Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/23248#discussion_r239430315 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowEvalPythonExec.scala --- @@ -60,8 +60,12 @@ private class BatchIterator[T](iter: Iterator[T], batchSize: Int) /** * A logical plan that evaluates a [[PythonUDF]]. */ -case class ArrowEvalPython(udfs: Seq[PythonUDF], output: Seq[Attribute], child: LogicalPlan) - extends UnaryNode +case class ArrowEvalPython( + udfs: Seq[PythonUDF], + output: Seq[Attribute], + child: LogicalPlan) extends UnaryNode { + override def producedAttributes: AttributeSet = AttributeSet(output.drop(child.output.length)) --- End diff -- a different but related fix, to make the `missingAttributes` calculated correctly.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org