Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/21291#discussion_r188130563
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala ---
@@ -621,6 +621,25 @@ class PlannerSuite extends SharedSQLContext {
requiredOrdering = Seq(orderingA, orderingB),
shouldHaveSort = true)
}
+
+ test("SPARK-24242: RangeExec should have correct output ordering and
partitioning") {
+ val df = spark.range(10)
+ val rangeExec = df.queryExecution.executedPlan.collect {
+ case r: RangeExec => r
+ }
+ val range = df.queryExecution.optimizedPlan.collect {
+ case r: Range => r
+ }
+ assert(rangeExec.head.outputOrdering == range.head.outputOrdering)
+ assert(rangeExec.head.outputPartitioning ==
+ RangePartitioning(rangeExec.head.outputOrdering,
df.rdd.getNumPartitions))
+
+ val rangeInOnePartition = spark.range(1, 10, 1, 1)
+ val rangeExecInOnePartition =
rangeInOnePartition.queryExecution.executedPlan.collect {
+ case r: RangeExec => r
+ }
+ assert(rangeExecInOnePartition.head.outputPartitioning ==
SinglePartition)
--- End diff --
Ok.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
