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.mapreduce.lib.aggregate;
020    
021    import java.util.ArrayList;
022    import java.util.Map.Entry;
023    
024    import org.apache.hadoop.classification.InterfaceAudience;
025    import org.apache.hadoop.classification.InterfaceStability;
026    import org.apache.hadoop.conf.Configuration;
027    import org.apache.hadoop.io.Text;
028    
029    /**
030     * This interface defines the contract a value aggregator descriptor must
031     * support. Such a descriptor can be configured with a {@link Configuration}
032     * object. Its main function is to generate a list of aggregation-id/value 
033     * pairs. An aggregation id encodes an aggregation type which is used to 
034     * guide the way to aggregate the value in the reduce/combiner phrase of an
035     * Aggregate based job. 
036     * The mapper in an Aggregate based map/reduce job may create one or more of
037     * ValueAggregatorDescriptor objects at configuration time. For each input
038     * key/value pair, the mapper will use those objects to create aggregation
039     * id/value pairs.
040     * 
041     */
042    @InterfaceAudience.Public
043    @InterfaceStability.Stable
044    public interface ValueAggregatorDescriptor {
045    
046      public static final String TYPE_SEPARATOR = ":";
047    
048      public static final Text ONE = new Text("1");
049    
050      /**
051       * Generate a list of aggregation-id/value pairs for 
052       * the given key/value pair.
053       * This function is usually called by the mapper of an Aggregate based job.
054       * 
055       * @param key
056       *          input key
057       * @param val
058       *          input value
059       * @return a list of aggregation id/value pairs. An aggregation id encodes an
060       *         aggregation type which is used to guide the way to aggregate the
061       *         value in the reduce/combiner phrase of an Aggregate based job.
062       */
063      public ArrayList<Entry<Text, Text>> generateKeyValPairs(Object key,
064                                                              Object val);
065    
066      /**
067       * Configure the object
068       * 
069       * @param conf
070       *          a Configuration object that may contain the information 
071       *          that can be used to configure the object.
072       */
073      public void configure(Configuration conf);
074    }