maropu commented on a change in pull request #28830:
URL: https://github.com/apache/spark/pull/28830#discussion_r439907906
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
##########
@@ -2541,7 +2542,20 @@ class Dataset[T] private[sql](
def dropDuplicates(colNames: Seq[String]): Dataset[T] = withTypedPlan {
val resolver = sparkSession.sessionState.analyzer.resolver
val allColumns = queryExecution.analyzed.output
- val groupCols = colNames.distinct.flatMap { (colName: String) =>
+ // SPARK-31990: We must preserve the input order of `colNames` because of
the compatibility
+ // issue (the Streaming's state store depends on the `groupCols` order).
+ val orderPreservingDistinctColNames = {
+ val nameSeen = mutable.Set[String]()
Review comment:
Ah, I see. Yea, I'll update the code based on `toSeq.toSeq`.
##########
File path: sql/core/src/main/scala/org/apache/spark/sql/Dataset.scala
##########
@@ -2541,7 +2542,20 @@ class Dataset[T] private[sql](
def dropDuplicates(colNames: Seq[String]): Dataset[T] = withTypedPlan {
val resolver = sparkSession.sessionState.analyzer.resolver
val allColumns = queryExecution.analyzed.output
- val groupCols = colNames.distinct.flatMap { (colName: String) =>
+ // SPARK-31990: We must preserve the input order of `colNames` because of
the compatibility
+ // issue (the Streaming's state store depends on the `groupCols` order).
+ val orderPreservingDistinctColNames = {
+ val nameSeen = mutable.Set[String]()
Review comment:
Ah, I see. Yea, I'll update the code based on `toSet.toSeq`.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
