JavaXML解析之SAX

Posted 2020-08-15 H__D

SAX介绍

　　SAX(Simple API for XML)是一种事件驱动的流式XML文件处理方式，区别与DOM方式的是不需要在内存中建一棵DOM树，而是根据读取XML时遇到的标签事件来顺序处理，因此具有速度快，内存占用上的优点。

XML生成

　　代码如下：

　　

 1 package com.test.sax;
 2 
 3 import javax.xml.transform.OutputKeys;
 4 import javax.xml.transform.Result;
 5 import javax.xml.transform.Transformer;
 6 import javax.xml.transform.TransformerConfigurationException;
 7 import javax.xml.transform.sax.SAXTransformerFactory;
 8 import javax.xml.transform.sax.TransformerHandler;
 9 import javax.xml.transform.stream.StreamResult;
10 
11 import org.xml.sax.SAXException;
12 import org.xml.sax.helpers.AttributesImpl;
13 
14 public class TestCreateXml {
15 
16     public static void main(String[] args) {
17         //创建SAXTransformerFactory实例
18         SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
19         try {
20             //创建TransformerHandler实例
21             TransformerHandler handler = factory.newTransformerHandler();
22             //创建Transformer实例
23             Transformer transformer = handler.getTransformer();
24             //设置输出的xml属性，encoding为编码，
25             transformer.setOutputProperty(OutputKeys.ENCODING, "UTF-8");
26             //indent是确保输出的xml文件能够自动换行
27             transformer.setOutputProperty(OutputKeys.INDENT, "yes");
28 
29             //创建Result对象，将Result对象加载到TransHandler中
30             // 注意：1、这一步必须在Transformer.setOutputProperty()之后，不然设置的xml属性将不生效
31             // 2、这一步也必须在TransformerHandler.startDocument()之前，不然会报错。
32             // 分析源码后发现，startDocument()会先判断result是否为空，为空则报错
33             Result result = new StreamResult("src/test-sax-create.xml");
34             handler.setResult(result);
35 
36             // 创建属性Attribute对象
37             AttributesImpl attr = new AttributesImpl();
38             //开始写文件
39             handler.startDocument();
40             //写入根节点conpany
41             handler.startElement("", "", "conpany", attr);
42 
43             //清空属性，
44             attr.clear();
45             //设置属性
46             attr.addAttribute( "", "", "name", "", "1");
47             //写入根节点的子节点book
48             handler.startElement("", "", "department", attr);
49             
50             attr.clear();
51             //分别写入book节点的子节点
52             attr.addAttribute( "", "", "name", "", "employee1");
53             attr.addAttribute( "", "", "id", "", "1");
54             handler.startElement("", "", "employee", attr);
55             //写入子节点内容
56             handler.characters("123".toCharArray(), 0, "123".toCharArray().length);
57             //写入子节点末尾
58             handler.endElement("", "", "employee");
59             //写入department节点末尾
60             handler.endElement("", "", "department");
61             //写入根节点末尾
62             handler.endElement("", "", "conpany");
63             //写文件结束
64             handler.endDocument();
65         } catch (TransformerConfigurationException e) {
66             e.printStackTrace();
67         } catch (SAXException e) {
68             e.printStackTrace();
69         }
70     }
71 }

生成文件如下：

　　

 

XML解析

　　代码如下：

　　

 1 package com.test.sax;
 2 
 3 import java.io.IOException;
 4 import java.util.ArrayList;
 5 import java.util.HashMap;
 6 import java.util.List;
 7 import java.util.Map;
 8 
 9 import javax.xml.parsers.ParserConfigurationException;
10 import javax.xml.parsers.SAXParser;
11 import javax.xml.parsers.SAXParserFactory;
12 
13 import org.xml.sax.Attributes;
14 import org.xml.sax.SAXException;
15 import org.xml.sax.helpers.DefaultHandler;
16 
17 
18 public class TestParseXml {
19     
20     public static void main(String[] args) throws SAXException, IOException, ParserConfigurationException {
21         //创建SAXTransformerFactory实例
22         SAXParserFactory saxParserFactory = SAXParserFactory.newInstance();
23         //创建TransformerHandler实例
24         SAXParser saxParser = saxParserFactory.newSAXParser();
25         
26         MyHandler myHandler = new MyHandler();
27         
28         saxParser.parse(TestParseXml.class.getClassLoader().getResourceAsStream("test.xml"), myHandler);
29     }
30     
31 }
32 
33 
34 class MyHandler extends DefaultHandler{
35     
36     /**
37      * 开始解析文档时，调用的方法
38      */
39     @Override
40     public void startDocument() throws SAXException {
41         System.out.println("---------startDocument-------");
42     }
43     
44     /**
45      * 文档解析完结时，调用的方法
46      */
47     @Override
48     public void endDocument() throws SAXException {
49         System.out.println("---------endDocument-------");
50         super.endDocument();
51     }
52     
53     /**
54      * 开始解析每个元素时，调用的方法，会重复调用
55      */
56     @Override
57     public void startElement(String uri, String localName, String qName, Attributes attributes) throws SAXException {
58         
59         //qName 元素标签
60         System.out.println("---------startElement-------" + qName);
61         
62         // 处理属性
63         if(attributes != null )
64         {
65             for (int i = 0; i < attributes.getLength(); ++i)
66             {
67                 String attrName = attributes.getQName(i);
68                 String attrValue = attributes.getValue(i);
69                 System.out.print("\\t "+ attrName +  "=" + attrValue);
70             }
71         }
72         System.out.println("");
73     }
74     
75     @Override
76     public void endElement(String uri, String localName, String qName) throws SAXException {
77         
78         System.out.println("---------endElement-------" + qName);
79     }
80     
81     /**
82      * 解析到每个元素的内容时会调用此方法
83      */
84     @Override
85     public void characters(char[] ch, int start, int length) throws SAXException {
86         String content = new String(ch,start,length);
87         System.out.println("---------characters-------" + "content == "+ content);
88     }
89 }

控制台输出：

　　

 1 ---------startDocument-------
 2 ---------startElement-------conpany
 3      name=hd
 4 ---------characters-------content ==   
 5     
 6 ---------startElement-------department
 7      name=department1
 8 ---------characters-------content ==   
 9         
10 ---------startElement-------employee
11      name=employee1     id=1
12 ---------characters-------content == 123
13 ---------endElement-------employee
14 ---------characters-------content ==   
15     
16 ---------endElement-------department
17 ---------characters-------content ==   
18     
19 ---------startElement-------department
20      name=department2
21 ---------characters-------content ==   
22         
23 ---------startElement-------employee
24      name=employee2     id=2
25 ---------characters-------content == 321
26 ---------endElement-------employee
27 ---------characters-------content ==     
28         
29 ---------startElement-------employee
30      name=employee3     id=3
31 ---------endElement-------employee
32 ---------characters-------content ==     
33     
34 ---------endElement-------department
35 ---------characters-------content ==   
36     
37 ---------startElement-------department
38      name=department3
39 ---------characters-------content ==   
40     
41 ---------endElement-------department
42 ---------characters-------content ==   
43 
44 ---------endElement-------conpany
45 ---------endDocument-------

 

Simple API for XML