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 | package org.apache.hadoop.fs; |
---|
19 | |
---|
20 | import java.io.IOException; |
---|
21 | import java.util.Iterator; |
---|
22 | |
---|
23 | import org.apache.commons.logging.Log; |
---|
24 | import org.apache.commons.logging.LogFactory; |
---|
25 | import org.apache.hadoop.io.UTF8; |
---|
26 | import org.apache.hadoop.io.WritableComparable; |
---|
27 | import org.apache.hadoop.mapred.MapReduceBase; |
---|
28 | import org.apache.hadoop.mapred.OutputCollector; |
---|
29 | import org.apache.hadoop.mapred.Reducer; |
---|
30 | import org.apache.hadoop.mapred.Reporter; |
---|
31 | |
---|
32 | /** |
---|
33 | * Reducer that accumulates values based on their type. |
---|
34 | * <p> |
---|
35 | * The type is specified in the key part of the key-value pair |
---|
36 | * as a prefix to the key in the following way |
---|
37 | * <p> |
---|
38 | * <tt>type:key</tt> |
---|
39 | * <p> |
---|
40 | * The values are accumulated according to the types: |
---|
41 | * <ul> |
---|
42 | * <li><tt>s:</tt> - string, concatenate</li> |
---|
43 | * <li><tt>f:</tt> - float, summ</li> |
---|
44 | * <li><tt>l:</tt> - long, summ</li> |
---|
45 | * </ul> |
---|
46 | * |
---|
47 | */ |
---|
48 | public class AccumulatingReducer extends MapReduceBase |
---|
49 | implements Reducer<UTF8, UTF8, UTF8, UTF8> { |
---|
50 | private static final Log LOG = LogFactory.getLog(AccumulatingReducer.class); |
---|
51 | |
---|
52 | protected String hostName; |
---|
53 | |
---|
54 | public AccumulatingReducer () { |
---|
55 | LOG.info("Starting AccumulatingReducer !!!"); |
---|
56 | try { |
---|
57 | hostName = java.net.InetAddress.getLocalHost().getHostName(); |
---|
58 | } catch(Exception e) { |
---|
59 | hostName = "localhost"; |
---|
60 | } |
---|
61 | LOG.info("Starting AccumulatingReducer on " + hostName); |
---|
62 | } |
---|
63 | |
---|
64 | public void reduce(UTF8 key, |
---|
65 | Iterator<UTF8> values, |
---|
66 | OutputCollector<UTF8, UTF8> output, |
---|
67 | Reporter reporter |
---|
68 | ) throws IOException { |
---|
69 | String field = key.toString(); |
---|
70 | |
---|
71 | reporter.setStatus("starting " + field + " ::host = " + hostName); |
---|
72 | |
---|
73 | // concatenate strings |
---|
74 | if (field.startsWith("s:")) { |
---|
75 | String sSum = ""; |
---|
76 | while (values.hasNext()) |
---|
77 | sSum += values.next().toString() + ";"; |
---|
78 | output.collect(key, new UTF8(sSum)); |
---|
79 | reporter.setStatus("finished " + field + " ::host = " + hostName); |
---|
80 | return; |
---|
81 | } |
---|
82 | // sum long values |
---|
83 | if (field.startsWith("f:")) { |
---|
84 | float fSum = 0; |
---|
85 | while (values.hasNext()) |
---|
86 | fSum += Float.parseFloat(values.next().toString()); |
---|
87 | output.collect(key, new UTF8(String.valueOf(fSum))); |
---|
88 | reporter.setStatus("finished " + field + " ::host = " + hostName); |
---|
89 | return; |
---|
90 | } |
---|
91 | // sum long values |
---|
92 | if (field.startsWith("l:")) { |
---|
93 | long lSum = 0; |
---|
94 | while (values.hasNext()) { |
---|
95 | lSum += Long.parseLong(values.next().toString()); |
---|
96 | } |
---|
97 | output.collect(key, new UTF8(String.valueOf(lSum))); |
---|
98 | } |
---|
99 | reporter.setStatus("finished " + field + " ::host = " + hostName); |
---|
100 | } |
---|
101 | } |
---|