MapReduce Features - Hadoop: The Definitive Guide - page 298

public class MissingTemperatureFields extends Configured implements
Tool {
@Override
public int run ( String [] args ) throws Exception {
if ( args . length != 1 ) {
JobBuilder . printUsage ( this , "<job ID>" );
return - 1 ;
}
String jobID = args [ 0 ];
Cluster cluster = new Cluster ( getConf ());
Job job = cluster . getJob ( JobID . forName ( jobID ));
if ( job == null ) {
System . err . printf ( "No job with ID %s found.\n" , jobID );
return - 1 ;
}
if (! job . isComplete ()) {
System . err . printf ( "Job %s is not complete.\n" , jobID );
return - 1 ;
}
Counters counters = job . getCounters ();
long missing = counters . findCounter (
MaxTemperatureWithCounters . Temperature . MISSING ). getValue ();
long total =
counters . findCounter ( TaskCounter . MAP_INPUT_RECORDS ). getValue ();
System . out . printf ( "Records with missing temperature fields:
%.2f%%\n" ,
100.0 * missing / total );
return 0 ;
}
public static void main ( String [] args ) throws Exception {
int exitCode = ToolRunner . run ( new MissingTemperatureFields (), args );
System . exit ( exitCode );
}
}
First we retrieve a Job object from a Cluster by calling the getJob() method with
the job ID. We check whether there is actually a job with the given ID by checking if it is
null . There may not be, either because the ID was incorrectly specified or because the
job is no longer in the job history.