XML文件解析大杂烩

XML文件解析总结

一、DOM(document object model)解析
1. 简述
由W3C提供的接口，将整个XML文档一次性加载到内存中，构造一个DOM树来对各个节点进行操作。提供了DomcumentBuilderFactory/DomcumentBuilder接口来完成对XML文档的解析
2. 实例代码

public void createXml() throws Exception {
		// 创建解析工厂
		DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
		// 创建解析器
		DocumentBuilder builder = factory.newDocumentBuilder();
		// 创建Document对象
		Document document = builder.newDocument();
		// 创建根结点
		Element root = document.createElement("china");
		// 创建子节点
		Element c1 = document.createElement("beijin");
		Element c2 = document.createElement("shanghai");
		Element c3 = document.createElement("guangdong");
		Element c3_1 = document.createElement("guangzhou");
		Element c3_2 = document.createElement("shenzhen");
		Element c3_3 = document.createElement("dongguang");
		// 设置节点值
		Text t3_1 = document.createTextNode("广州");
		Text t3_2 = document.createTextNode("深圳");
		Text t3_3 = document.createTextNode("东莞");

		// 设置文档层次结构
		root.appendChild(c1);
		root.appendChild(c2);
		c3_1.appendChild(t3_1);
		c3_2.appendChild(t3_2);
		c3_3.appendChild(t3_3);

		c3.appendChild(c3_1);
		c3.appendChild(c3_2);
		c3.appendChild(c3_3);

		root.appendChild(c3);
		document.appendChild(root);
		document2xml(document);
		System.out.println("基于DOM方式的XML文件创建完成。。。。");
	}

	@Override
	public void parserXml() throws Exception {
		// 创建解析工厂
		DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
		// 创建解析器
		DocumentBuilder builder = factory.newDocumentBuilder();
		Document document = builder.parse(FILE_NAME);
		NodeList nodeList4Root = document.getChildNodes();
		// 此方法只为介绍DOM解析XML文件的简单例子，只限于3层
		// 遍历所有XML文件中的第一层结构
		for (int i = 0; i < nodeList4Root.getLength(); i++) {
			Node node = nodeList4Root.item(i);
			NodeList nodeList4Child = node.getChildNodes();
			// 遍历所有XML文件中的第二层结构
			for (int j = 0; j < nodeList4Child.getLength(); j++) {
				Node node4CC = nodeList4Child.item(j);
				NodeList nodeList4CC = node4CC.getChildNodes();
				if (nodeList4CC.getLength() > 1) {
					// 遍历所有XML文件中的第三层结构
					for (int k = 0; k < nodeList4CC.getLength(); k++) {
						Node n = nodeList4CC.item(k);
						System.out.println("nodeName:" + n.getNodeName()
								+ " nodeValue:" + n.getTextContent());
					}
				} else {
					System.out.println("nodeName:" + node4CC.getNodeName()
							+ " nodeValue:" + node4CC.getTextContent());
				}
			}
			System.out.println("解析完成!!!");
		}
	}

	private void document2xml(Document document) throws Exception {
		TransformerFactory factory = TransformerFactory.newInstance();
		Transformer transformer = factory.newTransformer();
		transformer.setOutputProperty(OutputKeys.INDENT, "yes");
		DOMSource source = new DOMSource(document);
		StreamResult sr = new StreamResult(new File(FILE_NAME));
		transformer.transform(source, sr);
	}

二、SAX解析
1. 简述
   SAX解析是基于事件驱动方式来对整个XML文件进行解析操作，它在解析XML文件的时候会触发一系列事件，当发现给定的标签时，将调用一个回调函数，告知该方法制定的标签已经找到。提供SAXParserFactory/SAXParser接口完成文档的解析。
2. 实例代码

public void createXml() throws Exception {

		// 设置输出地址
		Result result = new StreamResult(new FileOutputStream(FILE_NAME));

		// 创建SAX转换器
		SAXTransformerFactory sff = (SAXTransformerFactory) SAXTransformerFactory
				.newInstance();

		// 创建SAX转化处理对象
		TransformerHandler handler = sff.newTransformerHandler();
		Transformer transformer = handler.getTransformer();

		// 设置文档输出格式
		transformer.setOutputProperty(OutputKeys.INDENT, "yes");
		transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");

		// 将处理结果输出到文件中
		handler.setResult(result);

		// 开始创建
		handler.startDocument();

		// 设置文档标签与标签之间的距离,子级与父级为4个字节长度，子级与祖父级为8个字节长度
		String four = "\n    ";
		String eight = "\n        ";

		// 设置标签属性
		AttributesImpl attr = new AttributesImpl();

		// 处理开始标签，根节点
		handler.startElement("", "", "china", attr);
		handler.characters(four.toCharArray(), 0, four.length());

		// 处理各个子标签
		handler.startElement("", "", "beijin", attr);
		// handler.characters(eight.toCharArray(), 0, eight.length());
		handler.endElement("", "", "beijin");

		handler.characters(four.toCharArray(), 0, four.length());
		handler.startElement("", "", "shanghai", attr);
		// handler.characters(four.toCharArray(), 0, four.length());
		handler.endElement("", "", "shanghai");

		handler.characters(four.toCharArray(), 0, four.length());
		handler.startElement("", "", "guangdong", attr);
		handler.characters(eight.toCharArray(), 0, eight.length());

		handler.startElement("", "", "guangzhou", attr);
		String gz = "广州";
		handler.characters(gz.toCharArray(), 0, gz.length());
		handler.endElement("", "", "guangzhou");

		handler.characters(eight.toCharArray(), 0, eight.length());
		handler.startElement("", "", "shenzhen", attr);
		String sz = "深圳";
		handler.characters(sz.toCharArray(), 0, sz.length());
		handler.endElement("", "", "shenzhen");
		handler.characters(eight.toCharArray(), 0, eight.length());

		handler.startElement("", "", "dongguang", attr);
		String dg = "东莞";
		handler.characters(dg.toCharArray(), 0, dg.length());
		handler.endElement("", "", "dongguang");

		handler.characters(four.toCharArray(), 0, four.length());

		handler.endElement("", "", "guangdong");

		handler.endElement("", "", "china");
		// 处理结束
		handler.endDocument();

		System.out.println("SAX创建文件完成!!!");

	}

	@Override
	public void parserXml() throws Exception {
		SAXParserFactory factory = SAXParserFactory.newInstance();
		javax.xml.parsers.SAXParser parser = factory.newSAXParser();
		InputStream is = new FileInputStream(new File(FILE_NAME));
		parser.parse(is, new SAXParserInner());
	}

	class SAXParserInner extends DefaultHandler {

		private Stack tags = new Stack();

		@Override
		public void endDocument() throws SAXException {
			System.out.println("文档解析结束！！！");
		}

		@Override
		public void endElement(String uri, String localName, String name)
				throws SAXException {
			System.out.println("endElment name: " + name);
		}

		@Override
		public void startDocument() throws SAXException {
			System.out.println("文档解析开始！！！");
		}

		@Override
		public void startElement(String uri, String localName, String name,
				Attributes attributes) throws SAXException {
			tags.push(name);
			System.out.println("startElement name: " + name);
		}

		@Override
		public void characters(char[] ch, int start, int length)
				throws SAXException {
			String tagName = (String) tags.peek();
			if (tagName.equalsIgnoreCase("guangzhou")
					|| tagName.equalsIgnoreCase("shenzhen")
					|| tagName.equalsIgnoreCase("dongguang")) {
				System.out.println("value = " + new String(ch, start, length));
                
			}
		}

	}

三、JDOM解析
1. 简述
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。
2.实例代码

public void createXml() throws Exception {
		// 创建根节点
		Element root = new Element("china");
		// 将根结点添加到文档
		Document doc = new Document(root);
		// 设置子节点
		Element bj = new Element("beijin");
		Element sh = new Element("shanghai");
		Element gd = new Element("guangdong");
		gd.addContent(new Element("guangzhou").setText("广州"));
		gd.addContent(new Element("shenzhen").setText("深圳"));
		gd.addContent(new Element("dongguan").setText("东莞"));
		root.addContent(bj);
		root.addContent(sh);
		root.addContent(gd);
        
		Format fmt = Format.getPrettyFormat();
		fmt.setIndent(" ");
		// 将内容输出到文件中
		XMLOutputter op = new XMLOutputter();
		op.setFormat(fmt);
		op.output(doc, new FileOutputStream(new File(FILE_NAME)));
		System.out.println("JDOM创建文件结束！！！");
	}

	@Override
	public void parserXml() throws Exception {
		SAXBuilder sb = new SAXBuilder();// 建立构造器
		Document doc = sb.build(new FileInputStream(FILE_NAME));// 读入指定文件
		Element root = doc.getRootElement();// 获得根节点
		List<?> list = root.getChildren();// 将根节点下的所有子节点放入List中
		for (int i = 0; i < list.size(); i++) {
			Element child = (Element) list.get(i);// 取得节点实例
			if (child.getContent() != null) {
				List<Element> child_2 = child.getChildren();
				for (Element ch : child_2) {
					System.out.println("name= " + ch.getName() + " value= "
							+ ch.getText());
				}
			}
		}
		System.out.println("JDOM解析文件完成!!!");
	}

四、DOM4j解析
1. 简述
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。
2.实例代码

public void createXml() throws Exception {
		// 创建文档实例
		Document doc = DocumentHelper.createDocument();
		Element root = doc.addElement("china");
		// 增加注释
		root.addComment("根节点");
		// 增加子节点
		root.addElement("beijing");
		root.addElement("shanghai");
		Element gd = root.addElement("guangdong");
		Element gz = gd.addElement("guangzhou");
		gz.addText("广州");
		Element sz = gd.addElement("shenzhen");
		sz.addText("深圳");
		Element dg = gd.addElement("dongguang");
		dg.addText("东莞");
		// 格式化输出的XML
		OutputFormat output = OutputFormat.createPrettyPrint();
		output.setEncoding(Charset.forName("gbk").displayName());
		// 把XML从内存中写入文件
		XMLWriter writer = new XMLWriter(new FileWriter(FILE_NAME), output);
		writer.write(doc);
		writer.close();// 不能缺少，说明文档已创建完成，否则文件内容为空
		System.out.println("DOM4j创建文件完成！！！");
	}

	@Override
	public void parserXml() throws Exception {
		/** 使用SAXReader解析文件 **/
		SAXReader saxReader = new SAXReader();
		Document doc = saxReader.read(FILE_NAME);
		Element root = doc.getRootElement();
		// 遍历所有子节点
		for (Iterator it = root.elementIterator(); it.hasNext();) {
			Element element = (Element) it.next();
			if (element.getText() != null && !"".equals(element.getText()))
				for (Iterator it1 = element.elementIterator(); it1.hasNext();) {
					Element element1 = (Element) it1.next();
					System.out.println("name= " + element1.getName()
							+ " value= " + element1.getText());

				}
		}
		System.out.println("DOM4J parser completed by SAXReader!!!");
		/**DOMReader解析文件**/
		DocumentBuilderFactory factory =  DocumentBuilderFactory.newInstance();
		DocumentBuilder builder = factory.newDocumentBuilder();
		org.w3c.dom.Document document = builder.parse(FILE_NAME);
		DOMReader domReader = new DOMReader();
		Document document_4j = domReader.read(document);
		Element r = document_4j.getRootElement();
		// 遍历所有子节点
		for (Iterator it = r.elementIterator(); it.hasNext();) {
			Element element = (Element) it.next();
			if (element.getText() != null && !"".equals(element.getText()))
				for (Iterator it1 = element.elementIterator(); it1.hasNext();) {
					Element element1 = (Element) it1.next();
					System.out.println("name= " + element1.getName()
							+ " value= " + element1.getText());

				}
		}
		System.out.println("DOM4J parser completed by DOMReader!!!");
        /**XPath解析文件**/
		SAXReader saxReader_xpath = new SAXReader();
		Document doc_xpath = saxReader_xpath.read(FILE_NAME);
		List list = doc_xpath.selectNodes("/china/guangdong/shenzhen");
		for(Iterator it = list.iterator();it.hasNext();){
			Element element = (Element) it.next();
			System.out.println("name= " + element.getName()
					+ " value= " + element.getText());
		}
		System.out.println("DOM4J parser completed by XPathParser!!!");
	}

五、XStream解析
1.简介
使用 XStream 不用任何映射就能实现多数 Java 对象的序列化。在生成的 XML 中对象名变成了元素名，类中的字符串组成了 XML 中的元素内容。使用 XStream 序列化的类不需要实现 Serializable 接口
2.实例代码

public void createXml() throws Exception {
		//创建转换类
		//XStream xs = new XStream();
		XStream xs = new XStream(new DomDriver("utf-8")); 
		//根节点
		China china = new China();
		xs.alias("china", China.class);
		china.setId("china");
		//将成员变量设置为属性值
		xs.useAttributeFor(China.class, "id");
		//子节点
		Beijin bj = new Beijin();
		china.setBeijin(bj);
		
		//子节点
		ShangHai sh = new ShangHai();
		
		//转换China对象中sh属性名为shanghai
		xs.aliasAttribute(China.class,"sh", "shanghai");
		china.setSh(sh);
		//子节点
		GuangDong gd = new GuangDong();
		xs.aliasAttribute(China.class,"gd", "guangdong");
		gd.setGz("广州");
		//装换属性别名
		xs.aliasField("guangzhou", GuangDong.class, "gz");
		china.setGd(gd);
		
		gd.setShenzhen("深圳");
	    gd.setDg("东莞");
	    xs.aliasField("dongguang", GuangDong.class, "dg");
		String result = xs.toXML(china);
		System.out.println(result);
		//将装换后的结果写入文件中
		OutputStream fos = new FileOutputStream(FILE_NAME);
		//字符编码装换,默认为UTF-8
		Writer writer = new OutputStreamWriter(fos,Charset.forName("UTF-8"));
 		xs.toXML(china, writer);
 		fos.close();
 		System.out.println("Xstream创建文件成功!!!");
 		
	}

	@Override
	public void parserXml() throws Exception {
		//依懒xpp解析器 
		//XStream xs = new XStream();
		//运用标准的DOM解析器 
		XStream xs = new XStream(new DomDriver("utf-8")); 
		InputStream fos = new FileInputStream(new File(FILE_NAME));
		xs.alias("china", China.class);
		xs.aliasAttribute(China.class,"id","id");
		xs.aliasAttribute(China.class,"sh","shanghai");
		xs.aliasAttribute(China.class,"gd","guangdong");
		xs.aliasAttribute(GuangDong.class,"gz","guangzhou");
		xs.aliasAttribute(GuangDong.class,"dg","dongguang");
		China china =(China)xs.fromXML(fos);
		System.out.println("属性值：" + china.getId());
		System.out.println("shenzhen ：" + china.getGd().getShenzhen());
	}