1 /**
2  * Licensed to the Apache Software Foundation (ASF) under one
3  * or more contributor license agreements.  See the NOTICE file
4  * distributed with this work for additional information
5  * regarding copyright ownership.  The ASF licenses this file
6  * to you under the Apache License, Version 2.0 (the
7  * "License"); you may not use this file except in compliance
8  * with the License.  You may obtain a copy of the License at
9  *
10  *     http://www.apache.org/licenses/LICENSE-2.0
11  *
12  * Unless required by applicable law or agreed to in writing, software
13  * distributed under the License is distributed on an "AS IS" BASIS,
14  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15  * See the License for the specific language governing permissions and
16  * limitations under the License.
17  */
18 
19 package org.apache.hadoop.mapreduce.lib.aggregate;
20 
21 import java.util.ArrayList;
22 import java.util.Map.Entry;
23 
24 import org.apache.hadoop.classification.InterfaceAudience;
25 import org.apache.hadoop.classification.InterfaceStability;
26 import org.apache.hadoop.conf.Configuration;
27 import org.apache.hadoop.io.Text;
28 
29 /**
30  * This interface defines the contract a value aggregator descriptor must
31  * support. Such a descriptor can be configured with a {@link Configuration}
32  * object. Its main function is to generate a list of aggregation-id/value
33  * pairs. An aggregation id encodes an aggregation type which is used to
34  * guide the way to aggregate the value in the reduce/combiner phrase of an
35  * Aggregate based job.
36  * The mapper in an Aggregate based map/reduce job may create one or more of
37  * ValueAggregatorDescriptor objects at configuration time. For each input
38  * key/value pair, the mapper will use those objects to create aggregation
39  * id/value pairs.
40  *
41  */
42 @InterfaceAudience.Public
43 @InterfaceStability.Stable
44 public interface ValueAggregatorDescriptor {
45 
46   public static final String TYPE_SEPARATOR = ":";
47 
48   public static final Text ONE = new Text("1");
49 
50   /**
51    * Generate a list of aggregation-id/value pairs for
52    * the given key/value pair.
53    * This function is usually called by the mapper of an Aggregate based job.
54    *
55    * @param key
56    *          input key
57    * @param val
58    *          input value
59    * @return a list of aggregation id/value pairs. An aggregation id encodes an
60    *         aggregation type which is used to guide the way to aggregate the
61    *         value in the reduce/combiner phrase of an Aggregate based job.
62    */
generateKeyValPairs(Object key, Object val)63   public ArrayList<Entry<Text, Text>> generateKeyValPairs(Object key,
64                                                           Object val);
65 
66   /**
67    * Configure the object
68    *
69    * @param conf
70    *          a Configuration object that may contain the information
71    *          that can be used to configure the object.
72    */
configure(Configuration conf)73   public void configure(Configuration conf);
74 }
75