Github user BryanCutler commented on a diff in the pull request: https://github.com/apache/spark/pull/18659#discussion_r139493581 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/python/ArrowEvalPythonExec.scala --- @@ -0,0 +1,127 @@ +/* + * 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 java.io.File + +import scala.collection.mutable.ArrayBuffer + +import org.apache.spark.{SparkEnv, TaskContext} +import org.apache.spark.api.python.{ChainedPythonFunctions, PythonEvalType, PythonRunner} +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.execution.SparkPlan +import org.apache.spark.sql.execution.arrow.{ArrowConverters, ArrowPayload} +import org.apache.spark.sql.types.{DataType, StructField, StructType} +import org.apache.spark.util.Utils + + +/** + * A physical plan that evaluates a [[PythonUDF]], + */ +case class ArrowEvalPythonExec(udfs: Seq[PythonUDF], output: Seq[Attribute], child: SparkPlan) + extends SparkPlan { + + def children: Seq[SparkPlan] = child :: Nil + + override def producedAttributes: AttributeSet = AttributeSet(output.drop(child.output.length)) + + private def collectFunctions(udf: PythonUDF): (ChainedPythonFunctions, Seq[Expression]) = { --- End diff -- Yes, these functions are duplicated, as well as some code in `doExecute()`. I could add a common base class like `EvalPythonExec` to clean this up, and maybe move to the same file?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org