grundprinzip commented on code in PR #39091:
URL: https://github.com/apache/spark/pull/39091#discussion_r1055281974
##########
connector/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala:
##########
@@ -372,6 +374,22 @@ class SparkConnectPlanner(session: SparkSession) {
}
}
+ private def transformCollectMetrics(rel: proto.CollectMetrics): LogicalPlan
= {
+ val metrics = rel.getMetricsList.asScala.toSeq.map { expr =>
+ Column(transformExpression(expr))
+ }
+
+ if (rel.getIsObservation) {
+ val observation = Observation(rel.getName)
+ Dataset
+ .ofRows(session, transformRelation(rel.getInput))
+ .observe(observation, metrics.head, metrics.tail: _*)
+ .logicalPlan
+ } else {
+ CollectMetrics(rel.getName, metrics.map(_.named),
transformRelation(rel.getInput))
Review Comment:
Can you please give me an example of where we're exposing the catalyst
operator directly in our API (in particular in the Dataset API)?
--
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]
