Hey ,
I am using solr as my search engine to search my pdf files. I have 18219 
files(different file names) and all the files are in one same directory。But 
when I use solr to import the files into index using Dataimport method, solr 
report only import 17233 files. It's very strange. This problem has stoped out 
project for a few days. I can't handle it.


 please help me!


Schema.xml


<fields>
   <field name="text" type="text" indexed="true" multiValued="true" 
termVectors="true" termPositions="true" termOffsets="true"/>
   <field name="filename" type="filenametext" indexed="true" required="true" 
termVectors="true" termPositions="true" termOffsets="true"/>
   <field name="id" type="string" stored="true"/> 
 </fields>
 <uniqueKey>id</uniqueKey> 
 <copyField source="filename" dest="text"/>


and 
<dataConfig> 
    <dataSource type="BinFileDataSource" name="bin"/> 
 <document> 
<entity name="f" processor="FileListEntityProcessor" recursive="true" 
rootEntity="false" 
 dataSource="null"  baseDir="H:/pdf/cls_1_16800_OCRed/1" 
fileName=".*\.(PDF)|(pdf)|(Pdf)|(pDf)|(pdF)|(PDf)|(PdF)|(pDF)" onError="skip"> 


<entity name="tika-test" processor="TikaEntityProcessor" 
url="${f.fileAbsolutePath}" format="text" dataSource="bin" onError="skip">
                <field column="text" name="text"/>      
</entity> 
 <field column="file" name="id"/>
 <field column="file" name="filename"/> 
</entity> 
    </document> 
</dataConfig> 




sincerecly
Rong Kang



Reply via email to