icexelloss commented on a change in pull request #22305: [SPARK-24561][SQL][Python] User-defined window aggregation functions with Pandas UDF (bounded window) URL: https://github.com/apache/spark/pull/22305#discussion_r242298316
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/window/WindowExecBase.scala ########## @@ -0,0 +1,226 @@ +/* + * 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.window + +import scala.collection.mutable +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.catalyst.expressions.aggregate.AggregateExpression +import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode} +import org.apache.spark.sql.types.{CalendarIntervalType, DateType, IntegerType, TimestampType} + +abstract class WindowExecBase( + windowExpression: Seq[NamedExpression], + partitionSpec: Seq[Expression], + orderSpec: Seq[SortOrder], + child: SparkPlan) extends UnaryExecNode { + + /** + * Create the resulting projection. + * + * This method uses Code Generation. It can only be used on the executor side. + * + * @param expressions unbound ordered function expressions. + * @return the final resulting projection. + */ + protected def createResultProjection(expressions: Seq[Expression]): UnsafeProjection = { + val references = expressions.zipWithIndex.map { case (e, i) => + // Results of window expressions will be on the right side of child's output + BoundReference(child.output.size + i, e.dataType, e.nullable) + } + val unboundToRefMap = expressions.zip(references).toMap + val patchedWindowExpression = windowExpression.map(_.transform(unboundToRefMap)) + UnsafeProjection.create( + child.output ++ patchedWindowExpression, + child.output) + } + + /** + * Create a bound ordering object for a given frame type and offset. A bound ordering object is + * used to determine which input row lies within the frame boundaries of an output row. + * + * This method uses Code Generation. It can only be used on the executor side. + * + * @param frame to evaluate. This can either be a Row or Range frame. + * @param bound with respect to the row. + * @param timeZone the session local timezone for time related calculations. + * @return a bound ordering object. + */ + protected def createBoundOrdering( Review comment: Fixed ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
