how to index files over ftp , the FTP repo contain all my documents in different format, i am able to do this task for system folder but it doesn't work with ftp
i have this configuration via (DIH)
<dataConfig>
<dataSource type="BinFileDataSource" />
<dataSource type="BinURLDataSource" name="binSource" baseUrl="ftp://localhost:21/" onError="skip" user="solr_ftp" password="solr_ftp_pass" />
<document>
<!-- baseDir: path to the folder that containt the files (pdf | doc | docx | ...) -->
<entity name="files" dataSource="binSource" baseDir="ftp://localhost" rootEntity="false" processor="FileListEntityProcessor" fileName=".*\.(doc)|(pdf)|(docx)|(txt)|(rtf)|(html)|(htm)" onError="skip" recursive="true">
<field column="fileAbsolutePath" name="filePath" />
<field column="resourceName" name="resourceName" />
<field column="fileSize" name="size" />
<field column="fileLastModified" name="lastModified" />
<!-- tika -->
<entity name="documentImport" processor="TikaEntityProcessor" url="${files.fileAbsolutePath}" format="text">
<field column="title" name="title" meta="true"/>
<field column="subject" name="subject" meta="true"/>
<field column="description" name="description" meta="true"/>
<field column="comments" name="comments" meta="true"/>
<field column="Author" name="author" meta="true"/>
<field column="Keywords" name="keywords" meta="true"/>
<field column="category" name="category" meta="true"/>
<field column="xmpTPg:NPages" name="Page-Count" meta="true"/>
<field column="text" name="content"/>
</entity>
</entity>
</document>
</dataConfig>
Error:
failed:java.lang.RuntimeException: java.lang.RuntimeException: org.apache.solr.handler.dataimport.DataImportHandlerException: 'baseDir' value: ftp://localhost is not a directory Processing Document # 1