Hi Gora, thank you for your reply.  I am not using any commands, I just go on
the Solr dashboard, db > Dataimport and execute a full-import.

*My schema.xml looks like this:*

<field name="id" type="string" indexed="true" stored="true" required="true"
multiValued="false" /> 
   <field name="sku" type="textTight" indexed="true" stored="true"
omitNorms="true"/>
   <field name="name" type="text" indexed="true" stored="true"/>
   <field name="nameSort" type="string" indexed="true" stored="false"/>
   <field name="alphaNameSort" type="alphaOnlySort" indexed="true"
stored="false"/>
   <field name="manu" type="text" indexed="true" stored="true"
omitNorms="true"/>
   <field name="cat" type="text_ws" indexed="true" stored="true"
multiValued="true" omitNorms="true" termVectors="true" />
   <field name="features" type="text" indexed="true" stored="true"
multiValued="true"/>
   <field name="includes" type="text" indexed="true" stored="true"/>
   <field name="weight" type="sfloat" indexed="true" stored="true"/>
   <field name="price"  type="sfloat" indexed="true" stored="true"/>
   <field name="fileDir" type="text" indexed="true" stored="true" />
        <field name="file" type="text" indexed="true" stored="true" />
    <field name="initials" type="string" indexed="true" stored="true" />
   <field name="company" type="text" indexed="true" stored="true" />
   <field name="file_size" type="long" indexed="true" stored="true" />
  
   
   
   
   <field name="title" type="text" indexed="true" stored="true"
multiValued="true"/>
   <field name="subject" type="text_ws" indexed="true" stored="true"/>
   <field name="description" type="text_ws" indexed="true" stored="true" />
   <field name="comments" type="text_ws" indexed="true" stored="true"/>
    <field name="resour" type="text_ws" indexed="true" stored="true"/>
        <field name="creator" type="text_ws" indexed="true" stored="true"/>
   <field name="keywords" type="text_ws" indexed="true" stored="true"/>
   <field name="category" type="text_ws" indexed="true" stored="true"/>
   <field name="resourcename" type="text_ws" indexed="true" stored="true"/>
   <field name="url" type="text_ws" indexed="true" stored="true"/>
   <field name="content_type" type="string" indexed="true" stored="true"
multiValued="true"/>
   <field name="last_modified" type="date" indexed="true" stored="true"/>
   <field name="creation_date" type="date" indexed="true" stored="true"/>
   <field name="links" type="string" indexed="true" stored="true"
multiValued="true"/>  
   <field name="author" type="string" indexed="true" stored="true" />
   <field name="fileName" type="string" indexed="true" stored="true" />
   <field name="type" type="string" indexed="true" stored="true"
multiValued="true" />
   <field name="mime" type="string" indexed="true" stored="true" />
  <field name="summary" type="text_ws" indexed="true" stored="true" />
   <field name="date_published" type="string" indexed="true" stored="true"
multiValued="false"/>


<dynamicField name="*_i"  type="sint"    indexed="true"  stored="true"/>
   <dynamicField name="*_s"  type="string"  indexed="true"  stored="true"/>
   <dynamicField name="*_l"  type="slong"   indexed="true"  stored="true"/>
   <dynamicField name="*_t"  type="text"    indexed="true"  stored="true"/>
   <dynamicField name="*_b"  type="boolean" indexed="true"  stored="true"/>
   <dynamicField name="*_f"  type="sfloat"  indexed="true"  stored="true"/>
   <dynamicField name="*_d"  type="sdouble" indexed="true"  stored="true"/>
   <dynamicField name="*_dt" type="date"    indexed="true"  stored="true"/>
<dynamicField name="metadata_*" type="text" indexed="true" stored="true"
multiValued="false"/>
   <dynamicField name="random*" type="random" />
<dynamicField name="attr_*" type="text_general" indexed="true" stored="true"
multiValued="false"/>
    
  * <dynamicField name="*" type="text_general" multiValued="true" />*

*My db-data-config.xml looks like this:*

<dataConfig>
        <dataSource type="JdbcDataSource" driver="com.mysql.jdbc.Driver"
                     url="jdbc:mysql://localhost:3306/opspedia" 
                     user="username" batchSize="-1" name="mysql" />
        <dataSource type="BinURLDataSource" name="bin"/>
        
        <document>
                
                <entity onError="skip" name="fileSourcePaths" rootEntity="true"
dataSource="mysql" query="select ID, urlpath from myposts"
                deltaImportQuery="SELECT * FROM myposts WHERE id =
'${dataimporter.delta.id}'"
                  deltaQuery="SELECT id FROM myposts WHERE last_modified >
'${dataimporter.last_index_time}'">
                  
                        <entity name="tika-test" 
processor="TikaEntityProcessor" fileName=".*"
recursive="true" url="${fileSourcePaths.guid}" format="text"
dataSource="bin" >
                <field column="ID" name="id" />
                                <field column="Author" name="author" 
meta="true"/>
                                <field column="Creation-Date" 
name="date_published" meta="true"/>
                                <field column="modified" name="last_modified" 
meta="true" />
                                <field column="title" name="title" meta="true" 
/>
                                <field column="file_size" name="file_size" 
meta="true" />
</entity>                               
                </entity>
        </document>
</dataConfig>

*In my solrconfig.xml I have this:*

<requestHandler name="/dataimport"
class="org.apache.solr.handler.dataimport.DataImportHandler">
    <lst name="defaults">
        <str name="config">db-data-config.xml</str>
    </lst>
  </requestHandler>
  
   <requestHandler name="/update/extract" 
                  startup="lazy"
                  class="solr.extraction.ExtractingRequestHandler" >
    <lst name="defaults">
      <str name="lowernames">true</str>
      <str name="uprefix">metadata_</str>
                <str name="map.Last-Modified">last_modified</str>
                <str name="fmap.content">text</str>
                <str name="fmap.Size">size</str>
                <str name="fmap.Initials">initials</str>
                <str name="fmap.application-name">name</str>
                <str name="fmap.Subject">subject</str>
                <str name="Company">company</str>
                <str name="fmap.Title">title</str>
                <str name="fmap.Comments">comments</str>
                <str name="Words">words</str>
                <str name="Last-Modified-By">last_modified_by</str>
                 <str name="captureAttr">true</str>
    </lst>
  </requestHandler>

Thank you for your help!




--
View this message in context: 
http://lucene.472066.n3.nabble.com/Solr-indexing-binary-files-tp4047470p4047702.html
Sent from the Solr - User mailing list archive at Nabble.com.

Reply via email to