icexelloss commented on a change in pull request #22305:
[SPARK-24561][SQL][Python] User-defined window aggregation functions with
Pandas UDF (bounded window)
URL: https://github.com/apache/spark/pull/22305#discussion_r240688367
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/python/WindowInPandasExec.scala
##########
@@ -73,68 +138,141 @@ case class WindowInPandasExec(
}
/**
- * Create the resulting projection.
- *
- * This method uses Code Generation. It can only be used on the executor
side.
- *
- * @param expressions unbound ordered function expressions.
- * @return the final resulting projection.
+ * See [[WindowBoundHelpers]] for details.
*/
- private[this] def createResultProjection(expressions: Seq[Expression]):
UnsafeProjection = {
- val references = expressions.zipWithIndex.map { case (e, i) =>
- // Results of window expressions will be on the right side of child's
output
- BoundReference(child.output.size + i, e.dataType, e.nullable)
+ private def computeWindowBoundHelpers(
+ factories: Seq[InternalRow => WindowFunctionFrame]
+ ): WindowBoundHelpers = {
+ val dummyRow = new SpecificInternalRow()
Review comment:
Ha neat trick.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
