Hadoop NumberFormatException on string ” “

20.2 on windows with cygwin (for a class project). I’m not sure why but I cannot run any jobs — I just get a NumberFormatException. I’m thinking its an issue with my machine because I cannot even run the example wordcount. I am simply running the program through vscode using the args p5_in/wordcount.txt out.

21/04/22 20:55:29 INFO jvm.JvmMetrics: Initializing JVM Metrics with processName=JobTracker, sessionId=
21/04/22 20:55:29 WARN mapred.JobClient: No job jar file set.  User classes may not be found. See JobConf(Class) or JobConf#setJar(String).
21/04/22 20:55:29 INFO input.FileInputFormat: Total input paths to process : 1
21/04/22 20:55:29 INFO input.FileInputFormat: Total input paths to process : 1
21/04/22 20:55:30 INFO mapred.MapTask: io.sort.mb = 100
21/04/22 20:55:30 INFO mapred.MapTask: data buffer = 79691776/99614720
21/04/22 20:55:30 INFO mapred.MapTask: record buffer = 262144/327680
21/04/22 20:55:30 INFO mapred.MapTask: Starting flush of map output
21/04/22 20:55:30 WARN mapred.LocalJobRunner: job_local_0001
java.lang.NumberFormatException: For input string: " "

Here is my code, copied directly from https://hadoop.apache.org/docs/current/hadoop-mapreduce-client/hadoop-mapreduce-client-core/MapReduceTutorial.html

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;

public class WordCount {

  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 {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one);
      }
    }
  }

  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();
    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

Answer

Turns out WSL was conflicting with something. I disabled WSL and it ran fine.