ulysses-you commented on code in PR #43435:
URL: https://github.com/apache/spark/pull/43435#discussion_r1368490194
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala:
##########
@@ -295,7 +295,7 @@ case class HashPartitioning(expressions: Seq[Expression],
numPartitions: Int)
}
}
- override def createShuffleSpec(distribution: ClusteredDistribution):
ShuffleSpec =
+ override def createShuffleSpec(distribution: ClusteredDistribution):
HashShuffleSpec =
Review Comment:
unnecessary change
##########
sql/core/src/test/scala/org/apache/spark/sql/DatasetSuite.scala:
##########
@@ -71,6 +71,19 @@ class DatasetSuite extends QueryTest
private implicit val ordering = Ordering.by((c: ClassData) => c.a -> c.b)
+ test("SPARK-45592: correctness issue") {
Review Comment:
please refine the suite name
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala:
##########
@@ -306,6 +306,34 @@ case class HashPartitioning(expressions: Seq[Expression],
numPartitions: Int)
override protected def withNewChildrenInternal(
newChildren: IndexedSeq[Expression]): HashPartitioning = copy(expressions
= newChildren)
+
+}
+
+case class CoalescedBoundary(startReducerIndex: Int, endReducerIndex: Int)
+
+/**
+ * Represents a partitioning where partitions have been coalesced from a
HashPartitioning into a
+ * fewer number of partitions.
+ */
+case class CoalescedHashPartitioning(from: HashPartitioning, partitions:
Seq[CoalescedBoundary])
Review Comment:
shall we add `@transient` for `partitions` ?
--
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]
