/**
* Create a map-only Hadoop Job out of the passed in parameters. Does not set the
* Job name.
*
* @see #getCustomJobName(String, org.apache.hadoop.mapreduce.JobContext, Class, Class)
*/
@SuppressWarnings("rawtypes")
public static Job prepareJob(Path inputPath,
Path outputPath,
Class<? extends InputFormat> inputFormat,
Class<? extends Mapper> mapper,
Class<? extends Writable> mapperKey,
Class<? extends Writable> mapperValue,
Class<? extends OutputFormat> outputFormat, Configuration conf) throws IOException {
//Job job = new Job(new Configuration(conf));
Job job = Job.getInstance(conf);
Configuration jobConf = job.getConfiguration();
if (mapper.equals(Mapper.class)) {
throw new IllegalStateException("Can't figure out the user class jar file from mapper/reducer");
}
job.setJarByClass(mapper);
job.setInputFormatClass(inputFormat);
jobConf.set("mapred.input.dir", inputPath.toString());
job.setMapperClass(mapper);
job.setMapOutputKeyClass(mapperKey);
job.setMapOutputValueClass(mapperValue);
job.setOutputKeyClass(mapperKey);
job.setOutputValueClass(mapperValue);
jobConf.setBoolean("mapred.compress.map.output", true);
job.setNumReduceTasks(0);
job.setOutputFormatClass(outputFormat);
jobConf.set("mapred.output.dir", outputPath.toString());
return job;
}
public static void main(String[] args) throws Exception {
final String NAME_NODE = "hdfs://sandbox.hortonworks.com:8020";
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
job.setJarByClass(WordCount.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputValueClass(NullWritable.class);
if (args.length > 2) {
job.setNumReduceTasks(Integer.parseInt(args[2]));
}
job.setMapperClass(CountMapper.class);
job.setReducerClass(CountReducer.class);
job.setJarByClass(WordCount.class);
job.setNumReduceTasks(1);
FileInputFormat.addInputPath(job, new Path(args[0] + "data/plot_summaries.txt"));
FileSystem fs = FileSystem.get(conf);
// handle (e.g. delete) existing output path
Path outputDestination = new Path(args[0] + args[1]);
if (fs.exists(outputDestination)) {
fs.delete(outputDestination, true);
}
// set output path & start job1
FileOutputFormat.setOutputPath(job, outputDestination);
int jobCompletionStatus = job.waitForCompletion(true) ? 0 : 1;
}