blob: 5286fc418f74fc53147ee2e37960bf03a0d7c858 [file] [log] [blame]
<dataConfig>
<dataSource type="BinFileDataSource"/>
<document>
<entity name="file" processor="FileListEntityProcessor" dataSource="null"
baseDir="${solr.install.dir}/example/exampledocs" fileName=".*pdf"
rootEntity="false">
<field column="file" name="id"/>
<entity name="pdf" processor="TikaEntityProcessor"
url="${file.fileAbsolutePath}" format="text">
<field column="Author" name="author" meta="true"/>
<!-- in the original PDF, the Author meta-field name is upper-cased,
but in Solr schema it is lower-cased
-->
<field column="title" name="title" meta="true"/>
<field column="dc:format" name="format" meta="true"/>
<field column="text" name="text"/>
</entity>
</entity>
</document>
</dataConfig>