dom4j的小例子

Posted 2020-08-09 掉尾瓶

1.要解析的xml文件book.xml

<?xml version="1.0" encoding="UTF-8"?>
<books>
	<book id="book1">
		<title>JAVA编程思想</title>
		<price>80.00</price>
	</book>
	<book id="book2">
		<title>JAVA核心技术</title>
		<price>100.00</price>
	</book>
</books>

 

 2.解析xml文件

package com.chen.dom;

import java.io.File;
import java.io.FileOutputStream;
import java.io.FileWriter;
import java.io.OutputStreamWriter;
import java.util.Iterator;
import java.util.List;

import org.dom4j.Attribute;
import org.dom4j.Document;
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.junit.Test;

public class Dom4jTest {
    @Test
    public void read() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read(new File("resource/book.xml"));
        Element root = document.getRootElement();
        Element book1 = (Element) root.elements("book").get(0);
        String id1 = book1.attributeValue("id");
        String titleText = book1.element("title").getTextTrim();
        System.out.println(id1 + "---" + titleText);
    }

    /*
     * 将整个xml使用递归完整输出
     */
    @Test
    public void readIterator() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read(new File("resource/book.xml"));
        Element root = document.getRootElement();
        // 递归解析xml
        parse(root);

    }

    // 递归解析xml
    public void parse(Element element) {
        System.out.print("<" + element.getName());
        // 遍历节点的属性
        List<Attribute> attributes = element.attributes();
        for (int i = 0; i < attributes.size(); i++) {
            Attribute attr = attributes.get(i);
            String name = attr.getName();
            String value = attr.getValue();
            System.out.print(" " + name + "=\"" + value + "\"");
        }
        System.out.println(">");
        // 获取节点的文本信息
        if (element.getTextTrim() != null && !"".equals(element.getTextTrim())) {
            System.out.println(element.getTextTrim());
        }
        // 对该节点进行递归
        for (Iterator i = element.elementIterator(); i.hasNext();) {
            parse((Element) i.next());
        }
        System.out.println("</" + element.getName() + ">");
    }

    @Test
    public void add() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read(new File("resource/book.xml"));
        Element root = document.getRootElement();
        Element book1 = (Element) root.elements("book").get(1);
        Element authorElement = book1.addElement("author")
                .addAttribute("id", "author2").addText("张三");
        
        
        OutputFormat format = OutputFormat.createPrettyPrint();
        //从这里可以看出dom4j默认的编码方式为utf-8
        System.out.println(format.getEncoding());
        //设置编码格式防止乱码   <?xml version="1.0" encoding="gb2312"?> 
        format.setEncoding("utf-8");
        
        //使用FileWriter会乱码，因为使用了默认的gb2312编码输出，而dom4j使用的是默认的UTF-8编码
        //如果format.setEncoding("gb2312"); 使用FileWriter就不会乱码
        //XMLWriter writer = new XMLWriter(new FileWriter("resource/book.xml"),format);
        
        //使用FileOutputStream输出时指定编码  这个编码要和format.setEncoding("utf-8"); 一样
        //XMLWriter writer = new XMLWriter(new OutputStreamWriter(new FileOutputStream("resource/book.xml"), "utf-8"),format);
        //最简单的方法是设置format.setEncoding("utf-8");然后使用字节流输出
        XMLWriter writer = new XMLWriter(new FileOutputStream("resource/book.xml"),format);
        
        writer.write(document);
        writer.close();
    }

    
    //在指定位置上添加个新节点(改变list集合的顺序)
    @Test
    public void add2() throws Exception {
        SAXReader reader = new SAXReader();
        Document document = reader.read(new File("resource/book.xml"));
        Element element = document.getRootElement().element("book");
        List list = element.elements();
        Element publishElement = DocumentHelper.createElement("publish");
        publishElement.addText("机械工业出版社");
        //改变list集合的顺序，就可以达到在指定位置添加新节点
        list.add(1, publishElement);
        
        OutputFormat format = OutputFormat.createPrettyPrint();
        format.setEncoding("utf-8");
        
        XMLWriter writer = new XMLWriter(new FileOutputStream("resource/book.xml"),format);
        writer.write(document);
        writer.close();
    }
}

xml乱码的样子：