read/partitioning/Partitioning.java

0001 /*
0002  * Licensed to the Apache Software Foundation (ASF) under one or more
0003  * contributor license agreements.  See the NOTICE file distributed with
0004  * this work for additional information regarding copyright ownership.
0005  * The ASF licenses this file to You under the Apache License, Version 2.0
0006  * (the "License"); you may not use this file except in compliance with
0007  * the License.  You may obtain a copy of the License at
0008  *
0009  *    http://www.apache.org/licenses/LICENSE-2.0
0010  *
0011  * Unless required by applicable law or agreed to in writing, software
0012  * distributed under the License is distributed on an "AS IS" BASIS,
0013  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
0014  * See the License for the specific language governing permissions and
0015  * limitations under the License.
0016  */
0017
0018 package org.apache.spark.sql.connector.read.partitioning;
0019
0020 import org.apache.spark.annotation.Evolving;
0021 import org.apache.spark.sql.connector.read.InputPartition;
0022 import org.apache.spark.sql.connector.read.SupportsReportPartitioning;
0023
0024 /**
0025  * An interface to represent the output data partitioning for a data source, which is returned by
0026  * {@link SupportsReportPartitioning#outputPartitioning()}. Note that this should work
0027  * like a snapshot. Once created, it should be deterministic and always report the same number of
0028  * partitions and the same "satisfy" result for a certain distribution.
0029  *
0030  * @since 3.0.0
0031  */
0032 @Evolving
0033 public interface Partitioning {
0034
0035   /**
0036    * Returns the number of partitions(i.e., {@link InputPartition}s) the data source outputs.
0037    */
0038   int numPartitions();
0039
0040   /**
0041    * Returns true if this partitioning can satisfy the given distribution, which means Spark does
0042    * not need to shuffle the output data of this data source for some certain operations.
0043    *
0044    * Note that, Spark may add new concrete implementations of {@link Distribution} in new releases.
0045    * This method should be aware of it and always return false for unrecognized distributions. It's
0046    * recommended to check every Spark new release and support new distributions if possible, to
0047    * avoid shuffle at Spark side for more cases.
0048    */
0049   boolean satisfy(Distribution distribution);
0050 }