File tempDir =
new File("grep-temp-"+
Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
JobConf grepJob = new JobConf();
grepJob.setNumMapTasks(18);
grepJob.setInputDir(new File(args[0]));
grepJob.setMapperClass(RegexMapper.class);
grepJob.set("mapred.mapper.regex", args[2]);
if (args.length == 4)
grepJob.set("mapred.mapper.regex.group", args[3]);
grepJob.setCombinerClass(LongSumReducer.class);
grepJob.setReducerClass(LongSumReducer.class);
grepJob.setNumReduceTasks(6);
grepJob.setOutputDir(tempDir);
grepJob.setOutputFormat(OutputFormats.get("seq"));
grepJob.setOutputKeyClass(UTF8.class);
grepJob.setOutputValueClass(LongWritable.class);
JobClient.runJob(grepJob);
JobConf sortJob = new JobConf();
sortJob.setNumMapTasks(6);
sortJob.setInputDir(tempDir);
sortJob.setInputFormat(InputFormats.get("seq"));
sortJob.setInputKeyClass(UTF8.class);
sortJob.setInputValueClass(LongWritable.class);
sortJob.setMapperClass(InverseMapper.class);
sortJob.setNumReduceTasks(1); // write a single file
sortJob.setOutputDir(new File(args[1]));
sortJob.setOutputKeyComparatorClass // sort by decreasing freq
(LongWritable.DecreasingComparator.class);
JobClient.runJob(sortJob);
new JobClient().getFs().delete(tempDir);