JAVA解析XML(StAX)

<?xml version="1.0"?>

<!-- xxxtask, not xxxChecker -->

<service>
	<item>
		<task>HostAliveTask</task>
		<strategy>repeat</strategy>
		<repeatFreq>180</repeatFreq>
	</item>
	<item>
		<task>WebpageRespTask</task>
		<strategy>repeat</strategy>
		<repeatFreq>180</repeatFreq>
	</item>
	
	<item>
		<task>AlarmNumTask</task>
		<strategy>daily</strategy>
		<dailyRuntime>16:45:00</dailyRuntime>
	</item>
</service>

import global.Global;

import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.InputStream;
import java.util.Calendar;
import java.util.Date;
import java.util.Scanner;
import java.util.Timer;
import java.util.TimerTask;

import javax.xml.stream.XMLEventReader;
import javax.xml.stream.XMLInputFactory;
import javax.xml.stream.XMLStreamException;
import javax.xml.stream.events.EndElement;
import javax.xml.stream.events.StartElement;
import javax.xml.stream.events.XMLEvent;

import org.apache.log4j.Logger;

/**
 * schedule the checking task.
 */
public class Scheduler {
//	private static final String TAG_SERVICE = "service";
	private static final String TAG_ITEM = "item";
	private static final String TAG_TASK = "task";
	
	private static final String TAG_STRATEGY = "strategy";
	private static final String STRATEGE_REPEAT = "repeat";
	private static final String STRATEGE_DAILY = "daily";
	
	private static final String TAG_REPEATFREQ = "repeatFreq";
	private static final String TAG_DAILYRUNTIME = "dailyRuntime";
	
	private static Logger _logger = Logger.getLogger(Scheduler.class);
	
	void readConfig(){
		try {
			// First create a new XMLInputFactory
			XMLInputFactory inputFactory = XMLInputFactory.newInstance();
			inputFactory.setProperty("javax.xml.stream.isCoalescing", true); //否则读取多行数据时出问题

			// Setup a new eventReader
			InputStream in = new FileInputStream(Global.SERVICE_CONFIGURE_FILE);
			XMLEventReader eventReader = inputFactory.createXMLEventReader(in);

			// One specification
			String task 	= null;
			String strategy = null;
			Integer freq 	= null;// by second
			
			// for daily job
			Date firstTime 	= null;
			Calendar calendar = Calendar.getInstance();  
	        
			// Read the XML document
			while (eventReader.hasNext()) {
				XMLEvent event = eventReader.nextEvent();

				if (event.isStartElement()) {
					StartElement startElement = event.asStartElement();

					if (startElement.getName().getLocalPart().equals(TAG_ITEM)) {
					/*
						Iterator<Attribute> attributes = startElement.getAttributes();
						while (attributes.hasNext()) {
							attributes.next();
							// skip
						}
					*/
					}

					if (event.asStartElement().getName().getLocalPart().equals(TAG_TASK)) {
						event = eventReader.nextEvent();
						task = event.asCharacters().getData();
						
						continue;
					}
					if (event.asStartElement().getName().getLocalPart().equals(TAG_STRATEGY)) {
						event = eventReader.nextEvent();
						strategy = event.asCharacters().getData();
						
						continue;
					}
					
					if (event.asStartElement().getName().getLocalPart().equals(TAG_REPEATFREQ)) {
						event = eventReader.nextEvent();
						freq = Integer.parseInt(event.asCharacters().getData());
						
						continue;
					}
					
					if (event.asStartElement().getName().getLocalPart().equals(TAG_DAILYRUNTIME)) {
						event = eventReader.nextEvent();
						
						// hour:min:sec
						Scanner scanner = new Scanner(event.asCharacters().getData());
						scanner.useDelimiter(":");
						
						int hour = scanner.nextInt();
						int minute = scanner.nextInt();
						int second = scanner.nextInt();
						
						// firstTime (today)
						calendar.set(Calendar.HOUR_OF_DAY, hour);  
				        calendar.set(Calendar.MINUTE, minute);  
				        calendar.set(Calendar.SECOND, second);  
				        firstTime = calendar.getTime();
					
						continue;
					}
				}
				// If we reach the end of an item element we add it to the list
				if (event.isEndElement()) {
					EndElement endElement = event.asEndElement();
					if (endElement.getName().getLocalPart().equals(TAG_ITEM)) {
						
						Timer timer = new Timer();

						if(strategy.equals(STRATEGE_REPEAT)) {
							
							Class<?> clz = Class.forName(Global.TASK_PACKAGE_PREFIX + task);
							TimerTask ctr = (TimerTask)clz.newInstance();
							
							timer.schedule(ctr, 0, freq*1000);
							
						} else if(strategy.equals(STRATEGE_DAILY)){
							
							Class<?> clz = Class.forName(Global.TASK_PACKAGE_PREFIX + task);
							TimerTask ctr = (TimerTask)clz.newInstance();
							
							timer.schedule(ctr, firstTime, Global.PERIOD_DAY);
						} else {
							_logger.error("Unexpected configuration option "+ strategy +" in " + Global.SERVICE_CONFIGURE_FILE);
						}
					}
				}
			}
		} catch (FileNotFoundException ex) {
			_logger.error(ex.getLocalizedMessage(), ex);
			
		} catch (XMLStreamException ex) {
			_logger.error(ex.getLocalizedMessage(), ex);
			
		} catch (Exception ex) {
			_logger.error(ex.getLocalizedMessage(), ex);
			
		}
	}

}

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

Stax介绍参考：Sample Event Mapping

Event Type	Description
StartDocument	Reports the beginning of a set of XML events, including encoding, XML version, and standalone properties.
StartElement	Reports the start of an element, including any attributes and namespace declarations; also provides access to the prefix, namespace URI, and local name of the start tag.
EndElement	Reports the end tag of an element. Namespaces that have gone out of scope can be recalled here if they have been explicitly set on their corresponding StartElement.
Characters	Corresponds to XML CData sections and CharacterData entities. Note that ignorable whitespace and significant whitespace are also reported as Character events.
EntityReference	Character entities can be reported as discrete events, which an application developer can then choose to resolve or pass through unresolved. By default, entities are resolved. Alternatively, if you do not want to report the entity as an event, replacement text can be substituted and reported as Characters.
ProcessingInstruction	Reports the target and data for an underlying processing instruction.
Comment	Returns the text of a comment
EndDocument	Reports the end of a set of XML events.
DTD	Reports as java.lang.String information about the DTD, if any, associated with the stream, and provides a method for returning custom objects found in the DTD.
Attribute	Attributes are generally reported as part of a StartElement event. However, there are times when it is desirable to return an attribute as a standalone Attribute event; for example, when a namespace is returned as the result of an XQuery or XPath expression.
Namespace	As with attributes, namespaces are usually reported as part of a StartElement, but there are times when it is desirable to report a namespace as a discrete Namespace event.

As an example of how the event iterator API maps an XML stream, consider the following XML document:

<?xml version="1.0"?>
<BookCatalogue xmlns="http://www.publishing.org">
  <Book>
    <Title>Yogasana Vijnana: the Science of Yoga</Title>
    <ISBN>81-40-34319-4</ISBN>
    <Cost currency="INR">11.50</Cost>
  </Book>
</BookCatalogue>

This document would be parsed into eighteen primary and secondary events, as shown below. Note that secondary events, shown in curly braces ({}), are typically accessed from a primary event rather than directly.

#	Element/Attribute	Event
1	version="1.0"	StartDocument
2	isCData = false	Characters
	data = "\n"
	IsWhiteSpace = true
3	qname = BookCatalogue:http://www.publishing.org	StartElement
	attributes = null
	namespaces = {BookCatalogue" -> http://www.publishing.org"}
4	qname = Book	StartElement
	attributes = null
	namespaces = null
5	qname = Title	StartElement
	attributes = null
	namespaces = null
6	isCData = false	Characters
	data = "Yogasana Vijnana: the Science of Yoga\n\t"
	IsWhiteSpace = false
7	qname = Title	EndElement
	namespaces = null
8	qname = ISBN	StartElement
	attributes = null
	namespaces = null
9	isCData = false	Characters
	data = "81-40-34319-4\n\t"
	IsWhiteSpace = false
10	qname = ISBN	EndElement
	namespaces = null
11	qname = Cost	StartElement
	attributes = {"currency" -> INR}
	namespaces = null
12	isCData = false	Characters
	data = "11.50\n\t"
	IsWhiteSpace = false
13	qname = Cost	EndElement
	namespaces = null
14	isCData = false	Characters
	data = "\n"
	IsWhiteSpace = true
15	qname = Book	EndElement
	namespaces = null
16	isCData = false	Characters
	data = "\n"
	IsWhiteSpace = true
17	qname = BookCatalogue:http://www.publishing.org	EndElement
	namespaces = {BookCatalogue" -> http://www.publishing.org"}
18	EndDocument