review comments

sunchao · Aug 7, 2023 · 0d44668 · 0d44668
1 parent 28d16df
commit 0d44668
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/physical/partitioning.scala
@@ -313,7 +313,7 @@ case class HashPartitioning(expressions: Seq[Expression], numPartitions: Int)
  * by `expressions`. `partitionValues`, if defined, should contain value of partition key(s) in
  * ascending order, after evaluated by the transforms in `expressions`, for each input partition.
  * In addition, its length must be the same as the number of input partitions (and thus is a 1-1
- * mapping), and each row in `partitionValues` must be unique.
+ * mapping). The `partitionValues` may contain duplicated partition values.
  *
  * For example, if `expressions` is `[years(ts_col)]`, then a valid value of `partitionValues` is
  * `[0, 1, 2]`, which represents 3 input partitions with distinct partition values. All rows
@@ -356,7 +356,7 @@ case class KeyGroupedPartitioning(
   override def createShuffleSpec(distribution: ClusteredDistribution): ShuffleSpec =
     KeyGroupedShuffleSpec(this, distribution)
 
-  def uniquePartitionValues: Seq[InternalRow] = {
+  lazy val uniquePartitionValues: Seq[InternalRow] = {
     partitionValues
         .map(InternalRowComparableWrapper(_, expressions))
         .distinct