Github user nongli commented on a diff in the pull request: https://github.com/apache/spark/pull/10498#discussion_r48889876 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/bucket.scala --- @@ -0,0 +1,83 @@ +/* + * 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 org.apache.hadoop.mapreduce.{Job, TaskAttemptContext} +import org.apache.spark.sql.SQLContext +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.sources.{OutputWriter, OutputWriterFactory, HadoopFsRelationProvider, HadoopFsRelation} +import org.apache.spark.sql.types.StructType + +/** + * A container for bucketing information. + * Bucketing is a technology for decomposing data sets into more manageable parts, and the number + * of buckets is fixed so it does not fluctuate with data. + * + * @param numBuckets number of buckets. + * @param bucketColumnNames the names of the columns that used to generate the bucket id. + * @param sortColumnNames the names of the columns that used to sort data in each bucket. + */ +private[sql] case class BucketSpec( + numBuckets: Int, + bucketColumnNames: Seq[String], + sortColumnNames: Seq[String]) + +private[sql] trait BucketedHadoopFsRelationProvider extends HadoopFsRelationProvider { + final override def createRelation( + sqlContext: SQLContext, + paths: Array[String], + dataSchema: Option[StructType], + partitionColumns: Option[StructType], + parameters: Map[String, String]): HadoopFsRelation = + createRelation(sqlContext, paths, dataSchema, partitionColumns, None, parameters) + + def createRelation( + sqlContext: SQLContext, + paths: Array[String], + dataSchema: Option[StructType], + partitionColumns: Option[StructType], + bucketSpec: Option[BucketSpec], + parameters: Map[String, String]): BucketedHadoopFsRelation +} + +private[sql] abstract class BucketedHadoopFsRelation( + maybePartitionSpec: Option[PartitionSpec], + parameters: Map[String, String]) + extends HadoopFsRelation(maybePartitionSpec, parameters) { + def this() = this(None, Map.empty[String, String]) + + def this(parameters: Map[String, String]) = this(None, parameters) + + def bucketSpec: Option[BucketSpec] + + def prepareJobForWrite(job: Job): BucketedOutputWriterFactory +} + +private[sql] abstract class BucketedOutputWriterFactory extends OutputWriterFactory { + final override def newInstance( + path: String, + dataSchema: StructType, + context: TaskAttemptContext): OutputWriter = + newInstance(path, None, dataSchema, context) + + def newInstance( + path: String, + bucketId: Option[Int], --- End diff -- Should this just be bucketId: Int? What does it mean to pass a none bucket?
--- If your project is set up for it, you can reply to this email and have your reply appear on GitHub as well. If your project does not have this feature enabled and wishes so, or if the feature is enabled but not working, please contact infrastructure at infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org