I'm trying to index certain data from a table and documents located on disk
using jdbc and tika. I can derive the file locations from the table and
using that data I want to also import documents into Solr. However I'm
having trouble with my configuration.

<dataConfig>
<dataSource type="JdbcDataSource"
        name="db"
    jndiName="java:comp/env/jdbc/BuildDB"
  />
  
  <dataSource name="data" type="BinURLDataSource" />
  <dataSource  name="dataUrl" type="BinURLDataSource"/>
  <document>
    <entity
      name="productDocument"
      onError="skip"
      datsource="db"
      query="SELECT pa.prdAttachmentID id, pa.productId, pa.manufacturer,
pa.fileName, pa.attachmentType, pa.displayName,
                lower('/mnt/shares/nasdev/mediabase/specifications/' + 
pa.manufacturer +
'/' + CAST(pm.productid_manufacturer_id AS VARCHAR(50))) basePath,
pa.fileName
                FROM mmc.dbo.product_attachments pa WITH (NOLOCK) 
                        INNER JOIN mmc.dbo.productid_manufacturer pm WITH 
(NOLOCK) ON
pa.productId = pm.productid and pa.manufacturer = pm.manufacturer
                WHERE pa.productid = '3551LF'"
    >
      <field column="id" name="id"/>
      <field column="productCompositeid" name="productCompositeid"/>
      <field column="productid" name="productid"/>
      <field column="manufacturer" name="manufacturer"/>
      <field column="filename" name="filename"/>
      <field column="displayname" name="displayname"/>
      <field column="attachmentType" type="text" indexed="true"
stored="true" />

      <entity name="f" processor="FileListEntityProcessor"
baseDir="${productDocument.basePath}" fileName="${productDocument.filename}"
dataSource="data" onError="skip">
              
              <entity name="extract" processor="TikaEntityProcessor"
url="${f.fileAbsolutePath}" >
                  <field column="title" meta="true" name="author"/>
                  <field column="text" name="text"/>
              </entity>
          </entity>
    </entity>
  </document>
</dataConfig>


The error is as follows:
32367126 [Thread-1180] ERROR org.apache.solr.handler.dataimport.DocBuilder 
? Exception while processing: productDocument document :
SolrInputDocument(fields: [id=395623, manufacturer=Delta,
filename=delta_3551lf_parts_1027.pdf, displayname=Parts Breakdown,
attachmentType=ExplodedParts,
productid=3551LF]):org.apache.solr.handler.dataimport.DataImportHandlerException:
Unable to execute query:
/mnt/shares/nasdev/mediabase/specifications/delta/181075/delta_3551lf_spec_1027.pdf
Processing Document # 1
        at
org.apache.solr.handler.dataimport.DataImportHandlerException.wrapAndThrow(DataImportHandlerException.java:71)
        at
org.apache.solr.handler.dataimport.JdbcDataSource$ResultSetIterator.<init>(JdbcDataSource.java:281)
        at
org.apache.solr.handler.dataimport.JdbcDataSource.getData(JdbcDataSource.java:238)
        at
org.apache.solr.handler.dataimport.JdbcDataSource.getData(JdbcDataSource.java:42)
        at
org.apache.solr.handler.dataimport.TikaEntityProcessor.nextRow(TikaEntityProcessor.java:112)
        at
org.apache.solr.handler.dataimport.EntityProcessorWrapper.nextRow(EntityProcessorWrapper.java:243)
        at
org.apache.solr.handler.dataimport.DocBuilder.buildDocument(DocBuilder.java:477)
        at
org.apache.solr.handler.dataimport.DocBuilder.buildDocument(DocBuilder.java:503)
        at
org.apache.solr.handler.dataimport.DocBuilder.buildDocument(DocBuilder.java:503)
        at
org.apache.solr.handler.dataimport.DocBuilder.buildDocument(DocBuilder.java:416)
        at
org.apache.solr.handler.dataimport.DocBuilder.doFullDump(DocBuilder.java:331)
        at
org.apache.solr.handler.dataimport.DocBuilder.execute(DocBuilder.java:239)
        at
org.apache.solr.handler.dataimport.DataImporter.doFullImport(DataImporter.java:411)
        at
org.apache.solr.handler.dataimport.DataImporter.runCmd(DataImporter.java:483)
        at
org.apache.solr.handler.dataimport.DataImporter$1.run(DataImporter.java:464)
Caused by: com.microsoft.sqlserver.jdbc.SQLServerException: Incorrect syntax
near '/'.
        at
com.microsoft.sqlserver.jdbc.SQLServerException.makeFromDatabaseError(SQLServerException.java:216)
        at
com.microsoft.sqlserver.jdbc.SQLServerStatement.getNextResult(SQLServerStatement.java:1515)
        at
com.microsoft.sqlserver.jdbc.SQLServerStatement.doExecuteStatement(SQLServerStatement.java:792)
        at
com.microsoft.sqlserver.jdbc.SQLServerStatement$StmtExecCmd.doExecute(SQLServerStatement.java:689)
        at com.microsoft.sqlserver.jdbc.TDSCommand.execute(IOBuffer.java:5696)
        at
com.microsoft.sqlserver.jdbc.SQLServerConnection.executeCommand(SQLServerConnection.java:1715)
        at
com.microsoft.sqlserver.jdbc.SQLServerStatement.executeCommand(SQLServerStatement.java:180)
        at
com.microsoft.sqlserver.jdbc.SQLServerStatement.executeStatement(SQLServerStatement.java:155)
        at
com.microsoft.sqlserver.jdbc.SQLServerStatement.execute(SQLServerStatement.java:662)
        at
org.apache.tomcat.dbcp.dbcp.DelegatingStatement.execute(DelegatingStatement.java:264)
        at
org.apache.tomcat.dbcp.dbcp.DelegatingStatement.execute(DelegatingStatement.java:264)
        at
org.apache.solr.handler.dataimport.JdbcDataSource$ResultSetIterator.<init>(JdbcDataSource.java:274)
        ... 13 more



--
View this message in context: 
http://lucene.472066.n3.nabble.com/Solr-DIH-using-JDBC-with-TIKA-tp4180737.html
Sent from the Solr - User mailing list archive at Nabble.com.

Reply via email to