imback82 commented on a change in pull request #27842: [SPARK-31078][SQL]
Respect aliases in output ordering
URL: https://github.com/apache/spark/pull/27842#discussion_r390032035
##########
File path:
sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala
##########
@@ -975,6 +975,25 @@ class PlannerSuite extends SharedSparkSession with
AdaptiveSparkPlanHelper {
}
}
}
+
+ test("aliases in the sort aggregate expressions should not introduce extra
sort") {
+ withSQLConf(SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") {
+ withSQLConf(SQLConf.USE_OBJECT_HASH_AGG.key -> "false") {
+ val t1 = spark.range(10).selectExpr("floor(id/4) as k1")
+ val t2 = spark.range(20).selectExpr("floor(id/4) as k2")
+
+ val agg1 =
t1.groupBy("k1").agg(collect_list("k1")).withColumnRenamed("k1", "k3")
+ val agg2 = t2.groupBy("k2").agg(collect_list("k2"))
+
+ val planned = agg1.join(agg2, $"k3" ===
$"k2").queryExecution.executedPlan
+ assert(planned.collect { case s: SortAggregateExec => s }.nonEmpty)
+
+ // We expect two SortExec nodes on each side of join.
+ val sorts = planned.collect { case s: SortExec => s }
+ assert(sorts.size == 4)
Review comment:
FYI, this is 5 without the fix.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
