Example usage for org.apache.hadoop.mapred JobConf setJarByClass

List of usage examples for org.apache.hadoop.mapred JobConf setJarByClass

  1. HOME
  2. Java
  3. org.apache.hadoop
  4. org.apache.hadoop.mapred.*
  5. JobConf
  6. setJarByClass

Introduction

In this page you can find the example usage for org.apache.hadoop.mapred JobConf setJarByClass.

Prototype

public void setJarByClass(Class cls)

Source Link

Document

Set the job's jar file by finding an example class location.

Usage

From source file:edu.ucsb.cs.sort.length.LengthSortMain.java

License:Apache License

/**
 * Sets the job configurations including the mapper and reducer classes to
 * do the sorting based on vector lengths.
 *//*  www .ja  v  a2  s. c o  m*/
public static void main(String[] args) throws IOException {

    JobConf job = new JobConf();
    new GenericOptionsParser(job, args);
    job.setJobName(LengthSortMain.class.getSimpleName());
    job.setJarByClass(LengthSortMain.class);
    job.setMapperClass(LengthSortMapper.class);
    job.setMapOutputKeyClass(FloatWritable.class);
    job.setMapOutputValueClass(IdFeatureWeightArrayWritable.class);

    job.setPartitionerClass(LengthRangePartitioner.class);

    job.setReducerClass(LengthSortReducer.class);
    job.setNumReduceTasks(job.getInt(SortDriver.NUM_REDUCE_PROPERTY, SortDriver.NUM_REDUCE_VALUE));
    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(FeatureWeightArrayWritable.class);
    //
    // set input & output
    //
    String inputDir = SortDriver.INPUT_DIR;
    if (inputDir == null) {
        throw new UnsupportedOperationException("ERROR: input path not set");
    }
    job.setInputFormat(SequenceFileInputFormat.class);
    SequenceFileInputFormat.addInputPath(job, new Path(inputDir));
    Path outputPath = new Path(SortDriver.OUTPUT_DIR);
    FileSystem.get(job).delete(outputPath, true);
    job.setOutputFormat(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(job, outputPath);

    //
    // run
    //
    JobSubmitter.run(job, "Sort By Vector Lenghts", -1);
}

From source file:edu.ucsb.cs.sort.maxw.MaxwSortMain.java

License:Apache License

/**
 * Main method sets the job configurations including the mapper and reducer
 * classes to do the sorting.//  ww  w  . ja  v  a  2s .  c o m
 */
public static void main(String[] args) throws IOException {

    JobConf job = new JobConf();
    new GenericOptionsParser(job, args);
    // ToolRunner.printGenericCommandUsage(System.out);
    job.setJobName(MaxwSortMain.class.getSimpleName());
    job.setJarByClass(MaxwSortMain.class);
    job.setMapperClass(MaxwSortMapper.class);
    job.setMapOutputKeyClass(FloatWritable.class);
    job.setMapOutputValueClass(IdFeatureWeightArrayWritable.class);

    job.setPartitionerClass(MaxwRangePartitioner.class);

    job.setReducerClass(MaxwSortReducer.class);
    job.setNumReduceTasks(job.getInt(SortDriver.NUM_REDUCE_PROPERTY, SortDriver.NUM_REDUCE_VALUE));
    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(FeatureWeightArrayWritable.class);
    //
    // set input & output
    //
    String inputDir = SortDriver.INPUT_DIR;
    if (inputDir == null) {
        throw new UnsupportedOperationException("ERROR: input path not set");
    }
    job.setInputFormat(SequenceFileInputFormat.class);
    SequenceFileInputFormat.addInputPath(job, new Path(inputDir));
    Path outputPath = new Path(SortDriver.OUTPUT_DIR);
    FileSystem.get(job).delete(outputPath, true);
    job.setOutputFormat(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(job, outputPath);
    //
    // run
    //
    JobSubmitter.run(job, "Sort By infinity-Norm", -1);
}

From source file:edu.ucsb.cs.sort.norm.NormSortMain.java

License:Apache License

/**
 * Main method sets the job configurations including the mapper and reducer
 * classes to do the sorting. Some of the produced partitions might be
 * merged later to reflect the number of partitions chosen by the user.
 *//* w  w  w.  java 2  s  .c o  m*/
public static void main(String[] args) throws IOException {

    JobConf job = new JobConf();
    new GenericOptionsParser(job, args);
    job.setJobName("NormSort");
    job.setJarByClass(NormSortMain.class);
    job.setMapperClass(NormSortMapper.class);
    job.setMapOutputKeyClass(FloatWritable.class);
    job.setMapOutputValueClass(IdFeatureWeightArrayWritable.class);

    job.setPartitionerClass(NormRangePartitioner.class);

    job.setReducerClass(NormSortReducer.class);
    job.setNumReduceTasks(job.getInt(SortDriver.NUM_REDUCE_PROPERTY, SortDriver.NUM_REDUCE_VALUE));
    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(FeatureWeightArrayWritable.class);
    //
    // set input & output
    //
    String inputDir = SortDriver.INPUT_DIR;
    if (inputDir == null) {
        throw new UnsupportedOperationException("ERROR: input path not set");
    }
    job.setInputFormat(SequenceFileInputFormat.class);
    SequenceFileInputFormat.addInputPath(job, new Path(inputDir));
    Path outputPath = new Path(SortDriver.OUTPUT_DIR);
    FileSystem.get(job).delete(outputPath, true);
    job.setOutputFormat(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(job, outputPath);
    //
    // run
    //
    JobSubmitter.run(job, "Sort By p-norm", -1);
}

From source file:edu.ucsb.cs.sort.signature.SigSortMain.java

License:Apache License

/**
 * Sets the job configurations including the mapper and reducer classes to
 * do the sorting based signatures./* w w  w  .j  av  a 2  s . c o  m*/
 */
public static void main(String[] args) throws IOException {

    JobConf job = new JobConf();
    new GenericOptionsParser(job, args);
    job.setJobName(SigSortMain.class.getSimpleName());
    job.setJarByClass(SigSortMain.class);
    job.setMapperClass(SigSortMapper.class);
    job.setMapOutputKeyClass(BitSignature.class);
    job.setMapOutputValueClass(LongWritable.class);

    job.setPartitionerClass(SigRangePartitioner.class);

    job.setReducerClass(SigSortReducer.class);
    job.setNumReduceTasks(job.getInt(SortDriver.NUM_REDUCE_PROPERTY, SortDriver.NUM_REDUCE_VALUE));
    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(BitSignature.class);
    //
    // set input & output
    //
    String inputDir = SortDriver.INPUT_DIR;
    if (inputDir == null) {
        throw new UnsupportedOperationException("ERROR: input path not set");
    }
    job.setInputFormat(SequenceFileInputFormat.class);
    SequenceFileInputFormat.addInputPath(job, new Path(inputDir));
    Path outputPath = new Path(OUTPUT_PATH);
    FileSystem.get(job).delete(outputPath, true);
    job.setOutputFormat(SequenceFileOutputFormat.class);
    FileOutputFormat.setOutputPath(job, outputPath);

    //
    // run
    //
    JobSubmitter.run(job, "Sort By Signature Bytes", -1);
}

From source file:edu.umd.cloud9.webgraph.driver.BuildIndexableAnchorCollection.java

License:Apache License

/**
 * Runs this tool./*from   w  w  w .  j  a  v a2s . c o m*/
 */
public int run(String[] args) throws Exception {
    if (args.length < 5) {
        printUsage();
        return -1;
    }

    JobConf conf = new JobConf(getConf());
    FileSystem fs = FileSystem.get(conf);

    String collectionPath = DriverUtil.argValue(args, DriverUtil.CL_INPUT);
    String outputPath = DriverUtil.argValue(args, DriverUtil.CL_OUTPUT);
    String docnoMappingClass = DriverUtil.argValue(args, DriverUtil.CL_DOCNO_MAPPING_CLASS);
    String docnoMapping = DriverUtil.argValue(args, DriverUtil.CL_DOCNO_MAPPING);
    int numReducers = Integer.parseInt(DriverUtil.argValue(args, DriverUtil.CL_NUMBER_OF_REDUCERS));
    if (DriverUtil.argExists(args, DriverUtil.CL_MAX_LENGTH)) {
        conf.setInt("Cloud9.maxContentLength",
                Integer.parseInt(DriverUtil.argValue(args, DriverUtil.CL_MAX_LENGTH)));
    }
    conf.set("Cloud9.DocnoMappingClass", docnoMappingClass);

    LOG.info("Tool name: BuildAnchorTextForwardIndex");
    LOG.info(" - collection path: " + collectionPath);
    LOG.info(" - output path: " + outputPath);
    LOG.info(" - docno-mapping class: " + docnoMappingClass);
    LOG.info(" - docno-mapping file: " + docnoMapping);
    if (args.length == 6) {
        LOG.info(" - maximum content length: " + conf.getInt("Cloud9.maxContentLength", 0));
    }

    conf.set("mapred.child.java.opts", "-Xmx2048m");
    conf.setJobName("BuildIndexableAnchorCollection");
    conf.setJarByClass(BuildIndexableAnchorCollection.class);

    conf.setNumMapTasks(100);
    conf.setNumReduceTasks(numReducers);
    DistributedCache.addCacheFile(new URI(docnoMapping), conf);

    conf.setInputFormat(SequenceFileInputFormat.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    SequenceFileOutputFormat.setCompressOutput(conf, true);
    SequenceFileOutputFormat.setOutputCompressionType(conf, SequenceFile.CompressionType.BLOCK);
    SequenceFileInputFormat.setInputPaths(conf, new Path(collectionPath));
    SequenceFileOutputFormat.setOutputPath(conf, new Path(outputPath));

    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(IndexableAnchorText.class);

    conf.setMapperClass(MyMapper.class);
    conf.setReducerClass(IdentityReducer.class);

    // delete the output directory if it exists already
    fs.delete(new Path(outputPath), true);
    RunningJob job = JobClient.runJob(conf);

    return 0;
}

From source file:eu.stratosphere.myriad.driver.hadoop.MyriadDriverHadoopJob.java

License:Apache License

private JobConf createJobConf() {
    // create job
    JobConf conf = new JobConf(getConf());

    conf.setJarByClass(MyriadDriverHadoopJob.class);
    conf.setJobName(String.format("%s", this.parameters.getDGenName()));

    conf.setOutputKeyClass(NullWritable.class);
    conf.setOutputValueClass(Text.class);

    conf.setMapperClass(IdentityMapper.class);
    conf.setNumReduceTasks(0);//  w  w w  .  ja v a  2s. c  o  m

    conf.setInputFormat(MyriadInputFormat.class);
    conf.setOutputFormat(TextOutputFormat.class);

    // input format configuration
    MyriadInputFormat.setDriverJobParameters(conf, this.parameters);
    // output format configuration
    FileOutputFormat.setOutputPath(conf, new Path(this.parameters.getJobOutputPath()));

    return conf;
}

From source file:findstableweatherstate.FindStableWeatherState.java

public String call() throws Exception {

    Path firstOutputPath = new Path("input/firstOutput");
    Path secondOutputPath = new Path("input/secondOutput");

    long startTime, stopTime, elapsedTime;

    JobConf job = new JobConf();
    job.setJarByClass(getClass());
    job.setJobName("invertedindex");

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

    job.setReducerClass(JoinReducer.class);

    MultipleInputs.addInputPath(job, new Path(getInputPathStation()), TextInputFormat.class,
            StationMapper.class);
    MultipleInputs.addInputPath(job, new Path(getInputPathReadings()), TextInputFormat.class,
            ReadingsMapper.class);

    FileOutputFormat.setOutputPath(job, firstOutputPath);

    JobConf job2 = new JobConf();
    job2.setJarByClass(getClass());//w  w w.j  a  v a 2 s.c o m
    job2.setJobName("secondJob");

    job2.setOutputKeyClass(Text.class);
    job2.setOutputValueClass(Text.class);

    //job2.setInputFormat(org.apache.hadoop.mapred.TextInputFormat.class);
    FileInputFormat.setInputPaths(job2, firstOutputPath);

    job2.setMapperClass(CalculateMinMaxTemperatureMapper.class);

    job2.setReducerClass(CalculateMaxMinTemperatureReducer.class);
    if (getOutputPath() != null) {
        FileOutputFormat.setOutputPath(job2, secondOutputPath);
    }

    JobConf job3 = new JobConf();
    job3.setJarByClass(getClass());
    job3.setJobName("thirdJob");

    job3.setOutputKeyClass(Text.class);
    job3.setOutputValueClass(Text.class);
    job3.setMapOutputKeyClass(DoubleWritable.class);
    job3.setMapOutputValueClass(Text.class);
    //job2.setInputFormat(org.apache.hadoop.mapred.TextInputFormat.class);
    FileInputFormat.setInputPaths(job3, secondOutputPath);

    job3.setMapperClass(SortStateMapper.class);

    job3.setReducerClass(SortStateReducer.class);
    if (getOutputPath() != null) {
        FileOutputFormat.setOutputPath(job3, new Path(getOutputPath()));
    }

    startTime = System.currentTimeMillis();

    JobClient.runJob(job);

    stopTime = System.currentTimeMillis();
    elapsedTime = stopTime - startTime;
    System.out.println("******************** First Job : " + elapsedTime / 1000);

    startTime = System.currentTimeMillis();

    JobClient.runJob(job2);

    stopTime = System.currentTimeMillis();
    elapsedTime = stopTime - startTime;
    System.out.println("******************** Second Job : " + elapsedTime / 1000);

    startTime = System.currentTimeMillis();

    JobClient.runJob(job3);

    stopTime = System.currentTimeMillis();
    elapsedTime = stopTime - startTime;
    System.out.println("******************** Third Job : " + elapsedTime / 1000);

    return "";
}

From source file:FormatStorage1.MergeFileUtil.java

License:Open Source License

public static void run(String inputdir, String outputdir, Configuration conf) throws IOException {
    JobConf job = new JobConf(conf);
    job.setJobName("MergeFileUtil");
    job.setJarByClass(MergeFileUtil.class);
    FileSystem fs = null;//ww  w  .jav  a  2  s . c  om
    fs = FileSystem.get(job);
    if (fs.exists(new Path(outputdir))) {
        throw new IOException("outputdir: " + outputdir + " exist!!!");
    }

    FileStatus[] fss = fs.listStatus(new Path(inputdir));

    if (fss == null || fss.length <= 0) {
        throw new IOException("no input files");
    }

    IFormatDataFile ifdf = new IFormatDataFile(job);
    ifdf.open(fss[0].getPath().toString());
    job.set("ifdf.head.info", ifdf.fileInfo().head().toStr());
    ifdf.close();

    long wholesize = 0;
    for (FileStatus status : fss) {
        wholesize += status.getLen();
    }

    job.setNumReduceTasks(0);

    FileInputFormat.setInputPaths(job, inputdir);
    FileOutputFormat.setOutputPath(job, new Path(outputdir));

    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(IRecord.class);

    job.setMapperClass(MergeMap.class);

    job.setInputFormat(CombineFormatStorageFileInputFormat.class);
    job.setOutputFormat(MergeIFormatOutputFormat.class);

    JobClient jc = new JobClient(job);
    RunningJob rjob = jc.submitJob(job);
    try {

        String lastReport = "";
        SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS");
        long reportTime = System.currentTimeMillis();
        long maxReportInterval = 3 * 1000;

        while (!rjob.isComplete()) {
            Thread.sleep(1000);

            int mapProgress = Math.round(rjob.mapProgress() * 100);
            int reduceProgress = Math.round(rjob.reduceProgress() * 100);

            String report = " map = " + mapProgress + "%,  reduce = " + reduceProgress + "%";

            if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) {

                String output = dateFormat.format(Calendar.getInstance().getTime()) + report;
                System.err.println(output);
                lastReport = report;
                reportTime = System.currentTimeMillis();
            }
        }
        LOG.info(rjob.getJobState());

    } catch (IOException e1) {
        e1.printStackTrace();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }
}

From source file:FormatStorage1.MergeFileUtil.java

License:Open Source License

public static void runold(String inputdir, String outputdir, Configuration conf) throws IOException {
    JobConf job = new JobConf(conf);
    job.setJobName("MergeFileUtil");
    job.setJarByClass(MergeFileUtil.class);
    FileSystem fs = null;/*from   w  w w  . j a v  a 2  s.  c o m*/
    fs = FileSystem.get(job);
    if (fs.exists(new Path(outputdir))) {
        throw new IOException("outputdir: " + outputdir + " exist!!!");
    }

    FileStatus[] fss = fs.listStatus(new Path(inputdir));

    if (fss == null || fss.length <= 0) {
        throw new IOException("no input files");
    }

    for (FileStatus status : fss) {
        if (status.isDir()) {
            throw new IOException("!!!input dir contains directory:\t" + status.getPath().toString());
        }
    }

    IFormatDataFile ifdf = new IFormatDataFile(job);
    ifdf.open(fss[0].getPath().toString());
    job.set("ifdf.head.info", ifdf.fileInfo().head().toStr());
    ifdf.close();

    long wholesize = 0;
    for (FileStatus status : fss) {
        wholesize += status.getLen();
    }

    long fl = 512 * 1024 * 1024;
    int reduces = (int) (wholesize / fl + 1);
    job.setNumReduceTasks(reduces);

    FileInputFormat.setInputPaths(job, inputdir);
    FileOutputFormat.setOutputPath(job, new Path(outputdir));

    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(IRecord.class);

    job.setMapperClass(MergeMap.class);
    job.setReducerClass(MergeReduce.class);

    job.setInputFormat(MergeIFormatInputFormat.class);
    job.setOutputFormat(MergeIFormatOutputFormat.class);

    JobClient jc = new JobClient(job);
    RunningJob rjob = jc.submitJob(job);
    try {

        String lastReport = "";
        SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS");
        long reportTime = System.currentTimeMillis();
        long maxReportInterval = 3 * 1000;

        while (!rjob.isComplete()) {
            Thread.sleep(1000);

            int mapProgress = Math.round(rjob.mapProgress() * 100);
            int reduceProgress = Math.round(rjob.reduceProgress() * 100);

            String report = " map = " + mapProgress + "%,  reduce = " + reduceProgress + "%";

            if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) {

                String output = dateFormat.format(Calendar.getInstance().getTime()) + report;
                System.err.println(output);
                lastReport = report;
                reportTime = System.currentTimeMillis();
            }
        }
        LOG.info(rjob.getJobState());

    } catch (IOException e1) {
        e1.printStackTrace();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }
}

From source file:FormatStorage1.MergeFileUtil1.java

License:Open Source License

public static void run(String inputdir, String outputdir, Configuration conf) throws IOException {
    JobConf job = new JobConf(conf);
    job.setJobName("MergeFileUtil1");
    job.setJarByClass(MergeFileUtil1.class);
    FileSystem fs = null;//from w w w .  j  a  v a2  s .co m
    fs = FileSystem.get(job);
    if (fs.exists(new Path(outputdir))) {
        throw new IOException("outputdir: " + outputdir + " exist!!!");
    }

    FileStatus[] fss = fs.listStatus(new Path(inputdir));

    if (fss == null || fss.length <= 0) {
        throw new IOException("no input files");
    }

    IFormatDataFile ifdf = new IFormatDataFile(job);
    ifdf.open(fss[0].getPath().toString());
    job.set("ifdf.head.info", ifdf.fileInfo().head().toStr());
    ifdf.close();

    long wholesize = 0;
    for (FileStatus status : fss) {
        wholesize += status.getLen();
    }

    job.setNumReduceTasks(0);

    FileInputFormat.setInputPaths(job, inputdir);
    FileOutputFormat.setOutputPath(job, new Path(outputdir));

    job.setOutputKeyClass(LongWritable.class);
    job.setOutputValueClass(IRecord.class);

    job.setMapperClass(MergeMap.class);

    job.setInputFormat(CombineFormatStorageFileInputFormat.class);
    job.setOutputFormat(MergeIFormatOutputFormat1.class);

    JobClient jc = new JobClient(job);
    RunningJob rjob = jc.submitJob(job);
    try {

        String lastReport = "";
        SimpleDateFormat dateFormat = new SimpleDateFormat("yyyy-MM-dd hh:mm:ss,SSS");
        long reportTime = System.currentTimeMillis();
        long maxReportInterval = 3 * 1000;

        while (!rjob.isComplete()) {
            Thread.sleep(1000);

            int mapProgress = Math.round(rjob.mapProgress() * 100);
            int reduceProgress = Math.round(rjob.reduceProgress() * 100);

            String report = " map = " + mapProgress + "%,  reduce = " + reduceProgress + "%";

            if (!report.equals(lastReport) || System.currentTimeMillis() >= reportTime + maxReportInterval) {

                String output = dateFormat.format(Calendar.getInstance().getTime()) + report;
                System.err.println(output);
                lastReport = report;
                reportTime = System.currentTimeMillis();
            }
        }
        LOG.info(rjob.getJobState());

    } catch (IOException e1) {
        e1.printStackTrace();
    } catch (InterruptedException e) {
        e.printStackTrace();
    }
}