标签:
DOM的全称是Document Object Model,也即文档对象模型。在应用程序中,基于DOM的XML分析器将一个XML文档转换成一个对象模型的集合(通常称DOM树),应用程序正是通过对这个对象模型的操作,来实现对XML文档数据的操作。通过DOM接口,应用程序可以在任何时候访问XML文档中的任何一部分数据,因此,这种利用DOM接口的机制也被称作随机访问机制。
DOM接口提供了一种通过分层对象模型来访问XML文档信息的方式,这些分层对象模型依据XML的文档结构形成了一棵节点树。无论XML文档中所描述的是什么类型的信息,即便是制表数据、项目列表或一个文档,利用DOM所生成的模型都是节点树的形式。也就是说,DOM强制使用树模型来访问XML文档中的信息。由于XML本质上就是一种分层结构,所以这种描述方法是相当有效的。
DOM树所提供的随机访问方式给应用程序的开发带来了很大的灵活性,它可以任意地控制整个XML文档中的内容。然而,由于DOM分析器把整个XML文档转化成DOM树放在了内存中,因此,当文档比较大或者结构比较复杂时,对内存的需求就比较高。而且,对于结构复杂的树的遍历也是一项耗时的操作。所以,DOM分析器对机器性能的要求比较高,实现效率不十分理想。不过,由于DOM分析器所采用的树结构的思想与XML文档的结构相吻合,同时鉴于随机访问所带来的方便,因此,DOM分析器还是有很广泛的使用价值的。
1 import java.io.File; 2 3 import javax.xml.parsers.DocumentBuilder; 4 import javax.xml.parsers.DocumentBuilderFactory; 5 6 import org.w3c.dom.Document; 7 import org.w3c.dom.Element; 8 import org.w3c.dom.NodeList; 9 10 public class DomTest1 11 { 12 public static void main(String[] args) throws Exception 13 { 14 // step 1: 获得dom解析器工厂(工作的作用是用于创建具体的解析器) 15 DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); 16 17 // System.out.println("class name: " + dbf.getClass().getName()); 18 19 // step 2:获得具体的dom解析器 20 DocumentBuilder db = dbf.newDocumentBuilder(); 21 22 // System.out.println("class name: " + db.getClass().getName()); 23 24 // step3: 解析一个xml文档,获得Document对象(根结点) 25 Document document = db.parse(new File("candidate.xml")); 26 27 NodeList list = document.getElementsByTagName("PERSON"); 28 29 for(int i = 0; i < list.getLength(); i++) 30 { 31 Element element = (Element)list.item(i); 32 33 String content = element.getElementsByTagName("NAME").item(0).getFirstChild().getNodeValue(); 34 35 System.out.println("name:" + content); 36 37 content = element.getElementsByTagName("ADDRESS").item(0).getFirstChild().getNodeValue(); 38 39 System.out.println("address:" + content); 40 41 content = element.getElementsByTagName("TEL").item(0).getFirstChild().getNodeValue(); 42 43 System.out.println("tel:" + content); 44 45 content = element.getElementsByTagName("FAX").item(0).getFirstChild().getNodeValue(); 46 47 System.out.println("fax:" + content); 48 49 content = element.getElementsByTagName("EMAIL").item(0).getFirstChild().getNodeValue(); 50 51 System.out.println("email:" + content); 52 53 System.out.println("--------------------------------------"); 54 } 55 } 56 }
1 import java.io.File; 2 3 import javax.xml.parsers.DocumentBuilder; 4 import javax.xml.parsers.DocumentBuilderFactory; 5 6 import org.w3c.dom.Attr; 7 import org.w3c.dom.Comment; 8 import org.w3c.dom.Document; 9 import org.w3c.dom.Element; 10 import org.w3c.dom.NamedNodeMap; 11 import org.w3c.dom.Node; 12 import org.w3c.dom.NodeList; 13 14 /** 15 * 使用递归解析给定的任意一个xml文档并且将其内容输出到命令行上 16 * @author zhanglong 17 * 18 */ 19 public class DomTest3 20 { 21 public static void main(String[] args) throws Exception 22 { 23 DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); 24 DocumentBuilder db = dbf.newDocumentBuilder(); 25 26 Document doc = db.parse(new File("student.xml")); 27 //获得根元素结点 28 Element root = doc.getDocumentElement(); 29 30 parseElement(root); 31 } 32 33 private static void parseElement(Element element) 34 { 35 String tagName = element.getNodeName(); 36 37 NodeList children = element.getChildNodes(); 38 39 System.out.print("<" + tagName); 40 41 //element元素的所有属性所构成的NamedNodeMap对象,需要对其进行判断 42 NamedNodeMap map = element.getAttributes(); 43 44 //如果该元素存在属性 45 if(null != map) 46 { 47 for(int i = 0; i < map.getLength(); i++) 48 { 49 //获得该元素的每一个属性 50 Attr attr = (Attr)map.item(i); 51 52 String attrName = attr.getName(); 53 String attrValue = attr.getValue(); 54 55 System.out.print(" " + attrName + "=\"" + attrValue + "\""); 56 } 57 } 58 59 System.out.print(">"); 60 61 for(int i = 0; i < children.getLength(); i++) 62 { 63 Node node = children.item(i); 64 //获得结点的类型 65 short nodeType = node.getNodeType(); 66 67 if(nodeType == Node.ELEMENT_NODE) 68 { 69 //是元素,继续递归 70 parseElement((Element)node); 71 } 72 else if(nodeType == Node.TEXT_NODE) 73 { 74 //递归出口 75 System.out.print(node.getNodeValue()); 76 } 77 else if(nodeType == Node.COMMENT_NODE) 78 { 79 System.out.print("<!--"); 80 81 Comment comment = (Comment)node; 82 83 //注释内容 84 String data = comment.getData(); 85 86 System.out.print(data); 87 88 System.out.print("-->"); 89 } 90 } 91 92 System.out.print("</" + tagName + ">"); 93 } 94 }
sax:SAX的全称是Simple APIs for XML,也即XML简单应用程序接口。与DOM不同,SAX提供的访问模式是一种顺序模式,这是一种快速读写XML数据的方式。当使用SAX分析器对XML文档进行分析时,会触发一系列事件,并激活相应的事件处理函数,应用程序通过这些事件处理函数实现对XML文档的访问,因而SAX接口也被称作事件驱动接口。
1 import java.io.File; 2 3 import javax.xml.parsers.SAXParser; 4 import javax.xml.parsers.SAXParserFactory; 5 6 import org.xml.sax.Attributes; 7 import org.xml.sax.SAXException; 8 import org.xml.sax.helpers.DefaultHandler; 9 10 public class SaxTest1 11 { 12 public static void main(String[] args) throws Exception 13 { 14 //step1: 获得SAX解析器工厂实例 15 SAXParserFactory factory = SAXParserFactory.newInstance(); 16 17 //step2: 获得SAX解析器实例 18 SAXParser parser = factory.newSAXParser(); 19 20 //step3: 开始进行解析 21 parser.parse(new File("student.xml"), new MyHandler()); 22 23 } 24 } 25 26 class MyHandler extends DefaultHandler 27 { 28 @Override 29 public void startDocument() throws SAXException 30 { 31 System.out.println("parse began"); 32 } 33 34 @Override 35 public void endDocument() throws SAXException 36 { 37 System.out.println("parse finished"); 38 } 39 40 @Override 41 public void startElement(String uri, String localName, String qName, 42 Attributes attributes) throws SAXException 43 { 44 System.out.println("start element"); 45 } 46 47 @Override 48 public void endElement(String uri, String localName, String qName) 49 throws SAXException 50 { 51 System.out.println("finish element"); 52 } 53 }
import java.io.File; import java.util.Stack; import javax.xml.parsers.SAXParser; import javax.xml.parsers.SAXParserFactory; import org.xml.sax.Attributes; import org.xml.sax.SAXException; import org.xml.sax.helpers.DefaultHandler; public class SaxTest2 { public static void main(String[] args) throws Exception { SAXParserFactory factory = SAXParserFactory.newInstance(); SAXParser parser = factory.newSAXParser(); parser.parse(new File("student.xml"), new MyHandler2()); } } class MyHandler2 extends DefaultHandler { private Stack<String> stack = new Stack<String>(); private String name; private String gender; private String age; @Override public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException { stack.push(qName); for(int i = 0; i < attributes.getLength(); i++) { String attrName = attributes.getQName(i); String attrValue = attributes.getValue(i); System.out.println(attrName + "=" + attrValue); } } @Override public void characters(char[] ch, int start, int length) throws SAXException { String tag = stack.peek(); if("姓名".equals(tag)) { name = new String(ch, start,length); } else if("性别".equals(tag)) { gender = new String(ch, start, length); } else if("年龄".equals(tag)) { age = new String(ch, start, length); } } @Override public void endElement(String uri, String localName, String qName) throws SAXException { stack.pop(); //表示该元素已经解析完毕,需要从栈中弹出 if("学生".equals(qName)) { System.out.println("姓名:" + name); System.out.println("性别:" + gender); System.out.println("年龄:" + age); System.out.println(); } } }
JDOM:
JDOM是一个开源项目,它基于树型结构,利用纯JAVA的技术对XML文档实现解析、生成、序列化以及多种操作。(http://jdom.org)
•JDOM 直接为JAVA编程服务。它利用更为强有力的JAVA语言的诸多特性(方法重载、集合概念等),把SAX和DOM的功能有效地结合起来。
•JDOM是用Java语言读、写、操作XML的新API函数。在直接、简单和高效的前提下,这些API函数被最大限度的优化。
1 import java.io.FileWriter; 2 3 import org.jdom.Attribute; 4 import org.jdom.Comment; 5 import org.jdom.Document; 6 import org.jdom.Element; 7 import org.jdom.output.Format; 8 import org.jdom.output.XMLOutputter; 9 10 public class JDomTest1 11 { 12 public static void main(String[] args) throws Exception 13 { 14 Document document = new Document(); 15 16 Element root = new Element("root"); 17 18 document.addContent(root); 19 20 Comment comment = new Comment("This is my comments"); 21 22 root.addContent(comment); 23 24 Element e = new Element("hello"); 25 26 e.setAttribute("sohu", "www.sohu.com"); 27 28 root.addContent(e); 29 30 Element e2 = new Element("world"); 31 32 Attribute attr = new Attribute("test", "hehe"); 33 34 e2.setAttribute(attr); 35 36 e.addContent(e2); 37 38 e2.addContent(new Element("aaa").setAttribute("a", "b") 39 .setAttribute("x", "y").setAttribute("gg", "hh").setText("text content")); 40 41 42 Format format = Format.getPrettyFormat(); 43 44 format.setIndent(" "); 45 // format.setEncoding("gbk"); 46 47 XMLOutputter out = new XMLOutputter(format); 48 49 out.output(document, new FileWriter("jdom.xml")); 50 51 } 52 }
1 import java.io.File; 2 import java.io.FileOutputStream; 3 import java.util.List; 4 5 import org.jdom.Attribute; 6 import org.jdom.Document; 7 import org.jdom.Element; 8 import org.jdom.input.SAXBuilder; 9 import org.jdom.output.Format; 10 import org.jdom.output.XMLOutputter; 11 12 public class JDomTest2 13 { 14 public static void main(String[] args) throws Exception 15 { 16 SAXBuilder builder = new SAXBuilder(); 17 18 Document doc = builder.build(new File("jdom.xml")); 19 20 Element element = doc.getRootElement(); 21 22 System.out.println(element.getName()); 23 24 Element hello = element.getChild("hello"); 25 26 System.out.println(hello.getText()); 27 28 List list = hello.getAttributes(); 29 30 for(int i = 0 ;i < list.size(); i++) 31 { 32 Attribute attr = (Attribute)list.get(i); 33 34 String attrName = attr.getName(); 35 String attrValue = attr.getValue(); 36 37 System.out.println(attrName + "=" + attrValue); 38 } 39 40 hello.removeChild("world"); 41 42 XMLOutputter out = new XMLOutputter(Format.getPrettyFormat().setIndent(" ")); 43 44 45 out.output(doc, new FileOutputStream("jdom2.xml")); 46 47 } 48 }
1 import java.io.FileOutputStream; 2 import java.io.FileWriter; 3 4 import org.dom4j.Document; 5 import org.dom4j.DocumentHelper; 6 import org.dom4j.Element; 7 import org.dom4j.io.OutputFormat; 8 import org.dom4j.io.XMLWriter; 9 10 public class Test1 11 { 12 public static void main(String[] args) throws Exception 13 { 14 // 创建文档并设置文档的根元素节点 :第一种方式 15 // Document document = DocumentHelper.createDocument(); 16 // 17 // Element root = DocumentHelper.createElement("student"); 18 // 19 // document.setRootElement(root); 20 21 // 创建文档并设置文档的根元素节点 :第二种方式 22 Element root = DocumentHelper.createElement("student"); 23 Document document = DocumentHelper.createDocument(root); 24 25 root.addAttribute("name", "zhangsan"); 26 27 Element helloElement = root.addElement("hello"); 28 Element worldElement = root.addElement("world"); 29 30 helloElement.setText("hello"); 31 worldElement.setText("world"); 32 33 helloElement.addAttribute("age", "20"); 34 35 XMLWriter xmlWriter = new XMLWriter(); 36 xmlWriter.write(document); 37 38 OutputFormat format = new OutputFormat(" ", true); 39 40 XMLWriter xmlWriter2 = new XMLWriter(new FileOutputStream("student2.xml"), format); 41 xmlWriter2.write(document); 42 43 XMLWriter xmlWriter3 = new XMLWriter(new FileWriter("student3.xml"), format); 44 45 xmlWriter3.write(document); 46 xmlWriter3.close(); 47 48 } 49 }
1 import java.io.File; 2 import java.util.Iterator; 3 import java.util.List; 4 5 import javax.xml.parsers.DocumentBuilder; 6 import javax.xml.parsers.DocumentBuilderFactory; 7 8 import org.dom4j.Document; 9 import org.dom4j.Element; 10 import org.dom4j.io.DOMReader; 11 import org.dom4j.io.SAXReader; 12 13 public class Test2 14 { 15 public static void main(String[] args) throws Exception 16 { 17 SAXReader saxReader = new SAXReader(); 18 19 Document doc = saxReader.read(new File("student2.xml")); 20 21 Element root = doc.getRootElement(); 22 23 System.out.println("root element: " + root.getName()); 24 25 List childList = root.elements(); 26 27 System.out.println(childList.size()); 28 29 List childList2 = root.elements("hello"); 30 31 System.out.println(childList2.size()); 32 33 Element first = root.element("hello"); 34 35 System.out.println(first.attributeValue("age")); 36 37 for(Iterator iter = root.elementIterator(); iter.hasNext();) 38 { 39 Element e = (Element)iter.next(); 40 41 System.out.println(e.attributeValue("age")); 42 } 43 44 System.out.println("---------------------------"); 45 46 DocumentBuilderFactory dbf = DocumentBuilderFactory.newInstance(); 47 DocumentBuilder db = dbf.newDocumentBuilder(); 48 org.w3c.dom.Document document = db.parse(new File("student2.xml")); 49 50 DOMReader domReader = new DOMReader(); 51 52 //将JAXP的Document转换为dom4j的Document 53 Document d = domReader.read(document); 54 55 Element rootElement = d.getRootElement(); 56 57 System.out.println(rootElement.getName()); 58 59 } 60 }
1 import java.io.FileWriter; 2 3 import org.jdom.Attribute; 4 import org.jdom.Document; 5 import org.jdom.Element; 6 import org.jdom.output.Format; 7 import org.jdom.output.XMLOutputter; 8 9 public class Test3 10 { 11 public static void main(String[] args) throws Exception 12 { 13 Document document = new Document(); 14 15 Element root = new Element("联系人列表").setAttribute(new Attribute("公司", 16 "A集团")); 17 18 document.addContent(root); 19 20 Element contactPerson = new Element("联系人"); 21 22 root.addContent(contactPerson); 23 24 contactPerson 25 .addContent(new Element("姓名").setText("张三")) 26 .addContent(new Element("公司").setText("A公司")) 27 .addContent(new Element("电话").setText("021-55556666")) 28 .addContent( 29 new Element("地址") 30 .addContent(new Element("街道").setText("5街")) 31 .addContent(new Element("城市").setText("上海")) 32 .addContent(new Element("省份").setText("上海市"))); 33 34 XMLOutputter output = new XMLOutputter(Format.getPrettyFormat() 35 .setIndent(" ").setEncoding("gbk")); 36 37 output.output(document, new FileWriter("contact.xml")); 38 39 } 40 }
标签:
原文地址:http://www.cnblogs.com/jiafuwei/p/4507523.html