解析XML的4种方式及优缺点比较

dom, sax是解析xml的底层接口
而jdom和dom4j则是基于底层api的更高级封装   
dom是通用的,而jdom和dom4j则是面向java语言的

 

(方法一). DOM解析说明:为 XML 文档的已解析版本定义了一组接口。解析器读入整个文档,然后构建一个驻留内存的树结
构, 然后代码就可以使用 DOM 接口来操作这个树结构。优点:整个文档树在内存中,便于操作;支持删除、修改、重新排列等多种功能;缺点:将整个文档调入内 存(包括无用的节点),浪费时间和空间;使用场合:一旦解析了文档还需多次访问这些数据;硬件资源充足(内存、CPU).

 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.Document;
 8 import org.w3c.dom.Element;
 9 import org.w3c.dom.NamedNodeMap;
10 import org.w3c.dom.Node;
11 import org.w3c.dom.NodeList;
12 
13 public class DomDemo {
14 
15     private final static String xmlPath = "D:\\WHS01.xml";
16 
17     /**
18      * 递归输出节点
19      * 
20      * @param element
21      */
22     public static void parseElement(Element element) {
23 
24         System.out.print("<" + element.getTagName());
25         NamedNodeMap map = element.getAttributes();
26         if (null != map) {
27             for (int i = 0; i < map.getLength(); i++) {
28                 Attr attr = (Attr) map.item(i);
29                 System.out.print(" " + attr.getName() + "=\"" + attr.getValue()
30                         + "\"");
31             }
32         }
33         System.out.print(">");
34 
35         NodeList childList = element.getChildNodes();
36 
37         for (int i = 0; i < childList.getLength(); i++) {
38             Node node = childList.item(i);
39 
40             switch (node.getNodeType()) {
41             case Node.ELEMENT_NODE:
42                 parseElement((Element) node);
43                 break;
44             case Node.TEXT_NODE:
45                 System.out.print(node.getNodeValue());
46                 break;
47             default:
48                 break;
49             }
50         }
51         System.out.print("</" + element.getTagName() + ">");
52     }
53 
54     /**
55      * 根据指定路径获取Document对象
56      * 
57      * @param xmlPath
58      * @return
59      * @throws Exception
60      */
61     public static Document getDocument(String xmlPath) throws Exception {
62 
63         Document document = null;
64         if (null == xmlPath || "".equals(xmlPath.trim()))
65             return document;
66 
67         File file = new File(xmlPath);
68         if (file.canRead() && file.exists()) {
69             DocumentBuilderFactory factory = DocumentBuilderFactory
70                     .newInstance();
71             DocumentBuilder builder = factory.newDocumentBuilder();
72             document = builder.parse(file);
73         }
74         return document;
75     }
76 
77     public static void main(String[] args) {
78         Document document = null;
79         try {
80             document = getDocument(xmlPath);
81         } catch (Exception e) {
82             e.printStackTrace();
83         }
84         // 传入根节点
85         parseElement(document.getDocumentElement());
86     }
87 }
View Code

(方法二)SAX解析说明:为解决DOM的问题,出现了SAX。SAX ,事件驱动。当解析器发现元素开始、元素结束、文本、文档的

开 始或结束等时,发送事件,程序员编写响应这些事件的代码,保存数据。优点:不用事先调入整个文档,占用资源少;SAX解析器代码比DOM解析器代码小,适 于Applet,下载。缺点:不是持久的;事件过后,若没保存数据,那么数据就丢了;无状态性;从事件中只能得到文本,但不知该文本属于哪个元素;使用场 合:Applet;只需XML文档的少量内容,很少回头访问;机器内存少

 1 <?xml version="1.0" encoding="UTF-8"?>
 2 <BOM Code="LM4029">
 3     <Child Code="LM4029MC">
 4         <Quantity>2.000000</Quantity>
 5     </Child>
 6     <Child Code="LM4029D">
 7         <Quantity>1.000000</Quantity>
 8     </Child>
 9     <Child Code="LM4029PH">
10         <Quantity>1.000000</Quantity>
11     </Child>
12     <Child Code ="LM4029PS">
13         <Quantity>1.000000</Quantity>
14     </Child>
15     <Child Code="LM4029SB">
16         <Quantity>1.000000</Quantity>
17     </Child>
18 </BOM>
XML
 1 import java.util.Stack;
 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 SAXDemo {
11 
12     private final static String uri = "D:\\bom.xml";
13 
14     public static void main(String[] args) {
15         SAXParserFactory factory = SAXParserFactory.newInstance();
16         try {
17             SAXParser parser = factory.newSAXParser();
18             parser.parse(uri, new MyHandler());
19         } catch (Exception e) {
20             e.printStackTrace();
21         }
22     }
23 }
24 
25 class Child {
26     private String code;
27     private double quantity;
28 
29     public String getCode() {
30         return code;
31     }
32 
33     public void setCode(String code) {
34         this.code = code;
35     }
36 
37     public double getQuantity() {
38         return quantity;
39     }
40 
41     public void setQuantity(double quantity) {
42         this.quantity = quantity;
43     }
44 
45 }
46 
47 class MyHandler extends DefaultHandler {
48 
49     Stack<String> stack = null;
50     Child child = null;
51 
52     @Override
53     public void startDocument() throws SAXException {
54         System.out.println("start document");
55         stack = new Stack<String>();
56     }
57 
58     @Override
59     public void endDocument() throws SAXException {
60         System.out.println("end document");
61         stack = null;
62     }
63 
64     @Override
65     public void startElement(String uri, String localName, String qName,
66             Attributes attributes) throws SAXException {
67         stack.push(qName);
68         if ("Child".equals(qName)) {
69             child = new Child();
70             child.setCode(attributes.getValue("Code"));
71         }
72     }
73 
74     @Override
75     public void endElement(String uri, String localName, String qName)
76             throws SAXException {
77         stack.pop();
78         if ("Child".equals(qName)) {
79             System.out.println("Code -> " + child.getCode() + ", Quantity -> "
80                     + child.getQuantity());
81             child = null;
82         }
83     }
84 
85     @Override
86     public void characters(char[] ch, int start, int length)
87             throws SAXException {
88         if ("Quantity".equals(stack.peek())) {
89             child.setQuantity(Double.parseDouble(new String(ch, start, length)));
90         }
91     }
92 }
View Code

(方法三)JDOM解析说明:为减少DOM、SAX的编码量,出现了JDOM;优点:20-80原则,极大减少了代码量。使用场合:要实现的功能
简单,如解析、创建等,但在底层,JDOM还是使用SAX(最常用),DOM

 1 import java.io.File;
 2 import java.io.IOException;
 3 import java.util.List;
 4 
 5 import org.jdom2.Document;
 6 import org.jdom2.Element;
 7 import org.jdom2.JDOMException;
 8 import org.jdom2.input.SAXBuilder;
 9 
10 public class JdomDemo {
11 
12     private final static String xmlPath = "D:\\bom.xml";
13 
14     public static void readXml() throws JDOMException, IOException {
15         SAXBuilder builder = new SAXBuilder();
16         Document document = builder.build(new File(xmlPath));
17 
18         Element element = document.getRootElement();
19         List<Element> childList = element.getChildren("Child");
20 
21         for (int i = 0; i < childList.size(); i++) {
22             String code = childList.get(i).getAttributeValue("Code");
23             double quantity = Double.parseDouble(childList.get(i).getChildText(
24                     "Quantity"));
25             System.out.println("Code -> " + code + ", Quantity -> " + quantity);
26         }
27     }
28 }
View Code

(方法四)DOM4J解析说明:DOM4J 是一个非常非常优秀的Java XML API,具有性能优异、功能强大和极端易用使用的特点,同

时它也是一个开放源代码的软件。如今你可以看到越来越多的 Java 软件都在使用 DOM4J 来读写 XML

 1 import java.io.File;
 2 import java.io.IOException;
 3 import java.util.Iterator;
 4 
 5 import javax.xml.parsers.DocumentBuilder;
 6 import javax.xml.parsers.DocumentBuilderFactory;
 7 import javax.xml.parsers.ParserConfigurationException;
 8 
 9 import org.dom4j.Attribute;
10 import org.dom4j.Document;
11 import org.dom4j.DocumentException;
12 import org.dom4j.Element;
13 import org.dom4j.io.DOMReader;
14 import org.dom4j.io.SAXReader;
15 import org.xml.sax.SAXException;
16 
17 public class Dom4jDemo {
18 
19     private final static String xmlPath = "D:\\bom.xml";
20 
21     public static void parseElement() throws DocumentException,
22             ParserConfigurationException, SAXException, IOException {
23         // 方式一 DOM 
24         // DocumentBuilderFactory factory =
25         // DocumentBuilderFactory.newInstance();
26         // DocumentBuilder builder = factory.newDocumentBuilder();
27         // org.w3c.dom.Document domDoc = builder.parse(xmlPath);
28         // DOMReader domReader = new DOMReader();
29         // Document document = domReader.read(domDoc);
30 
31         //方式二 SAX(常用)
32         SAXReader saxReader = new SAXReader();
33         Document document = saxReader.read(new File(xmlPath));
34         Element rootEl = document.getRootElement();
35 
36         for (Iterator iterator = rootEl.elementIterator("Child"); iterator
37             .hasNext();) {
38             Element e = (Element) iterator.next();
39             System.out.print("Code -> " + e.attributeValue("Code"));
40             System.out.println(" Quantity -> " + e.elementText("Quantity"));
41         }
42     }
43 
44 }
View Code

总结:

1.DOM, JDOM在性能上不如SAX, DOM4J, 在小文档情况下还值得考虑使用 DOM 和 JDOM。

2.DOM 实现广泛应用于多种编程语言。它还是许多其它与 XML 相关的标准的基础,因为它正式获得 W3C 推荐(与基于非标准的 Java 模型相对),所以在某些类型的项目中可能也需要它(如在 javascript 中使用 DOM)。

3.SAX 的高效取决于特定的解析方式,不用事先调入整个文档,占用资源少。

4.如果不考虑可移植性, 首先考虑使用DOM4J。

posted @ 2015-06-30 09:53  liuxiujun  阅读(2764)  评论(0编辑  收藏  举报