WordCount Version Three

package org.myorg;

import java.io.BufferedReader; import java.io.File; import java.io.FileReader; import java.io.IOException; import java.net.URI; import java.util.HashSet; import java.util.Set; import java.util.StringTokenizer; import java.util.regex.Pattern; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.conf.Configured; 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.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.input.FileSplit; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.StringUtils; import org.apache.hadoop.util.Tool; import org.apache.hadoop.util.ToolRunner; import org.apache.log4j.Logger;

public class WordCount extends Configured implements Tool {

private static final Logger LOG = Logger.getLogger(WordCount.class);

public static void main(String[] args) throws Exception { int res = ToolRunner.run(new WordCount(), args); System.exit(res); }

public int run(String[] args) throws Exception { Job job = Job.getInstance(getConf(), "wordcount");

for (int i = 0; i < args.length; i += 1) {
  if ("-skip".equals(args[i])) {
    job.getConfiguration().setBoolean("wordcount.skip.patterns", true);
    i += 1;
    job.addCacheFile(new Path(args[i]).toUri());
    // this demonstrates logging
    LOG.info("Added file to the distributed cache: " + args[i]);
  }
}

job.setJarByClass(this.getClass());
// Use TextInputFormat, the default unless job.setInputFormatClass is used
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);

return job.waitForCompletion(true) ? 0 : 1;

}

public static class Map extends Mapper<LongWritable, Text, Text, IntWritable> { private final static IntWritable one = new IntWritable(1); private Text word = new Text(); private boolean caseSensitive = false; private long numRecords = 0; private String input; private Set patternsToSkip = new HashSet();

private static final Pattern WORD_BOUNDARY = Pattern.compile("\\s*\\b\\s*");

protected void setup(Mapper.Context context)
    throws IOException,
    InterruptedException {
  if (context.getInputSplit() instanceof FileSplit) {
    this.input = ((FileSplit) context.getInputSplit()).getPath().toString();
  } else {
    this.input = context.getInputSplit().toString();
  }

  Configuration config = context.getConfiguration();

  this.caseSensitive = config.getBoolean("wordcount.case.sensitive", false);

  if (config.getBoolean("wordcount.skip.patterns", false)) {
    URI[] localPaths = context.getCacheFiles();
    parseSkipFile(localPaths[0]);
  }
}

private void parseSkipFile(URI patternsURI) {
  LOG.info("Added file to the distributed cache: " + patternsURI);
  try {
    BufferedReader fis = new BufferedReader(new FileReader(new File(patternsURI.getPath()).getName()));

    String pattern;
    while ((pattern = fis.readLine()) != null) {
      patternsToSkip.add(pattern);
    }
  } catch (IOException ioe) {
    System.err.println("Caught exception while parsing the cached file '"
        + patternsURI + "' : " + StringUtils.stringifyException(ioe));
  }
}

public void map(LongWritable offset, Text lineText, Context context)
    throws IOException, InterruptedException {

  String line = lineText.toString();

  if (!caseSensitive) {
    line = line.toLowerCase();
  }
  Text currentWord = new Text();
  for (String word : WORD_BOUNDARY.split(line)) {
	if (word.isEmpty() || patternsToSkip.contains(word)) {
		continue;
	}
		currentWord = new Text(word);
		context.write(currentWord,one);
	}	      
  
  if ((++numRecords % 100) == 0) {
    context.setStatus("Finished processing " + numRecords + " records "
        + "from the input: " + input);
  }
}

}

public static class Reduce extends Reducer<Text, IntWritable, Text, IntWritable> { @Override public void reduce(Text word, Iterable counts, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable count : counts) { sum += count.get(); } context.write(word, new IntWritable(sum)); } } }