Github user aray commented on a diff in the pull request:
https://github.com/apache/spark/pull/19080#discussion_r136419947
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala
---
@@ -284,24 +241,17 @@ case class RangePartitioning(ordering:
Seq[SortOrder], numPartitions: Int)
override def nullable: Boolean = false
override def dataType: DataType = IntegerType
- override def satisfies(required: Distribution): Boolean = required match
{
- case UnspecifiedDistribution => true
- case OrderedDistribution(requiredOrdering) =>
- val minSize = Seq(requiredOrdering.size, ordering.size).min
- requiredOrdering.take(minSize) == ordering.take(minSize)
- case ClusteredDistribution(requiredClustering) =>
- ordering.map(_.child).forall(x =>
requiredClustering.exists(_.semanticEquals(x)))
- case _ => false
- }
-
- override def compatibleWith(other: Partitioning): Boolean = other match {
- case o: RangePartitioning => this.semanticEquals(o)
- case _ => false
- }
-
- override def guarantees(other: Partitioning): Boolean = other match {
- case o: RangePartitioning => this.semanticEquals(o)
- case _ => false
+ override def satisfies(required: Distribution): Boolean = {
+ super.satisfies(required) || {
+ required match {
+ case OrderedDistribution(requiredOrdering) =>
+ val minSize = Seq(requiredOrdering.size, ordering.size).min
+ requiredOrdering.take(minSize) == ordering.take(minSize)
--- End diff --
While we are cleaning things up, this needs fixed.
`RangePartitioning(a+,b+)` does not satisfy `OrderedDistribution(a+)`. It
violates the requirement that all values of `a` need to be in the same
partition.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
