Java Code Examples for org.apache.hadoop.mapred.JobConf#setMapOutputKeyClass()

public void delete(String crawldb, String solrUrl, boolean noCommit) throws IOException {
  SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
  long start = System.currentTimeMillis();
  LOG.info("SolrClean: starting at " + sdf.format(start));

  JobConf job = new NutchJob(getConf());

  FileInputFormat.addInputPath(job, new Path(crawldb, CrawlDb.CURRENT_NAME));
  job.setBoolean("noCommit", noCommit);
  job.set(SolrConstants.SERVER_URL, solrUrl);
  job.setInputFormat(SequenceFileInputFormat.class);
  job.setOutputFormat(NullOutputFormat.class);
  job.setMapOutputKeyClass(ByteWritable.class);
  job.setMapOutputValueClass(Text.class);
  job.setMapperClass(DBFilter.class);
  job.setReducerClass(SolrDeleter.class);

  JobClient.runJob(job);

  long end = System.currentTimeMillis();
  LOG.info("SolrClean: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end));
}
 

private static JobConf createJobConf(Configuration conf, boolean useFastCopy) {
  Class<? extends InputFormat> inputFormat =
    (useFastCopy) ? FastCopyInputFormat.class : CopyInputFormat.class;
  JobConf jobconf = new JobConf(conf, DistCp.class);
  jobconf.setJobName(NAME);

  // turn off speculative execution, because DFS doesn't handle
  // multiple writers to the same file.
  jobconf.setReduceSpeculativeExecution(false);
  jobconf.setMapOutputKeyClass(FilePairComparable.class);
  jobconf.setMapOutputValueClass(Text.class);
  jobconf.setOutputKeyClass(FilePairComparable.class);
  jobconf.setOutputValueClass(Text.class);

  jobconf.setInputFormat(inputFormat);
  jobconf.setMapperClass(CopyFilesTask.class);
  jobconf.setReducerClass(CopyFilesTask.class);
    
  jobconf.setNumReduceTasks(conf.getInt(MAX_REDUCE_LABEL, 1));
  // Prevent the reducer from starting until all maps are done.
  jobconf.setInt("mapred.job.rushreduce.reduce.threshold", 0);
  jobconf.setFloat("mapred.reduce.slowstart.completed.maps", 1.0f);
  return jobconf;
}
 

public int run(final String[] args) throws Exception {

        log.info("run starting");

        final Configuration conf = getConf();

        JobConf job = new JobConf(conf, ExternalJoin.class);
        job.setJobName("AerospikeExternalJoin");

        job.setMapperClass(Map.class);
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(LongWritable.class);
        // job.setCombinerClass(Reduce.class);  // Reduce changes format.
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Session.class);

        job.setOutputFormat(SessionOutputFormat.class);

        for (int ii = 0; ii < args.length; ++ii)
            FileInputFormat.addInputPath(job, new Path(args[ii]));

        JobClient.runJob(job);

        log.info("finished");
        return 0;
    }
 

public int run(final String[] args) throws Exception {

        log.info("run starting");

        final Configuration conf = getConf();

        JobConf job = new JobConf(conf, GenerateProfiles.class);
        job.setJobName("AerospikeGenerateProfiles");

        job.setMapperClass(Map.class);
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(IntWritable.class);
        // job.setCombinerClass(Reduce.class);  // Reduce changes format.
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Profile.class);

        job.setOutputFormat(ProfileOutputFormat.class);

        for (int ii = 0; ii < args.length; ++ii)
            FileInputFormat.addInputPath(job, new Path(args[ii]));

        JobClient.runJob(job);

        log.info("finished");
        return 0;
    }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("Busy Airport Count");

    Path outputPath = new Path(args[0]);
    String hdfsHomeDir = args[1];
    String tableName = args[2];

    outputPath.getFileSystem(conf).delete(outputPath, true);

    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);

    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(SampleMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(IntWritable.class);

    conf.setReducerClass(SampleReducer.class);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    FileOutputFormat.setOutputPath(conf, outputPath);

    JobClient.runJob(conf);
    return 0;
  }
 

public JobConf setupJobConf(int numMapper, int numReducer, 
                              long mapSleepTime, int mapSleepCount, 
                              long reduceSleepTime, int reduceSleepCount,
                              boolean doSpeculation, List<String> slowMaps,
                              List<String> slowReduces, int slowRatio,
                              int countersPerTask, List<String> hosts,
                              int hostsPerSplit, boolean setup) {
  
  JobConf job = new JobConf(getConf(), SleepJob.class);
  job.setNumMapTasks(numMapper);
  job.setNumReduceTasks(numReducer);
  job.setMapperClass(SleepJob.class);
  job.setMapOutputKeyClass(IntWritable.class);
  job.setMapOutputValueClass(NullWritable.class);
  job.setReducerClass(SleepJob.class);
  job.setOutputFormat(NullOutputFormat.class);
  job.setJobSetupCleanupNeeded(setup);
  job.setInputFormat(SleepInputFormat.class);
  job.setPartitionerClass(SleepJob.class);
  job.setJobName("Sleep job");
  FileInputFormat.addInputPath(job, new Path("ignored"));
  job.setLong("sleep.job.map.sleep.time", mapSleepTime);
  job.setLong("sleep.job.reduce.sleep.time", reduceSleepTime);
  job.setInt("sleep.job.map.sleep.count", mapSleepCount);
  job.setInt("sleep.job.reduce.sleep.count", reduceSleepCount);
  job.setSpeculativeExecution(doSpeculation);
  job.setInt(SLOW_RATIO, slowRatio);
  job.setStrings(SLOW_MAPS, slowMaps.toArray(new String[slowMaps.size()]));
  job.setStrings(SLOW_REDUCES, slowMaps.toArray(new String[slowReduces.size()]));
  job.setInt("sleep.job.counters.per.task", countersPerTask);
  job.setStrings(HOSTS_FOR_LOCALITY, hosts.toArray(new String[hosts.size()]));
  job.setInt(HOSTS_PER_SPLIT, hostsPerSplit);
  return job;
}
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("Busy Airport Count");

    Path outputPath = new Path(args[0]);
    Path intermediateOutputPath = new Path(args[0] + "_int");
    String hdfsHomeDir = args[1];
    String tableName = args[2];

    outputPath.getFileSystem(conf).delete(outputPath, true);
    intermediateOutputPath.getFileSystem(conf).delete(intermediateOutputPath, true);

    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);

    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(SampleMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(IntWritable.class);

    conf.setReducerClass(SampleReducer.class);
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    FileOutputFormat.setOutputPath(conf, intermediateOutputPath);

    int rc = JobClient.runJob(conf).isSuccessful() ? 0 : 1;
    if (rc == 0) {
      JobConf topConf = new JobConf(getConf());
      topConf.setJobName("Top Busy Airport");

      // Only run a single reducer
      topConf.setNumReduceTasks(1);

      FileInputFormat.setInputPaths(topConf, intermediateOutputPath);

      topConf.setInputFormat(TextInputFormat.class);
      topConf.setMapperClass(TopBusyAirportMapper.class);
      topConf.setMapOutputKeyClass(Text.class);
      topConf.setMapOutputValueClass(StringIntPair.class);

      topConf.setReducerClass(TopBusyAirportReducer.class);
      topConf.setOutputKeyClass(Text.class);
      topConf.setOutputValueClass(IntWritable.class);

      FileOutputFormat.setOutputPath(topConf, outputPath);

      rc = JobClient.runJob(topConf).isSuccessful() ? 0 : 1;
    }
    return rc;
  }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("TradesHdfsDataVerifier");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("TradesHdfsDataVerifier.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(TradesRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, tableName + "_HDFS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(TradeOutputObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

public static JobConf createDataJoinJob(String args[]) throws IOException {

    String inputDir = args[0];
    String outputDir = args[1];
    Class inputFormat = SequenceFileInputFormat.class;
    if (args[2].compareToIgnoreCase("text") != 0) {
      System.out.println("Using SequenceFileInputFormat: " + args[2]);
    } else {
      System.out.println("Using TextInputFormat: " + args[2]);
      inputFormat = TextInputFormat.class;
    }
    int numOfReducers = Integer.parseInt(args[3]);
    Class mapper = getClassByName(args[4]);
    Class reducer = getClassByName(args[5]);
    Class mapoutputValueClass = getClassByName(args[6]);
    Class outputFormat = TextOutputFormat.class;
    Class outputValueClass = Text.class;
    if (args[7].compareToIgnoreCase("text") != 0) {
      System.out.println("Using SequenceFileOutputFormat: " + args[7]);
      outputFormat = SequenceFileOutputFormat.class;
      outputValueClass = getClassByName(args[7]);
    } else {
      System.out.println("Using TextOutputFormat: " + args[7]);
    }
    long maxNumOfValuesPerGroup = 100;
    String jobName = "";
    if (args.length > 8) {
      maxNumOfValuesPerGroup = Long.parseLong(args[8]);
    }
    if (args.length > 9) {
      jobName = args[9];
    }
    Configuration defaults = new Configuration();
    JobConf job = new JobConf(defaults, DataJoinJob.class);
    job.setJobName("DataJoinJob: " + jobName);

    FileSystem fs = FileSystem.get(defaults);
    fs.delete(new Path(outputDir), true);
    FileInputFormat.setInputPaths(job, inputDir);

    job.setInputFormat(inputFormat);

    job.setMapperClass(mapper);
    FileOutputFormat.setOutputPath(job, new Path(outputDir));
    job.setOutputFormat(outputFormat);
    SequenceFileOutputFormat.setOutputCompressionType(job,
            SequenceFile.CompressionType.BLOCK);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(mapoutputValueClass);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(outputValueClass);
    job.setReducerClass(reducer);

    job.setNumMapTasks(1);
    job.setNumReduceTasks(numOfReducers);
    job.setLong("datajoin.maxNumOfValuesPerGroup", maxNumOfValuesPerGroup);
    return job;
  }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("TradeCustomersHdfsDataVerifier");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("TradeCustomersHdfsDataVerifier.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(TradeCustomersRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, tableName + "_HDFS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(TradeCustomerOutputObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("TradeSecurityHdfsDataVerifier");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("TradeSecurityHdfsDataVerifier.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(TradeNetworthRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, tableName +"_HDFS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(TradeNetworthOutputObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("TradeSecurityHdfsDataVerifier");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("TradeSecurityHdfsDataVerifier.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(TradeSecurityRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE,tableName + "_HDFS");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(TradeSecurityOutputObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

JobConf createJob(Configuration conf, Path[] inputPaths, Path outputPath,
    int numMapTasks, Shard[] shards) throws IOException {
  // set the starting generation for each shard
  // when a reduce task fails, a new reduce task
  // has to know where to re-start
  setShardGeneration(conf, shards);

  // iconf.set sets properties in conf
  IndexUpdateConfiguration iconf = new IndexUpdateConfiguration(conf);
  Shard.setIndexShards(iconf, shards);

  // MapTask.MapOutputBuffer uses "io.sort.mb" to decide its max buffer size
  // (max buffer size = 1/2 * "io.sort.mb").
  // Here we half-en "io.sort.mb" because we use the other half memory to
  // build an intermediate form/index in Combiner.
  iconf.setIOSortMB(iconf.getIOSortMB() / 2);

  // create the job configuration
  JobConf jobConf = new JobConf(conf, IndexUpdater.class);
  jobConf.setJobName(this.getClass().getName() + "_"
      + System.currentTimeMillis());

  // provided by application
  FileInputFormat.setInputPaths(jobConf, inputPaths);
  FileOutputFormat.setOutputPath(jobConf, outputPath);

  jobConf.setNumMapTasks(numMapTasks);

  // already set shards
  jobConf.setNumReduceTasks(shards.length);

  jobConf.setInputFormat(iconf.getIndexInputFormatClass());

  Path[] inputs = FileInputFormat.getInputPaths(jobConf);
  StringBuilder buffer = new StringBuilder(inputs[0].toString());
  for (int i = 1; i < inputs.length; i++) {
    buffer.append(",");
    buffer.append(inputs[i].toString());
  }
  LOG.info("mapred.input.dir = " + buffer.toString());
  LOG.info("mapred.output.dir = " + 
           FileOutputFormat.getOutputPath(jobConf).toString());
  LOG.info("mapred.map.tasks = " + jobConf.getNumMapTasks());
  LOG.info("mapred.reduce.tasks = " + jobConf.getNumReduceTasks());
  LOG.info(shards.length + " shards = " + iconf.getIndexShards());
  // better if we don't create the input format instance
  LOG.info("mapred.input.format.class = "
      + jobConf.getInputFormat().getClass().getName());

  // set by the system
  jobConf.setMapOutputKeyClass(IndexUpdateMapper.getMapOutputKeyClass());
  jobConf.setMapOutputValueClass(IndexUpdateMapper.getMapOutputValueClass());
  jobConf.setOutputKeyClass(IndexUpdateReducer.getOutputKeyClass());
  jobConf.setOutputValueClass(IndexUpdateReducer.getOutputValueClass());

  jobConf.setMapperClass(IndexUpdateMapper.class);
  jobConf.setPartitionerClass(IndexUpdatePartitioner.class);
  jobConf.setCombinerClass(IndexUpdateCombiner.class);
  jobConf.setReducerClass(IndexUpdateReducer.class);

  jobConf.setOutputFormat(IndexUpdateOutputFormat.class);

  return jobConf;
}
 

public int run(String[] args) throws Exception {

    // todo@lhughes -- why do we need this?
    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("hdfsMapReduce");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("VerifyHdfsData.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(MyRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, "TRADE.HDFS_CUSTOMERS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(DataObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    // not planning to use this, but I get an NPE without it
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("TradesHdfsDataVerifier");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("TradesHdfsDataVerifier.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(TradesRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, tableName + "_HDFS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(TradeOutputObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

public int run(String[] args) throws Exception {

    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("TradeCustomersHdfsDataVerifier");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("TradeCustomersHdfsDataVerifier.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(TradeCustomersRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, tableName + "_HDFS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(TradeCustomerOutputObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

public int run(String[] args) throws Exception {

    // todo@lhughes -- why do we need this?
    GfxdDataSerializable.initTypes();

    JobConf conf = new JobConf(getConf());
    conf.setJobName("hdfsMapReduce");

    String hdfsHomeDir = args[0];
    String url         = args[1];
    String tableName   = args[2];

    System.out.println("VerifyHdfsData.run() invoked with " 
                       + " hdfsHomeDir = " + hdfsHomeDir 
                       + " url = " + url
                       + " tableName = " + tableName);

    // Job-specific params
    conf.set(RowInputFormat.HOME_DIR, hdfsHomeDir);
    conf.set(RowInputFormat.INPUT_TABLE, tableName);
    conf.setBoolean(RowInputFormat.CHECKPOINT_MODE, false);
    
    conf.setInputFormat(RowInputFormat.class);
    conf.setMapperClass(HdfsDataMapper.class);
    conf.setMapOutputKeyClass(Text.class);
    conf.setMapOutputValueClass(MyRow.class);
    
    conf.setReducerClass(HdfsDataReducer.class);
    conf.set(RowOutputFormat.OUTPUT_TABLE, "TRADE.HDFS_CUSTOMERS");
    //conf.set(GfxdOutputFormat.OUTPUT_SCHEMA, "APP");
    conf.set(RowOutputFormat.OUTPUT_URL, url);
    conf.setOutputFormat(RowOutputFormat.class);
    conf.setOutputKeyClass(Key.class);
    conf.setOutputValueClass(DataObject.class);

    StringBuffer aStr = new StringBuffer();
    aStr.append("HOME_DIR = " + conf.get(RowInputFormat.HOME_DIR) + " ");
    aStr.append("INPUT_TABLE = " + conf.get(RowInputFormat.INPUT_TABLE) + " ");
    aStr.append("OUTPUT_TABLE = " + conf.get(RowOutputFormat.OUTPUT_TABLE) + " ");
    aStr.append("OUTPUT_URL = " + conf.get(RowOutputFormat.OUTPUT_URL) + " ");
    System.out.println("VerifyHdfsData running with the following conf: " + aStr.toString());

    // not planning to use this, but I get an NPE without it
    FileOutputFormat.setOutputPath(conf, new Path("" + System.currentTimeMillis()));
    
    JobClient.runJob(conf);
    return 0;
  }
 

private void scan(Path crawlDb, Path outputPath, String regex, String status,
    boolean text) throws IOException {

  SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
  long start = System.currentTimeMillis();
  LOG.info("CrawlDB scanner: starting at " + sdf.format(start));

  JobConf job = new NutchJob(getConf());

  job.setJobName("Scan : " + crawlDb + " for URLS matching : " + regex);

  job.set("CrawlDBScanner.regex", regex);
  if (status != null) job.set("CrawlDBScanner.status", status);

  FileInputFormat.addInputPath(job, new Path(crawlDb, CrawlDb.CURRENT_NAME));
  job.setInputFormat(SequenceFileInputFormat.class);

  job.setMapperClass(CrawlDBScanner.class);
  job.setReducerClass(CrawlDBScanner.class);

  FileOutputFormat.setOutputPath(job, outputPath);

  // if we want a text dump of the entries
  // in order to check something - better to use the text format and avoid
  // compression
  if (text) {
    job.set("mapred.output.compress", "false");
    job.setOutputFormat(TextOutputFormat.class);
  }
  // otherwise what we will actually create is a mini-crawlDB which can be
  // then used
  // for debugging
  else {
    job.setOutputFormat(MapFileOutputFormat.class);
  }

  job.setMapOutputKeyClass(Text.class);
  job.setMapOutputValueClass(CrawlDatum.class);

  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(CrawlDatum.class);

  try {
    JobClient.runJob(job);
  } catch (IOException e) {
    throw e;
  }

  long end = System.currentTimeMillis();
  LOG.info("CrawlDb scanner: finished at " + sdf.format(end) + ", elapsed: " + TimingUtil.elapsedTime(start, end));
}
 

/**
 * Runs the counter job. The counter job determines the number of links in the
 * webgraph. This is used during analysis.
 * 
 * @param fs The job file system.
 * @param webGraphDb The web graph database to use.
 * 
 * @return The number of nodes in the web graph.
 * @throws IOException If an error occurs while running the counter job.
 */
private int runCounter(FileSystem fs, Path webGraphDb)
  throws IOException {

  // configure the counter job
  Path numLinksPath = new Path(webGraphDb, NUM_NODES);
  Path nodeDb = new Path(webGraphDb, WebGraph.NODE_DIR);
  JobConf counter = new NutchJob(getConf());
  counter.setJobName("LinkRank Counter");
  FileInputFormat.addInputPath(counter, nodeDb);
  FileOutputFormat.setOutputPath(counter, numLinksPath);
  counter.setInputFormat(SequenceFileInputFormat.class);
  counter.setMapperClass(Counter.class);
  counter.setCombinerClass(Counter.class);
  counter.setReducerClass(Counter.class);
  counter.setMapOutputKeyClass(Text.class);
  counter.setMapOutputValueClass(LongWritable.class);
  counter.setOutputKeyClass(Text.class);
  counter.setOutputValueClass(LongWritable.class);
  counter.setNumReduceTasks(1);
  counter.setOutputFormat(TextOutputFormat.class);
  counter.setBoolean("mapreduce.fileoutputcommitter.marksuccessfuljobs", false);

  // run the counter job, outputs to a single reduce task and file
  LOG.info("Starting link counter job");
  try {
    JobClient.runJob(counter);
  }
  catch (IOException e) {
    LOG.error(StringUtils.stringifyException(e));
    throw e;
  }
  LOG.info("Finished link counter job");

  // read the first (and only) line from the file which should be the
  // number of links in the web graph
  LOG.info("Reading numlinks temp file");
  FSDataInputStream readLinks = fs.open(new Path(numLinksPath, "part-00000"));
  BufferedReader buffer = new BufferedReader(new InputStreamReader(readLinks));
  String numLinksLine = buffer.readLine();
  readLinks.close();
  
  // check if there are links to process, if none, webgraph might be empty
  if (numLinksLine == null || numLinksLine.length() == 0) {
    fs.delete(numLinksPath, true);
    throw new IOException("No links to process, is the webgraph empty?");
  }
  
  // delete temp file and convert and return the number of links as an int
  LOG.info("Deleting numlinks temp file");
  fs.delete(numLinksPath, true);
  String numLinks = numLinksLine.split("\\s+")[1];
  return Integer.parseInt(numLinks);
}
 

/**
 * Adds a Mapper class to the chain job's JobConf.
 * <p/>
 * It has to be specified how key and values are passed from one element of
 * the chain to the next, by value or by reference. If a Mapper leverages the
 * assumed semantics that the key and values are not modified by the collector
 * 'by value' must be used. If the Mapper does not expect this semantics, as
 * an optimization to avoid serialization and deserialization 'by reference'
 * can be used.
 * <p/>
 * For the added Mapper the configuration given for it,
 * <code>mapperConf</code>, have precedence over the job's JobConf. This
 * precedence is in effect when the task is running.
 * <p/>
 * IMPORTANT: There is no need to specify the output key/value classes for the
 * ChainMapper, this is done by the addMapper for the last mapper in the chain
 * <p/>
 *
 * @param job              job's JobConf to add the Mapper class.
 * @param klass            the Mapper class to add.
 * @param inputKeyClass    mapper input key class.
 * @param inputValueClass  mapper input value class.
 * @param outputKeyClass   mapper output key class.
 * @param outputValueClass mapper output value class.
 * @param byValue          indicates if key/values should be passed by value
 * to the next Mapper in the chain, if any.
 * @param mapperConf       a JobConf with the configuration for the Mapper
 * class. It is recommended to use a JobConf without default values using the
 * <code>JobConf(boolean loadDefaults)</code> constructor with FALSE.
 */
public static <K1, V1, K2, V2> void addMapper(JobConf job,
                         Class<? extends Mapper<K1, V1, K2, V2>> klass,
                         Class<? extends K1> inputKeyClass,
                         Class<? extends V1> inputValueClass,
                         Class<? extends K2> outputKeyClass,
                         Class<? extends V2> outputValueClass,
                         boolean byValue, JobConf mapperConf) {
  job.setMapperClass(ChainMapper.class);
  job.setMapOutputKeyClass(outputKeyClass);
  job.setMapOutputValueClass(outputValueClass);
  Chain.addMapper(true, job, klass, inputKeyClass, inputValueClass,
                  outputKeyClass, outputValueClass, byValue, mapperConf);
}