ueshin commented on code in PR #37253: URL: https://github.com/apache/spark/pull/37253#discussion_r928057713
########## sql/core/src/main/scala/org/apache/spark/sql/execution/python/PythonArrowInput.scala: ########## @@ -0,0 +1,109 @@ +/* + * 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.DataOutputStream +import java.net.Socket + +import org.apache.arrow.vector.VectorSchemaRoot +import org.apache.arrow.vector.ipc.ArrowStreamWriter + +import org.apache.spark.{SparkEnv, TaskContext} +import org.apache.spark.api.python.{BasePythonRunner, PythonRDD} +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.execution.arrow.ArrowWriter +import org.apache.spark.sql.types.StructType +import org.apache.spark.sql.util.ArrowUtils +import org.apache.spark.util.Utils + +/** + * A trait that can be mixed-in with [[BasePythonRunner]]. It implements the logic from + * Python (Arrow) to JVM (ColumnarBatch). + */ +private[python] trait PythonArrowInput { self: BasePythonRunner[Iterator[InternalRow], _] => + protected val workerConf: Map[String, String] + + protected val schema: StructType + + protected val timeZoneId: String + + protected def handleMetadataBeforeExec(stream: DataOutputStream): Unit = { + // Write config for the worker as a number of key -> value pairs of strings + stream.writeInt(workerConf.size) + for ((k, v) <- workerConf) { + PythonRDD.writeUTF(k, stream) + PythonRDD.writeUTF(v, stream) + } + } Review Comment: For the `Dataset.groupByKey().flatMapGroupsWithState`, you are planning to override this method? In that case, I guess we should implement this in `ArrowPythonRunner` and leave this empty the same as `PythonArrowOutput.handleMetadataAfterExec`? -- 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]
