jingz-db commented on code in PR #49488:
URL: https://github.com/apache/spark/pull/49488#discussion_r1950054020
##########
sql/connect/common/src/main/scala/org/apache/spark/sql/connect/KeyValueGroupedDataset.scala:
##########
@@ -526,6 +553,71 @@ private class KeyValueGroupedDatasetImpl[K, V, IK, IV](
}
}
+ override protected[sql] def transformWithStateHelper[U: Encoder, S: Encoder](
+ statefulProcessor: StatefulProcessor[K, V, U],
+ timeMode: TimeMode,
+ outputMode: OutputMode,
+ initialState: Option[sql.KeyValueGroupedDataset[K, S]] = None,
+ eventTimeColumnName: String = ""): Dataset[U] = {
+ val outputEncoder = agnosticEncoderFor[U]
+ val stateEncoder = agnosticEncoderFor[S]
+
+ val inputEncoders: Seq[AgnosticEncoder[_]] = Seq(kEncoder, stateEncoder,
ivEncoder)
+ val dummyGroupingFunc = SparkUserDefinedFunction(
+ function = UdfUtils.noOp[K, U](),
+ inputEncoders = inputEncoders,
+ outputEncoder = outputEncoder)
+ val udf = toExpr(
+ dummyGroupingFunc.apply(
+ inputEncoders.map(_ => col("*")):
_*)).getCommonInlineUserDefinedFunction
+
+ val initialStateImpl = if (initialState.isDefined) {
+ assert(initialState.get.isInstanceOf[KeyValueGroupedDatasetImpl[K, S, _,
_]])
+ initialState.get.asInstanceOf[KeyValueGroupedDatasetImpl[K, S, _, _]]
+ } else {
+ null
+ }
+
+ val statefulProcessorStr = if (!initialState.isDefined) {
+ ByteString.copyFrom(SparkSerDeUtils.serialize(statefulProcessor))
+ } else {
+ ByteString.copyFrom(
+ SparkSerDeUtils.serialize(
+ statefulProcessor.asInstanceOf[StatefulProcessorWithInitialState[K,
V, U, S]]))
+ }
+
+ val twsDataset = sparkSession.newDataset[U](outputEncoder) { builder =>
+ val twsBuilder = builder.getGroupMapBuilder
+ twsBuilder
+ .setInput(plan.getRoot)
+ .addAllGroupingExpressions(groupingExprs)
+ .setFunc(udf)
+ .setTransformWithStateInfo(
+ proto.TransformWithStateInfo
+ .newBuilder()
+ .setOutputMode(outputMode.toString)
+ // we pass time mode as string here and restore it in planner
Review Comment:
Replied in TimeMode.scala comment above.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
