Example usage for org.apache.hadoop.mapreduce Job setJarByClass

List of usage examples for org.apache.hadoop.mapreduce Job setJarByClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapreduce.*
  5. Job
  6. setJarByClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapreduce Job setJarByClass.

Prototype

public void setJarByClass(Class<?> cls)

Source Link

Document

Set the Jar by finding where a given class came from.

Usage

From source file:com.cotdp.hadoop.ZipFileTest.java

License:Apache License

/**
 * This test refers to a corrupt (truncated) ZIP file, upon reaching the corruption
 * the Job will fail and no output will be written through the Reducer.
 * /*from  w w  w.  java2s  .  co  m*/
 * Expected result: failure
 * 
 * @throws IOException 
 * @throws InterruptedException 
 * @throws ClassNotFoundException 
 */
public void testCorruptZip() throws IOException, ClassNotFoundException, InterruptedException

{
    LOG.info("============================================================");
    LOG.info("==                Running testCorruptZip()                ==");
    LOG.info("============================================================");

    // Standard stuff
    Job job = new Job(conf);
    job.setJobName(this.getClass().getSimpleName());
    job.setJarByClass(this.getClass());
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // 
    job.setInputFormatClass(ZipFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // The output files will contain "Word [TAB] Count"
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    //
    ZipFileInputFormat.setInputPaths(job, new Path(inputPath, "corrupt.zip"));
    TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_Corrupt"));

    //
    assertFalse(job.waitForCompletion(true));
}

From source file:com.cotdp.hadoop.ZipFileTest.java

License:Apache License

/**
 * This test refers to a corrupt (truncated) ZIP file, upon reaching the corruption
 * the Mapper will ignore the corrupt entry and close the ZIP file. All previous
 * output will be treated as normal and passed through the Reducer. 
 * //w w w. j  a va 2  s.c om
 * Expected result: success
 * 
 * @throws IOException 
 * @throws InterruptedException 
 * @throws ClassNotFoundException 
 */
public void testCorruptZipLenient() throws IOException, ClassNotFoundException, InterruptedException

{
    LOG.info("============================================================");
    LOG.info("==                Running testCorruptZipLenient()         ==");
    LOG.info("============================================================");

    // Standard stuff
    Job job = new Job(conf);
    job.setJobName(this.getClass().getSimpleName());
    job.setJarByClass(this.getClass());
    job.setMapperClass(MyMapper.class);
    job.setReducerClass(MyReducer.class);

    // 
    job.setInputFormatClass(ZipFileInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    // The output files will contain "Word [TAB] Count"
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);

    //
    ZipFileInputFormat.setLenient(true);
    ZipFileInputFormat.setInputPaths(job, new Path(inputPath, "corrupt.zip"));
    TextOutputFormat.setOutputPath(job, new Path(workingPath, "Output_CorruptLenient"));

    //
    assertTrue(job.waitForCompletion(true));
}

From source file:com.cqx.mr.MRSearchAuto.java

public void searchHBase(int numOfDays) throws IOException, InterruptedException, ClassNotFoundException {
    long startTime;
    long endTime;

    Configuration conf = HBaseConfiguration.create();
    conf.set("hbase.zookeeper.quorum", "node2,node3,node4");
    conf.set("fs.default.name", "hdfs://node1");
    conf.set("mapred.job.tracker", "node1:54311");
    /*/* ww w  .  j  av  a  2s.c o m*/
     * ?map
     */
    conf.set("search.license", "C87310");
    conf.set("search.color", "10");
    conf.set("search.direction", "2");

    Job job = new Job(conf, "MRSearchHBase");
    System.out.println("search.license: " + conf.get("search.license"));
    job.setNumReduceTasks(0);
    job.setJarByClass(MRSearchAuto.class);
    Scan scan = new Scan();
    scan.addFamily(FAMILY_NAME);
    byte[] startRow = Bytes.toBytes("2011010100000");
    byte[] stopRow;
    switch (numOfDays) {
    case 1:
        stopRow = Bytes.toBytes("2011010200000");
        break;
    case 10:
        stopRow = Bytes.toBytes("2011011100000");
        break;
    case 30:
        stopRow = Bytes.toBytes("2011020100000");
        break;
    case 365:
        stopRow = Bytes.toBytes("2012010100000");
        break;
    default:
        stopRow = Bytes.toBytes("2011010101000");
    }
    // ?key
    scan.setStartRow(startRow);
    scan.setStopRow(stopRow);

    TableMapReduceUtil.initTableMapperJob(TABLE_NAME, scan, SearchMapper.class, ImmutableBytesWritable.class,
            Text.class, job);
    Path outPath = new Path("searchresult");
    HDFS_File file = new HDFS_File();
    file.DelFile(conf, outPath.getName(), true); // 
    FileOutputFormat.setOutputPath(job, outPath);// 

    startTime = System.currentTimeMillis();
    job.waitForCompletion(true);
    endTime = System.currentTimeMillis();
    System.out.println("Time used: " + (endTime - startTime));
    System.out.println("startRow:" + Text.decode(startRow));
    System.out.println("stopRow: " + Text.decode(stopRow));
}

From source file:com.daleway.training.hadoop.condprob.ConditionalProbabilityPairs.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(ConditionalProbabilityPairs.class);
    job.setMapperClass(TokenizerMapper.class);
    //job.setCombinerClass(IntSumReducer.class);
    job.setPartitionerClass(ProbDistPartitioner.class);
    job.setReducerClass(IntSumReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    job.setNumReduceTasks(5);/*  w w w  .ja  v  a 2 s.  c  o  m*/
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;

}

From source file:com.daleway.training.hadoop.condprob.ConditionalProbabilityPairsSecondarySort.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(ConditionalProbabilityPairsSecondarySort.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setSortComparatorClass(KeyComparator.class);
    job.setGroupingComparatorClass(GroupComparator.class);
    //job.setCombinerClass(IntSumReducer.class);
    job.setPartitionerClass(ProbDistPartitioner.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    //Is the output value class for Map or Reduce ?
    job.setOutputValueClass(Text.class);
    //job.setNumReduceTasks(5);
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;//from  www  .ja v a2 s. c  o  m
}

From source file:com.daleway.training.hadoop.condprob.ConditionalProbabilityPairWordExtractor.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(ConditionalProbabilityPairWordExtractor.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;// w  ww.  j av  a 2  s.  c o m

}

From source file:com.daleway.training.hadoop.condprob.ConditionalProbabilityStripes.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(ConditionalProbabilityStripes.class);
    job.setMapperClass(TokenizerMapper.class);
    // job.setCombinerClass(IntSumReducer.class);
    job.setPartitionerClass(ProbDistPartitioner.class);
    job.setReducerClass(IntSumReducer.class);

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

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

    job.setNumReduceTasks(5);//from   w  ww .j  av  a  2  s .c  o m
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;
}

From source file:com.daleway.training.hadoop.pagerank.PageRankAdjList.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(PageRankAdjList.class);
    job.setMapperClass(PageRankMapper.class);
    //job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(PageRankReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;//from   w  w w . ja  va  2  s  . c  o  m

}

From source file:com.daleway.training.hadoop.pagerank.PageRankCalcDanglingNodeMass.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(PageRankCalcDanglingNodeMass.class);
    job.setMapperClass(PageRankMapper.class);
    //job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(PageRankReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;//from  w w  w  .j  a  v  a 2 s . com

}

From source file:com.daleway.training.hadoop.pagerank.PageRankComplete.java

License:Apache License

public static Job createJob(Configuration conf, String inputPath, String outputPath) throws IOException {
    Job job = new Job(conf, "pair wise count");
    job.setJarByClass(PageRankComplete.class);
    job.setMapperClass(PageRankMapper.class);
    //job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(PageRankReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    FileInputFormat.addInputPath(job, new Path(inputPath));
    FileOutputFormat.setOutputPath(job, new Path(outputPath));
    return job;//from  ww w.  j a  v  a 2s.com

}