Apache Solr Content Extraction Library integrates Apache Tika content extraction framework into Solr
'org.apache.solr:solr-cell:3.6.1'
<dependency>
<groupId>org.apache.solr</groupId>
<artifactId>solr-cell</artifactId>
<version>3.6.1</version>
</dependency>
<dependency org="org.apache.solr" name="solr-cell" rev="3.6.1"/>
"org.apache.solr", "solr-cell", "3.6.1"