Vowel and Consonant map reduce program in Hadoop

Vowel and Consonant map reduce program in Hadoop

  6:51 AM    ssaikgame

---

The following program is to finds number of vowels and Consonants in the given input file, for example, 

my input file is "vandc.txt" Contains::

Hello there!
i love you.

it contains 1 vowel ("i") and 4 consonants ("Hello, There!, love, you."), So the output would be vowels 1
consonants 4

How to execute the program, please click here.

package tut.ssaik.com.vandc;

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

import org.apache.hadoop.conf.Configuration;
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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class vowel {
 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 map(Object key, Text value, Context context) throws IOException, InterruptedException {
   String line = value.toString();

   String[] letters = line.split(" ");

   for (String letter : letters) {
    if (isVowel(letter))
     context.write(new Text("Vowel"), new IntWritable(1));
    else
     context.write(new Text("Consonant"), new IntWritable(1));
   }
  }

  public boolean isVowel(String line) {
   char wr = line.charAt(0);
   if (wr == 'a' || wr == 'e' || wr == 'i' || wr == 'o' || wr == 'u') {
    return true;
   } else {
    return false;
   }
  }
 }

 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 {
  Configuration conf = new Configuration();
  String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
  if (otherArgs.length != 2) {
   System.err.println("Usage: WordCount <in> <out>");
   System.exit(2);
  }
  Job job = new Job(conf, "word count");
  job.setJarByClass(vowel.class);
  job.setMapperClass(TokenizerMapper.class);
  job.setCombinerClass(IntSumReducer.class);
  // filesystem fs = filesystem.get(conf);
  job.setReducerClass(IntSumReducer.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(IntWritable.class);
  FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
  FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
  System.exit(job.waitForCompletion(true) ? 0 : 1);
  // if(fs.exists(outputDir))
  // fs.delete(outputDir,true);

 }
}

**Comment below for encourage.**
post by SsaiK