source: sample/hadoop-0.16/WordCount2.java @ 24

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.HashSet;
import java.util.Iterator;
import java.util.Set;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.filecache.DistributedCache;
import org.apache.hadoop.fs.FileSystem;
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.util.StringUtils;

public class WordCount2 extends Configured {

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

    static enum Counters {
      INPUT_WORDS
    }

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

    private Text word = new Text();

    private boolean caseSensitive = true;

    private Set<String> patternsToSkip = new HashSet<String>();

    private long numRecords = 0;

    private String inputFile;

    public void configure(JobConf job) {
      caseSensitive = job.getBoolean("wordcount.case.sensitive", true);
      inputFile = job.get("map.input.file");

      if (job.getBoolean("wordcount.skip.patterns", false)) {
        Path[] patternsFiles = new Path[0];
        try {
          patternsFiles = DistributedCache.getLocalCacheFiles(job);
        } catch (IOException ioe) {
          System.err
              .println("Caught exception while getting cached files: "
                  + StringUtils.stringifyException(ioe));
        }
        for (Path patternsFile : patternsFiles) {
          parseSkipFile(patternsFile);
        }
      }
    }

    private void parseSkipFile(Path patternsFile) {
      try {
        BufferedReader fis = new BufferedReader(new FileReader(
            patternsFile.toString()));
        String pattern = null;
        while ((pattern = fis.readLine()) != null) {
          patternsToSkip.add(pattern);
        }
      } catch (IOException ioe) {
        System.err
            .println("Caught exception while parsing the cached file '"
                + patternsFile
                + "' : "
                + StringUtils.stringifyException(ioe));
      }
    }

    public void map(LongWritable key, Text value,
        OutputCollector<Text, IntWritable> output, Reporter reporter)
        throws IOException {
      String line = (caseSensitive) ? value.toString() : value.toString()
          .toLowerCase();

      for (String pattern : patternsToSkip) {
        line = line.replaceAll(pattern, "");
      }

      StringTokenizer tokenizer = new StringTokenizer(line);
      while (tokenizer.hasMoreTokens()) {
        word.set(tokenizer.nextToken());
        output.collect(word, one);
        reporter.incrCounter(Counters.INPUT_WORDS, 1);
      }

      if ((++numRecords % 100) == 0) {
        reporter.setStatus("Finished processing " + numRecords
            + " records " + "from the input file: " + inputFile);
      }
    }
  }

  public static class Reduce extends MapReduceBase implements
      Reducer<Text, IntWritable, Text, IntWritable> {
    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 IOException {
    String filename = "/user/waue/input/";
    String outputPath = "sample-counts";
    int mapTasks = 20;
    int reduceTasks = 1;

    JobConf conf = new JobConf(WordCount2.class);
    conf.setJobName("wordcount");

    conf.setNumMapTasks(mapTasks);
    conf.setNumReduceTasks(reduceTasks);

//    conf.setInputPath(new Path(filename));
    FileInputFormat.setInputPaths(conf,new Path(filename));
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);
    
//    conf.setOutputPath(new Path(outputPath));
    FileOutputFormat.setOutputPath( conf, new Path(filename));


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

    // Delete the output directory if it exists already
    Path outputDir = new Path(outputPath);
    FileSystem.get(conf).delete(outputDir,true);
    JobClient.runJob(conf);
  }
}