hvanhovell commented on code in PR #49111:
URL: https://github.com/apache/spark/pull/49111#discussion_r1940423815
##########
connector/connect/client/jvm/src/main/scala/org/apache/spark/sql/KeyValueGroupedDataset.scala:
##########
@@ -588,16 +681,24 @@ private object KeyValueGroupedDatasetImpl {
val dummyGroupingFunc = SparkUserDefinedFunction(
function = UdfUtils.noOp[V, K](),
inputEncoders = vEncoder :: Nil,
- outputEncoder = kEncoder).apply(col("*"))
+ outputEncoder = kEncoder).withName(DUMMY_UDF_NAME).apply(col("*"))
val session = df.sparkSession
new KeyValueGroupedDatasetImpl(
session,
df.plan,
kEncoder,
vEncoder,
vEncoder,
- (Seq(dummyGroupingFunc) ++ groupingExprs).map(toExpr).asJava,
+ Seq(dummyGroupingFunc) ++ groupingExprs,
None,
() => df.select(groupingExprs: _*).as(kEncoder))
}
+
+ val DUMMY_UDF_NAME = "__spark__connect__internal__dummy__"
Review Comment:
You can also check the instance. There is nothing mutable in the current
UDF, so we might as well reuse it.
--
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]
