mapreduce实现wordcount

WordCount.java

/**
 * Licensed to the Apache Software Foundation (ASF) under one
 * or more contributor license agreements.  See the NOTICE file
 * distributed with this work for additional information
 * regarding copyright ownership.  The ASF 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
 *
 * Unless required by applicable law or agreed to in writing, software
 * distributed under the License 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.
 */

// Modified by Shimin Chen to demonstrate functionality for Homework 2
// April-May 2015

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

  // This is the Mapper class
  // reference: http://hadoop.apache.org/docs/r2.6.0/api/org/apache/hadoop/mapreduce/Mapper.html
  //
  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, IntWritable>{
    
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
      
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }
  
  public static class IntSumCombiner
       extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();

    public void reduce(Text key, Iterable<IntWritable> values,
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      context.write(key, result);
    }
  }

  // This is the Reducer class
  // reference http://hadoop.apache.org/docs/r2.6.0/api/org/apache/hadoop/mapreduce/Reducer.html
  //
  // We want to control the output format to look at the following:
  //
  // count of word = count
  //
  public static class IntSumReducer
       extends Reducer<Text,IntWritable,Text,Text> {

    private Text result_key= new Text();
    private Text result_value= new Text();
    private byte[] prefix;
    private byte[] suffix;

    protected void setup(Context context) {
      try {
        prefix= Text.encode("count of ").array();
        suffix= Text.encode(" =").array();
      } catch (Exception e) {
        prefix = suffix = new byte[0];
      }
    }

    public void reduce(Text key, Iterable<IntWritable> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }

      // generate result key
      result_key.set(prefix);
      result_key.append(key.getBytes(), 0, key.getLength());
      result_key.append(suffix, 0, suffix.length);

      // generate result value
      result_value.set(Integer.toString(sum));

      context.write(result_key, result_value);
    }
  }

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length < 2) {
      System.err.println("Usage: wordcount <in> [<in>...] <out>");
      System.exit(2);
    }

    Job job = Job.getInstance(conf, "word count");

    job.setJarByClass(WordCount.class);

    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumCombiner.class);
    job.setReducerClass(IntSumReducer.class);

    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);

    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);

    // add the input paths as given by command line
    for (int i = 0; i < otherArgs.length - 1; ++i) {
      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));
    }

    // add the output path as given by the command line
    FileOutputFormat.setOutputPath(job,
      new Path(otherArgs[otherArgs.length - 1]));

    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

WordCount-manifest.txt
Main-Class: WordCount

执行命令：

1. start hadoop

   $ start-dfs.sh
   $ start-yarn.sh

2. Example: WordCount.java

   compile and generate jar
   $ javac WordCount.java
   $ jar cfm WordCount.jar WordCount-manifest.txt WordCount*.class

   remove output hdfs directory then run MapReduce job
   $ hdfs dfs -rm -f -r /hw2/output
   $ hadoop jar ./WordCount.jar /hw2/example-input.txt /hw2/output

   display output
   $ hdfs dfs -cat '/hw2/output/part-*'