<?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 Parse_Syntax_Error Help in Data Engineering</title>
    <link>https://community.databricks.com/t5/data-engineering/parse-syntax-error-help/m-p/62183#M31918</link>
    <description>&lt;P&gt;i'm getting this error: Exception in thread "main" org.apache.spark.sql.catalyst.parser.ParseException: [PARSE_SYNTAX_ERROR] Syntax error at or near ','.(line 1, pos 18) == SQL == sum(mp4) AS Videos, sum(csv+xlsx) AS Sheets, sum(docx+txt+pdf) AS Documents, sum(zip+html+pptx) AS Others, sum(gif+jgp+png) AS Images ------------------^^^&lt;BR /&gt;for my code in scala:&lt;/P&gt;&lt;DIV&gt;&lt;PRE&gt;&lt;SPAN&gt;// Define field mappings and aggregations&lt;BR /&gt;&lt;/SPAN&gt;    &lt;SPAN&gt;val &lt;/SPAN&gt;fieldMappings = &lt;SPAN&gt;Map&lt;/SPAN&gt;(&lt;BR /&gt;      &lt;SPAN&gt;"Documents" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"docx"&lt;/SPAN&gt;, &lt;SPAN&gt;"txt"&lt;/SPAN&gt;, &lt;SPAN&gt;"pdf"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Sheets" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"csv"&lt;/SPAN&gt;, &lt;SPAN&gt;"xlsx"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Images" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"gif"&lt;/SPAN&gt;, &lt;SPAN&gt;"jgp"&lt;/SPAN&gt;, &lt;SPAN&gt;"png"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Videos" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"mp4"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Others" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"zip"&lt;/SPAN&gt;, &lt;SPAN&gt;"html"&lt;/SPAN&gt;, &lt;SPAN&gt;"pptx"&lt;/SPAN&gt;)&lt;BR /&gt;    )&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;//    // Define aggregation pipeline&lt;BR /&gt;&lt;/SPAN&gt;    &lt;SPAN&gt;val &lt;/SPAN&gt;aggregatedDF = inputDF.&lt;SPAN&gt;groupBy&lt;/SPAN&gt;(&lt;SPAN&gt;"u_id"&lt;/SPAN&gt;).&lt;SPAN&gt;agg&lt;/SPAN&gt;(&lt;BR /&gt;      &lt;SPAN&gt;expr&lt;/SPAN&gt;(&lt;BR /&gt;        fieldMappings.&lt;SPAN&gt;map &lt;/SPAN&gt;{ &lt;SPAN&gt;case &lt;/SPAN&gt;(category, fields) =&amp;gt;&lt;BR /&gt;          &lt;SPAN&gt;sum&lt;/SPAN&gt;(fields.&lt;SPAN&gt;mkString&lt;/SPAN&gt;(&lt;SPAN&gt;"+"&lt;/SPAN&gt;)).&lt;SPAN&gt;alias&lt;/SPAN&gt;(category)&lt;BR /&gt;        }.&lt;SPAN&gt;mkString&lt;/SPAN&gt;(&lt;SPAN&gt;", "&lt;/SPAN&gt;)&lt;BR /&gt;      )&lt;BR /&gt;    )&lt;/PRE&gt;&lt;/DIV&gt;</description>
    <pubDate>Wed, 28 Feb 2024 09:19:05 GMT</pubDate>
    <dc:creator>deltax_07</dc:creator>
    <dc:date>2024-02-28T09:19:05Z</dc:date>
    <item>
      <title>Parse_Syntax_Error Help</title>
      <link>https://community.databricks.com/t5/data-engineering/parse-syntax-error-help/m-p/62183#M31918</link>
      <description>&lt;P&gt;i'm getting this error: Exception in thread "main" org.apache.spark.sql.catalyst.parser.ParseException: [PARSE_SYNTAX_ERROR] Syntax error at or near ','.(line 1, pos 18) == SQL == sum(mp4) AS Videos, sum(csv+xlsx) AS Sheets, sum(docx+txt+pdf) AS Documents, sum(zip+html+pptx) AS Others, sum(gif+jgp+png) AS Images ------------------^^^&lt;BR /&gt;for my code in scala:&lt;/P&gt;&lt;DIV&gt;&lt;PRE&gt;&lt;SPAN&gt;// Define field mappings and aggregations&lt;BR /&gt;&lt;/SPAN&gt;    &lt;SPAN&gt;val &lt;/SPAN&gt;fieldMappings = &lt;SPAN&gt;Map&lt;/SPAN&gt;(&lt;BR /&gt;      &lt;SPAN&gt;"Documents" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"docx"&lt;/SPAN&gt;, &lt;SPAN&gt;"txt"&lt;/SPAN&gt;, &lt;SPAN&gt;"pdf"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Sheets" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"csv"&lt;/SPAN&gt;, &lt;SPAN&gt;"xlsx"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Images" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"gif"&lt;/SPAN&gt;, &lt;SPAN&gt;"jgp"&lt;/SPAN&gt;, &lt;SPAN&gt;"png"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Videos" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"mp4"&lt;/SPAN&gt;),&lt;BR /&gt;      &lt;SPAN&gt;"Others" &lt;/SPAN&gt;&lt;SPAN&gt;-&amp;gt; &lt;/SPAN&gt;&lt;SPAN&gt;Seq&lt;/SPAN&gt;(&lt;SPAN&gt;"zip"&lt;/SPAN&gt;, &lt;SPAN&gt;"html"&lt;/SPAN&gt;, &lt;SPAN&gt;"pptx"&lt;/SPAN&gt;)&lt;BR /&gt;    )&lt;BR /&gt;&lt;BR /&gt;&lt;SPAN&gt;//    // Define aggregation pipeline&lt;BR /&gt;&lt;/SPAN&gt;    &lt;SPAN&gt;val &lt;/SPAN&gt;aggregatedDF = inputDF.&lt;SPAN&gt;groupBy&lt;/SPAN&gt;(&lt;SPAN&gt;"u_id"&lt;/SPAN&gt;).&lt;SPAN&gt;agg&lt;/SPAN&gt;(&lt;BR /&gt;      &lt;SPAN&gt;expr&lt;/SPAN&gt;(&lt;BR /&gt;        fieldMappings.&lt;SPAN&gt;map &lt;/SPAN&gt;{ &lt;SPAN&gt;case &lt;/SPAN&gt;(category, fields) =&amp;gt;&lt;BR /&gt;          &lt;SPAN&gt;sum&lt;/SPAN&gt;(fields.&lt;SPAN&gt;mkString&lt;/SPAN&gt;(&lt;SPAN&gt;"+"&lt;/SPAN&gt;)).&lt;SPAN&gt;alias&lt;/SPAN&gt;(category)&lt;BR /&gt;        }.&lt;SPAN&gt;mkString&lt;/SPAN&gt;(&lt;SPAN&gt;", "&lt;/SPAN&gt;)&lt;BR /&gt;      )&lt;BR /&gt;    )&lt;/PRE&gt;&lt;/DIV&gt;</description>
      <pubDate>Wed, 28 Feb 2024 09:19:05 GMT</pubDate>
      <guid>https://community.databricks.com/t5/data-engineering/parse-syntax-error-help/m-p/62183#M31918</guid>
      <dc:creator>deltax_07</dc:creator>
      <dc:date>2024-02-28T09:19:05Z</dc:date>
    </item>
  </channel>
</rss>

