Home‎ > ‎

Hadoop: How to count number of lines in a file using Map Reduce framework

The following program counts the number of lines in the input file/directory and places the results in the output directory
 
1. Create file LineCount.java and paste the following code
 
package org.myorg;
import java.io.IOException;
import java.util.*;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.conf.*;
import org.apache.hadoop.io.*;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.*;
public class LineCount {
        public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
                private final static IntWritable one = new IntWritable(1);
                private Text word = new Text("Total Lines");
                public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
                        output.collect(word, one);
                }
   }
   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 Exception {
     JobConf conf = new JobConf(LineCount.class);
     conf.setJobName("LineCount");
     conf.setOutputKeyClass(Text.class);
     conf.setOutputValueClass(IntWritable.class);
     conf.setMapperClass(Map.class);
     conf.setCombinerClass(Reduce.class);
     conf.setReducerClass(Reduce.class);
     conf.setInputFormat(TextInputFormat.class);
     conf.setOutputFormat(TextOutputFormat.class);
     FileInputFormat.setInputPaths(conf, new Path(args[0]));
     FileOutputFormat.setOutputPath(conf, new Path(args[1]));
     JobClient.runJob(conf);
   }
}
 
2. Compile, Create Jar and Run
 
javac -classpath hadoop-0.20.1-dev-core.jar -d LineCount/ LineCount.java
jar -cvf LineCount.jar -C LineCount/ .
hadoop jar LineCount.jar org.myorg.LineCount in out
 
Comments