solr DataImport

转帖地址：http://www.cnblogs.com/chenying99/archive/2012/08/04/2622905.html

1 配置RequestHandler

 <!-- dataimporthandler -->

  < requestHandler  name ="/dataimport"  class ="org.apache.solr.handler.dataimport.dataimporthandler" >  
      < lst  name ="defaults" >  
        < str  name ="config" >db/db-data-config.xml </ str >  
      </ lst >  
   </ requestHandler >

2 配置数据源和数据实体

包括全部导入和增量导入

< dataConfig >      

< dataSource  driver ="net.sourceforge.jtds.jdbc.Driver"  url ="jdbc:jtds:sqlserver://IP;instance=sqlSRV2005;DatabaseName=Cloudplat"  user ="sa"  password ="sa"   batchSize ="100" />
< document >
         < entity  name ="article"  pk ="DocAutoId"  query ="select * from CP_InfoListPub order by DocAutoId"          
        deltaimportQuery ="select * from CP_InfoListPubClone where DocAutoId='${dataimporter.delta.DocAutoId}'"
        deltaQuery ="select DocAutoId from CP_InfoListPubClone where Doc_GatherDate &gt; '${dataimporter.last_index_time}'"
        deletedPkQuery ="select DocAutoId from CP_InfoListPubClone where DocAutoId=0"
        transformer ="ClobTransformer,HTMLStripTransformer,DateFormatTransformer"   >
             < field  column ="DocAutoId"  name ="id"   />        
             < field  column ="Doc_Title"  name ="title"   /> 
             < field  column ="Doc_RegionName"  name ="region"   />
             < field  column ="Doc_TradeName"  name ="Trade"   />
             < field  column ="Doc_Content"  name ="content"  clob ="true"  stripHTML ="true" />            
             < field  column ="Doc_PubDate"  name ="update"   dateTimeFormat ="yyyy-MM-dd" />
             < field  column ="Doc_Url"  name ="link"   />
         </ entity >
     </ document >

</dataConfig> 

3 引入相关的文件，apache-solr-dataimporthandler-1.4.0.jar，apache-solr-dataimporthandler-extras-1.4.0.jar，mysql-connector-java-5.1.10.jar等

4 启动tomcat，访问http://localhost:8080/solr/dataimport?command=full-import 将数据全部导入solr服务器进行索引

访问http://localhost:8080/solr/dataimport?command=status可以查看运行状态

当修改data-config.xml 文件配置时运行http://localhost:8080/solr/dataimport?command=reload-config可以进行重新加载配置文件

如果想终止运行http://localhost:8080/solr/dataimport?command=abort