SAX解析XML file

来源：互联网发布：小明看看发布永久域名编辑：程序博客网时间：2024/04/26 07:02

SAX解析XML file

http://chris-freedream.iteye.com/blog/375772

1. SAX简述:
SAX全称Simple APIfor 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:

<?xmlversion="1.0" encoding="utf-8"?>

<books>

<bookpages="1000" price="$99">

<name>Thinkingin java</name>

</book>

<bookpages="800" price="$40">

<name>JUnitin Action</name>

</book>

<bookpages="900" price="$70">

<name>Lucenein Action</name>

</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;

importorg.xml.sax.helpers.XMLReaderFactory;

public class XMLParser

{

//handlernormal info.

protected PrintStream output =

new PrintStream( new BufferedOutputStream( new FileOutputStream(java.io.FileDescriptor.out ), 128 ), true );

//handlererror 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( newMyContentHandler() );

reader.setErrorHandler( new MyErrorHandler());

InputSource source = new InputSource( newFileInputStream( new File( fileName ) ) );

reader.parse(source);

}

classMyErrorHandler implements ErrorHandler

{

publicvoid error( SAXParseException exception ) throws SAXException

{

error.println(exception.getMessage() );

}

publicvoid fatalError( SAXParseException exception ) throws SAXException

{

error.println(exception.getMessage() );

}

publicvoid warning( SAXParseException exception ) throws SAXException

{

output.println(exception.getMessage() );

}

classMyContentHandler implements ContentHandler

{

publicvoid characters( char[] ch, int start, int length )

throwsSAXException

{

output.print(ch);

}

publicvoid endDocument() throws SAXException

{

}

publicvoid endElement( String uri, String localName, String name )

throwsSAXException

{

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

}

publicvoid endPrefixMapping( String prefix ) throws SAXException

{

}

publicvoid ignorableWhitespace( char[] ch, int start, int length )

throwsSAXException

{

}

publicvoid processingInstruction( String target, String data )

throwsSAXException

{

}

publicvoid setDocumentLocator( Locator locator )

{

}

publicvoid skippedEntity( String name ) throws SAXException

{

}

publicvoid startDocument() throws SAXException

{

output.println("<xmlversion=\"1.0\" encoding=\"utf-8\"?>");

}

publicvoid startElement( String uri, String localName, String name,

Attributesatts ) throws SAXException

{

//uriis identifier of namespace

//name-->prefix:localName

output.print("<"+localName );

for(int i = 0; i < atts.getLength(); i++ )

{

StringattrName = atts.getLocalName( i );

StringattrValue = atts.getValue( i );

output.print("" + attrName + "=" + attrValue );

}

output.print(">");

}

publicvoid startPrefixMapping( String prefix, String uri )

throwsSAXException

{

}

publicstatic void main( String[] args ) throws Exception, IOException

{

XMLParserparser = new XMLParser();

parser.parserXMLFile("books.xml");

}

解析后的结果如下:

<books>

<bookpages="1000" price="$99">

<name>Thinkingin java</name>

</book>

<bookpages="800" price="$40">

<name>JUnitin Action</name>

</book>

<bookpages="900" price="$70">

<name>Lucenein Action</name>

</book>

</books>

<books>

<bookpages="1000" price="$99">

<name>Thinkingin java</name>

</book>

<bookpages="800" price="$40">

<name>JUnitin Action</name>

</book>

<bookpages="900" price="$70">

<name>Lucenein Action</name>

</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;

importorg.xml.sax.helpers.XMLReaderFactory;

public class XMLParser

{

//handlernormal info.

protected PrintStream output =

new PrintStream( new BufferedOutputStream( new FileOutputStream(java.io.FileDescriptor.out ), 128 ), true );

//handlererror 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( newMyContentHandler() );

reader.setErrorHandler( new MyErrorHandler());

InputSource source = new InputSource( newFileInputStream( new File( fileName ) ) );

reader.parse(source);

}

classMyErrorHandler implements ErrorHandler

{

publicvoid error( SAXParseException exception ) throws SAXException

{

error.println(exception.getMessage() );

}

publicvoid fatalError( SAXParseException exception ) throws SAXException

{

error.println(exception.getMessage() );

}

publicvoid warning( SAXParseException exception ) throws SAXException

{

output.println(exception.getMessage() );

}

classMyContentHandler implements ContentHandler

{

private StringBuffer buffer = new StringBuffer();

private String key;

publicvoid characters( char[] ch, int start, int length )

throwsSAXException

{

buffer.append(ch, start, length);

}

publicvoid endDocument() throws SAXException

{

}

publicvoid endElement( String uri, String localName, String name )

throwsSAXException

{

if(key.equals( localName))

{

output.print(buffer);

}

output.print("</"+localName+">");

}

publicvoid endPrefixMapping( String prefix ) throws SAXException

{

}

publicvoid ignorableWhitespace( char[] ch, int start, int length )

throwsSAXException

{

}

publicvoid processingInstruction( String target, String data )

throwsSAXException

{

}

publicvoid setDocumentLocator( Locator locator )

{

}

publicvoid skippedEntity( String name ) throws SAXException

{

}

publicvoid startDocument() throws SAXException

{

output.println("<xmlversion=\"1.0\" encoding=\"utf-8\"?>");

}

publicvoid startElement( String uri, String localName, String name,

Attributesatts ) throws SAXException

{

//uriis identifier of namespace

//name-->prefix:localName

buffer.delete(0,buffer.length());

key= localName;

output.print("<"+localName );

for(int i = 0; i < atts.getLength(); i++ )

{

StringattrName = atts.getLocalName( i );

StringattrValue = atts.getValue( i );

output.print("" + attrName + "=" + attrValue );

}

output.print(">");

}

publicvoid startPrefixMapping( String prefix, String uri )

throwsSAXException

{

}

publicstatic void main( String[] args ) throws Exception, IOException

{

XMLParserparser = new XMLParser();

parser.parserXMLFile("books.xml");

}

输出结果如下:

<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>