SAX解析XML file

chris_freedream

浏览: 32934 次
性别:
来自: 深圳

最近访客更多访客>>

博主相关

博客

微博

相册

留言

关于我

文章分类

社区版块

存档分类

博客分类：

XML-SAX

XML Java lucene junit UML

1. SAX简述
2. SAX in practice

1.SAX简述:
SAX全称Simple API for XML, 用于简单并快速的解析XML文件，是基于事件处理的模型，SUN定义了规范，常用的主要接口包括ContentHandler, ErrorHanlder, XMLReader, XMLFilter, Attributes, InputSource, Locator, 及不常用的EntityResolver, DTDHandler, LexicalHandler, DeclHandler等, UML静态类图如下:

, 也许读者会问，这么多接口都要去实现，并且，很多接口中的方法并不是所要的，那岂不是做无用功，放心，其中有一个DefaultHanlder已经适配了所有的重要的接口，你只需要继承DefaultHandler并重写你所想处理的方法即可，比如startElement, endElement, charactors等。

其中Apache下的Xerces(http://sax.sourceforge.net/)对这些接口有个集体的实现.
2.SAX in practice

被解析的XML文件:

<?xml version="1.0" encoding="utf-8"?>
<books>
	<book pages="1000" price="$99">
		<name>Thinking in java</name>
		<version>3.0</version>
	</book>
	<book pages="800" price="$40">
		<name>JUnit in Action</name>
		<version>2.0</version>
	</book>
	<book pages="900" price="$70">
		<name>Lucene in Action</name>
		<version>2.0</version>
	</book>
</books>

解析代码如下：

package com.chris.sax.action;

import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintStream;


import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.ErrorHandler;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.XMLReaderFactory;

public class XMLParser
{
	//handler normal info.
	protected  PrintStream output =
      new PrintStream( new BufferedOutputStream( new FileOutputStream( java.io.FileDescriptor.out ), 128 ), true );
	//handler error info.
   protected  PrintStream error =
      new PrintStream( new BufferedOutputStream( new FileOutputStream( java.io.FileDescriptor.err ), 128 ), true );
   
   public void parserXMLFile(String fileName ) throws SAXException, IOException
   {
   	XMLReader reader = XMLReaderFactory.createXMLReader();
   	reader.setContentHandler( new MyContentHandler() );
   	reader.setErrorHandler( new MyErrorHandler() );
   	InputSource source = new InputSource( new FileInputStream( new File( fileName ) ) );
   	reader.parse(source);
   }
	
	class MyErrorHandler implements ErrorHandler
	{

		public void error( SAXParseException exception ) throws SAXException
		{
			
			error.println( exception.getMessage() );
		}

		public void fatalError( SAXParseException exception ) throws SAXException
		{

			error.println( exception.getMessage() );
		}

		public void warning( SAXParseException exception ) throws SAXException
		{
			output.println( exception.getMessage() );
			
		}
		
	}
	class MyContentHandler implements ContentHandler
	{
		
	   
		public void characters( char[] ch, int start, int length )
				throws SAXException
		{
			output.print(ch);
		}

		public void endDocument() throws SAXException
		{
			
		}

		public void endElement( String uri, String localName, String name )
				throws SAXException
		{

			output.println("</"+localName+">");
			
		}

		public void endPrefixMapping( String prefix ) throws SAXException
		{

			
		}

		public void ignorableWhitespace( char[] ch, int start, int length )
				throws SAXException
		{
			
		}

		public void processingInstruction( String target, String data )
				throws SAXException
		{
					
		}

		public void setDocumentLocator( Locator locator )
		{
			
		}

		public void skippedEntity( String name ) throws SAXException
		{
			
		}

		public void startDocument() throws SAXException
		{
			output.println("<xml version=\"1.0\" encoding=\"utf-8\"?>");
		}

		public void startElement( String uri, String localName, String name,
											Attributes atts ) throws SAXException
		{
			//uri is identifier of namespace
			//name-->prefix:localName
			output.print("<" +localName );
			for( int i = 0; i < atts.getLength(); i++ )
			{
				String attrName = atts.getLocalName( i );
				String attrValue = atts.getValue( i );
				output.print(" " + attrName + "=" + attrValue );
			}
			output.print(">");
			
		}

		public void startPrefixMapping( String prefix, String uri )
				throws SAXException
		{
			
		}		
	}
	
	public static void main( String[] args ) throws Exception, IOException
	{
		
		XMLParser parser = new XMLParser();
		parser.parserXMLFile("books.xml");
	}
}

解析后的结果如下:

<xml version="1.0" encoding="utf-8"?>
<books>
<books>
	<book pages="1000" price="$99">
		<name>Thinking in java</name>
		<version>3.0</version>
	</book>
	<book pages="800" price="$40">
		<name>JUnit in Action</name>
		<version>2.0</version>
	</book>
	<book pages="900" price="$70">
		<name>Lucene in Action</name>
		<version>2.0</version>
	</book>
</books>
<books>
	<book pages="1000" price="$99">
		<name>Thinking in java</name>
		<version>3.0</version>
	</book>
	<book pages="800" price="$40">
		<name>JUnit in Action</name>
		<version>2.0</version>
	</book>
	<book pages="900" price="$70">
		<name>Lucene in Action</name>
		<version>2.0</version>
	</book>
</books>

这样就把XML文件大体输出到屏幕上来了，但是你会发现，这些不是你真正想要的结果，甚至出现了乱码，原因就在于characters可能被多次调用，甚至次数不定，以下是个改进的版本

package com.chris.sax.action;


import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.PrintStream;
import java.util.ArrayList;
import java.util.List;


import org.xml.sax.Attributes;
import org.xml.sax.ContentHandler;
import org.xml.sax.ErrorHandler;
import org.xml.sax.InputSource;
import org.xml.sax.Locator;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
import org.xml.sax.XMLReader;
import org.xml.sax.helpers.XMLReaderFactory;

public class XMLParser
{
	//handler normal info.
	protected  PrintStream output =
      new PrintStream( new BufferedOutputStream( new FileOutputStream( java.io.FileDescriptor.out ), 128 ), true );
	//handler error info.
   protected  PrintStream error =
      new PrintStream( new BufferedOutputStream( new FileOutputStream( java.io.FileDescriptor.err ), 128 ), true );
   
   public void parserXMLFile(String fileName ) throws SAXException, IOException
   {
   	XMLReader reader = XMLReaderFactory.createXMLReader();
   	reader.setContentHandler( new MyContentHandler() );
   	reader.setErrorHandler( new MyErrorHandler() );
   	InputSource source = new InputSource( new FileInputStream( new File( fileName ) ) );
   	reader.parse(source);
   }
	
	class MyErrorHandler implements ErrorHandler
	{

		public void error( SAXParseException exception ) throws SAXException
		{
			
			error.println( exception.getMessage() );
		}

		public void fatalError( SAXParseException exception ) throws SAXException
		{

			error.println( exception.getMessage() );
		}

		public void warning( SAXParseException exception ) throws SAXException
		{
			output.println( exception.getMessage() );
			
		}
		
	}
	class MyContentHandler implements ContentHandler
	{
		
	    private StringBuffer  buffer = new StringBuffer();
	    private String key;
	    
	    
		public void characters( char[] ch, int start, int length )
				throws SAXException
		{
			buffer.append( ch, start, length);
			
		}

		public void endDocument() throws SAXException
		{
			
		}

		public void endElement( String uri, String localName, String name )
				throws SAXException
		{

			if( key.equals( localName))
			{
				output.print(buffer);
			}
			
			output.print("</"+localName+">");

			
			
		}

		public void endPrefixMapping( String prefix ) throws SAXException
		{

			
		}

		public void ignorableWhitespace( char[] ch, int start, int length )
				throws SAXException
		{
			
		}

		public void processingInstruction( String target, String data )
				throws SAXException
		{
					
		}

		public void setDocumentLocator( Locator locator )
		{
			
		}

		public void skippedEntity( String name ) throws SAXException
		{
			
		}

		public void startDocument() throws SAXException
		{
			output.println("<xml version=\"1.0\" encoding=\"utf-8\"?>");
		}

		public void startElement( String uri, String localName, String name,
											Attributes atts ) throws SAXException
		{
			//uri is identifier of namespace
			//name-->prefix:localName
			
			buffer.delete(0, buffer.length());
			key = localName;
			
			output.print("<" +localName );			
			for( int i = 0; i < atts.getLength(); i++ )
			{
				String attrName = atts.getLocalName( i );
				String attrValue = atts.getValue( i );
				output.print(" " + attrName + "=" + attrValue );
			}
			output.print(">");
			
		}

		public void startPrefixMapping( String prefix, String uri )
				throws SAXException
		{
			
		}		
	}
	
	public static void main( String[] args ) throws Exception, IOException
	{
		
		XMLParser parser = new XMLParser();
		parser.parserXMLFile("books.xml");
	}
}

输出结果如下:

<xml version="1.0" encoding="utf-8"?>
<books><book pages=1000 price=$99><name>Thinking in java</name><version>3.0</version></book><book pages=800 price=$40><name>JUnit in Action</name><version>2.0</version></book><book pages=900 price=$70><name>Lucene in Action</name><version>2.0</version></book></books>

当然你可以根据你需求，调整程序使得产生更好的输出.