bogao007 commented on code in PR #47133: URL: https://github.com/apache/spark/pull/47133#discussion_r1714251830
########## sql/core/src/main/scala/org/apache/spark/sql/execution/python/TransformWithStateInPandasExec.scala: ########## @@ -0,0 +1,161 @@ +/* + * 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.python + +import scala.concurrent.duration.NANOSECONDS + +import org.apache.hadoop.conf.Configuration + +import org.apache.spark.JobArtifactSet +import org.apache.spark.api.python.{ChainedPythonFunctions, PythonEvalType} +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder +import org.apache.spark.sql.catalyst.expressions.{Ascending, Attribute, Expression, PythonUDF, SortOrder} +import org.apache.spark.sql.catalyst.plans.physical.Distribution +import org.apache.spark.sql.catalyst.types.DataTypeUtils +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.execution.python.PandasGroupUtils.{executePython, groupAndProject, resolveArgOffsets} +import org.apache.spark.sql.execution.streaming.{StatefulOperatorPartitioning, StatefulOperatorStateInfo, StatefulProcessorHandleImpl, StateStoreWriter, WatermarkSupport} +import org.apache.spark.sql.execution.streaming.state.{NoPrefixKeyStateEncoderSpec, StateSchemaValidationResult, StateStore, StateStoreOps} +import org.apache.spark.sql.streaming.{OutputMode, TimeMode} +import org.apache.spark.sql.types.{BinaryType, StructField, StructType} +import org.apache.spark.util.CompletionIterator + +/** + * Physical operator for executing + * [[org.apache.spark.sql.catalyst.plans.logical.TransformWithStateInPandas]] + * @param functionExpr function called on each group + * @param groupingAttributes used to group the data + * @param output used to define the output rows + * @param outputMode defines the output mode for the statefulProcessor + * @param timeMode The time mode semantics of the stateful processor for timers and TTL. + * @param stateInfo Used to identify the state store for a given operator. + * @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 TransformWithStateInPandasExec( + functionExpr: Expression, + groupingAttributes: Seq[Attribute], + output: Seq[Attribute], + outputMode: OutputMode, + timeMode: TimeMode, + stateInfo: Option[StatefulOperatorStateInfo], + batchTimestampMs: Option[Long], + eventTimeWatermarkForLateEvents: Option[Long], + eventTimeWatermarkForEviction: Option[Long], + child: SparkPlan) extends UnaryExecNode with StateStoreWriter with WatermarkSupport { + + private val pythonUDF = functionExpr.asInstanceOf[PythonUDF] + private val pythonFunction = pythonUDF.func + private val chainedFunc = + Seq((ChainedPythonFunctions(Seq(pythonFunction)), pythonUDF.resultId.id)) + + private val sessionLocalTimeZone = conf.sessionLocalTimeZone + private val pythonRunnerConf = ArrowPythonRunner.getPythonRunnerConfMap(conf) + private[this] val jobArtifactUUID = JobArtifactSet.getCurrentJobArtifactState.map(_.uuid) + + private val groupingKeyStructFields = groupingAttributes + .map(a => StructField(a.name, a.dataType, a.nullable)) + private val groupingKeySchema = StructType(groupingKeyStructFields) + private val groupingKeyExprEncoder = ExpressionEncoder(groupingKeySchema) + .resolveAndBind().asInstanceOf[ExpressionEncoder[Any]] + + /** The keys that may have a watermark attribute. */ + override def keyExpressions: Seq[Attribute] = groupingAttributes + + protected val schemaForKeyRow: StructType = new StructType().add("key", BinaryType) + + protected val schemaForValueRow: StructType = new StructType().add("value", BinaryType) + + override def requiredChildDistribution: Seq[Distribution] = { + StatefulOperatorPartitioning.getCompatibleDistribution(groupingAttributes, + getStateInfo, conf) :: + Nil + } + + override def requiredChildOrdering: Seq[Seq[SortOrder]] = Seq( + groupingAttributes.map(SortOrder(_, Ascending))) + + override def validateAndMaybeEvolveStateSchema( + hadoopConf: Configuration, + batchId: Long, + stateSchemaVersion: Int): List[StateSchemaValidationResult] = { + List.empty Review Comment: We will implement this support later, added TODO with followup jira task ########## sql/core/src/main/scala/org/apache/spark/sql/execution/python/TransformWithStateInPandasExec.scala: ########## @@ -0,0 +1,161 @@ +/* + * 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.python + +import scala.concurrent.duration.NANOSECONDS + +import org.apache.hadoop.conf.Configuration + +import org.apache.spark.JobArtifactSet +import org.apache.spark.api.python.{ChainedPythonFunctions, PythonEvalType} +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.encoders.ExpressionEncoder +import org.apache.spark.sql.catalyst.expressions.{Ascending, Attribute, Expression, PythonUDF, SortOrder} +import org.apache.spark.sql.catalyst.plans.physical.Distribution +import org.apache.spark.sql.catalyst.types.DataTypeUtils +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.execution.python.PandasGroupUtils.{executePython, groupAndProject, resolveArgOffsets} +import org.apache.spark.sql.execution.streaming.{StatefulOperatorPartitioning, StatefulOperatorStateInfo, StatefulProcessorHandleImpl, StateStoreWriter, WatermarkSupport} +import org.apache.spark.sql.execution.streaming.state.{NoPrefixKeyStateEncoderSpec, StateSchemaValidationResult, StateStore, StateStoreOps} +import org.apache.spark.sql.streaming.{OutputMode, TimeMode} +import org.apache.spark.sql.types.{BinaryType, StructField, StructType} +import org.apache.spark.util.CompletionIterator + +/** + * Physical operator for executing + * [[org.apache.spark.sql.catalyst.plans.logical.TransformWithStateInPandas]] + * @param functionExpr function called on each group + * @param groupingAttributes used to group the data + * @param output used to define the output rows + * @param outputMode defines the output mode for the statefulProcessor + * @param timeMode The time mode semantics of the stateful processor for timers and TTL. + * @param stateInfo Used to identify the state store for a given operator. + * @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 TransformWithStateInPandasExec( + functionExpr: Expression, + groupingAttributes: Seq[Attribute], + output: Seq[Attribute], + outputMode: OutputMode, + timeMode: TimeMode, + stateInfo: Option[StatefulOperatorStateInfo], + batchTimestampMs: Option[Long], + eventTimeWatermarkForLateEvents: Option[Long], + eventTimeWatermarkForEviction: Option[Long], + child: SparkPlan) extends UnaryExecNode with StateStoreWriter with WatermarkSupport { + + private val pythonUDF = functionExpr.asInstanceOf[PythonUDF] + private val pythonFunction = pythonUDF.func + private val chainedFunc = + Seq((ChainedPythonFunctions(Seq(pythonFunction)), pythonUDF.resultId.id)) + + private val sessionLocalTimeZone = conf.sessionLocalTimeZone + private val pythonRunnerConf = ArrowPythonRunner.getPythonRunnerConfMap(conf) + private[this] val jobArtifactUUID = JobArtifactSet.getCurrentJobArtifactState.map(_.uuid) + + private val groupingKeyStructFields = groupingAttributes + .map(a => StructField(a.name, a.dataType, a.nullable)) + private val groupingKeySchema = StructType(groupingKeyStructFields) + private val groupingKeyExprEncoder = ExpressionEncoder(groupingKeySchema) + .resolveAndBind().asInstanceOf[ExpressionEncoder[Any]] + + /** The keys that may have a watermark attribute. */ + override def keyExpressions: Seq[Attribute] = groupingAttributes + + protected val schemaForKeyRow: StructType = new StructType().add("key", BinaryType) Review Comment: done -- 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]
