java基础系列—

java基础系列——解析XML

测试用xml

<?xml version="1.0" encoding="UTF-8"?>
<employees>
    <employee>
        <name>LeoSun</name>
        <sex>m</sex>
        <age>26</age>
    </employee>
</employees>

接口XmlDocument 它定义了XML文档的建立与解析的接口。

/**
 *  它定义了XML文档的建立与解析的接口
 *  
 * Author: Leo Sun
 * Blog: http://fuxinci.com/
 * Date: 4/24/13
 */
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);
}

一、DOM生成和解析XML文档

View Code

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;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.*;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintWriter;

/**
 * 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）
 * 
 * Author: Leo Sun
 * Blog: http://fuxinci.com/
 * Date: 4/24/13
 */

public class DomDemo implements XmlDocument {
    private Document document;
    private String fileName;

    public void init() {
        try {
            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            DocumentBuilder builder = factory.newDocumentBuilder();
            this.document = builder.newDocument();
        } catch (ParserConfigurationException e) {
            System.out.println(e.getMessage());
        }
    }

    public void createXml(String fileName) {
        Element root = this.document.createElement("employees");
        this.document.appendChild(root);
        Element employee = this.document.createElement("employee");

        Element name = this.document.createElement("name");
        name.appendChild(this.document.createTextNode("丁宏亮"));
        employee.appendChild(name);

        Element sex = this.document.createElement("sex");
        sex.appendChild(this.document.createTextNode("m"));
        employee.appendChild(sex);

        Element age = this.document.createElement("age");
        age.appendChild(this.document.createTextNode("30"));
        employee.appendChild(age);

        root.appendChild(employee);

        TransformerFactory tf = TransformerFactory.newInstance();
        try {
            Transformer transformer = tf.newTransformer();
            DOMSource source = new DOMSource(document);
            transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
            transformer.setOutputProperty(OutputKeys.INDENT, "yes");
            PrintWriter pw = new PrintWriter(new FileOutputStream(fileName));
            StreamResult result = new StreamResult(pw);
            transformer.transform(source, result);

            System.out.println("生成XML文件成功!");
        } catch (TransformerConfigurationException e) {
            System.out.println(e.getMessage());
        } catch (IllegalArgumentException e) {
            System.out.println(e.getMessage());
        } catch (FileNotFoundException e) {
            System.out.println(e.getMessage());
        } catch (TransformerException e) {
            System.out.println(e.getMessage());
        }
    }

    public void parserXml(String fileName) {
        try {
            DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
            DocumentBuilder db = dbf.newDocumentBuilder();
            Document document = db.parse(fileName);
            NodeList employees = document.getChildNodes();

            for (int i = 0; i < employees.getLength(); i++) {
                Node employee = employees.item(i);
                NodeList employeeInfo = employee.getChildNodes();
                for (int j = 0; j < employeeInfo.getLength(); j++) {
                    Node node = employeeInfo.item(j);
                    NodeList employeeMeta = node.getChildNodes();
                    for (int k = 0; k < employeeMeta.getLength(); k++) {
                        System.out.println(employeeMeta.item(k).getNodeName()
                                + ":" + employeeMeta.item(k).getTextContent());
                    }
                }
            }

            System.out.println("解析完毕");
        } catch (FileNotFoundException e) {
            System.out.println(e.getMessage());
        } catch (ParserConfigurationException e) {
            System.out.println(e.getMessage());
        } catch (SAXException e) {
            System.out.println(e.getMessage());
        } catch (IOException e) {
            System.out.println(e.getMessage());
        }
    }
}

二、SAX生成和解析XML文档

View Code

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;

import javax.xml.parsers.DocumentBuilder;
import javax.xml.parsers.DocumentBuilderFactory;
import javax.xml.parsers.ParserConfigurationException;
import javax.xml.transform.*;
import javax.xml.transform.dom.DOMSource;
import javax.xml.transform.stream.StreamResult;
import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintWriter;

/**
 * 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）
 * 
 * Author: Leo Sun
 * Blog: http://fuxinci.com/
 * Date: 4/24/13
 */

public class DomDemo implements XmlDocument {
    private Document document;
    private String fileName;

    public void init() {
        try {
            DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
            DocumentBuilder builder = factory.newDocumentBuilder();
            this.document = builder.newDocument();
        } catch (ParserConfigurationException e) {
            System.out.println(e.getMessage());
        }
    }

    public void createXml(String fileName) {
        Element root = this.document.createElement("employees");
        this.document.appendChild(root);
        Element employee = this.document.createElement("employee");

        Element name = this.document.createElement("name");
        name.appendChild(this.document.createTextNode("丁宏亮"));
        employee.appendChild(name);

        Element sex = this.document.createElement("sex");
        sex.appendChild(this.document.createTextNode("m"));
        employee.appendChild(sex);

        Element age = this.document.createElement("age");
        age.appendChild(this.document.createTextNode("30"));
        employee.appendChild(age);

        root.appendChild(employee);

        TransformerFactory tf = TransformerFactory.newInstance();
        try {
            Transformer transformer = tf.newTransformer();
            DOMSource source = new DOMSource(document);
            transformer.setOutputProperty(OutputKeys.ENCODING, "utf-8");
            transformer.setOutputProperty(OutputKeys.INDENT, "yes");
            PrintWriter pw = new PrintWriter(new FileOutputStream(fileName));
            StreamResult result = new StreamResult(pw);
            transformer.transform(source, result);

            System.out.println("生成XML文件成功!");
        } catch (TransformerConfigurationException e) {
            System.out.println(e.getMessage());
        } catch (IllegalArgumentException e) {
            System.out.println(e.getMessage());
        } catch (FileNotFoundException e) {
            System.out.println(e.getMessage());
        } catch (TransformerException e) {
            System.out.println(e.getMessage());
        }
    }

    public void parserXml(String fileName) {
        try {
            DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance();
            DocumentBuilder db = dbf.newDocumentBuilder();
            Document document = db.parse(fileName);
            NodeList employees = document.getChildNodes();

            for (int i = 0; i < employees.getLength(); i++) {
                Node employee = employees.item(i);
                NodeList employeeInfo = employee.getChildNodes();
                for (int j = 0; j < employeeInfo.getLength(); j++) {
                    Node node = employeeInfo.item(j);
                    NodeList employeeMeta = node.getChildNodes();
                    for (int k = 0; k < employeeMeta.getLength(); k++) {
                        System.out.println(employeeMeta.item(k).getNodeName()
                                + ":" + employeeMeta.item(k).getTextContent());
                    }
                }
            }

            System.out.println("解析完毕");
        } catch (FileNotFoundException e) {
            System.out.println(e.getMessage());
        } catch (ParserConfigurationException e) {
            System.out.println(e.getMessage());
        } catch (SAXException e) {
            System.out.println(e.getMessage());
        } catch (IOException e) {
            System.out.println(e.getMessage());
        }
    }
}

三、DOM4J生成和解析XML文档

View Code

import java.io.File;
import java.io.FileWriter;
import java.io.IOException;
import java.io.Writer;
import java.util.Iterator;

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

/**
 * 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。
 * <p/>
 * Author: Leo Sun
 * Blog: http://fuxinci.com/
 * Date: 4/24/13
 */

public class Dom4jDemo implements XmlDocument {

    public void createXml(String fileName) {
        Document document = DocumentHelper.createDocument();

        Element employees = document.addElement("employees");
        Element employee = employees.addElement("employee");
        Element name = employee.addElement("name");
        name.setText("LeoSun");
        Element sex = employee.addElement("sex");
        sex.setText("m");
        Element age = employee.addElement("age");
        age.setText("29");

        try {
            Writer fileWriter = new FileWriter(fileName);
            XMLWriter xmlWriter = new XMLWriter(fileWriter);
            xmlWriter.write(document);
            xmlWriter.close();

        } catch (IOException e) {
            System.out.println(e.getMessage());
        }
    }


    public void parserXml(String fileName) {
        File inputXml = new File(fileName);
        SAXReader saxReader = new SAXReader();

        try {
            Document document = saxReader.read(inputXml);
            Element employees = document.getRootElement();

            for (Iterator i = employees.elementIterator(); i.hasNext(); ) {
                Element employee = (Element) i.next();
                for (Iterator j = employee.elementIterator(); j.hasNext(); ) {
                    Element node = (Element) j.next();
                    System.out.println(node.getName() + ":" + node.getText());
                }
            }
        } catch (DocumentException e) {
            System.out.println(e.getMessage());
        }
        System.out.println("dom4j parserXml");
    }
}

注：运行此代码必须引入dom4j的jar，可在maven 中添加

        <dependency>
            <groupId>maven</groupId>
            <artifactId>dom4j</artifactId>
            <version>1.7-20060614</version>
        </dependency>

四、JDOM生成和解析XML

View Code

import java.io.FileNotFoundException;
import java.io.FileOutputStream;
import java.io.IOException;
import java.util.List;

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

/**
 * 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。
 * Author: Leo Sun
 * Blog: http://fuxinci.com/
 * Date: 4/24/13
 */

public class JDomDemo implements XmlDocument {

    public void createXml(String fileName) {
        Element root = new Element("employees");
        Document document = new Document(root);

        Element employee = new Element("employee");
        root.addContent(employee);

        Element name = new Element("name");
        name.setText("LeoSun");
        employee.addContent(name);

        Element sex = new Element("sex");
        sex.setText("m");
        employee.addContent(sex);

        Element age = new Element("age");
        age.setText("23");
        employee.addContent(age);

        XMLOutputter XMLOut = new XMLOutputter();
        try {
            XMLOut.output(document, new FileOutputStream(fileName));
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public void parserXml(String fileName) {
        SAXBuilder builder = new SAXBuilder(false);

        try {
            Document document = builder.build(fileName);
            Element employees = document.getRootElement();
            List employeeList = employees.getChildren("employee");
            for (int i = 0; i < employeeList.size(); i++) {
                Element employee = (Element) employeeList.get(i);
                List employeeInfo = employee.getChildren();
                for (int j = 0; j < employeeInfo.size(); j++)
                    System.out.println(((Element) employeeInfo.get(j)).getName() + ":" + ((Element) employeeInfo.get(j)).getValue());
            }

        } catch (JDOMException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

注：运行此代码必须引入JDom的jar，可在maven 中添加

        <dependency>
            <groupId>org.jdom</groupId>
            <artifactId>jdom2</artifactId>
            <version>2.0.4</version>
        </dependency>

参考：http://developer.51cto.com/art/200903/117512.htm