<?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: how to add source filename to cloudera search result? in Archives of Support Questions (Read Only)</title>
    <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/16716#M2525</link>
    <description>&lt;P&gt;I found the solution.&lt;/P&gt;&lt;P&gt;When morphline&amp;nbsp;process data from hdfs it&amp;nbsp;appends&amp;nbsp;additional fields for every record:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;file_download_url=[hdfs://MYHOST:2080/testdata/log],&lt;BR /&gt;file_group=[nobody],&lt;BR /&gt;file_host=[MYHOST],&lt;BR /&gt;file_last_modified=[1405102390179],&lt;BR /&gt;file_length=[198923],&lt;BR /&gt;file_name=[log.txt],&lt;BR /&gt;file_owner=[pmezentsev],&lt;BR /&gt;file_path=[/testdata/log/log.txt],&lt;BR /&gt;file_permissions_group=[r--],&lt;BR /&gt;file_permissions_other=[r--],&lt;BR /&gt;file_permissions_stickybit=[false],&lt;BR /&gt;file_permissions_user=[rw-],&lt;BR /&gt;file_port=[8020],&lt;BR /&gt;file_scheme=[hdfs],&lt;BR /&gt;file_upload_url=[hdfs://MYHOST/testdata/log/log.txt],&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;so if you want to get full filename into your index, just&amp;nbsp;file_path to your schema.xml&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp;&amp;lt;field name="file_path" type="string" indexed="true" stored="true" /&amp;gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Mon, 11 Aug 2014 15:35:08 GMT</pubDate>
    <dc:creator>pavel</dc:creator>
    <dc:date>2014-08-11T15:35:08Z</dc:date>
    <item>
      <title>how to add source filename to cloudera search result?</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/16686#M2524</link>
      <description>&lt;P&gt;Hello!&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I have a files with data, for example web servers logs.&lt;/P&gt;&lt;P&gt;/data/log/000001.txt&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;/data/log/000002.txt&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;/data/log/000003.txt&lt;/P&gt;&lt;P&gt;/data/log/000004.txt&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;I want to build full text search on them and get&amp;nbsp;filename in the&amp;nbsp;search result.&lt;/P&gt;&lt;P&gt;How I can do this?&lt;/P&gt;</description>
      <pubDate>Fri, 16 Sep 2022 09:04:38 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/16686#M2524</guid>
      <dc:creator>pavel</dc:creator>
      <dc:date>2022-09-16T09:04:38Z</dc:date>
    </item>
    <item>
      <title>Re: how to add source filename to cloudera search result?</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/16716#M2525</link>
      <description>&lt;P&gt;I found the solution.&lt;/P&gt;&lt;P&gt;When morphline&amp;nbsp;process data from hdfs it&amp;nbsp;appends&amp;nbsp;additional fields for every record:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;file_download_url=[hdfs://MYHOST:2080/testdata/log],&lt;BR /&gt;file_group=[nobody],&lt;BR /&gt;file_host=[MYHOST],&lt;BR /&gt;file_last_modified=[1405102390179],&lt;BR /&gt;file_length=[198923],&lt;BR /&gt;file_name=[log.txt],&lt;BR /&gt;file_owner=[pmezentsev],&lt;BR /&gt;file_path=[/testdata/log/log.txt],&lt;BR /&gt;file_permissions_group=[r--],&lt;BR /&gt;file_permissions_other=[r--],&lt;BR /&gt;file_permissions_stickybit=[false],&lt;BR /&gt;file_permissions_user=[rw-],&lt;BR /&gt;file_port=[8020],&lt;BR /&gt;file_scheme=[hdfs],&lt;BR /&gt;file_upload_url=[hdfs://MYHOST/testdata/log/log.txt],&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;so if you want to get full filename into your index, just&amp;nbsp;file_path to your schema.xml&lt;/P&gt;&lt;P&gt;&amp;nbsp; &amp;nbsp;&amp;lt;field name="file_path" type="string" indexed="true" stored="true" /&amp;gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 11 Aug 2014 15:35:08 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/16716#M2525</guid>
      <dc:creator>pavel</dc:creator>
      <dc:date>2014-08-11T15:35:08Z</dc:date>
    </item>
    <item>
      <title>Re: how to add source filename to cloudera search result?</title>
      <link>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/17292#M2526</link>
      <description>See &lt;A href="http://www.cloudera.com/content/cloudera-content/cloudera-docs/CDH5/latest/Search/Cloudera-Search-User-Guide/csug_metadata.html" target="_blank"&gt;http://www.cloudera.com/content/cloudera-content/cloudera-docs/CDH5/latest/Search/Cloudera-Search-User-Guide/csug_metadata.html&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;</description>
      <pubDate>Wed, 20 Aug 2014 18:20:56 GMT</pubDate>
      <guid>https://community.cloudera.com/t5/Archives-of-Support-Questions/how-to-add-source-filename-to-cloudera-search-result/m-p/17292#M2526</guid>
      <dc:creator>whosch</dc:creator>
      <dc:date>2014-08-20T18:20:56Z</dc:date>
    </item>
  </channel>
</rss>

