java解析xml的方式总结

java对xml的操作主要有两种：dom解析和sax解析方式

1. dom方式

       dom方式的解析方法是一次性将xml文档加载到内存中。然后根据标签的层次关系，排列成类似一棵树的形状。

       例如：有下面的xml文档（test.xml)

<?xml version="1.0" encoding="UTF-8" ?>
<shelf>
    <book comment="first">
        <id>1</id>
        <name>aaaaa</name>
        <price>10.2</price>
    </book>
    
    <book>
        <id>1</id>
        <name>bbbb</name>
        <price>10</price>
    </book>
</shelf>

    使用dom 方式解析后的树状图为：

解析API:JAXP（Sun公司开发）、Jdom、dom4j,  其中，解析效率从小到大

2. sax方式

sax方式是一边读取文档，一边解析文档。当文档读取完成后，文档也就解析完成。

3.两种方式优缺点比较

	优点	缺点
dom方式	可以对xml文档方便的进行CRUD(增，删，改，查)操作	当文档太大的时候，比较消耗内存
sax方式	只能对xml文档进行读取，查询。也就是说插入、删除等操作是玩法进行的	消耗内存较小

4.具体代码示例

      示例中使用的xml文件为上述xml文档（test.xml）

下列代码有一部分是使用了Junit单元测试，不了解JUnit的，请读者自行学习

   4.1 JAXP方式

package com.zyh.xml;

import java.io.FileOutputStream;

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

import org.junit.Before;
import org.junit.Test;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;

//使用dom方式对xml进行CRUD
public class TestJAXPDom {

	DocumentBuilderFactory factory;
	DocumentBuilder builder;
	Document document;
	
	@Before
	public void befor() throws Exception {
//		实例化DocumentBuilderFactory，并创建新的DocumentBuilder
		factory = DocumentBuilderFactory.newInstance();
		builder = factory.newDocumentBuilder();
//		根据builder对象解析test.xml文件，产生Document对象
		document = builder.parse("src/test.xml");
	}
	
//	读取<name>bbbbb</name>节点的值
	@Test
	public void test()  {
//		获取到所有name结点
		NodeList lists = document.getElementsByTagName("name");
//		得到第二个name结点，以下标0开始算
		Node node = lists.item(1);
		System.out.println(node.getNodeName() + ":" + node.getTextContent());
	}
	
	@Test
	public void test2() throws Exception {
		Node root = document.getElementsByTagName("shelf").item(0);
//		递归获取各个结点
		list(root, 1);
	}

	private void list(Node node, int level) {
		String str = "";
		for(int i=0; i<level; i++) {
			str += " ";
		}
//		如果是元素结点，输出该节点的节点名称（其中会将空格解析为#text）
		if(node instanceof Element) {
			System.out.println(str + node.getNodeName());
		}
		
		NodeList lists = node.getChildNodes();
		for(int i=0; i<lists.getLength(); i++) {
			Node child = lists.item(i);
			list(child, level+1);
		}
	}
	
//	读取<book comment="first">中的属性comment的属性值
	@Test
	public void test3() throws Exception {
//		应为我们知道该结点是元素结点，可以直接强制转换成Element类型（Node类型无法直接得到属性值）
		Element element = (Element)document.getElementsByTagName("book").item(0);
//		根据Element队形的getAttribute方法得到属性值
		System.out.println(element.getAttribute("comment"));
	}
	
//	向第一个book节点添加一个元素节点<author>me</author>
	@Test
	public void add() throws Exception {
//		新建一个author节点
		Node author = document.createElement("author");
//		为author节点添加值me
		author.setTextContent("me");
		
		Node node = document.getElementsByTagName("book").item(0);
//		将author节点添加到book节点中
		node.appendChild(author);
		
//		以下是将新产生的xml写回到原文件中,如果不进行这一步，只是在内存中添加了一个节点，原文件并没有改变
		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer former = tf.newTransformer();
		former.transform(new DOMSource(document), new StreamResult(new FileOutputStream("src/test.xml")));
	}
	
//	向第一个book节点的指定位置如name节点之前添加一个节点<author>me</author>
	@Test
	public void add2() throws Exception {
//		新建一个author节点
		Node author = document.createElement("author");
//		为author节点添加值me
		author.setTextContent("me");
//		得到参考节点		
		Node refChild = document.getElementsByTagName("name").item(0);
//		得到要添加节点的父节点
		Node book = document.getElementsByTagName("book").item(0);
//		将author节点添加到指定位置
		book.insertBefore(author, refChild);
		
//		以下是将新产生的xml写回到原文件中,如果不进行这一步，只是在内存中添加了一个节点，原文件并没有改变
		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer former = tf.newTransformer();
		former.transform(new DOMSource(document), new StreamResult(new FileOutputStream("src/test.xml")));
	}
	
//	向第二个book节点添加属性comment,属性值为second
	@Test
	public void add3() throws Exception {
//		得到第二个book节点
		Element book = (Element)document.getElementsByTagName("book").item(1);
//		添加属性comment
		book.setAttribute("comment", "second");
		
//		以下是将新产生的xml写回到原文件中,如果不进行这一步，只是在内存中添加了一个节点，原文件并没有改变
		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer former = tf.newTransformer();
		former.transform(new DOMSource(document), new StreamResult(new FileOutputStream("src/test.xml")));
	}
	
//	删除第二个book节点的id节点
	@Test
	public void delete() throws Exception {
		Node book = document.getElementsByTagName("book").item(1);
		Node oldChild = document.getElementsByTagName("id").item(1);
		book.removeChild(oldChild);
		
		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer former = tf.newTransformer();
		former.transform(new DOMSource(document), new StreamResult(new FileOutputStream("src/test.xml")));
	}
	
//	更新第二个book节点的price节点的值为109
	@Test
	public void update() throws Exception {
		Node price = document.getElementsByTagName("price").item(1);
		
		price.setTextContent("109");
		
		TransformerFactory tf = TransformerFactory.newInstance();
		Transformer former = tf.newTransformer();
		former.transform(new DOMSource(document), new StreamResult(new FileOutputStream("src/test.xml")));
	}
}

  4.2 dom4j

     dom4j并不是sun公司开发的，因此需要第三方的api, jar包的下载请移步：http://download.youkuaiyun.com/download/zyh5540/5806377

package com.zyh.xml;

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

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 TestDom4j {
	
	@Test
	public void read() throws Exception {
		SAXReader reader = new SAXReader();
		Document document = reader.read("src/test.xml");
		
		//获取根节点shelf
		Element root = (Element)document.getRootElement();
		//获取第二本书的名称
		//获取第二本书的book节点
		Element book = (Element)root.elements("book").get(1);
		//获取name节点
		Element name = (Element)book.element("name");
		String nameValue = name.getText();
		System.out.println(nameValue);
		
		//获取第一本书的comment属性
		//此处使用的是element()方法，得到的是root下的第一个元素节点，使用elements()方法，得到的是一个集合
		Element book1 = (Element)root.element("book");
		//获取属性值的两种方式
//		String comment = book1.attribute("comment").getValue();
		String comment = book1.attributeValue("comment");
		System.out.println(comment);
	}
	
	@Test
	public void write() throws Exception {
		SAXReader reader = new SAXReader();
		Document document = reader.read("src/test.xml");
		
		//向第一本书添加<author>张三</author>(添加位置为book标签最后)
		document.getRootElement().element("book").addElement("author").addText("张三");
		
		OutputFormat format = OutputFormat.createPrettyPrint();
		format.setEncoding("UTF-8");
//		format.setEncoding("gb2312");
		
//		XMLWriter writer = new XMLWriter(new FileWriter("src/test.xml"), format);
//		XMLWriter writer = new XMLWriter(new OutputStreamWriter(new FileOutputStream("src/test.xml"), "UTF-8"), format);
		XMLWriter writer = new XMLWriter(new FileOutputStream("src/test.xml"), format);
		writer.write(document);
		writer.close();
	}
	
	//向指定位置添加节点
	//向第二本书的price节点上方添加<author>zyh</author>
	@Test
	public void write2() throws Exception {
		SAXReader reader = new SAXReader();
		Document document = reader.read("src/test.xml");
		
		//向特定位置添加节点，只能先得到添加节点的父节点的所有子节点，然后在需要添加的位置添加
		Element book = (Element)document.getRootElement().elements("book").get(1);
		List childs = book.elements();
		
		Element author = DocumentHelper.createElement("author");
		author.setText("zyh");
		
		//在price节点上方添加节点，price节点的索引值为2，2往后的节点自动后移
		childs.add(2, author);
		
		OutputFormat format = OutputFormat.createPrettyPrint();
		format.setEncoding("UTF-8");
		XMLWriter writer = new XMLWriter(new FileOutputStream("src/test.xml"), format);
		writer.write(document);
		writer.close();
	}
	
	//删除第一本书的<price>10.2</price>标签
	@Test
	public void delete() throws Exception {
		SAXReader reader = new SAXReader();
		Document document = reader.read("src/test.xml");
		
		Element price = (Element)document.getRootElement().element("book").element("price");
		price.getParent().remove(price);
		
		OutputFormat format = OutputFormat.createPrettyPrint();
		format.setEncoding("UTF-8");
		XMLWriter writer = new XMLWriter(new FileOutputStream("src/test.xml"), format);
		writer.write(document);
		writer.close();
	}
	
	//将第一本书的名称改为：java核心技术
	@Test
	public void update() throws Exception {
		SAXReader reader = new SAXReader();
		Document document = reader.read("src/test.xml");
		
		Element name = (Element)document.getRootElement().element("book").element("name");
		name.setText("java核心技术");
		
		OutputFormat format = OutputFormat.createPrettyPrint();
		format.setEncoding("UTF-8");
		XMLWriter writer = new XMLWriter(new FileOutputStream("src/test.xml"), format);
		writer.write(document);
		writer.close();
	}

}

 4.3 jdom

JDOM是一个开源项目,因此需要第三方的api, jar包的下载请移步：http://download.youkuaiyun.com/download/zyh5540/5806147

package com.zyh.xml;

import java.io.FileOutputStream;
import java.io.IOException;
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.Format;
import org.jdom.output.XMLOutputter;
import org.junit.Test;

public class TestJdom {

	//将整个文件读取出来
	@Test
	public void list() throws JDOMException, IOException {
		SAXBuilder builder = new SAXBuilder();
		Document document = builder.build("src/test.xml");
		
		Element root = document.getRootElement();
		//得到子节点，并循环遍历
		List lists = root.getChildren();
		System.out.println("<" + root.getName() + ">");
		for(int i=0; i<lists.size(); i++) {
			Element element = (Element)lists.get(i);
			System.out.print("  <" + element.getName());
			//得到当前标签的所有属性
			List attrs = element.getAttributes();
			for(int j=0; j<attrs.size(); j++) {
				Attribute attr = (Attribute)attrs.get(j);
				System.out.print(" " + attr.getName() +"=" + attr.getValue() );
			}
			System.out.println( ">");
			//得到当前标签的所有子节点
			List children = element.getChildren();
			for(int j=0; j<children.size(); j++) {
				Element child = (Element)children.get(j);
				System.out.println("    <"+ child.getName() +">" + child.getTextTrim() +"</"+ child.getName() +">");
			}
			System.out.println("  </" + element.getName()+ ">");
		}
		System.out.print("</" + root.getName() + ">");
	}
	
	//读取第二本书的name的值
	@Test
	public void read() throws Exception {
		SAXBuilder builder = new SAXBuilder();
		Document document = builder.build("src/test.xml");
		
		Element root = document.getRootElement();
		Element book = (Element)root.getChildren("book").get(1);
		//第一种方法
		Element name = (Element)book.getChild("name");
		System.out.println(name.getText());
		//第二种方法
		System.out.println(book.getChildText("name"));
		
	}
	
	//向第一本书增加author,<author>张三</author>
	@Test
	public void add() throws Exception {
		SAXBuilder builder = new SAXBuilder();
		Document document = builder.build("src/test.xml");
		
		Element book = document.getRootElement().getChild("book");
		Element author = new Element("author");
		author.setText("张三");
		//插入位置为book标签的最后
//		book.addContent(author);
		//向book标签的第二个位置插入author
		book.addContent(2, author);
		
		 XMLOutputter out = new XMLOutputter();
		 out.setFormat(Format.getPrettyFormat().setEncoding("UTF-8"));//设置文件编码，默认为UTF-8  
		 out.output(document, new FileOutputStream("src/test.xml"));
	}
	
	//删除第一本书的author标签
	@Test
	public void delete() throws Exception {
		SAXBuilder builder = new SAXBuilder();
		Document document = builder.build("src/test.xml");
		
		Element book = document.getRootElement().getChild("book");
		book.removeChild("author");
		
		XMLOutputter out = new XMLOutputter();
		out.setFormat(Format.getPrettyFormat().setEncoding("UTF-8"));//设置文件编码，默认为UTF-8  
		out.output(document, new FileOutputStream("src/test.xml"));
	}
      //更新第一本书的price为111
	@Test
	public void update() throws Exception {
		SAXBuilder builder = new SAXBuilder();
		Document document = builder.build("src/test.xml");
		
		Element price = document.getRootElement().getChild("book").getChild("price");
		price.setText("111");
		
		XMLOutputter out = new XMLOutputter();
		out.setFormat(Format.getPrettyFormat().setEncoding("UTF-8"));//设置文件编码，默认为UTF-8  
		out.output(document, new FileOutputStream("src/test.xml"));
	}

4.4 sax

在这个程序中使用的JavaBean,请读者自己根据xml文档建立

package com.zyh.xml.sax;

import java.util.ArrayList;
import java.util.List;

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

import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.DefaultHandler;

import com.zyh.bean.Book;

public class SaxXml {
    
    public static void main(String[] args) throws Exception {
        //1.创建解析工厂
         SAXParserFactory factory = SAXParserFactory.newInstance();
        //2.得到解析器
         SAXParser parser = factory.newSAXParser();
        //3.读取解析器
         XMLReader reader = parser.getXMLReader();
        //4.设置内容处理器
//         reader.setContentHandler(new ListHandler());
//         reader.setContentHandler(new TagValueHandler());
         BeanHandler beanHandler = new BeanHandler();
         reader.setContentHandler(beanHandler);
        
        //5.读取xml文件
         reader.parse("src/test.xml");
        
         List<Book> books = beanHandler.getBooks();
         System.out.println(books);
    }
}

//列举出所有标签
class ListHandler implements ContentHandler {

    @Override
    public void setDocumentLocator(Locator locator) {
    }

    @Override
    public void startDocument() throws SAXException {
    }

    @Override
    public void endDocument() throws SAXException {
    }

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

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

    @Override
    public void startElement(String uri, String localName, String name,
            Attributes atts) throws SAXException {
        System.out.print("<" + name);
        
        for(int i=0; null!=atts && i<atts.getLength(); i++) {
            String attrName = atts.getQName(i);
            String attrValue = atts.getValue(i);
            System.out.print(" " + attrName + "=" + attrValue);
        }
        System.out.print(">");
    }

    @Override
    public void endElement(String uri, String localName, String qName)
            throws SAXException {
        System.out.print("</" + qName + ">");
    }

    @Override
    public void characters(char[] ch, int start, int length)
            throws SAXException {
        System.out.print(new String(ch, start, length));
    }

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

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

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

//获取特定标签的值，如第二个book的name值
class TagValueHandler extends DefaultHandler {
    //当前标签的名称
    private String currentTagName;
    //当前name标签的数量
    private int currentNumber = 0;
    //需要的name标签的索引（从1开始）
    private int needNumber = 2;
    
    @Override
    public void startElement(String uri, String localName, String qName,
            Attributes attributes) throws SAXException {
        if("name".equals(qName)) {
            this.currentTagName = "name";
            this.currentNumber++;
        }
    }
    
    @Override
    public void characters(char[] ch, int start, int length)
            throws SAXException {
        //当前标签是name标签，且当前标签数量等于要查找标签的索引
        if("name".equals(currentTagName) && currentNumber == needNumber) {
            System.out.println(new String(ch, start, length));
        }
    }

    @Override
    public void endElement(String uri, String localName, String qName)
            throws SAXException {
        this.currentTagName = null;
    }
}

//将xml文档中的数据封装到JavaBean中
class BeanHandler extends DefaultHandler {
    private List<Book> books = new ArrayList<Book>();
    private Book book = null;
    private String currentTagName;
    public List<Book> getBooks() {
        return books;
    }
    
    @Override
    public void startElement(String uri, String localName, String qName,
            Attributes attributes) throws SAXException {
        this.currentTagName = qName;
        if("book".equals(qName)) {
            book = new Book();
        }
    }

    @Override
    public void characters(char[] ch, int start, int length)
            throws SAXException {
        if("id".equals(currentTagName)) {
            book.setId(new String(ch, start, length));
        } else if("name".equals(currentTagName)) {
            book.setName(new String(ch, start, length));
        } else if("price".equals(currentTagName)) {
            book.setPrice(new String(ch, start, length));
        }
    }
    
    @Override
    public void endElement(String uri, String localName, String qName)
            throws SAXException {
        if("book".equals(qName)) {
            books.add(book);
            book = null;
        }
        this.currentTagName = null;
    }
}