com.cloudera.hbase.OldWordCount.java Source code

Introduction

Here is the source code for com.cloudera.hbase.OldWordCount.java

Source

/**
 * Copyright (c) 2011, Cloudera, Inc. All Rights Reserved.
 *
 * Cloudera, Inc. licenses this file to you under the Apache License,
 * Version 2.0 (the "License"). You may not use this file except in
 * compliance with the License. You may obtain a copy of the License at
 *
 *     http://www.apache.org/licenses/LICENSE-2.0
 *
 * This software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
 * CONDITIONS OF ANY KIND, either express or implied. See the License for
 * the specific language governing permissions and limitations under the
 * License.
 */
package com.cloudera.hbase;

import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

/**
 * See {@link org.apache.hadoop.examples.WordCount}
 * 
 * Version for org.apache.hadoop.mapred.* API.
 */
@SuppressWarnings({ "deprecation" })
public class OldWordCount {

    public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private final Text word = new Text();

        public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter)
                throws IOException {
            String line = value.toString();
            StringTokenizer tokenizer = new StringTokenizer(line);
            while (tokenizer.hasMoreTokens()) {
                word.set(tokenizer.nextToken());
                output.collect(word, one);
            }
        }
    }

    public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {

        @Override
        public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output,
                Reporter reporter) throws IOException {
            int sum = 0;
            while (values.hasNext()) {
                sum += values.next().get();
            }
            output.collect(key, new IntWritable(sum));
        }
    }

    public static void main(String[] args) throws Exception {
        JobConf conf = new JobConf(WordCount.class);
        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }
        conf.setJobName("word count");

        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(IntWritable.class);

        conf.setMapperClass(Map.class);
        conf.setCombinerClass(Reduce.class);
        conf.setReducerClass(Reduce.class);

        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);

        FileInputFormat.setInputPaths(conf, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(conf, new Path(otherArgs[1]));
        JobClient.runJob(conf);
        return;
    }
}