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
019package org.apache.hadoop.mapred.lib;
020
021import java.io.IOException;
022import java.util.StringTokenizer;
023
024import org.apache.hadoop.classification.InterfaceAudience;
025import org.apache.hadoop.classification.InterfaceStability;
026import org.apache.hadoop.io.LongWritable;
027import org.apache.hadoop.io.Text;
028import org.apache.hadoop.mapred.MapReduceBase;
029import org.apache.hadoop.mapred.Mapper;
030import org.apache.hadoop.mapred.OutputCollector;
031import org.apache.hadoop.mapred.Reporter;
032
033
034/** 
035 * A {@link Mapper} that maps text values into <token,freq> pairs.  Uses
036 * {@link StringTokenizer} to break text into tokens. 
037 */
038@InterfaceAudience.Public
039@InterfaceStability.Stable
040public class TokenCountMapper<K> extends MapReduceBase
041    implements Mapper<K, Text, Text, LongWritable> {
042
043  public void map(K key, Text value,
044                  OutputCollector<Text, LongWritable> output,
045                  Reporter reporter)
046    throws IOException {
047    // get input text
048    String text = value.toString();       // value is line of text
049
050    // tokenize the value
051    StringTokenizer st = new StringTokenizer(text);
052    while (st.hasMoreTokens()) {
053      // output <token,1> pairs
054      output.collect(new Text(st.nextToken()), new LongWritable(1));
055    }  
056  }
057  
058}