Skip to content

Instantly share code, notes, and snippets.

@ngvinay
Forked from amita-shukla/FileMapperDriver.java
Created February 2, 2019 19:16
Show Gist options
  • Select an option

  • Save ngvinay/2aa60f66f6c28be4fe6aa7620d7f59f7 to your computer and use it in GitHub Desktop.

Select an option

Save ngvinay/2aa60f66f6c28be4fe6aa7620d7f59f7 to your computer and use it in GitHub Desktop.
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hive.ql.io.orc.OrcNewOutputFormat;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class FileMapperDriver extends Configured implements Tool{
public static void main(String[] args) throws Exception {
ToolRunner.run(new FileMapperDriver(), args);
}
@Override
public int run(String[] args) throws Exception {
Configuration conf = this.getConf();
Job job = Job.getInstance(conf);
job.setJarByClass(FileMapperDriver.class);
job.setMapperClass(FileMapper.class);
job.setNumReduceTasks(0);
job.setInputFormatClass(TextInputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
job.setOutputFormatClass(OrcNewOutputFormat.class);
OrcNewOutputFormat.setOutputPath(job, new Path(args[1]));
job.setOutputKeyClass(NullWritable.class);
job.setOutputValueClass(Writable.class);
job.waitForCompletion(true);
return 0;
}
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment