<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>question Re: Filter duplicate files in NifI in Support Questions</title>
    <link>https://community.cloudera.com/t5/Support-Questions/Filter-duplicate-files-in-NifI/m-p/305977#M222607</link>
    <description>&lt;P&gt;Hello,&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;You can use DetectDuplicate processor and only route non-duplicate to HDFS.&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;But using the GETSFTP processor should work fine as you configured it to run on primary node only. What errors were you facing back then ?&lt;/P&gt;</description>
    <pubDate>Fri, 13 Nov 2020 16:49:21 GMT</pubDate>
    <dc:creator>Kezia</dc:creator>
    <dc:date>2020-11-13T16:49:21Z</dc:date>
  </channel>
</rss>

