主函数中使用该种解析方式，输出如下：
public class TestXml{
public static void main(String[] args) throws Exception {
//Simple factory mode
XmlHelper helper = XmlHelperFactory.newInstance(ParserMethod.DOM4J);
helper.parseXml("./example.xml");
helper.writeXml("./output.xml");
}
}
id=1 name:Andrea age:10 gender:Male
id=2 name:Bell age:20 gender:Male
id=3 name:Calinda age:30 gender:Female
第二种方式为SAX解析方式，也是W3C提供的xml解析标准，与DOM解析方式不同的是，SAX解析以事件驱动方式进行，顺序部分解析，还必须定义自己的事件处理器类，该类继承自DefaultHandler类。主要方法有startDocument方法，文档开始自动调用，endDocument文档结束自动调用，startElement，元素开始自动调用（根元素和节点元素都是如此）,endElement，元素结束自动调用。characters方法遇到具体的元素结点内部值会自动调用，并解析。SAX解析方式不在乎文档大小，即时加载元素结点，存在于内存的东西相当少，因此SAX解析方式更加灵活，可以针对那些XML文档较大的解析，SAX易于读取，但不支持文件修改,因此transformXml方法无内容。
/**
* SaxHelper, another XmlHelper product
*/
class SaxHelper implements XmlHelper {
public void parseXml(String fileName) throws Exception{
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser parser = factory.newSAXParser();
parser.parse(fileName,new MySaxHandler());
}
public void writeXml(String fileName) throws Exception {
}
}
class MySaxHandler extends DefaultHandler{
public void startDocument() throws SAXException {
System.out.println("<?xml version=\"1.0\" encoding=\"utf-8\"");
}
public void endDocument() throws SAXException{
System.out.println("document ended!");
}
public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
System.out.print("<");
System.out.print(qName);
if(attributes.getLength() > 0){
for(int i=0;i<attributes.getLength();i++){
System.out.print(" "+attributes.getQName(i)+"=\"" + attributes.getValue(i)+"\"");
}
}
System.out.print(">");
}
public void endElement(String uri,String localName,String qName) throws SAXException {
System.out.print("</");
System.out.print(qName);
System.out.print(">");
}
public void characters(char[] ch, int start, int length){
System.out.print(new String(ch,start,length));
}
}
输出如下：
<?xml version="1.0" encoding="utf-8"
<users>
<user id="1">
<name>Andrea</name>
<age>10</age>
<gender>Male</gender>
</user>
<user id="2">
<name>Bell</name>
<age>20</age>
<gender>Male</gender>
</user>
<user id="3">
<name>Calinda</name>
<age>30</age>
<gender>Female</gender>
</user>
</users>document ended!
第三种方式JDOM方式，JDOM解析方式=DOM可以修改+SAX大文件读取，相对DOM解析方式，更加简单灵活，统一以Element组织。
/**
* Dom4JHelper, another XmlHelper product
*/
class Dom4JHelper implements XmlHelper {
public void parseXml(String fileName) throws Exception{
SAXReader reader = new SAXReader();
org.dom4j.Document document = reader.read(new File(fileName));
org.dom4j.Element users = document.getRootElement();
Iterator<org.dom4j.Element> userIter = users.elementIterator();
while (userIter.hasNext()) {
org.dom4j.Element user = userIter.next();
List<org.dom4j.Attribute> userAttr = user.attributes();
for(int i=0;i<userAttr.size();i++){
org.dom4j.Attribute attr = userAttr.get(i);
System.out.println(attr.getName()+":"+attr.getValue());
}
Iterator<org.dom4j.Element> infoIter = user.elementIterator();
while(infoIter.hasNext()){
org.dom4j.Element info = infoIter.next();
System.out.println(info.getName()+":"+info.getText());
}
System.out.println();
}
}
public void writeXml(String fileName) throws Exception {
org.dom4j.Document document = DocumentHelper.createDocument();
org.dom4j.Element users = document.addElement("users");
org.dom4j.Element user = users.addElement("user");
org.dom4j.Element name = user.addElement("name");
org.dom4j.Element age = user.addElement("age");
org.dom4j.Element gender = user.addElement("gender");
user.addAttribute("id", "1");
name.setText("zhangsan");
age.setText("20");
gender.setText("Male");
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("utf-8");
XMLWriter writer = new XMLWriter(new FileOutputStream(new File(fileName)));
writer.write(document);
writer.close();
}
}
第四种方式为DOM4J方式，Hibernate和Spring等框架都采用DOM4J方式支持XML文件的解析。生成xml文件时，Document对象是依靠DocumentHelper的createDocument完成
class Dom4JParser implements XmlParser {
public void parseXml(String fileName) throws Exception{
SAXReader reader = new SAXReader();
org.dom4j.Document document = reader.read(new File(fileName));
org.dom4j.Element users = document.getRootElement();
Iterator<org.dom4j.Element> userIter = users.elementIterator();
while (userIter.hasNext()) {
org.dom4j.Element user = userIter.next();
List<org.dom4j.Attribute> userAttr = user.attributes();
for(int i=0;i<userAttr.size();i++){
org.dom4j.Attribute attr = userAttr.get(i);
System.out.println(attr.getName()+":"+attr.getValue());
}
Iterator<org.dom4j.Element> infoIter = user.elementIterator();
while(infoIter.hasNext()){
org.dom4j.Element info = infoIter.next();
System.out.println(info.getName()+":"+info.getText());
}
System.out.println();
}
}
public void transformXml(String fileName) throws Exception {
org.dom4j.Document document = DocumentHelper.createDocument();
org.dom4j.Element users = document.addElement("users");
org.dom4j.Element user = users.addElement("user");
org.dom4j.Element name = user.addElement("name");
org.dom4j.Element age = user.addElement("age");
org.dom4j.Element gender = user.addElement("gender");
user.addAttribute("id", "1");
name.setText("zhangsan");
age.setText("20");
gender.setText("Male");
OutputFormat format = OutputFormat.createPrettyPrint();
format.setEncoding("utf-8");
XMLWriter writer = new XMLWriter(new FileOutputStream(new File(fileName)));
writer.write(document);
writer.close();
}
}