vladimirg-db commented on code in PR #57629:
URL: https://github.com/apache/spark/pull/57629#discussion_r3695723601
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InsertMapSortExpression.scala:
##########
@@ -42,8 +45,16 @@ object InsertMapSortInGroupingExpressions extends
Rule[LogicalPlan] {
if (!plan.containsPattern(AGGREGATE)) {
return plan
}
+ val normalizeDistinctAggregates =
+ conf.getConf(SQLConf.INSERT_MAP_SORT_IN_DISTINCT_AGGREGATES_ENABLED)
val shouldRewrite = plan.exists {
Review Comment:
Done
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InsertMapSortExpression.scala:
##########
@@ -17,18 +17,21 @@
package org.apache.spark.sql.catalyst.optimizer
+import scala.collection.immutable.VectorMap
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.expressions.{Alias, ArrayTransform,
Attribute, CreateNamedStruct, Expression, GetStructField, If, IsNull,
LambdaFunction, Literal, MapFromArrays, MapKeys, MapSort, MapValues,
NamedExpression, NamedLambdaVariable}
+import
org.apache.spark.sql.catalyst.expressions.aggregate.{AggregateExpression,
AggregateFunction}
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.{AGGREGATE,
REPARTITION_OPERATION}
+import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.types.{ArrayType, MapType, StructType}
import org.apache.spark.util.ArrayImplicits.SparkArrayOps
/**
- * Adds [[MapSort]] to [[Aggregate]] expressions containing map columns,
- * as the key/value pairs need to be in the correct order before grouping:
+ * Adds [[MapSort]] to grouping expressions and distinct aggregate arguments
that contain maps,
+ * ensuring key/value pairs have a consistent order before aggregation:
*
Review Comment:
Done
--
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]
