<?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>topic Re: Json without duplicates in Getting Data In</title>
    <link>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383126#M69013</link>
    <description>&lt;P&gt;But there is no method that at the time of indexing look at two fields of the json and make a hash or something so that these duplicates do not exist&lt;/P&gt;</description>
    <pubDate>Fri, 15 Feb 2019 07:04:29 GMT</pubDate>
    <dc:creator>Dherom</dc:creator>
    <dc:date>2019-02-15T07:04:29Z</dc:date>
    <item>
      <title>Json without duplicates</title>
      <link>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383123#M69010</link>
      <description>&lt;P&gt;Good afternoon guys,&lt;/P&gt;

&lt;P&gt;We need help.&lt;/P&gt;

&lt;P&gt;We have a JSON file in which duplicate events are written.&lt;/P&gt;

&lt;P&gt;We want to know how to have a primary key so that it does not index those duplicates and is not in the Splunk index.&lt;/P&gt;

&lt;P&gt;{&lt;BR /&gt;
    "security": {&lt;BR /&gt;
        "notices": [&lt;BR /&gt;
            {&lt;BR /&gt;
                "rss_published": "2019-02-12T13:33:31.000Z",&lt;BR /&gt;
                "rss_message": "Email provider VFEmail has suffered what the company is calling \"catastrophic destruction\" at the hands of an as-yet unknown intruder who trashed all of the company's primary and backup data in the United States. The firm's founder says he ....",&lt;BR /&gt;
                "rss_fuente": "rss_krebsonsecurity",&lt;BR /&gt;
                "rss_title": "Email Provider VFEmail Suffers \u2018Catastrophic\u2019 Hack",&lt;BR /&gt;
                "rss_link": "&lt;A href="https://krebsonsecurity.com/2019/02/email-provider-vfemail-suffers-catastrophic-hack/" target="_blank"&gt;https://krebsonsecurity.com/2019/02/email-provider-vfemail-suffers-catastrophic-hack/&lt;/A&gt;"&lt;BR /&gt;
            }&lt;BR /&gt;
        ]&lt;BR /&gt;
    }&lt;BR /&gt;
}&lt;BR /&gt;
{&lt;BR /&gt;
    "security": {&lt;BR /&gt;
        "notices": [&lt;BR /&gt;
            {&lt;BR /&gt;
                "rss_published": "2019-02-12T13:33:31.000Z",&lt;BR /&gt;
                "rss_message": "Email provider VFEmail has suffered what the company is calling \"catastrophic destruction\" at the hands of an as-yet unknown intruder who trashed all of the company's primary and backup data in the United States. The firm's founder says he ....",&lt;BR /&gt;
                "rss_fuente": "rss_krebsonsecurity",&lt;BR /&gt;
                "rss_title": "Email Provider VFEmail Suffers \u2018Catastrophic\u2019 Hack",&lt;BR /&gt;
                "rss_link": "&lt;A href="https://krebsonsecurity.com/2019/02/email-provider-vfemail-suffers-catastrophic-hack/" target="_blank"&gt;https://krebsonsecurity.com/2019/02/email-provider-vfemail-suffers-catastrophic-hack/&lt;/A&gt;"&lt;BR /&gt;
            }&lt;BR /&gt;
        ]&lt;BR /&gt;
    }&lt;BR /&gt;
}&lt;BR /&gt;
{&lt;BR /&gt;
    "security": {&lt;BR /&gt;
        "notices": [&lt;BR /&gt;
            {&lt;BR /&gt;
                "rss_published": "2019-02-12T11:33:54.000Z",&lt;BR /&gt;
                "rss_message": "El fallo afecta a otros productos derivados de Docker que usan runc y al propio LXC, permitiendo acceder a la m\u00e1quina host con permisos de superusuario. Los investigadores Adam Iwaniuk y Borys Pop\u0142awski han descubierto una vulnerabilidad en....",&lt;BR /&gt;
                "rss_fuente": "rss_hispasec",&lt;BR /&gt;
                "rss_title": "Vulnerabilidad en runc permite escapar de contenedor Docker con permisos root",&lt;BR /&gt;
                "rss_link": "&lt;A href="https://unaaldia.hispasec.com/2019/02/vulnerabilidad-en-runc-permite-escapar-de-contenedor-docker-con-permisos-root.html" target="_blank"&gt;https://unaaldia.hispasec.com/2019/02/vulnerabilidad-en-runc-permite-escapar-de-contenedor-docker-con-permisos-root.html&lt;/A&gt;"&lt;BR /&gt;
            }&lt;BR /&gt;
        ]&lt;BR /&gt;
    }&lt;BR /&gt;
}&lt;BR /&gt;
thank you!&lt;/P&gt;</description>
      <pubDate>Tue, 29 Sep 2020 23:14:23 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383123#M69010</guid>
      <dc:creator>Dherom</dc:creator>
      <dc:date>2020-09-29T23:14:23Z</dc:date>
    </item>
    <item>
      <title>Re: Json without duplicates</title>
      <link>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383124#M69011</link>
      <description>&lt;P&gt;I think you'd be better off doing this at the source rather than in Splunk. Is it possible to write a script to cleanse the data before it's written to a file that Splunk monitors?&lt;/P&gt;</description>
      <pubDate>Thu, 14 Feb 2019 22:09:08 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383124#M69011</guid>
      <dc:creator>jluo_splunk</dc:creator>
      <dc:date>2019-02-14T22:09:08Z</dc:date>
    </item>
    <item>
      <title>Re: Json without duplicates</title>
      <link>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383125#M69012</link>
      <description>&lt;P&gt;You can use Cribl to preprocess this... @clintsharp @dritan &lt;/P&gt;</description>
      <pubDate>Thu, 14 Feb 2019 23:11:58 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383125#M69012</guid>
      <dc:creator>woodcock</dc:creator>
      <dc:date>2019-02-14T23:11:58Z</dc:date>
    </item>
    <item>
      <title>Re: Json without duplicates</title>
      <link>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383126#M69013</link>
      <description>&lt;P&gt;But there is no method that at the time of indexing look at two fields of the json and make a hash or something so that these duplicates do not exist&lt;/P&gt;</description>
      <pubDate>Fri, 15 Feb 2019 07:04:29 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383126#M69013</guid>
      <dc:creator>Dherom</dc:creator>
      <dc:date>2019-02-15T07:04:29Z</dc:date>
    </item>
    <item>
      <title>Re: Json without duplicates</title>
      <link>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383127#M69014</link>
      <description>&lt;P&gt;There may be something possible using the DSP beta, but at this point in time, it would be much less efficient to do it inside of Splunk - you would potentially cause some amount of ingestion latency.&lt;/P&gt;</description>
      <pubDate>Fri, 15 Feb 2019 17:03:53 GMT</pubDate>
      <guid>https://community.splunk.com/t5/Getting-Data-In/Json-without-duplicates/m-p/383127#M69014</guid>
      <dc:creator>jluo_splunk</dc:creator>
      <dc:date>2019-02-15T17:03:53Z</dc:date>
    </item>
  </channel>
</rss>

