Github user wzhfy commented on a diff in the pull request:
https://github.com/apache/spark/pull/20560#discussion_r180390907
--- Diff:
sql/core/src/test/scala/org/apache/spark/sql/execution/PlannerSuite.scala ---
@@ -197,6 +198,19 @@ class PlannerSuite extends SharedSQLContext {
assert(planned.child.isInstanceOf[CollectLimitExec])
}
+ test("SPARK-23375: Cached sorted data doesn't need to be re-sorted") {
+ val query = testData.select('key, 'value).sort('key.desc).cache()
+
assert(query.queryExecution.optimizedPlan.isInstanceOf[InMemoryRelation])
+ val resorted = query.sort('key.desc)
+ assert(resorted.queryExecution.optimizedPlan.collect { case s: Sort =>
s}.isEmpty)
+ assert(resorted.select('key).collect().map(_.getInt(0)).toSeq ==
+ (1 to 100).sorted(Ordering[Int].reverse))
+ // with a different order, the sort is needed
+ val sortedAsc = query.sort('key)
+ assert(sortedAsc.queryExecution.optimizedPlan.collect { case s: Sort
=> s}.nonEmpty)
--- End diff --
`.nonEmpty` -> `.size == 1`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
