jingz-db commented on code in PR #49488: URL: https://github.com/apache/spark/pull/49488#discussion_r1947167226
########## sql/connect/server/src/main/scala/org/apache/spark/sql/connect/planner/SparkConnectPlanner.scala: ########## @@ -679,6 +681,66 @@ class SparkConnectPlanner( rel.getGroupingExpressionsList, rel.getSortingExpressionsList) + if (rel.hasTransformWithStateInfo) { + val hasInitialState = !rel.getInitialGroupingExpressionsList.isEmpty && rel.hasInitialInput + + val twsInfo = rel.getTransformWithStateInfo + val statefulProcessorStr = twsInfo.getStatefulProcessorPayload + val keyDeserializer = udf.inputDeserializer(ds.groupingAttributes) + val outputAttr = udf.outputObjAttr + + val timeMode = TimeModes(twsInfo.getTimeMode, isScala = true) + val outputMode = InternalOutputModes(twsInfo.getOutputMode) + + val node = if (hasInitialState) { + val statefulProcessor = + Utils.deserialize[StatefulProcessorWithInitialState[Any, Any, Any, Any]]( + statefulProcessorStr.toByteArray, + Utils.getContextOrSparkClassLoader) + val initDs = UntypedKeyValueGroupedDataset( + rel.getInitialInput, + rel.getInitialGroupingExpressionsList, + rel.getSortingExpressionsList) + new TransformWithState( + keyDeserializer, + ds.valueDeserializer, + ds.groupingAttributes, + ds.dataAttributes, + statefulProcessor, + timeMode, + outputMode, + udf.inEnc.asInstanceOf[ExpressionEncoder[Any]], + outputAttr, + ds.analyzed, + hasInitialState, + initDs.groupingAttributes, + initDs.dataAttributes, + initDs.valueDeserializer, + initDs.analyzed) + } else { + val statefulProcessor = Utils.deserialize[StatefulProcessor[Any, Any, Any]]( + statefulProcessorStr.toByteArray, + Utils.getContextOrSparkClassLoader) + new TransformWithState( + keyDeserializer, + ds.valueDeserializer, + ds.groupingAttributes, + ds.dataAttributes, + statefulProcessor, + timeMode, + outputMode, + udf.inEnc.asInstanceOf[ExpressionEncoder[Any]], + outputAttr, + ds.analyzed, + hasInitialState, + ds.groupingAttributes, + ds.dataAttributes, + keyDeserializer, + LocalRelation(ds.vEncoder.schema)) + } + return SerializeFromObject(udf.outputNamedExpression, node) Review Comment: Thanks! I did not know about the `return` unintended behavior when I wrote this. I am removing `return`. -- 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