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.mapred.lib;
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.LongWritable;
027    import org.apache.hadoop.io.Text;
028    import org.apache.hadoop.mapred.MapReduceBase;
029    import org.apache.hadoop.mapred.Mapper;
030    import org.apache.hadoop.mapred.OutputCollector;
031    import org.apache.hadoop.mapred.Reporter;
032    
033    
034    /** A {@link Mapper} that maps text values into <token,freq> pairs.  Uses
035     * {@link StringTokenizer} to break text into tokens. 
036     * @deprecated Use 
037     *    {@link org.apache.hadoop.mapreduce.lib.map.TokenCounterMapper} instead.
038     */
039    @Deprecated
040    @InterfaceAudience.Public
041    @InterfaceStability.Stable
042    public class TokenCountMapper<K> extends MapReduceBase
043        implements Mapper<K, Text, Text, LongWritable> {
044    
045      public void map(K key, Text value,
046                      OutputCollector<Text, LongWritable> output,
047                      Reporter reporter)
048        throws IOException {
049        // get input text
050        String text = value.toString();       // value is line of text
051    
052        // tokenize the value
053        StringTokenizer st = new StringTokenizer(text);
054        while (st.hasMoreTokens()) {
055          // output <token,1> pairs
056          output.collect(new Text(st.nextToken()), new LongWritable(1));
057        }  
058      }
059      
060    }