in mapper combining hadoop program code example

Example: hadoop in mapper combiner

public static class Map extends Mapper<Object, Text, Text, IntWritable> {
    Map count = new HashMap<Integer, Integer>();

    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        StringTokenizer itr = new StringTokenizer(value.toString());

        while (itr.hasMoreTokens()) {
            String token = itr.nextToken();
            int length = token.length();

            if(count.containsKey(length)) {
                int sum = (int) count.get(length) + 1;
                count.put(length, sum);
            }
            else {
                count.put(length, 1);
            }
        }
    }

    public void cleanup(Context context) throws IOException, InterruptedException {
        Iterator<Map.Entry<Integer, Integer>> temp = count.entrySet().iterator();

        while(temp.hasNext()) {
            Map.Entry<Integer, Integer> entry = temp.next();
            String keyVal = entry.getKey()+"";
            Integer countVal = entry.getValue();

            context.write(new Text(keyVal), new IntWritable(countVal));
        }
    }
}

Tags:

Java Example