您的位置：首页 > 编程语言 > Java开发

SAX之Java实现学习笔记（一）

2004-01-04 10:22 381 查看

SAX之Java实现学习笔记（一）<?xml:namespace prefix = o ns = "urn:schemas-microsoft-com:office:office" />

本文假设读者对XML有些了解

首先，先给出一个比较基本的处理xml文件的程序。你不必细看，直接跳过即可。需要时可以返回来看。

Echo01.java

import java.io.*;

import org.xml.sax.*;

import org.xml.sax.helpers.DefaultHandler;

import javax.xml.parsers.SAXParserFactory;

import javax.xml.parsers.ParserConfigurationException;

import javax.xml.parsers.SAXParser;

public class Echo01 extends DefaultHandler

{

StringBuffer textBuffer;

public static void main(String argv[])

{

if (argv.length != 1) {

System.err.println("Usage: cmd filename");

System.exit(1);

}

// Use an instance of ourselves as the SAX event handler

DefaultHandler handler = new Echo01();

// Use the default (non-validating) parser

SAXParserFactory factory = SAXParserFactory.newInstance();

try {

// Set up output stream

out = new OutputStreamWriter(System.out, "UTF-8");

// Parse the input

SAXParser saxParser = factory.newSAXParser();

saxParser.parse( new File(argv[0]), handler);

} catch (Throwable t) {

t.printStackTrace();

}

System.exit(0);

}

static private Writer out;

//===========================================================

// SAX DocumentHandler methods

//===========================================================

public void startDocument()

throws SAXException

{

emit("<?xml version='1.0' encoding='UTF-8'?>");

nl();

}

public void endDocument()

throws SAXException

{

try {

nl();

out.flush();

} catch (IOException e) {

throw new SAXException("I/O error", e);

}

public void startElement(String namespaceURI,

String sName, // simple name

String qName, // qualified name

Attributes attrs)

throws SAXException

{

echoText();

String eName = sName; // element name

if ("".equals(eName)) eName = qName; // not namespaceAware

emit("<"+eName);

if (attrs != null) {

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

String aName = attrs.getLocalName(i); // Attr name

if ("".equals(aName)) aName = attrs.getQName(i);

emit(" ");

emit(aName+"=/""+attrs.getValue(i)+"/"");

}

emit(">");

}

public void endElement(String namespaceURI,

String sName, // simple name

String qName // qualified name

)

throws SAXException

{

echoText();

String eName = sName; // element name

if ("".equals(eName)) eName = qName; // not namespaceAware

emit("</"+eName+">");

}

public void characters(char buf[], int offset, int len)

throws SAXException

{

String s = new String(buf, offset, len);

if (textBuffer == null) {

textBuffer = new StringBuffer(s);

} else {

textBuffer.append(s);

}

//===========================================================

// Utility Methods ...

//===========================================================

// Display text accumulated in the character buffer

private void echoText()

throws SAXException

{

if (textBuffer == null) return;

String s = ""+textBuffer;

emit(s);

textBuffer = null;

}

// Wrap I/O exceptions in SAX exceptions, to

// suit handler signature requirements

private void emit(String s)

throws SAXException

{

try {

out.write(s);

out.flush();

} catch (IOException e) {

throw new SAXException("I/O error", e);

}

// Start a new line

private void nl()

throws SAXException

{

String lineEnd = System.getProperty("line.separator");

try {

out.write(lineEnd);

} catch (IOException e) {

throw new SAXException("I/O error", e);

}

从程序中可以看出，解析一个XML文件的核心语句是下面一部分：

// Use an instance of ourselves as the SAX event handler

DefaultHandler handler = new Echo01();

// Use the default (non-validating) parser

SAXParserFactory factory = SAXParserFactory.newInstance();

try {

// Set up output stream

out = new OutputStreamWriter(System.out, "UTF-8");

// Parse the input

SAXParser saxParser = factory.newSAXParser();

saxParser.parse( new File(argv[0]), handler);

} catch (Throwable t) {

t.printStackTrace();

}

先是创建一个SAXParserFactory工厂类的实例，然后通过SAXParser saxParser = factory.newSAXParser(); 这个工厂类的方法创建了一个saxParser。将xml文件（new File(argv[0])）和一个Sax Event Handler（handler）（在这个程序里面，这个Handler其实是本身这个类，这个类继承了org.xml.sax.helpers.DefaultHandler 这个类，并且在前面初始化了它：DefaultHandler handler = new Echo01(); ）传递给它，让它进行解析。

关于xml文件的解析过程中的处理全部在Handler里面实现。一般Parser接受的是DefaultHandler或者HandlerBase这两个类。这个例子里面的类是继承DefaultHandler这个虚类的。看下图：