Github user cloud-fan commented on a diff in the pull request: https://github.com/apache/spark/pull/21381#discussion_r189869751 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/FileFormatDataWriter.scala --- @@ -0,0 +1,310 @@ +/* + * 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.datasources + +import scala.collection.mutable + +import org.apache.hadoop.fs.Path +import org.apache.hadoop.mapreduce.TaskAttemptContext + +import org.apache.spark.internal.io.FileCommitProtocol +import org.apache.spark.internal.io.FileCommitProtocol.TaskCommitMessage +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.catalog.CatalogTypes.TablePartitionSpec +import org.apache.spark.sql.catalyst.catalog.ExternalCatalogUtils +import org.apache.spark.sql.catalyst.expressions._ +import org.apache.spark.sql.types.StringType +import org.apache.spark.util.SerializableConfiguration + +/** + * Abstract class for writing out data in a single Spark task. + * Exceptions thrown by the implementation of this trait will automatically trigger task aborts. + */ +abstract class FileFormatDataWriter( + description: WriteJobDescription, + taskAttemptContext: TaskAttemptContext, + committer: FileCommitProtocol) { + /** + * Max number of files a single task writes out due to file size. In most cases the number of + * files written should be very small. This is just a safe guard to protect some really bad + * settings, e.g. maxRecordsPerFile = 1. + */ + val MAX_FILE_COUNTER = 1000 * 1000 + protected val updatedPartitions = mutable.Set[String]() + protected var currentWriter: OutputWriter = _ + protected var fileCounter: Int = _ --- End diff -- This is not used in the abstract class, please move it to implementations.
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org