pan3793 commented on code in PR #52474:
URL: https://github.com/apache/spark/pull/52474#discussion_r2383868814
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatWriter.scala:
##########
@@ -153,10 +151,34 @@ object FileFormatWriter extends Logging {
case p: SparkPlan =>
p.withNewChildren(p.children.map(materializeAdaptiveSparkPlan))
}
+ val query =
writeFilesOpt.map(_.child).getOrElse(materializeAdaptiveSparkPlan(plan))
+
// the sort order doesn't matter
- val actualOrdering = writeFilesOpt.map(_.child)
- .getOrElse(materializeAdaptiveSparkPlan(plan))
- .outputOrdering
+ val actualOrdering = query.outputOrdering
+
+ val queryOutput = query match {
+ case o: OrderPreservingUnaryExecNode => o.outputExpressions
+ case _ => query.output
+ }
+
+ @tailrec
+ def isLiteral(e: Expression, name: String): Option[String] =
+ e match {
+ case Alias(child, n) => isLiteral(child, n)
+ case _: Literal => Some(name)
+ case _ => None
+ }
+
+ val literalColumns = queryOutput.flatMap { ne => isLiteral(ne, ne.name) }
+
+ // We should first sort by dynamic partition columns, then bucket id, and
finally sorting
+ // columns, then drop literal columns
Review Comment:
`SortOrder(Literal, ...)` is eliminated by `EliminateSorts`
--
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]
