Apache Solr Content Extraction Library integrates Apache Tika content extraction framework into Solr
'org.apache.solr:solr-cell:4.7.1'
<dependency>
<groupId>org.apache.solr</groupId>
<artifactId>solr-cell</artifactId>
<version>4.7.1</version>
</dependency>
<dependency org="org.apache.solr" name="solr-cell" rev="4.7.1"/>
"org.apache.solr", "solr-cell", "4.7.1"