Java Job.setJarByClass方法代碼示例

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public static void run(Configuration conf, Path inputPath, Path output, double params) throws IOException, ClassNotFoundException, InterruptedException {
    String jobName = "calculating parameter";
    conf.set("params",String.valueOf(params));

    Job job = new Job(conf, jobName);
    job.setMapOutputKeyClass(IntWritable.class);
    job.setMapOutputValueClass(indexToCountWritable.class);
    job.setOutputKeyClass(twoDimensionIndexWritable.class);
    job.setOutputValueClass(Text.class);

    job.setInputFormatClass(SequenceFileInputFormat.class);
    job.setOutputFormatClass(SequenceFileOutputFormat.class);

    job.setMapperClass(CalParamsMapper.class);
    job.setReducerClass(CalParamsReducer.class);

    FileInputFormat.addInputPath(job, inputPath);
    FileOutputFormat.setOutputPath(job,output);

    job.setJarByClass(LDADriver.class);
    if (!job.waitForCompletion(true)) {
        throw new InterruptedException("calculating parameter failed");
    }
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
private Job doVerify(Configuration conf, HTableDescriptor htd, String... auths)
    throws IOException, InterruptedException, ClassNotFoundException {
  Path outputDir = getTestDir(TEST_NAME, "verify-output");
  Job job = new Job(conf);
  job.setJarByClass(this.getClass());
  job.setJobName(TEST_NAME + " Verification for " + htd.getTableName());
  setJobScannerConf(job);
  Scan scan = new Scan();
  scan.setAuthorizations(new Authorizations(auths));
  TableMapReduceUtil.initTableMapperJob(htd.getTableName().getNameAsString(), scan,
      VerifyMapper.class, NullWritable.class, NullWritable.class, job);
  TableMapReduceUtil.addDependencyJars(job.getConfiguration(), AbstractHBaseTool.class);
  int scannerCaching = conf.getInt("verify.scannercaching", SCANNER_CACHING);
  TableMapReduceUtil.setScannerCaching(job, scannerCaching);
  job.setNumReduceTasks(0);
  FileOutputFormat.setOutputPath(job, outputDir);
  assertTrue(job.waitForCompletion(true));
  return job;
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
protected Job doLoad(Configuration conf, HTableDescriptor htd) throws Exception {
  Path outputDir = getTestDir(TEST_NAME, "load-output");
  LOG.info("Load output dir: " + outputDir);

  NMapInputFormat.setNumMapTasks(conf, conf.getInt(NUM_MAP_TASKS_KEY, NUM_MAP_TASKS_DEFAULT));
  conf.set(TABLE_NAME_KEY, htd.getTableName().getNameAsString());

  Job job = Job.getInstance(conf);
  job.setJobName(TEST_NAME + " Load for " + htd.getTableName());
  job.setJarByClass(this.getClass());
  setMapperClass(job);
  job.setInputFormatClass(NMapInputFormat.class);
  job.setNumReduceTasks(0);
  setJobScannerConf(job);
  FileOutputFormat.setOutputPath(job, outputDir);

  TableMapReduceUtil.addDependencyJars(job);

  TableMapReduceUtil.addDependencyJars(job.getConfiguration(), AbstractHBaseTool.class);
  TableMapReduceUtil.initCredentials(job);
  assertTrue(job.waitForCompletion(true));
  return job;
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
/**
 * To ensure nothing broken after we removed normalization 
 * from the MRAM side
 * @throws Exception
 */
@Test
public void testJobWithNonNormalizedCapabilities() throws Exception {
  if (!(new File(MiniMRYarnCluster.APPJAR)).exists()) {
    LOG.info("MRAppJar " + MiniMRYarnCluster.APPJAR
              + " not found. Not running test.");
    return;
  }

  JobConf jobConf = new JobConf(mrCluster.getConfig());
  jobConf.setInt("mapreduce.map.memory.mb", 700);
  jobConf.setInt("mapred.reduce.memory.mb", 1500);

  SleepJob sleepJob = new SleepJob();
  sleepJob.setConf(jobConf);
  Job job = sleepJob.createJob(3, 2, 1000, 1, 500, 1);
  job.setJarByClass(SleepJob.class);
  job.addFileToClassPath(APP_JAR); // The AppMaster jar itself.
  job.submit();
  boolean completed = job.waitForCompletion(true);
  Assert.assertTrue("Job should be completed", completed);
  Assert.assertEquals("Job should be finished successfully", 
                  JobStatus.State.SUCCEEDED, job.getJobState());
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
/** Create a job */
private Job createJob(String name, Summation sigma) throws IOException {
  final Job job = Job.getInstance(getConf(), parameters.remoteDir + "/" +
                                  name);
  final Configuration jobconf = job.getConfiguration();
  job.setJarByClass(DistSum.class);
  jobconf.setInt(N_PARTS, parameters.nParts);
  SummationWritable.write(sigma, DistSum.class, jobconf);

  // disable task timeout
  jobconf.setLong(MRJobConfig.TASK_TIMEOUT, 0);
  // do not use speculative execution
  jobconf.setBoolean(MRJobConfig.MAP_SPECULATIVE, false);
  jobconf.setBoolean(MRJobConfig.REDUCE_SPECULATIVE, false);

  return job; 
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();
        conf.setFloat("beta", Float.parseFloat(args[3]));
        Job job = Job.getInstance(conf);
        job.setJarByClass(UnitMultiplication.class);

        ChainMapper.addMapper(job, TransitionMapper.class, Object.class, Text.class, Text.class, Text.class, conf);
        ChainMapper.addMapper(job, PRMapper.class, Object.class, Text.class, Text.class, Text.class, conf);

        job.setReducerClass(MultiplicationReducer.class);

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

        MultipleInputs.addInputPath(job, new Path(args[0]), TextInputFormat.class, TransitionMapper.class);
        MultipleInputs.addInputPath(job, new Path(args[1]), TextInputFormat.class, PRMapper.class);

        FileOutputFormat.setOutputPath(job, new Path(args[2]));
        job.waitForCompletion(true);
    }
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public static void main(String [] args) throws Exception
{
  Path outDir = new Path("output");
  Configuration conf = new Configuration();
  Job job = Job.getInstance(conf, "user name check"); 
	
	
  job.setJarByClass(UserNamePermission.class);
  job.setMapperClass(UserNamePermission.UserNameMapper.class);
  job.setCombinerClass(UserNamePermission.UserNameReducer.class);
  job.setMapOutputKeyClass(Text.class);
  job.setMapOutputValueClass(Text.class);
  job.setReducerClass(UserNamePermission.UserNameReducer.class);
  job.setNumReduceTasks(1);
    
  job.setInputFormatClass(TextInputFormat.class);
  TextInputFormat.addInputPath(job, new Path("input"));
  FileOutputFormat.setOutputPath(job, outDir);
    
  System.exit(job.waitForCompletion(true) ? 0 : 1);
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public static void runJob(Configuration conf, Path inputPath, Path output) throws IOException, ClassNotFoundException, InterruptedException {

        Job job = new Job(conf, "Input Drive running input:"+inputPath);
        log.info("start running InputDriver");
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(indexToWordWritable.class);
        job.setOutputKeyClass(twoDimensionIndexWritable.class);
        job.setOutputValueClass(Text.class);

        job.setMapperClass(InputMapper.class);
        job.setReducerClass(InputReducer.class);
        job.setNumReduceTasks(1);
        job.setOutputFormatClass(SequenceFileOutputFormat.class);
        job.setJarByClass(InputDriver.class);

        FileInputFormat.addInputPath(job, inputPath);
        FileOutputFormat.setOutputPath(job, output);

        boolean succeeded = job.waitForCompletion(true);
        if (!succeeded) {
            throw new IllegalStateException("Job failed!");
        }

    }
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
@Override
public int run(String[] args) throws Exception {
  if (args.length != 2) {
    System.err.println("Usage: wordstddev <in> <out>");
    return 0;
  }

  Configuration conf = getConf();

  Job job = Job.getInstance(conf, "word stddev");
  job.setJarByClass(WordStandardDeviation.class);
  job.setMapperClass(WordStandardDeviationMapper.class);
  job.setCombinerClass(WordStandardDeviationReducer.class);
  job.setReducerClass(WordStandardDeviationReducer.class);
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(LongWritable.class);
  FileInputFormat.addInputPath(job, new Path(args[0]));
  Path outputpath = new Path(args[1]);
  FileOutputFormat.setOutputPath(job, outputpath);
  boolean result = job.waitForCompletion(true);

  // read output and calculate standard deviation
  stddev = readAndCalcStdDev(outputpath, conf);

  return (result ? 0 : 1);
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
/**
 * Creates and runs an MR job
 *
 * @param conf
 * @throws IOException
 * @throws InterruptedException
 * @throws ClassNotFoundException
 */
public void createAndRunJob(Configuration conf) throws IOException,
    InterruptedException, ClassNotFoundException {
  Job job = Job.getInstance(conf);
  job.setJarByClass(TestLineRecordReaderJobs.class);
  job.setMapperClass(Mapper.class);
  job.setReducerClass(Reducer.class);
  FileInputFormat.addInputPath(job, inputDir);
  FileOutputFormat.setOutputPath(job, outputDir);
  job.waitForCompletion(true);
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
/** Create and setup a job */
private static Job createJob(String name, Configuration conf
    ) throws IOException {
  final Job job = Job.getInstance(conf, NAME + "_" + name);
  final Configuration jobconf = job.getConfiguration();
  job.setJarByClass(BaileyBorweinPlouffe.class);

  // setup mapper
  job.setMapperClass(BbpMapper.class);
  job.setMapOutputKeyClass(LongWritable.class);
  job.setMapOutputValueClass(BytesWritable.class);

  // setup reducer
  job.setReducerClass(BbpReducer.class);
  job.setOutputKeyClass(LongWritable.class);
  job.setOutputValueClass(BytesWritable.class);
  job.setNumReduceTasks(1);

  // setup input
  job.setInputFormatClass(BbpInputFormat.class);

  // disable task timeout
  jobconf.setLong(MRJobConfig.TASK_TIMEOUT, 0);

  // do not use speculative execution
  jobconf.setBoolean(MRJobConfig.MAP_SPECULATIVE, false);
  jobconf.setBoolean(MRJobConfig.REDUCE_SPECULATIVE, false);
  return job;
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public static void runJob(Path input, Path output, String vectorClassName,Configuration config)
  throws IOException, InterruptedException, ClassNotFoundException {
  Configuration conf = config;
  conf.set("vector.implementation.class.name", vectorClassName);
  Job job = new Job(conf, "Input Driver running over input: " + input);
	 
  job.setOutputKeyClass(Text.class);
  job.setOutputValueClass(VectorWritable.class);
  job.setOutputFormatClass(SequenceFileOutputFormat.class);
  job.setMapperClass(InputMapper.class);   
  job.setNumReduceTasks(0);
  job.setJarByClass(InputDriver.class);
  
  FileInputFormat.addInputPath(job, input);
  FileOutputFormat.setOutputPath(job, output);
  
  job.waitForCompletion(true);
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public static void doTestWithMapReduce(HBaseTestingUtility util, TableName tableName,
    String snapshotName, byte[] startRow, byte[] endRow, Path tableDir, int numRegions,
    int expectedNumSplits, boolean shutdownCluster) throws Exception {

  //create the table and snapshot
  createTableAndSnapshot(util, tableName, snapshotName, startRow, endRow, numRegions);

  if (shutdownCluster) {
    util.shutdownMiniHBaseCluster();
  }

  try {
    // create the job
    Job job = new Job(util.getConfiguration());
    Scan scan = new Scan(startRow, endRow); // limit the scan

    job.setJarByClass(util.getClass());
    TableMapReduceUtil.addDependencyJars(job.getConfiguration(),
      TestTableSnapshotInputFormat.class);

    TableMapReduceUtil.initTableSnapshotMapperJob(snapshotName,
      scan, TestTableSnapshotMapper.class, ImmutableBytesWritable.class,
      NullWritable.class, job, true, tableDir);

    job.setReducerClass(TestTableSnapshotInputFormat.TestTableSnapshotReducer.class);
    job.setNumReduceTasks(1);
    job.setOutputFormatClass(NullOutputFormat.class);

    Assert.assertTrue(job.waitForCompletion(true));
  } finally {
    if (!shutdownCluster) {
      util.getHBaseAdmin().deleteSnapshot(snapshotName);
      util.deleteTable(tableName);
    }
  }
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
private boolean analyze(final String inputFilePath,
                           final String outputFilePath,
                           final Long startTime) throws Exception {
    Configuration conf = new Configuration();
    conf.setLong(Holistic.START_TIME, startTime);
    conf.setLong(Holistic.EXECUTE_TIME, executeHourTime);

    Job jobAnalyze = Job.getInstance(conf, "analyze");

    jobAnalyze.setJarByClass(Holistic.class);

    MultipleOutputs.addNamedOutput(jobAnalyze, MapKeyConfig.NEW_OLD_CUSTOMER,
            TextOutputFormat.class, KeyWrapper.class, Text.class);
    MultipleOutputs.addNamedOutput(jobAnalyze, MapKeyConfig.CUSTOMER_FLOW_KEY,
            TextOutputFormat.class, KeyWrapper.class, Text.class);
    MultipleOutputs.addNamedOutput(jobAnalyze, MapKeyConfig.CYCLE,
            TextOutputFormat.class, KeyWrapper.class, Text.class);
    MultipleOutputs.addNamedOutput(jobAnalyze, MapKeyConfig.IN_STORE_HOUR,
            TextOutputFormat.class, KeyWrapper.class, Text.class);

    jobAnalyze.setMapperClass(AnalysisMapper.class);
    jobAnalyze.setReducerClass(AnalysisReducer.class);
    jobAnalyze.setCombinerClass(AnalysisCombiner.class);

    jobAnalyze.setOutputKeyClass(LongWritable.class);
    jobAnalyze.setOutputValueClass(Text.class);

    jobAnalyze.setMapOutputKeyClass(KeyWrapper.class);
    jobAnalyze.setMapOutputValueClass(ValueWrapper.class);

    FileInputFormat.addInputPath(jobAnalyze, new Path(inputFilePath));
    FileOutputFormat.setOutputPath(jobAnalyze, new Path(outputFilePath));

    return jobAnalyze.waitForCompletion(true) ;
}
 

import org.apache.hadoop.mapreduce.Job; //導入方法依賴的package包/類
public void run() throws IOException, ClassNotFoundException, InterruptedException {

        Job job = Job.getInstance(configuration, "com.romanysik.util.Transposer");

        job.setJarByClass(MRNMF.class);

        FileInputFormat.addInputPath(job, new Path(inputPath));
        FileOutputFormat.setOutputPath(job, new Path(outputPath));

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);

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

        job.setMapperClass(TMapper.class);
        job.setReducerClass(TReducer.class);

        job.waitForCompletion(true);
    }