How can i fix InputBootStrapper error in eclipse for runnig Hadoop program?

Question

How can i fix it ? This code is Hadoop WordCount example in JAVA. I have added the external JARs and this is not a compile time issue, When i have tried o run the program this is happening. The input and out put arguments are set. All the mangers are up and running.

Hadoop version 2.9.0

Java version 1.8.0

Eclipse Oxygen

OS Ubuntu 14.04 64bit

What could be the issue?

wordcount.java

package mapreduce;

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 = Job.getInstance(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);
}
}

Console(Error)

 Exception in thread "main" java.lang.NoClassDefFoundError: com/ctc/wstx/io/InputBootstrapper
    at mapreduce.wordcount.main(wordcount.java:51)
 Caused by: java.lang.ClassNotFoundException:  com.ctc.wstx.io.InputBootstrapper
    at java.net.URLClassLoader.findClass(URLClassLoader.java:381)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
    at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:349)
    at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
    ... 1 more

Answer 1

For me missing jar was this: hadoop-client-runtime.jar<\/code> . Adding that additional dependency from Maven solved issue.

libraryDependencies ++= Seq(
  "org.apache.hadoop" % "hadoop-client-api" % "3.3.1",
  "commons-logging" % "commons-logging" %  "1.2",
  "org.slf4j" % "slf4j-api" % "1.7.35",
  "org.apache.hadoop" % "hadoop-client-runtime" % "3.3.1"
)