RowsSeparater.java

package separator;
 
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.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.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
 
public class hadoopSeparator {
 
	public static class Map extends Mapper<LongWritable, Text, Text, Text>
	{
		public void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException
		{
			String fields[] = value.toString().split(",");
			String country = fields[2];
			String sales = fields[3];
 
			if(country.length() == 0)
			{
				context.write(new Text(country), new Text("Missing"));
			}
			else if (!(Character.isDigit(sales.charAt(0))))
			{
				context.write(new Text(country), new Text("Invalid"));
			}
			else
			{
				context.write(new Text(country), new Text(sales));
			}
 
		}
	}
	public static class Reduce extends Reducer<Text, Text, Text, Text>
	{
		public void reduce(Text key, Iterable<Text> values, Context context) throws IOException, InterruptedException
		{
			String total="";
			for (Text details : values)
			{
				total = total+" "+details.toString();
			}
			context.write(key, new Text(total));
		}
	}
 
	public static void main(String args[]) throws Exception
	{
		Configuration conf = new Configuration();
		Job job=Job.getInstance(conf,"hadoopSeparator");
		job.setJarByClass(hadoopSeparator.class);
		job.setMapperClass(Map.class);
		job.setReducerClass(Reduce.class);
 
 
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(IntWritable.class);
 
		job.setInputFormatClass(TextInputFormat.class);
		job.setOutputFormatClass(TextOutputFormat.class);
 
		Path outputPath = new Path(args[1]);
 
		FileInputFormat.addInputPath(job, new Path(args[0]));
		FileOutputFormat.setOutputPath(job, new Path(args[1]));
 
		outputPath.getFileSystem(conf).delete(outputPath,true);
		System.exit(job.waitForCompletion(true)?0:1);
	}
}