Github user tdas commented on a diff in the pull request: https://github.com/apache/spark/pull/20243#discussion_r161968219 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/streaming/sources/PackedRowWriterFactory.scala --- @@ -0,0 +1,50 @@ +/* + * 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.sources + +import scala.collection.mutable + +import org.apache.spark.internal.Logging +import org.apache.spark.sql.Row +import org.apache.spark.sql.sources.v2.writer.{DataWriter, DataWriterFactory, WriterCommitMessage} + +/** + * A simple [[DataWriterFactory]] whose tasks just pack rows into the commit message for delivery + * to a [[org.apache.spark.sql.sources.v2.writer.DataSourceV2Writer]] on the driver. + */ +case object PackedRowWriterFactory extends DataWriterFactory[Row] { + def createDataWriter(partitionId: Int, attemptNumber: Int): DataWriter[Row] = { + new PackedRowDataWriter() + } +} + +case class PackedRowCommitMessage(rows: Array[Row]) extends WriterCommitMessage + +class PackedRowDataWriter() extends DataWriter[Row] with Logging { + private val data = mutable.Buffer[Row]() + + override def write(row: Row): Unit = data.append(row) + + override def commit(): PackedRowCommitMessage = { + val msg = PackedRowCommitMessage(data.clone().toArray) --- End diff -- why are you cloning and then calling toArray? Just toArray will create an immutable copy.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org