Simple hadoop example

1_MyCounter.java

import java.io.IOException;
import java.util.*;
import java.util.regex.Pattern;

import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.util.*;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class MyCounter {
  public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private final static Pattern notALetter = Pattern.compile("[^a-zA-Z]*");
    private Text word = new Text();

    private char[] outChars = new char[1];

    public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
      charMap(key, value, context);
    }

    protected void charMap(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
      String cleanedString = notALetter.matcher(value.toString()).replaceAll("").toLowerCase();

      for (int i = 0; i < cleanedString.length(); i++) {
        char charAtLoc = cleanedString.charAt(i);
        outChars[0] = charAtLoc;
        word.set(new String(outChars));
        context.write(word, one);        
      }
    }

    protected void wordMap(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
      String line = value.toString();
      StringTokenizer tokenizer = new StringTokenizer(line);
      while (tokenizer.hasMoreTokens()) {
        // String cleanedString = tokenizer.nextToken();
        String cleanedString = notALetter.matcher(tokenizer.nextToken()).replaceAll("").toLowerCase();
        if (cleanedString.length() > 0) {
          word.set(cleanedString);
          context.write(word, one);
        }
      }
    }
  }

  public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> {
    private IntWritable result = new IntWritable();

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

  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    Job job = new Job(conf, "mycounter");
    job.setJarByClass(MyCounter.class);

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

    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
  
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
  
    job.waitForCompletion(true);
  }
}

2_how_i_run_it.txt

# initial setup
curl http://mirrors.xmission.com/gutenberg/1/3/4/1342/1342.txt | hadoop fs -put - /gutenberg/1342.txt

# run these when I change it
javac -classpath /usr/local/Cellar/hadoop/1.0.4/libexec/hadoop-core-1.0.4.jar -d class src/MyCounter.java && cd class && jar cvf ../mycounter.jar * && cd -

hadoop fs -rmr /gutenberg-word-out && hadoop jar mycounter.jar MyCounter /gutenberg /gutenberg-word-out