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.map; 020 021 import java.io.IOException; 022 import java.util.StringTokenizer; 023 024 import org.apache.hadoop.classification.InterfaceAudience; 025 import org.apache.hadoop.classification.InterfaceStability; 026 import org.apache.hadoop.io.IntWritable; 027 import org.apache.hadoop.io.Text; 028 import org.apache.hadoop.mapreduce.Mapper; 029 030 /** 031 * Tokenize the input values and emit each word with a count of 1. 032 */ 033 @InterfaceAudience.Public 034 @InterfaceStability.Stable 035 public class TokenCounterMapper extends Mapper<Object, Text, Text, IntWritable>{ 036 037 private final static IntWritable one = new IntWritable(1); 038 private Text word = new Text(); 039 040 @Override 041 public void map(Object key, Text value, Context context 042 ) throws IOException, InterruptedException { 043 StringTokenizer itr = new StringTokenizer(value.toString()); 044 while (itr.hasMoreTokens()) { 045 word.set(itr.nextToken()); 046 context.write(word, one); 047 } 048 } 049 }