HeartSaVioR commented on code in PR #43961: URL: https://github.com/apache/spark/pull/43961#discussion_r1430748052
########## sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/TransformWithStateExec.scala: ########## @@ -0,0 +1,171 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.spark.sql.execution.streaming + +import java.util.concurrent.TimeUnit.NANOSECONDS + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.{Ascending, Attribute, Expression, SortOrder, UnsafeRow} +import org.apache.spark.sql.catalyst.plans.physical.Distribution +import org.apache.spark.sql.execution._ +import org.apache.spark.sql.execution.streaming.state._ +import org.apache.spark.sql.streaming.{OutputMode, StatefulProcessor} +import org.apache.spark.sql.types._ +import org.apache.spark.util.CompletionIterator + +/** + * Physical operator for executing `TransformWithState` + * + * @param statefulProcessor processor methods called on underlying data + * @param keyDeserializer used to extract the key object for each group. + * @param valueDeserializer used to extract the items in the iterator from an input row. + * @param groupingAttributes used to group the data + * @param dataAttributes used to read the data + * @param outputObjAttr Defines the output object + * @param batchTimestampMs processing timestamp of the current batch. + * @param eventTimeWatermarkForLateEvents event time watermark for filtering late events + * @param eventTimeWatermarkForEviction event time watermark for state eviction + * @param child the physical plan for the underlying data + */ +case class TransformWithStateExec( + keyDeserializer: Expression, + valueDeserializer: Expression, + groupingAttributes: Seq[Attribute], + dataAttributes: Seq[Attribute], + statefulProcessor: StatefulProcessor[Any, Any, Any], + outputMode: OutputMode, + outputObjAttr: Attribute, + stateInfo: Option[StatefulOperatorStateInfo], + batchTimestampMs: Option[Long], + eventTimeWatermarkForLateEvents: Option[Long], + eventTimeWatermarkForEviction: Option[Long], + child: SparkPlan) + extends UnaryExecNode + with StateStoreWriter + with WatermarkSupport + with ObjectProducerExec { + + override def shortName: String = "transformWithStateExec" + + override def shouldRunAnotherBatch(newInputWatermark: Long): Boolean = false Review Comment: Ah OK, no timer now. Could you please add TODO comment so that we don't forget? No need to add JIRA ticket as of now, as we need to pass SPIP to move forward. -- 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]
