void checkFormat(Job job) throws Exception {
TaskAttemptContext attemptContext =
new TaskAttemptContext(job.getConfiguration(), new TaskAttemptID("123", 0, false, 1, 2));
MyClassMessagePackBase64LineInputFormat format = new MyClassMessagePackBase64LineInputFormat();
FileInputFormat.setInputPaths(job, workDir);
List<InputSplit> splits = format.getSplits(job);
for (int j = 0; j < splits.size(); j++) {
RecordReader<LongWritable, MyClassWritable> reader =
format.createRecordReader(splits.get(j), attemptContext);
reader.initialize(splits.get(j), attemptContext);
int count = 0;
try {
while (reader.nextKeyValue()) {
LongWritable key = reader.getCurrentKey();
MyClassWritable val = reader.getCurrentValue();
MyClass mc = val.get();
assertEquals(mc.v, count);
assertEquals(mc.s, Integer.toString(count));
count++;
}
} finally {
reader.close();
}
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration();
String[] remainArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (remainArgs.length != 2) {
System.err.println("Usage: wordcount <input> <output>");
System.exit(1);
}
Job job = new Job(conf, "wordcount");
job.setJarByClass(WordCount.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.class);
job.setNumReduceTasks(4);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileSystem.get(conf).delete(new Path(remainArgs[1]), true);
FileInputFormat.setInputPaths(job, new Path(remainArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(remainArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
@Override
public int run(String[] arg0) throws Exception {
// config a job and start it
Configuration conf = getConf();
Job job = new Job(conf, "Index construction..");
job.setJarByClass(IndexConstructorDriver.class);
job.setMapperClass(IndexConstructorMapper.class);
job.setReducerClass(IndexConstructorReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(InvertedListWritable.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
// can add the dir by the config
FileSystem fs = FileSystem.get(conf);
String workdir = conf.get("org.joy.crawler.dir", "crawler/");
fs.delete(new Path(workdir + "indexOutput/"), true);
FileInputFormat.addInputPath(job, new Path(workdir + "content/"));
FileOutputFormat.setOutputPath(job, new Path(workdir + "indexOutput/"));
System.out.println(
"indexer starts to work, it begins to construct the index, please wait ...\n");
return job.waitForCompletion(true) ? 0 : 1;
}
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;
}
public int run(String[] args) throws Exception {
Job job = new Job(getConf());
job.setJarByClass(HadoopNBFilter.class);
job.setJobName("hadoopnbfilter");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setNumReduceTasks(Integer.parseInt(args[2]));
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
boolean jobCompleted = job.waitForCompletion(true);
return jobCompleted ? 0 : 1;
}
public int run(String[] args) throws Exception {
Path tempDir = new Path("/user/akhfa/temp");
Configuration conf = new Configuration();
Job job = Job.getInstance(conf, "word count");
job.setJarByClass(AuthorCounter.class);
job.setMapperClass(TokenizerMapper.class);
job.setCombinerClass(IntSumReducer.class);
job.setReducerClass(IntSumReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
FileInputFormat.addInputPath(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, tempDir);
System.exit(job.waitForCompletion(true) ? 0 : 1);
return 0;
}
@Override
public int run(String[] args) throws Exception {
Job job = new Job(getConf());
job.setJarByClass(ElimiateRepeat.class);
job.setJobName("ElimiateRepeat");
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setReducerClass(Reduce.class);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path("file0*"));
FileOutputFormat.setOutputPath(job, new Path("elimiateRepeat"));
boolean success = job.waitForCompletion(true);
return success ? 0 : 1;
}