001    /**
002     * Licensed to the Apache Software Foundation (ASF) under one
003     * or more contributor license agreements.  See the NOTICE file
004     * distributed with this work for additional information
005     * regarding copyright ownership.  The ASF licenses this file
006     * to you under the Apache License, Version 2.0 (the
007     * "License"); you may not use this file except in compliance
008     * with the License.  You may obtain a copy of the License at
009     *
010     *     http://www.apache.org/licenses/LICENSE-2.0
011     *
012     * Unless required by applicable law or agreed to in writing, software
013     * distributed under the License is distributed on an "AS IS" BASIS,
014     * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015     * See the License for the specific language governing permissions and
016     * limitations under the License.
017     */
018    
019    package org.apache.hadoop.mapred;
020    
021    import org.apache.hadoop.classification.InterfaceAudience;
022    import org.apache.hadoop.classification.InterfaceStability;
023    
024    /** 
025     * Partitions the key space.
026     * 
027     * <p><code>Partitioner</code> controls the partitioning of the keys of the 
028     * intermediate map-outputs. The key (or a subset of the key) is used to derive
029     * the partition, typically by a hash function. The total number of partitions
030     * is the same as the number of reduce tasks for the job. Hence this controls
031     * which of the <code>m</code> reduce tasks the intermediate key (and hence the 
032     * record) is sent for reduction.</p>
033     * 
034     * @see Reducer
035     */
036    @InterfaceAudience.Public
037    @InterfaceStability.Stable
038    public interface Partitioner<K2, V2> extends JobConfigurable {
039      
040      /** 
041       * Get the paritition number for a given key (hence record) given the total 
042       * number of partitions i.e. number of reduce-tasks for the job.
043       *   
044       * <p>Typically a hash function on a all or a subset of the key.</p>
045       *
046       * @param key the key to be paritioned.
047       * @param value the entry value.
048       * @param numPartitions the total number of partitions.
049       * @return the partition number for the <code>key</code>.
050       */
051      int getPartition(K2 key, V2 value, int numPartitions);
052    }