`

最新SH、Lucene3、IKAnalyzer3.2.3整合实例

阅读更多
Spring3.1, Hibernate3.6,Lucene3.0.3以及IKAnalyzer3.2.3, 数据库采用Mysql,连接池采用dbcp.主要Jar如下:




Spring重要Bean配置:
<!--配置定时任务 -->
<bean id="bagnetTask"
		class="org.springframework.scheduling.quartz.MethodInvokingJobDetailFactoryBean">
		<property name="targetObject">
			<ref bean="bagnetJob" />
		</property>
		<property name="targetMethod">
			<value>runJobs</value>
		</property>
		<!-- keep the job from running while the previous one hasn't finished yet -->
		<property name="concurrent" value="false" />
	</bean>

<!--配置定时任务触发器 -->

<bean id="jobTrigger"
		class="org.springframework.scheduling.quartz.CronTriggerBean">
		<property name="jobDetail">
			<ref bean="bagnetTask" />
		</property>
		<!-- every 10 mins in the working day from 9:00 to 19:00 we create/update index -->
		<property name="cronExpression">
			<value>0 0/10 9-19 *,* * ?</value>
		</property>
	</bean>
<!-- 定时调用的Scheduler-->
<bean autowire="no"
		class="org.springframework.scheduling.quartz.SchedulerFactoryBean">
		<property name="triggers">
			<list>
				<ref local="jobTrigger" />
			</list>
		</property>
	</bean>

<!-- 事务管理器 -->
	<bean id="transactionManger"
		class="org.springframework.orm.hibernate3.HibernateTransactionManager">
		<property name="sessionFactory">
			<ref bean="sessionFactory" />
		</property>
	</bean>

	<!--   配置事务拦截器-->
	<bean id="transactionInterceptor"
		class="org.springframework.transaction.interceptor.TransactionInterceptor">
		<property name="transactionManager">
			<ref bean="transactionManger" />
		</property>
		<!--   下面定义事务传播属性-->
		<property name="transactionAttributes">
			<props>
				<prop key="find*">PROPAGATION_REQUIRED</prop>
				<prop key="delete*">PROPAGATION_REQUIRED</prop>
				<prop key="add*">PROPAGATION_REQUIRED</prop>
				<prop key="update*">PROPAGATION_REQUIRED</prop>
				<prop key="do*">PROPAGATION_REQUIRED</prop>
			</props>
		</property>
	</bean>

	<!--  自动代理 -->
	<bean id="autoBeanNameProxyCreator"
		class="org.springframework.aop.framework.autoproxy.BeanNameAutoProxyCreator">
		<property name="beanNames">
			<list>
				<value>*Service</value>
			</list>
		</property>
		<property name="interceptorNames">
			<list>
				<idref local="transactionInterceptor" />
			</list>
		</property>
		<!--  这里的配置是必须的,否则无法完成代理的类型转化 这是使用CGLIB来生成代理 -->
		<property name="proxyTargetClass" value="true" />
	</bean>



Lucene工具类:
package com.dx.bags.util;

import java.io.File;
import java.io.IOException;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.wltea.analyzer.lucene.IKAnalyzer;

public class LuceneUtil
{
	private static LuceneUtil instance;
	private Analyzer analyzer;
	private Directory picDirectory;
	private Directory topDirectory;

	
	public Analyzer getAnalyzer()
	{
		return analyzer;
	}

	public void setAnalyzer(Analyzer analyzer)
	{
		this.analyzer = analyzer;
	}

	public Directory getPicDirectory()
	{
		return picDirectory;
	}

	public void setPicDirectory(Directory picDirectory)
	{
		this.picDirectory = picDirectory;
	}

	public Directory getTopDirectory()
	{
		return topDirectory;
	}

	public void setTopDirectory(Directory topDirectory)
	{
		this.topDirectory = topDirectory;
	}

	private LuceneUtil()
	{
		analyzer = new IKAnalyzer();
		try
		{
			picDirectory = FSDirectory.open(new File(DXConstants.PIC_INDEX_DIR));
			topDirectory = FSDirectory.open(new File(DXConstants.TOP_INDEX_DIR));
			
		} catch (IOException e)
		{
			throw new RuntimeException(e);
		}
	}

	public static LuceneUtil getInstance()
	{
		if (null == instance)
			instance = new LuceneUtil();
		return instance;
	}

}



建立索引的方法:
	public static void createTopIndex(List<SearchTop> list, boolean isFirstTime)
	{

		RAMDirectory ramDirectory = new RAMDirectory();
		try
		{
			IndexWriter indexwriter = new IndexWriter(ramDirectory, LuceneUtil.getInstance().getAnalyzer(),
					true, IndexWriter.MaxFieldLength.LIMITED);
			if (list != null && list.size() > 0)
			{
				for (int i = 0; i < list.size(); i++)
				{
					Document doc = new Document();
					
					SearchTop searchTop = list.get(i);
					
					Field field = new Field("id", String.valueOf(searchTop.getId()), Field.Store.YES, Field.Index.NO);
					doc.add(field);
					
					String title = DXUtil.characterUtil(searchTop.getTitle());
					if(title!=null && !"".equals(title)){
						field = new Field("title", title, Field.Store.YES, Field.Index.ANALYZED);
						doc.add(field);
					}
					
					String description = searchTop.getDescription();
					if(description!=null && !"".equals(description)){
						field = new Field("description", description, Field.Store.NO,Field.Index.ANALYZED);
						doc.add(field);
					}
					
					field = new Field("cid", String.valueOf(searchTop.getCid()), Field.Store.YES, Field.Index.NOT_ANALYZED);
					doc.add(field);
					
					field = new Field("addtime", String.valueOf(searchTop.getCreateDate()), Field.Store.YES, Field.Index.NOT_ANALYZED);
					doc.add(field);
					
					String content = DXUtil.characterUtil(searchTop.getContents());
					if(content!=null && !"".equals(content)){
						field = new Field("contents", content, Field.Store.NO, Field.Index.ANALYZED);
						doc.add(field);
					}
					
					field = new Field("sex", String.valueOf(searchTop.getSex()), Field.Store.YES, Field.Index.NOT_ANALYZED);
					doc.add(field);
					
					field = new Field("tid",String.valueOf(searchTop.getTid()),Field.Store.YES,Field.Index.NOT_ANALYZED);
					doc.add(field);
					
					field = new Field("topicid", String.valueOf(searchTop.getTopicId()), Field.Store.YES, Field.Index.ANALYZED);
					doc.add(field);
					
					field = new Field("piccount", String.valueOf(searchTop.getPiccount()), Field.Store.YES, Field.Index.NOT_ANALYZED);
					doc.add(field);
					
					String city = DXUtil.characterUtil(searchTop.getCityName());
					if(city!=null && !"".equals(city)){
						field = new Field("cityname", city, Field.Store.YES, Field.Index.ANALYZED);
						doc.add(field);
					}
					
					field = new Field("purview", dealPurview(searchTop.getSex(), searchTop.getCid()), Field.Store.YES, Field.Index.NOT_ANALYZED);
					doc.add(field);
					
					String seasonname = DXUtil.characterUtil(searchTop.getSeasonName());
					if(seasonname!=null && !"".equals(seasonname)){
						field = new Field("seasonname", seasonname, Field.Store.YES, Field.Index.ANALYZED);
						doc.add(field);
					}
					
					String recordurl = dealTopUrl(searchTop.getSex(), searchTop.getCid(), searchTop.getTid());
					if(recordurl!=null && !"".equals(recordurl)){
						field = new Field("recordurl", recordurl, Field.Store.YES, Field.Index.NOT_ANALYZED); 
						doc.add(field);
					}
					
					indexwriter.addDocument(doc);
				}
			}
			indexwriter.optimize();
			indexwriter.close();
			
			IndexWriter writer = new IndexWriter(LuceneUtil.getInstance()
					.getTopDirectory(), LuceneUtil.getInstance()
					.getAnalyzer(), isFirstTime, IndexWriter.MaxFieldLength.LIMITED);
			writer.addIndexesNoOptimize(new Directory[] { ramDirectory });
			writer.close();
		} catch (CorruptIndexException e)
		{

			throw new RuntimeException(e);
		} catch (IOException ex)
		{
			throw new RuntimeException(ex);
		}
	}


对增量数据循环建立索引:
private void createTopIndex() {
		long count = searchTopService.findTotalRecordNum();
		boolean flag = DXUtil.hasNotFile(new File(DXConstants.TOP_INDEX_DIR));
		List<SearchTop> tops = new ArrayList<SearchTop>();
		int max = DXConstants.PAGE_SIZE;
		int first = Integer.parseInt(DXUtil
				.getRecordNumFromFile(DXConstants.TOP_TXT));
		while (first < count) {
			tops = searchTopService.findTopToIndex(first, max);
			first = first + max;
			IndexCreator.createTopIndex(tops, flag);
			if(flag == true)
				flag = false;
			DXUtil.writeContent(String.valueOf(first), DXConstants.TOP_TXT);
		}
		if (first >= count)
			DXUtil.writeContent(String.valueOf(count), DXConstants.TOP_TXT);
		optimiseTopicIndex(flag);
	}

//optimize index
private void optimiseTopicIndex(boolean flag) {
		IndexWriter writer = null;
		try {
			writer = new IndexWriter(
					LuceneUtil.getInstance().getTopDirectory(), LuceneUtil
							.getInstance().getAnalyzer(), flag,
					IndexWriter.MaxFieldLength.LIMITED);
			writer.optimize();
			writer.close();

		} catch (Exception e) {

		}

	}



主要代码以备忘。








  • 大小: 62.8 KB
2
1
分享到:
评论

相关推荐

Global site tag (gtag.js) - Google Analytics