uros-b commented on code in PR #57629:
URL: https://github.com/apache/spark/pull/57629#discussion_r3700552628


##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InsertMapSortExpression.scala:
##########
@@ -17,33 +17,46 @@
 
 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:
  *
  * 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
+ *
+ * SELECT COUNT(DISTINCT map_column) FROM TABLE =>
+ * SELECT COUNT(DISTINCT _distinctmapsort) FROM (
+ *   SELECT map_sort(map_column) as _distinctmapsort FROM TABLE
+ * )
  */
-object InsertMapSortInGroupingExpressions extends Rule[LogicalPlan] {
+object InsertMapSortInAggregateExpressions extends Rule[LogicalPlan] {

Review Comment:
   Uber nit: aggregateExpressions conventionally refers to the whole select 
list of an Aggregate, whereas this rule touches grouping expressions and 
distinct arguments. InsertMapSortInAggregate would be marginally less 
ambiguous. WDYT?



-- 
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]

Reply via email to