DOM4J
与利用DOM、SAX、JAXP机制来解析xml相比,DOM4J 表现更优秀,具有性能优异、功能强大和极端易用使用的特点,只要懂得DOM基本概念,就可以通过dom4j的api文档来解析xml。dom4j是一套开源的api。实际项目中,往往选择dom4j来作为解析xml的利器。
先来看看dom4j中对应XML的DOM树建立的继承关系
针对于XML标准定义,对应于图2-1列出的内容,dom4j提供了以下实现:
同时,dom4j的NodeType枚举实现了XML规范中定义的node类型。如此可以在遍历xml文档的时候通过常量来判断节点类型了。
常用API
class org.dom4j.io.SAXReader
interface org.dom4j.Document
interface org.dom4j.Node
interface org.dom4j.Element
interface org.dom4j.Attribute
interface org.dom4j.Text
interface org.dom4j.CDATA
interface org.dom4j.Comment
实例一:
1 //先加入dom4j.jar包 2 import java.util.HashMap; 3 import java.util.Iterator; 4 import java.util.Map; 5 6 import org.dom4j.Document; 7 import org.dom4j.DocumentException; 8 import org.dom4j.DocumentHelper; 9 import org.dom4j.Element; 10 11 /** 12 * @Title: TestDom4j.java 13 * @Package 14 * @Description: 解析xml字符串 15 * @author 无处不在 16 * @date 2012-11-20 下午05:14:05 17 * @version V1.0 18 */ 19 public class TestDom4j { 20 21 public void readStringXml(String xml) { 22 Document doc = null; 23 try { 24 25 // 读取并解析XML文档 26 // SAXReader就是一个管道,用一个流的方式,把xml文件读出来 27 // 28 // SAXReader reader = new SAXReader(); //User.hbm.xml表示你要解析的xml文档 29 // Document document = reader.read(new File("User.hbm.xml")); 30 // 下面的是通过解析xml字符串的 31 doc = DocumentHelper.parseText(xml); // 将字符串转为XML 32 33 Element rootElt = doc.getRootElement(); // 获取根节点 34 System.out.println("根节点:" + rootElt.getName()); // 拿到根节点的名称 35 36 Iterator iter = rootElt.elementIterator("head"); // 获取根节点下的子节点head 37 38 // 遍历head节点 39 while (iter.hasNext()) { 40 41 Element recordEle = (Element) iter.next(); 42 String title = recordEle.elementTextTrim("title"); // 拿到head节点下的子节点title值 43 System.out.println("title:" + title); 44 45 Iterator iters = recordEle.elementIterator("script"); // 获取子节点head下的子节点script 46 47 // 遍历Header节点下的Response节点 48 while (iters.hasNext()) { 49 50 Element itemEle = (Element) iters.next(); 51 52 String username = itemEle.elementTextTrim("username"); // 拿到head下的子节点script下的字节点username的值 53 String password = itemEle.elementTextTrim("password"); 54 55 System.out.println("username:" + username); 56 System.out.println("password:" + password); 57 } 58 } 59 Iterator iterss = rootElt.elementIterator("body"); ///获取根节点下的子节点body 60 // 遍历body节点 61 while (iterss.hasNext()) { 62 63 Element recordEless = (Element) iterss.next(); 64 String result = recordEless.elementTextTrim("result"); // 拿到body节点下的子节点result值 65 System.out.println("result:" + result); 66 67 Iterator itersElIterator = recordEless.elementIterator("form"); // 获取子节点body下的子节点form 68 // 遍历Header节点下的Response节点 69 while (itersElIterator.hasNext()) { 70 71 Element itemEle = (Element) itersElIterator.next(); 72 73 String banlce = itemEle.elementTextTrim("banlce"); // 拿到body下的子节点form下的字节点banlce的值 74 String subID = itemEle.elementTextTrim("subID"); 75 76 System.out.println("banlce:" + banlce); 77 System.out.println("subID:" + subID); 78 } 79 } 80 } catch (DocumentException e) { 81 e.printStackTrace(); 82 83 } catch (Exception e) { 84 e.printStackTrace(); 85 86 } 87 } 88 89 /** 90 * @description 将xml字符串转换成map 91 * @param xml 92 * @return Map 93 */ 94 public static Map readStringXmlOut(String xml) { 95 Map map = new HashMap(); 96 Document doc = null; 97 try { 98 // 将字符串转为XML 99 doc = DocumentHelper.parseText(xml); 100 // 获取根节点 101 Element rootElt = doc.getRootElement(); 102 // 拿到根节点的名称 103 System.out.println("根节点:" + rootElt.getName()); 104 105 // 获取根节点下的子节点head 106 Iterator iter = rootElt.elementIterator("head"); 107 // 遍历head节点 108 while (iter.hasNext()) { 109 110 Element recordEle = (Element) iter.next(); 111 // 拿到head节点下的子节点title值 112 String title = recordEle.elementTextTrim("title"); 113 System.out.println("title:" + title); 114 map.put("title", title); 115 // 获取子节点head下的子节点script 116 Iterator iters = recordEle.elementIterator("script"); 117 // 遍历Header节点下的Response节点 118 while (iters.hasNext()) { 119 Element itemEle = (Element) iters.next(); 120 // 拿到head下的子节点script下的字节点username的值 121 String username = itemEle.elementTextTrim("username"); 122 String password = itemEle.elementTextTrim("password"); 123 124 System.out.println("username:" + username); 125 System.out.println("password:" + password); 126 map.put("username", username); 127 map.put("password", password); 128 } 129 } 130 131 //获取根节点下的子节点body 132 Iterator iterss = rootElt.elementIterator("body"); 133 // 遍历body节点 134 while (iterss.hasNext()) { 135 Element recordEless = (Element) iterss.next(); 136 // 拿到body节点下的子节点result值 137 String result = recordEless.elementTextTrim("result"); 138 System.out.println("result:" + result); 139 // 获取子节点body下的子节点form 140 Iterator itersElIterator = recordEless.elementIterator("form"); 141 // 遍历Header节点下的Response节点 142 while (itersElIterator.hasNext()) { 143 Element itemEle = (Element) itersElIterator.next(); 144 // 拿到body下的子节点form下的字节点banlce的值 145 String banlce = itemEle.elementTextTrim("banlce"); 146 String subID = itemEle.elementTextTrim("subID"); 147 148 System.out.println("banlce:" + banlce); 149 System.out.println("subID:" + subID); 150 map.put("result", result); 151 map.put("banlce", banlce); 152 map.put("subID", subID); 153 } 154 } 155 } catch (DocumentException e) { 156 e.printStackTrace(); 157 } catch (Exception e) { 158 e.printStackTrace(); 159 } 160 return map; 161 } 162 163 public static void main(String[] args) { 164 165 // 下面是需要解析的xml字符串例子 166 String xmlString = "<html>" + "<head>" + "<title>dom4j解析一个例子</title>" 167 + "<script>" + "<username>yangrong</username>" 168 + "<password>123456</password>" + "</script>" + "</head>" 169 + "<body>" + "<result>0</result>" + "<form>" 170 + "<banlce>1000</banlce>" + "<subID>36242519880716</subID>" 171 + "</form>" + "</body>" + "</html>"; 172 173 /* 174 * Test2 test = new Test2(); test.readStringXml(xmlString); 175 */ 176 Map map = readStringXmlOut(xmlString); 177 Iterator iters = map.keySet().iterator(); 178 while (iters.hasNext()) { 179 String key = iters.next().toString(); // 拿到键 180 String val = map.get(key).toString(); // 拿到值 181 System.out.println(key + "=" + val); 182 } 183 } 184 185 }
实例二:
1 /** 2 * 解析包含有DB连接信息的XML文件 3 * 格式必须符合如下规范: 4 * 1. 最多三级,每级的node名称自定义; 5 * 2. 二级节点支持节点属性,属性将被视作子节点; 6 * 3. CDATA必须包含在节点中,不能单独出现。 7 * 8 * 示例1——三级显示: 9 * <db-connections> 10 * <connection> 11 * <name>DBTest</name> 12 * <jndi></jndi> 13 * <url> 14 * <![CDATA[jdbc:mysql://localhost:3306/db_test?useUnicode=true&characterEncoding=UTF8]]> 15 * </url> 16 * <driver>org.gjt.mm.mysql.Driver</driver> 17 * <user>test</user> 18 * <password>test2012</password> 19 * <max-active>10</max-active> 20 * <max-idle>10</max-idle> 21 * <min-idle>2</min-idle> 22 * <max-wait>10</max-wait> 23 * <validation-query>SELECT 1+1</validation-query> 24 * </connection> 25 * </db-connections> 26 * 27 * 示例2——节点属性: 28 * <bookstore> 29 * <book category="cooking"> 30 * <title lang="en">Everyday Italian</title> 31 * <author>Giada De Laurentiis</author> 32 * <year>2005</year> 33 * <price>30.00</price> 34 * </book> 35 * 36 * <book category="children" title="Harry Potter" author="J K. Rowling" year="2005" price="$29.9"/> 37 * </bookstore> 38 * 39 * @param configFile 40 * @return 41 * @throws Exception 42 */ 43 public static List<Map<String, String>> parseDBXML(String configFile) throws Exception { 44 List<Map<String, String>> dbConnections = new ArrayList<Map<String, String>>(); 45 InputStream is = Parser.class.getResourceAsStream(configFile); 46 SAXReader saxReader = new SAXReader(); 47 Document document = saxReader.read(is); 48 Element connections = document.getRootElement(); 49 50 Iterator<Element> rootIter = connections.elementIterator(); 51 while (rootIter.hasNext()) { 52 Element connection = rootIter.next(); 53 Iterator<Element> childIter = connection.elementIterator(); 54 Map<String, String> connectionInfo = new HashMap<String, String>(); 55 List<Attribute> attributes = connection.attributes(); 56 for (int i = 0; i < attributes.size(); ++i) { // 添加节点属性 57 connectionInfo.put(attributes.get(i).getName(), attributes.get(i).getValue()); 58 } 59 while (childIter.hasNext()) { // 添加子节点 60 Element attr = childIter.next(); 61 connectionInfo.put(attr.getName().trim(), attr.getText().trim()); 62 } 63 dbConnections.add(connectionInfo); 64 } 65 66 return dbConnections; 67 }