cloud-fan commented on code in PR #49144:
URL: https://github.com/apache/spark/pull/49144#discussion_r1905305472
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InsertMapSortExpression.scala:
##########
@@ -20,41 +20,35 @@ package org.apache.spark.sql.catalyst.optimizer
import scala.collection.mutable
import org.apache.spark.sql.catalyst.expressions.{Alias, ArrayTransform,
CreateNamedStruct, Expression, GetStructField, If, IsNull, LambdaFunction,
Literal, MapFromArrays, MapKeys, MapSort, MapValues, NamedExpression,
NamedLambdaVariable}
-import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan,
Project}
+import org.apache.spark.sql.catalyst.plans.logical.{Aggregate, LogicalPlan,
Project, RepartitionByExpression}
import org.apache.spark.sql.catalyst.rules.Rule
-import org.apache.spark.sql.catalyst.trees.TreePattern
+import org.apache.spark.sql.catalyst.trees.TreePattern.REPARTITION_OPERATION
import org.apache.spark.sql.types.{ArrayType, MapType, StructType}
import org.apache.spark.util.ArrayImplicits.SparkArrayOps
/**
- * Adds [[MapSort]] to group expressions containing map columns, as the
key/value pairs need to be
- * in the correct order before grouping:
+ * Adds [[MapSort]] to [[Aggregate]] expressions containing map columns,
+ * as the key/value pairs need to be in the correct order before grouping:
*
- * SELECT map_column, COUNT(*) FROM TABLE GROUP BY map_column =>
+ * SELECT map_column, COUNT(*) FROM TABLE GROUP BY map_column =>
* SELECT _groupingmapsort as map_column, COUNT(*) FROM (
* SELECT map_sort(map_column) as _groupingmapsort FROM TABLE
* ) GROUP BY _groupingmapsort
*/
object InsertMapSortInGroupingExpressions extends Rule[LogicalPlan] {
- private def shouldAddMapSort(expr: Expression): Boolean = {
- expr.dataType.existsRecursively(_.isInstanceOf[MapType])
- }
+ import InsertMapSortExpression._
override def apply(plan: LogicalPlan): LogicalPlan = {
- if (!plan.containsPattern(TreePattern.AGGREGATE)) {
Review Comment:
why do we remove it?
--
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]
