Java解析XML汇总

【引言】
目前在Java中用于解析XML的技术很多，主流的有DOM、SAX、JDOM、DOM4j，下文主要介绍这4种解析XML文档技术的使用、优缺点及性能测试。

一、【基础知识——扫盲】
sax、dom是两种对xml文档进行解析的方法(没有具体实现，只是接口)，所以只有它们是无法解析xml文档的；jaxp只是api，它进一步封装了sax、dom两种接口，并且提供了DomcumentBuilderFactory/DomcumentBuilder和SAXParserFactory/SAXParser（默认使用xerces解释器）。

二、【DOM、SAX、JDOM、DOM4j简单使用介绍】
1、【DOM(Document Object Model) 】
由W3C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。
示例代码：

[html] view plaincopyprint?
<?xml version="1.0" encoding="UTF-8"?>
<university name="pku">
<college name="c1">
<class name="class1">
<student name="stu1" sex='male' age="21" />
<student name="stu2" sex='female' age="20" />
<student name="stu3" sex='female' age="20" />
</class>
<class name="class2">
<student name="stu4" sex='male' age="19" />
<student name="stu5" sex='female' age="20" />
<student name="stu6" sex='female' age="21" />
</class>
</college>
<college name="c2">
<class name="class3">
<student name="stu7" sex='male' age="20" />
</class>
</college>
<college name="c3">
</college>
</university>
<?xml version="1.0" encoding="UTF-8"?>
<university name="pku">
    <college name="c1">
        <class name="class1">
            <student name="stu1" sex='male' age="21" />
            <student name="stu2" sex='female' age="20" />
            <student name="stu3" sex='female' age="20" />
        </class>
        <class name="class2">
            <student name="stu4" sex='male' age="19" />
            <student name="stu5" sex='female' age="20" />
            <student name="stu6" sex='female' age="21" />
        </class>
    </college>
    <college name="c2">
        <class name="class3">
            <student name="stu7" sex='male' age="20" />
        </class>
    </college>
    <college name="c3">
    </college>
</university>
后文代码中有使用到text.xml（该文档放在src路径下，既编译后在classes路径下），都是指该xml文档。

[java] view plaincopyprint?
package test.xml;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;

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.w3c.dom.Text;
import org.xml.sax.SAXException;

public class TestDom {

public static void main(String[] args) {
read();
//write();
}

public static void read() {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder builder = dbf.newDocumentBuilder();
InputStream in = TestDom.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = builder.parse(in);
// root <university>
Element root = doc.getDocumentElement();
if (root == null) return;
System.err.println(root.getAttribute("name"));
// all college node
NodeList collegeNodes = root.getChildNodes();
if (collegeNodes == null) return;
for(int i = 0; i < collegeNodes.getLength(); i++) {
Node college = collegeNodes.item(i);
if (college != null && college.getNodeType() == Node.ELEMENT_NODE) {
System.err.println(" " + college.getAttributes().getNamedItem("name").getNodeValue());
// all class node
NodeList classNodes = college.getChildNodes();
if (classNodes == null) continue;
for (int j = 0; j < classNodes.getLength(); j++) {
Node clazz = classNodes.item(j);
if (clazz != null && clazz.getNodeType() == Node.ELEMENT_NODE) {
System.err.println(" " + clazz.getAttributes().getNamedItem("name").getNodeValue());
// all student node
NodeList studentNodes = clazz.getChildNodes();
if (studentNodes == null) continue;
for (int k = 0; k < studentNodes.getLength(); k++) {
Node student = studentNodes.item(k);
if (student != null && student.getNodeType() == Node.ELEMENT_NODE) {
System.err.print(" " + student.getAttributes().getNamedItem("name").getNodeValue());
System.err.print(" " + student.getAttributes().getNamedItem("sex").getNodeValue());
System.err.println(" " + student.getAttributes().getNamedItem("age").getNodeValue());
}
}
}
}
}
}
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}

}

public static void write() {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder builder = dbf.newDocumentBuilder();
InputStream in = TestDom.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = builder.parse(in);
// root <university>
Element root = doc.getDocumentElement();
if (root == null) return;
// 修改属性
root.setAttribute("name", "tsu");
NodeList collegeNodes = root.getChildNodes();
if (collegeNodes != null) {
for (int i = 0; i <collegeNodes.getLength() - 1; i++) {
// 删除节点
Node college = collegeNodes.item(i);
if (college.getNodeType() == Node.ELEMENT_NODE) {
String collegeName = college.getAttributes().getNamedItem("name").getNodeValue();
if ("c1".equals(collegeName) || "c2".equals(collegeName)) {
root.removeChild(college);
} else if ("c3".equals(collegeName)) {
Element newChild = doc.createElement_x("class");
newChild.setAttribute("name", "c4");
college.a(newChild);
}
}
}
}
// 新增节点
Element addCollege = doc.createElement_x("college");
addCollege.setAttribute("name", "c5");
root.a(addCollege);
Text text = doc.createTextNode("text");
addCollege.a(text);

// 将修改后的文档保存到文件
TransformerFactory transFactory = TransformerFactory.newInstance();
Transformer transFormer = transFactory.newTransformer();
DOMSource domSource = new DOMSource(doc);
File file = new File("src/dom-modify.xml");
if (file.exists()) {
file.delete();
}
file.createNewFile();
FileOutputStream out = new FileOutputStream(file);
StreamResult xmlResult = new StreamResult(out);
transFormer.transform(domSource, xmlResult);
System.out.println(file.getAbsolutePath());
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} catch (TransformerConfigurationException e) {
e.printStackTrace();
} catch (TransformerException e) {
e.printStackTrace();
}
}
}
package test.xml;

import java.io.File;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;

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.w3c.dom.Text;
import org.xml.sax.SAXException;

public class TestDom {
   
    public static void main(String[] args) {
        read();
        //write();
    }
   
    public static void read() {
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        try {
            DocumentBuilder builder = dbf.newDocumentBuilder();
            InputStream in = TestDom.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = builder.parse(in);
            // root <university>
            Element root = doc.getDocumentElement();
            if (root == null) return;
            System.err.println(root.getAttribute("name"));
            // all college node
            NodeList collegeNodes = root.getChildNodes();
            if (collegeNodes == null) return;
            for(int i = 0; i < collegeNodes.getLength(); i++) {
                Node college = collegeNodes.item(i);
                if (college != null && college.getNodeType() == Node.ELEMENT_NODE) {
                    System.err.println(" " + college.getAttributes().getNamedItem("name").getNodeValue());
                    // all class node
                    NodeList classNodes = college.getChildNodes();
                    if (classNodes == null) continue;
                    for (int j = 0; j < classNodes.getLength(); j++) {
                        Node clazz = classNodes.item(j);
                        if (clazz != null && clazz.getNodeType() == Node.ELEMENT_NODE) {
                            System.err.println(" " + clazz.getAttributes().getNamedItem("name").getNodeValue());
                            // all student node
                            NodeList studentNodes = clazz.getChildNodes();
                            if (studentNodes == null) continue;
                            for (int k = 0; k < studentNodes.getLength(); k++) {
                                Node student = studentNodes.item(k);
                                if (student != null && student.getNodeType() == Node.ELEMENT_NODE) {
                                    System.err.print(" " + student.getAttributes().getNamedItem("name").getNodeValue());
                                    System.err.print(" " + student.getAttributes().getNamedItem("sex").getNodeValue());
                                    System.err.println(" " + student.getAttributes().getNamedItem("age").getNodeValue());
                                }
                            }
                        }
                    }
                }
            }
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
       
    }
   
    public static void write() {
        DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
        try {
            DocumentBuilder builder = dbf.newDocumentBuilder();
            InputStream in = TestDom.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = builder.parse(in);
            // root <university>
            Element root = doc.getDocumentElement();
            if (root == null) return;
            // 修改属性
            root.setAttribute("name", "tsu");
            NodeList collegeNodes = root.getChildNodes();
            if (collegeNodes != null) {
                for (int i = 0; i <collegeNodes.getLength() - 1; i++) {
                    // 删除节点
                    Node college = collegeNodes.item(i);
                    if (college.getNodeType() == Node.ELEMENT_NODE) {
                        String collegeName = college.getAttributes().getNamedItem("name").getNodeValue();
                        if ("c1".equals(collegeName) || "c2".equals(collegeName)) {
                            root.removeChild(college);
                        } else if ("c3".equals(collegeName)) {
                            Element newChild = doc.createElement_x("class");
                            newChild.setAttribute("name", "c4");
                            college.a(newChild);
                        }
                    }
                }
            }
            // 新增节点
            Element addCollege = doc.createElement_x("college");
            addCollege.setAttribute("name", "c5");
            root.a(addCollege);
            Text text = doc.createTextNode("text");
            addCollege.a(text);
           
            // 将修改后的文档保存到文件
            TransformerFactory transFactory = TransformerFactory.newInstance();
            Transformer transFormer = transFactory.newTransformer();
            DOMSource domSource = new DOMSource(doc);
            File file = new File("src/dom-modify.xml");
            if (file.exists()) {
                file.delete();
            }
            file.createNewFile();
            FileOutputStream out = new FileOutputStream(file);        
            StreamResult xmlResult = new StreamResult(out);
            transFormer.transform(domSource, xmlResult);
            System.out.println(file.getAbsolutePath());
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } catch (TransformerConfigurationException e) {
            e.printStackTrace();
        } catch (TransformerException e) {
            e.printStackTrace();
        }
    }
}
该代码只要稍做修改，即可变得更加简洁，无需一直写if来判断是否有子节点。

2、【SAX (Simple API for XML) 】
SAX不用将整个文档加载到内存，基于事件驱动的API(Observer模式)，用户只需要注册自己感兴趣的事件即可。SAX提供EntityResolver, DTDHandler, ContentHandler, ErrorHandler接口，分别用于监听解析实体事件、DTD处理事件、正文处理事件和处理出错事件，与AWT类似，SAX还提供了一个对这4个接口默认的类DefaultHandler（这里的默认实现，其实就是一个空方法），一般只要继承DefaultHandler，重写自己感兴趣的事件即可。
示例代码：

[java] view plaincopyprint?
package test.xml;

import java.io.IOException;
import java.io.InputStream;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.helpers.DefaultHandler;

public class TestSAX {

public static void main(String[] args) {
read();
write();
}

public static void read() {
try {
SAXParserFactory factory = SAXParserFactory.newInstance();
SAXParser parser = factory.newSAXParser();
InputStream in = TestSAX.class.getClassLoader().getResourceAsStream("test.xml");
parser.parse(in, new MyHandler());
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

public static void write() {
System.err.println("纯SAX对于写操作无能为力");
}

}

// 重写对自己感兴趣的事件处理方法
class MyHandler extends DefaultHandler {

@Override
public InputSource resolveEntity(String publicId, String systemId)
throws IOException, SAXException {
return super.resolveEntity(publicId, systemId);
}

@Override
public void notationDecl(String name, String publicId, String systemId)
throws SAXException {
super.notationDecl(name, publicId, systemId);
}

@Override
public void unparsedEntityDecl(String name, String publicId,
String systemId, String notationName) throws SAXException {
super.unparsedEntityDecl(name, publicId, systemId, notationName);
}

@Override
public void setDocumentLocator(Locator locator) {
super.setDocumentLocator(locator);
}

@Override
public void startDocument() throws SAXException {
System.err.println("开始解析文档");
}

@Override
public void endDocument() throws SAXException {
System.err.println("解析结束");
}

@Override
public void startPrefixMapping(String prefix, String uri)
throws SAXException {
super.startPrefixMapping(prefix, uri);
}

@Override
public void endPrefixMapping(String prefix) throws SAXException {
super.endPrefixMapping(prefix);
}

@Override
public void startElement(String uri, String localName, String qName,
Attributes attributes) throws SAXException {
System.err.print("Element: " + qName + ", attr: ");
print(attributes);
}

@Override
public void endElement(String uri, String localName, String qName)
throws SAXException {
super.endElement(uri, localName, qName);
}

@Override
public void characters(char[] ch, int start, int length)
throws SAXException {
super.characters(ch, start, length);
}

@Override
public void ignorableWhitespace(char[] ch, int start, int length)
throws SAXException {
super.ignorableWhitespace(ch, start, length);
}

@Override
public void processingInstruction(String target, String data)
throws SAXException {
super.processingInstruction(target, data);
}

@Override
public void skippedEntity(String name) throws SAXException {
super.skippedEntity(name);
}

@Override
public void warning(SAXParseException e) throws SAXException {
super.warning(e);
}

@Override
public void error(SAXParseException e) throws SAXException {
super.error(e);
}

@Override
public void fatalError(SAXParseException e) throws SAXException {
super.fatalError(e);
}

private void print(Attributes attrs) {
if (attrs == null) return;
System.err.print("[");
for (int i = 0; i < attrs.getLength(); i++) {
System.err.print(attrs.getQName(i) + " = " + attrs.getValue(i));
if (i != attrs.getLength() - 1) {
System.err.print(", ");
}
}
System.err.println("]");
}
}
package test.xml;

import java.io.IOException;
import java.io.InputStream;

import javax.xml.parsers.ParserConfigurationException;
import javax.xml.parsers.SAXParser;
import javax.xml.parsers.SAXParserFactory;

import org.xml.sax.Attributes;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.helpers.DefaultHandler;

public class TestSAX {

    public static void main(String[] args) {
        read();
        write();
    }
   
    public static void read() {
        try {
            SAXParserFactory factory = SAXParserFactory.newInstance();
            SAXParser parser = factory.newSAXParser();
            InputStream in = TestSAX.class.getClassLoader().getResourceAsStream("test.xml");
            parser.parse(in, new MyHandler());
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
   
    public static void write() {
        System.err.println("纯SAX对于写操作无能为力");
    }
   
}

// 重写对自己感兴趣的事件处理方法
class MyHandler extends DefaultHandler {

    @Override
    public InputSource resolveEntity(String publicId, String systemId)
            throws IOException, SAXException {
        return super.resolveEntity(publicId, systemId);
    }

    @Override
    public void notationDecl(String name, String publicId, String systemId)
            throws SAXException {
        super.notationDecl(name, publicId, systemId);
    }

    @Override
    public void unparsedEntityDecl(String name, String publicId,
            String systemId, String notationName) throws SAXException {
        super.unparsedEntityDecl(name, publicId, systemId, notationName);
    }

    @Override
    public void setDocumentLocator(Locator locator) {
        super.setDocumentLocator(locator);
    }

    @Override
    public void startDocument() throws SAXException {
        System.err.println("开始解析文档");
    }

    @Override
    public void endDocument() throws SAXException {
        System.err.println("解析结束");
    }

    @Override
    public void startPrefixMapping(String prefix, String uri)
            throws SAXException {
        super.startPrefixMapping(prefix, uri);
    }

    @Override
    public void endPrefixMapping(String prefix) throws SAXException {
        super.endPrefixMapping(prefix);
    }

    @Override
    public void startElement(String uri, String localName, String qName,
            Attributes attributes) throws SAXException {
        System.err.print("Element: " + qName + ", attr: ");
        print(attributes);
    }

    @Override
    public void endElement(String uri, String localName, String qName)
            throws SAXException {
        super.endElement(uri, localName, qName);
    }

    @Override
    public void characters(char[] ch, int start, int length)
            throws SAXException {
        super.characters(ch, start, length);
    }

    @Override
    public void ignorableWhitespace(char[] ch, int start, int length)
            throws SAXException {
        super.ignorableWhitespace(ch, start, length);
    }

    @Override
    public void processingInstruction(String target, String data)
            throws SAXException {
        super.processingInstruction(target, data);
    }

    @Override
    public void skippedEntity(String name) throws SAXException {
        super.skippedEntity(name);
    }

    @Override
    public void warning(SAXParseException e) throws SAXException {
        super.warning(e);
    }

    @Override
    public void error(SAXParseException e) throws SAXException {
        super.error(e);
    }

    @Override
    public void fatalError(SAXParseException e) throws SAXException {
        super.fatalError(e);
    }
   
    private void print(Attributes attrs) {
        if (attrs == null) return;
        System.err.print("[");
        for (int i = 0; i < attrs.getLength(); i++) {
            System.err.print(attrs.getQName(i) + " = " + attrs.getValue(i));
            if (i != attrs.getLength() - 1) {
                System.err.print(", ");
            }
        }
        System.err.println("]");
    }
}
3、【JDOM】
JDOM与DOM非常类似，它是处理XML的纯JAVA API，API大量使用了Collections类，且JDOM仅使用具体类而不使用接口。　JDOM 它自身不包含解析器。它通常使用 SAX2 解析器来解析和验证输入 XML 文档（尽管它还可以将以前构造的 DOM 表示作为输入）。它包含一些转换器以将 JDOM 表示输出成 SAX2 事件流、DOM 模型或 XML 文本文档
示例代码：

[java] view plaincopyprint?
package test.xml;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.jdom.Attribute;
import org.jdom.Document;
import org.jdom.Element;
import org.jdom.JDOMException;
import org.jdom.input.SAXBuilder;
import org.jdom.output.XMLOutputter;

public class TestJDom {
public static void main(String[] args) {
//read();
write();
}

public static void read() {
try {
boolean validate = false;
SAXBuilder builder = new SAXBuilder(validate);
InputStream in = TestJDom.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = builder.build(in);
// 获取根节点 <university>
Element root = doc.getRootElement();
readNode(root, "");
} catch (JDOMException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

@SuppressWarnings("unchecked")
public static void readNode(Element root, String prefix) {
if (root == null) return;
// 获取属性
List<Attribute> attrs = root.getAttributes();
if (attrs != null && attrs.size() > 0) {
System.err.print(prefix);
for (Attribute attr : attrs) {
System.err.print(attr.getValue() + " ");
}
System.err.println();
}
// 获取他的子节点
List<Element> childNodes = root.getChildren();
prefix += " ";
for (Element e : childNodes) {
readNode(e, prefix);
}
}

public static void write() {
boolean validate = false;
try {
SAXBuilder builder = new SAXBuilder(validate);
InputStream in = TestJDom.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = builder.build(in);
// 获取根节点 <university>
Element root = doc.getRootElement();
// 修改属性
root.setAttribute("name", "tsu");
// 删除
boolean isRemoved = root.removeChildren("college");
System.err.println(isRemoved);
// 新增
Element newCollege = new Element("college");
newCollege.setAttribute("name", "new_college");
Element newClass = new Element("class");
newClass.setAttribute("name", "ccccc");
newCollege.addContent(newClass);
root.addContent(newCollege);
XMLOutputter out = new XMLOutputter();
File file = new File("src/jdom-modify.xml");
if (file.exists()) {
file.delete();
}
file.createNewFile();
FileOutputStream fos = new FileOutputStream(file);
out.output(doc, fos);
} catch (JDOMException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

}
package test.xml;

import java.io.File;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.jdom.Attribute;
import org.jdom.Document;
import org.jdom.Element;
import org.jdom.JDOMException;
import org.jdom.input.SAXBuilder;
import org.jdom.output.XMLOutputter;

public class TestJDom {
    public static void main(String[] args) {
        //read();
        write();
    }
   
    public static void read() {
        try {
            boolean validate = false;
            SAXBuilder builder = new SAXBuilder(validate);
            InputStream in = TestJDom.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = builder.build(in);
            // 获取根节点 <university>
            Element root = doc.getRootElement();
            readNode(root, "");
        } catch (JDOMException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
   
    @SuppressWarnings("unchecked")
    public static void readNode(Element root, String prefix) {
        if (root == null) return;
        // 获取属性
        List<Attribute> attrs = root.getAttributes();
        if (attrs != null && attrs.size() > 0) {
            System.err.print(prefix);
            for (Attribute attr : attrs) {
                System.err.print(attr.getValue() + " ");
            }
            System.err.println();
        }
        // 获取他的子节点
        List<Element> childNodes = root.getChildren();
        prefix += " ";
        for (Element e : childNodes) {
            readNode(e, prefix);
        }
    }
   
    public static void write() {
        boolean validate = false;
        try {
            SAXBuilder builder = new SAXBuilder(validate);
            InputStream in = TestJDom.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = builder.build(in);
            // 获取根节点 <university>
            Element root = doc.getRootElement();
            // 修改属性
            root.setAttribute("name", "tsu");
            // 删除
            boolean isRemoved = root.removeChildren("college");
            System.err.println(isRemoved);
            // 新增
            Element newCollege = new Element("college");
            newCollege.setAttribute("name", "new_college");
            Element newClass = new Element("class");
            newClass.setAttribute("name", "ccccc");
            newCollege.addContent(newClass);
            root.addContent(newCollege);
            XMLOutputter out = new XMLOutputter();
            File file = new File("src/jdom-modify.xml");
            if (file.exists()) {
                file.delete();
            }
            file.createNewFile();
            FileOutputStream fos = new FileOutputStream(file);
            out.output(doc, fos);
        } catch (JDOMException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
   
}
4、【DOM4j】
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
示例代码：

[java] view plaincopyprint?
package test.xml;

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.ProcessingInstruction;
import org.dom4j.VisitorSupport;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

public class TestDom4j {
public static void main(String[] args) {
read1();
//read2();
//write();
}

public static void read1() {
try {
SAXReader reader = new SAXReader();
InputStream in = TestDom4j.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = reader.read(in);
Element root = doc.getRootElement();
readNode(root, "");
} catch (DocumentException e) {
e.printStackTrace();
}
}

@SuppressWarnings("unchecked")
public static void readNode(Element root, String prefix) {
if (root == null) return;
// 获取属性
List<Attribute> attrs = root.attributes();
if (attrs != null && attrs.size() > 0) {
System.err.print(prefix);
for (Attribute attr : attrs) {
System.err.print(attr.getValue() + " ");
}
System.err.println();
}
// 获取他的子节点
List<Element> childNodes = root.elements();
prefix += " ";
for (Element e : childNodes) {
readNode(e, prefix);
}
}

public static void read2() {
try {
SAXReader reader = new SAXReader();
InputStream in = TestDom4j.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = reader.read(in);
doc.accept(new MyVistor());
} catch (DocumentException e) {
e.printStackTrace();
}
}

public static void write() {
try {
// 创建一个xml文档
Document doc = DocumentHelper.createDocument();
Element university = doc.addElement("university");
university.addAttribute("name", "tsu");
// 注释
university.addComment("这个是根节点");
Element college = university.addElement("college");
college.addAttribute("name", "cccccc");
college.setText("text");

File file = new File("src/dom4j-modify.xml");
if (file.exists()) {
file.delete();
}
file.createNewFile();
XMLWriter out = new XMLWriter(new FileWriter(file));
out.write(doc);
out.flush();
out.close();
} catch (IOException e) {
e.printStackTrace();
}
}
}

class MyVistor extends VisitorSupport {
public void visit(Attribute node) {
System.out.println("Attibute: " + node.getName() + "="
+ node.getValue());
}

public void visit(Element node) {
if (node.isTextOnly()) {
System.out.println("Element: " + node.getName() + "="
+ node.getText());
} else {
System.out.println(node.getName());
}
}

@Override
public void visit(ProcessingInstruction node) {
System.out.println("PI:" + node.getTarget() + " " + node.getText());
}
}
package test.xml;

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStream;
import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.Document;
import org.dom4j.DocumentException;
import org.dom4j.DocumentHelper;
import org.dom4j.Element;
import org.dom4j.ProcessingInstruction;
import org.dom4j.VisitorSupport;
import org.dom4j.io.SAXReader;
import org.dom4j.io.XMLWriter;

public class TestDom4j {
    public static void main(String[] args) {
        read1();
        //read2();
        //write();
    }

    public static void read1() {
        try {
            SAXReader reader = new SAXReader();
            InputStream in = TestDom4j.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = reader.read(in);
            Element root = doc.getRootElement();
            readNode(root, "");
        } catch (DocumentException e) {
            e.printStackTrace();
        }
    }
   
    @SuppressWarnings("unchecked")
    public static void readNode(Element root, String prefix) {
        if (root == null) return;
        // 获取属性
        List<Attribute> attrs = root.attributes();
        if (attrs != null && attrs.size() > 0) {
            System.err.print(prefix);
            for (Attribute attr : attrs) {
                System.err.print(attr.getValue() + " ");
            }
            System.err.println();
        }
        // 获取他的子节点
        List<Element> childNodes = root.elements();
        prefix += " ";
        for (Element e : childNodes) {
            readNode(e, prefix);
        }
    }
   
    public static void read2() {
        try {
            SAXReader reader = new SAXReader();
            InputStream in = TestDom4j.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = reader.read(in);
            doc.accept(new MyVistor());
        } catch (DocumentException e) {
            e.printStackTrace();
        }
    }
   
    public static void write() {
        try {
            // 创建一个xml文档
            Document doc = DocumentHelper.createDocument();
            Element university = doc.addElement("university");
            university.addAttribute("name", "tsu");
            // 注释
            university.addComment("这个是根节点");
            Element college = university.addElement("college");
            college.addAttribute("name", "cccccc");
            college.setText("text");
           
            File file = new File("src/dom4j-modify.xml");
            if (file.exists()) {
                file.delete();
            }
            file.createNewFile();
            XMLWriter out = new XMLWriter(new FileWriter(file));
            out.write(doc);
            out.flush();
            out.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

class MyVistor extends VisitorSupport {
    public void visit(Attribute node) {
        System.out.println("Attibute: " + node.getName() + "="
                + node.getValue());
    }

    public void visit(Element node) {
        if (node.isTextOnly()) {
            System.out.println("Element: " + node.getName() + "="
                    + node.getText());
        } else {
            System.out.println(node.getName());
        }
    }

    @Override
    public void visit(ProcessingInstruction node) {
        System.out.println("PI:" + node.getTarget() + " " + node.getText());
    }
}
三、【性能测试】
环境：AMD4400+ 2.0+GHz主频 JDK6.0
运行参数：-Xms400m -Xmx400m
xml文件大小：10.7M
结果：
DOM: >581297ms
SAX: 8829ms
JDOM: 581297ms
DOM4j: 5309ms
时间包括IO的，只是进行了简单的测试，仅供参考！！！！

四、【对比】
1、【DOM】
DOM是基于树的结构，通常需要加载整文档和构造DOM树，然后才能开始工作。
优点：
a、由于整棵树在内存中，因此可以对xml文档随机访问
b、可以对xml文档进行修改操作
c、较sax，dom使用也更简单。
缺点：
a、整个文档必须一次性解析完
a、由于整个文档都需要载入内存，对于大文档成本高
2、【SAX】
SAX类似流媒体，它基于事件驱动的，因此无需将整个文档载入内存，使用者只需要监听自己感兴趣的事件即可。
优点：
a、无需将整个xml文档载入内存，因此消耗内存少
b、可以注册多个ContentHandler
缺点：
a、不能随机的访问xml中的节点
b、不能修改文档
3、【JDOM】
JDOM是纯Java的处理XML的API，其API中大量使用Collections类，
优点：
a、DOM方式的优点
b、具有SAX的Java规则
缺点
a、DOM方式的缺点
4、【DOM4J】
这4中xml解析方式中，最优秀的一个，集易用和性能于一身。

五、【小插曲XPath】
XPath 是一门在 XML 文档中查找信息的语言， 可用来在 XML 文档中对元素和属性进行遍历。XPath 是 W3C XSLT 标准的主要元素，并且 XQuery 和 XPointer 同时被构建于 XPath 表达之上。因此，对 XPath 的理解是很多高级 XML 应用的基础。
XPath非常类似对数据库操作的SQL语言，或者说JQuery，它可以方便开发者抓起文档中需要的东西。（dom4j也支持xpath）
示例代码：

[java] view plaincopyprint?
package test.xml;

import java.io.IOException;
import java.io.InputStream;

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.NodeList;
import org.xml.sax.SAXException;

public class TestXPath {

public static void main(String[] args) {
read();
}

public static void read() {
try {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
DocumentBuilder builder = dbf.newDocumentBuilder();
InputStream in = TestXPath.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = builder.parse(in);
XPathFactory factory = XPathFactory.newInstance();
XPath xpath = factory.newXPath();
// 选取所有class元素的name属性
// XPath语法介绍： http://w3school.com.cn/xpath/
XPathExpression expr = xpath.compile("//class/@name");
NodeList nodes = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
for (int i = 0; i < nodes.getLength(); i++) {
System.out.println("name = " + nodes.item(i).getNodeValue());
}
} catch (XPathExpressionException e) {
e.printStackTrace();
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

}
package test.xml;

import java.io.IOException;
import java.io.InputStream;

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.NodeList;
import org.xml.sax.SAXException;

public class TestXPath {

    public static void main(String[] args) {
        read();
    }
   
    public static void read() {
        try {
            DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
            DocumentBuilder builder = dbf.newDocumentBuilder();
            InputStream in = TestXPath.class.getClassLoader().getResourceAsStream("test.xml");
            Document doc = builder.parse(in);
            XPathFactory factory = XPathFactory.newInstance();
            XPath xpath = factory.newXPath();
            // 选取所有class元素的name属性
            // XPath语法介绍： http://w3school.com.cn/xpath/
            XPathExpression expr = xpath.compile("//class/@name");
            NodeList nodes = (NodeList) expr.evaluate(doc, XPathConstants.NODESET);
            for (int i = 0; i < nodes.getLength(); i++) {
                System.out.println("name = " + nodes.item(i).getNodeValue());
                    }
        } catch (XPathExpressionException e) {
            e.printStackTrace();
        } catch (ParserConfigurationException e) {
            e.printStackTrace();
        } catch (SAXException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
   
}
六、【补充】

注意4种解析方法对TextNode（文本节点）的处理：

1、在使用DOM时，调用node.getChildNodes()获取该节点的子节点，文本节点也会被当作一个Node来返回，如：

[html] view plaincopyprint?
<?xml version="1.0" encoding="UTF-8"?>
<university name="pku">
<college name="c1">
<class name="class1">
<student name="stu1" sex='male' age="21" />
<student name="stu2" sex='female' age="20" />
<student name="stu3" sex='female' age="20" />
</class>
</college>
</university>
<?xml version="1.0" encoding="UTF-8"?>
<university name="pku">
 <college name="c1">
  <class name="class1">
   <student name="stu1" sex='male' age="21" />
   <student name="stu2" sex='female' age="20" />
   <student name="stu3" sex='female' age="20" />
  </class>
 </college>
</university>
[java] view plaincopyprint?
package test.xml;

import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;

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

public class TestDom2 {

public static void main(String[] args) {
read();
}

public static void read() {
DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
try {
DocumentBuilder builder = dbf.newDocumentBuilder();
InputStream in = TestDom2.class.getClassLoader().getResourceAsStream("test.xml");
Document doc = builder.parse(in);
// root <university>
Element root = doc.getDocumentElement();
if (root == null) return;
// System.err.println(root.getAttribute("name"));
// all college node
NodeList collegeNodes = root.getChildNodes();
if (collegeNodes == null) return;
System.err.println("university子节点数：" + collegeNodes.getLength());
System.err.println("子节点如下：");
for(int i = 0; i < collegeNodes.getLength(); i++) {
Node college = collegeNodes.item(i);
if (college == null) continue;
if (college.getNodeType() == Node.ELEMENT_NODE) {
System.err.println(" 元素节点：" + college.getNodeName());
} else if (college.getNodeType() == Node.TEXT_NODE) {
System.err.println(" 文本节点：" + Arrays.toString(college.getTextContent().getBytes()));
}
}
} catch (ParserConfigurationException e) {
e.printStackTrace();
} catch (FileNotFoundException e) {
e.printStackTrace();
} catch (SAXException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}

}
}
package test.xml;

import java.io.FileNotFoundException;
import java.io.IOException;
import java.io.InputStream;
import java.util.Arrays;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;

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

public class TestDom2 {
 
 public static void main(String[] args) {
  read();
 }
 
 public static void read() {
  DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
  try {
   DocumentBuilder builder = dbf.newDocumentBuilder();
   InputStream in = TestDom2.class.getClassLoader().getResourceAsStream("test.xml");
   Document doc = builder.parse(in);
   // root <university>
   Element root = doc.getDocumentElement();
   if (root == null) return;
//   System.err.println(root.getAttribute("name"));
   // all college node
   NodeList collegeNodes = root.getChildNodes();
   if (collegeNodes == null) return;
   System.err.println("university子节点数：" + collegeNodes.getLength());
   System.err.println("子节点如下：");
   for(int i = 0; i < collegeNodes.getLength(); i++) {
    Node college = collegeNodes.item(i);
    if (college == null) continue;
    if (college.getNodeType() == Node.ELEMENT_NODE) {
     System.err.println(" 元素节点：" + college.getNodeName());
    } else if (college.getNodeType() == Node.TEXT_NODE) {
     System.err.println(" 文本节点：" + Arrays.toString(college.getTextContent().getBytes()));
    }
   }
  } catch (ParserConfigurationException e) {
   e.printStackTrace();
  } catch (FileNotFoundException e) {
   e.printStackTrace();
  } catch (SAXException e) {
   e.printStackTrace();
  } catch (IOException e) {
   e.printStackTrace();
  }
  
 }
}

输出的结果是：

[java] view plaincopyprint?
university子节点数：3
子节点如下：
文本节点：[10, 9]
元素节点：college
文本节点：[10]
university子节点数：3
子节点如下：
 文本节点：[10, 9]
 元素节点：college
 文本节点：[10]
其中 的ASCII码为10， 的ASCII码为9。结果让人大吃一惊，university的子节点数不是1，也不是2，而是3，这3个子节点都是谁呢？为了看得更清楚点，把xml文档改为：

 

[html] view plaincopyprint?
<?xml version="1.0" encoding="UTF-8"?>
<university name="pku">11
<college name="c1">
<class name="class1">
<student name="stu1" sex='male' age="21" />
<student name="stu2" sex='female' age="20" />
<student name="stu3" sex='female' age="20" />
</class>
</college>22
</university>
<?xml version="1.0" encoding="UTF-8"?>
<university name="pku">11
 <college name="c1">
  <class name="class1">
   <student name="stu1" sex='male' age="21" />
   <student name="stu2" sex='female' age="20" />
   <student name="stu3" sex='female' age="20" />
  </class>
 </college>22
</university>
还是上面的程序，输出结果为：

[java] view plaincopyprint?
university子节点数：3
子节点如下：
文本节点：[49, 49, 10, 9]
元素节点：college
文本节点：[50, 50, 10]
university子节点数：3
子节点如下：
 文本节点：[49, 49, 10, 9]
 元素节点：college
 文本节点：[50, 50, 10]
其中数字1的ASCII码为49，数字2的ASCII码为50。

2、使用SAX来解析同DOM，当你重写它的public void characters(char[] ch, int start, int length)方法时，你就能看到。

3、JDOM，调用node.getChildren()只返回子节点，不包括TextNode节点（不管该节点是否有Text信息）。如果要获取该节点的Text信息，可以调用node.getText()方法，该方法返回节点的Text信息，也包括 等特殊字符。

4、DOM4j同JDOM

参考：

http://www.docin.com/p-78963650.html

http://wenku.baidu.com/view/b091f9360b4c2e3f5727638b.html

http://kree.iteye.com/blog/668280