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.map; |
---|
20 | |
---|
21 | import java.io.IOException; |
---|
22 | import java.util.StringTokenizer; |
---|
23 | |
---|
24 | import org.apache.hadoop.io.IntWritable; |
---|
25 | import org.apache.hadoop.io.Text; |
---|
26 | import org.apache.hadoop.mapreduce.Mapper; |
---|
27 | |
---|
28 | /** |
---|
29 | * Tokenize the input values and emit each word with a count of 1. |
---|
30 | */ |
---|
31 | public class TokenCounterMapper extends Mapper<Object, Text, Text, IntWritable>{ |
---|
32 | |
---|
33 | private final static IntWritable one = new IntWritable(1); |
---|
34 | private Text word = new Text(); |
---|
35 | |
---|
36 | @Override |
---|
37 | public void map(Object key, Text value, Context context |
---|
38 | ) throws IOException, InterruptedException { |
---|
39 | StringTokenizer itr = new StringTokenizer(value.toString()); |
---|
40 | while (itr.hasMoreTokens()) { |
---|
41 | word.set(itr.nextToken()); |
---|
42 | context.write(word, one); |
---|
43 | } |
---|
44 | } |
---|
45 | } |
---|