huaxingao commented on a change in pull request #34445:
URL: https://github.com/apache/spark/pull/34445#discussion_r744174328
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/AggregatePushDownUtils.scala
##########
@@ -138,4 +141,19 @@ object AggregatePushDownUtils {
converter.convert(aggregatesAsRow, columnVectors.toArray)
new ColumnarBatch(columnVectors.asInstanceOf[Array[ColumnVector]], 1)
}
+
+ /**
+ * Return the schema for aggregates only (exclude group by columns)
+ */
+ def getSchemaWithoutGroupingExpression(
+ aggregation: Aggregation,
+ aggSchema: StructType): StructType = {
+ val groupByColNums = aggregation.groupByColumns.length
Review comment:
changed to `numOfGroupByColumns`
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/orc/OrcUtils.scala
##########
@@ -457,17 +457,22 @@ object OrcUtils extends Logging {
}
}
+ // if there are group by columns, we will build result row first,
+ // and then append group by columns values (partition columns values) to
the result row.
+ val schemaWithoutGroupby =
Review comment:
changed
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
