wiki:NCHCCloudCourse100928_4_EXM_c1
package org.nchc.hadoop;

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

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.filecache.DistributedCache;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.hadoop.util.StringUtils;

public class WordCountV {

  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 setup(Context context) {
      Configuration conf = context.getConfiguration();
      System.err.println(conf.get("mapred.job.tracker"));

    }
    
    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 IntSumReducer 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);
    }
  }

  public static void main(String[] args) throws Exception {
    String[] argv = { "/home/nchc/input", "/home/nchc/output-wc3" };
    args =  argv;
    Configuration conf = new Configuration();
    conf.set("mapred.job.tracker", "local"); // for single
    conf.set("fs.default.name", "file:///"); // for single

    String[] otherArgs = new GenericOptionsParser(conf, args)
        .getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err
          .println("Usage: hadoop jar WordCount.jar <input> <output>");
      System.exit(2);
    }
    CheckAndDelete.checkAndDelete(args[1], conf);
    Job job = new Job(conf, "Word Count");
    job.setJarByClass(WordCountV.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

Last modified 13 years ago Last modified on Aug 2, 2011, 2:10:24 PM