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

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

Introduction

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

Prototype

public void setOutputValueClass(Class<?> theClass) throws IllegalStateException 

Source Link

Document

Set the value class for job outputs.

Usage

From source file:com.asakusafw.thundergate.runtime.cache.mapreduce.CacheBuildClient.java

License:Apache License

private void updateTable() throws IOException, InterruptedException {
    Job job = newJob();
    List<StageInput> inputList = new ArrayList<>();
    inputList.add(new StageInput(storage.getHeadContents("*").toString(), TemporaryInputFormat.class,
            TableJoinBaseMapper.class));
    inputList.add(new StageInput(storage.getPatchContents("*").toString(), TemporaryInputFormat.class,
            TableJoinPatchMapper.class));
    StageInputDriver.set(job, inputList);
    StageResourceDriver.add(job, storage.getPatchContents("*").toString(), TableJoinBaseMapper.RESOURCE_KEY);
    job.setInputFormatClass(StageInputFormat.class);
    job.setMapperClass(StageInputMapper.class);
    job.setMapOutputKeyClass(NullWritable.class);
    job.setMapOutputValueClass(modelClass);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(modelClass);

    TemporaryOutputFormat.setOutputPath(job, getNextDirectory());
    job.setOutputFormatClass(TemporaryOutputFormat.class);
    job.getConfiguration().setClass("mapred.output.committer.class", LegacyBridgeOutputCommitter.class,
            org.apache.hadoop.mapred.OutputCommitter.class);

    job.setNumReduceTasks(0);//  w  w w.  j a  v a 2 s .  c o  m

    LOG.info(MessageFormat.format("applying patch (table join): {0} / {1} -> {2}",
            storage.getPatchContents("*"), storage.getHeadContents("*"), getNextContents()));
    try {
        boolean succeed = job.waitForCompletion(true);
        LOG.info(MessageFormat.format("applied patch (table join): succeed={0}, {1} / {2} -> {3}", succeed,
                storage.getPatchContents("*"), storage.getHeadContents("*"), getNextContents()));
        if (succeed == false) {
            throw new IOException(MessageFormat.format("failed to apply patch (table join): {0} / {1} -> {2}",
                    storage.getPatchContents("*"), storage.getHeadContents("*"), getNextContents()));
        }
    } catch (ClassNotFoundException e) {
        throw new IOException(e);
    }
    putMeta();
}

From source file:com.asakusafw.thundergate.runtime.cache.mapreduce.CacheBuildClient.java

License:Apache License

private void create() throws InterruptedException, IOException {
    Job job = newJob();
    List<StageInput> inputList = new ArrayList<>();
    inputList.add(new StageInput(storage.getPatchContents("*").toString(), TemporaryInputFormat.class,
            CreateCacheMapper.class));
    StageInputDriver.set(job, inputList);
    job.setInputFormatClass(StageInputFormat.class);
    job.setMapperClass(StageInputMapper.class);
    job.setMapOutputKeyClass(NullWritable.class);
    job.setMapOutputValueClass(modelClass);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(modelClass);

    TemporaryOutputFormat.setOutputPath(job, getNextDirectory());
    job.setOutputFormatClass(TemporaryOutputFormat.class);
    job.getConfiguration().setClass("mapred.output.committer.class", LegacyBridgeOutputCommitter.class,
            org.apache.hadoop.mapred.OutputCommitter.class);

    job.setNumReduceTasks(0);//  w  ww  .  jav a2s.  co  m

    LOG.info(MessageFormat.format("applying patch (no join): {0} / (empty) -> {2}",
            storage.getPatchContents("*"), storage.getHeadContents("*"), getNextContents()));
    try {
        boolean succeed = job.waitForCompletion(true);
        LOG.info(MessageFormat.format("applied patch (no join): succeed={0}, {1} / (empty) -> {3}", succeed,
                storage.getPatchContents("*"), storage.getHeadContents("*"), getNextContents()));
        if (succeed == false) {
            throw new IOException(MessageFormat.format("failed to apply patch (no join): {0} / (empty) -> {2}",
                    storage.getPatchContents("*"), storage.getHeadContents("*"), getNextContents()));
        }
    } catch (ClassNotFoundException e) {
        throw new IOException(e);
    }
    putMeta();
}

From source file:com.avira.couchdoop.demo.ExportDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 1) {
        System.err.println("Usage: <input_path>");
        return 1;
    }//from   w ww. j ava 2 s .c om
    String input = args[0];

    Job job = Job.getInstance(getConf());
    job.setJarByClass(ExportDriver.class);

    // User classpath takes precedence in favor of Hadoop classpath.
    // This is because the Couchbase client requires a newer version of
    // org.apache.httpcomponents:httpcore.
    //        job.setUserClassesTakesPrecedence(true);

    // Input
    FileInputFormat.setInputPaths(job, input);

    // Mapper
    job.setMapperClass(ExportMapper.class);

    // Reducer
    job.setNumReduceTasks(0);

    // Output
    job.setOutputKeyClass(String.class);
    job.setOutputValueClass(CouchbaseAction.class);
    job.setOutputFormatClass(CouchbaseOutputFormat.class);

    if (!job.waitForCompletion(true)) {
        return 2;
    }

    return 0;
}

From source file:com.avira.couchdoop.demo.ImportDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 1) {
        System.err.println("Usage: <output_path>");
        return 1;
    }/*from w  ww .jav a 2s  .  c  o m*/
    String output = args[0];

    Job job = Job.getInstance(getConf());
    job.setJarByClass(this.getClass());

    // User classpath takes precedence in favor of Hadoop classpath.
    // This is because the Couchbase client requires a newer version of
    // org.apache.httpcomponents:httpcore.
    job.setUserClassesTakesPrecedence(true);

    // Input
    job.setInputFormatClass(CouchbaseViewInputFormat.class);

    // Mapper
    job.setMapperClass(ImportMapper.class);

    // Reducer
    job.setNumReduceTasks(0);

    // Output
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    FileOutputFormat.setOutputPath(job, new Path(output));

    if (!job.waitForCompletion(true)) {
        return 2;
    }

    return 0;
}

From source file:com.avira.couchdoop.exp.CouchbaseOutputFormat.java

License:Apache License

public static void initJob(Job job, String urls, String bucket, String password) {
    job.setOutputFormatClass(CouchbaseOutputFormat.class);
    job.setOutputKeyClass(String.class);
    job.setOutputValueClass(CouchbaseAction.class);

    Configuration conf = job.getConfiguration();
    conf.set(CouchbaseArgs.ARG_COUCHBASE_URLS.getPropertyName(), urls);
    conf.set(CouchbaseArgs.ARG_COUCHBASE_BUCKET.getPropertyName(), bucket);
    conf.set(CouchbaseArgs.ARG_COUCHBASE_PASSWORD.getPropertyName(), password);
}

From source file:com.avira.couchdoop.jobs.CouchbaseExporter.java

License:Apache License

public Job configureJob(Configuration conf, String input) throws IOException {
    conf.setInt("mapreduce.map.failures.maxpercent", 5);
    conf.setInt("mapred.max.map.failures.percent", 5);
    conf.setInt("mapred.max.tracker.failures", 20);

    Job job = Job.getInstance(conf);
    job.setJarByClass(CouchbaseExporter.class);

    // Input/*from   w ww  .ja v  a  2 s. co  m*/
    FileInputFormat.setInputPaths(job, input);

    // Mapper
    job.setMapperClass(CsvToCouchbaseMapper.class);
    job.setMapOutputKeyClass(String.class);
    job.setMapOutputValueClass(CouchbaseAction.class);

    // Reducer
    job.setNumReduceTasks(0);

    // Output
    job.setOutputFormatClass(CouchbaseOutputFormat.class);
    job.setOutputKeyClass(String.class);
    job.setOutputValueClass(CouchbaseAction.class);

    return job;
}

From source file:com.avira.couchdoop.jobs.CouchbaseViewImporter.java

License:Apache License

public Job configureJob(Configuration conf, String output) throws IOException {
    conf.setInt("mapreduce.map.failures.maxpercent", 5);
    conf.setInt("mapred.max.map.failures.percent", 5);
    conf.setInt("mapred.max.tracker.failures", 20);

    Job job = Job.getInstance(conf);
    job.setJarByClass(CouchbaseViewImporter.class);

    // Input//  www.j  av a  2 s.  c  o  m
    job.setInputFormatClass(CouchbaseViewInputFormat.class);

    // Mapper
    job.setMapperClass(CouchbaseViewToFileMapper.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(Text.class);

    // Reducer
    job.setNumReduceTasks(0);

    // Output
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(Text.class);
    FileOutputFormat.setOutputPath(job, new Path(output));

    return job;
}

From source file:com.awcoleman.BouncyCastleGenericCDRHadoop.BasicDriverMapReduce.java

License:Apache License

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

    if (args.length < 2) {
        System.out.println("Missing input and output filenames. Exiting.");
        System.exit(1);// w  w  w.j  a  va 2 s . c om
    }

    Job job = new Job(super.getConf());
    job.setJarByClass(BasicDriverMapReduce.class);
    job.setJobName("BasicDriver1");
    job.setMapperClass(BasicMapper.class);
    job.setReducerClass(BasicReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);
    job.setInputFormatClass(RawFileAsBinaryInputFormat.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.awcoleman.BouncyCastleGenericCDRHadoopWithWritable.BasicDriverMapReduce.java

License:Apache License

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

    if (args.length < 2) {
        System.out.println("Missing input and output filenames. Exiting.");
        System.exit(1);//from w  ww. j ava 2 s . c o m
    }

    @SuppressWarnings("deprecation")
    Job job = new Job(super.getConf());
    job.setJarByClass(BasicDriverMapReduce.class);
    job.setJobName("BasicDriverMapReduce");
    job.setMapperClass(BasicMapper.class);
    job.setReducerClass(BasicReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(CallDetailRecord.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(LongWritable.class);
    job.setInputFormatClass(RawFileAsBinaryInputFormat.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    return job.waitForCompletion(true) ? 0 : 1;
}

From source file:com.bah.applefox.main.plugins.fulltextindex.FTLoader.java

License:Apache License

/**
 * run takes the comandline args as arguments (in this case from a
 * configuration file), creates a new job, configures it, initiates it,
 * waits for completion, and returns 0 if it is successful (1 if it is not)
 * /*from   w w  w . j a  v  a2  s  .  c  o  m*/
 * @param args
 *            the commandline arguments (in this case from a configuration
 *            file)
 * 
 * @return 0 if the job ran successfully and 1 if it isn't
 */
public int run(String[] args) throws Exception {
    try {
        // Initialize variables
        FTLoader.articleFile = args[8];
        FTLoader.maxNGrams = Integer.parseInt(args[9]);
        FTLoader.stopWords = getStopWords();
        FTLoader.dTable = args[10];
        FTLoader.urlCheckedTable = args[11];
        FTLoader.divsFile = args[20];
        FTLoader.exDivs = getExDivs();

        // Give the job a name
        String jobName = this.getClass().getSimpleName() + "_" + System.currentTimeMillis();

        // Create job and set the jar
        Job job = new Job(getConf(), jobName);
        job.setJarByClass(this.getClass());

        String urlTable = args[5];

        job.setInputFormatClass(AccumuloInputFormat.class);
        InputFormatBase.setZooKeeperInstance(job.getConfiguration(), args[0], args[1]);
        InputFormatBase.setInputInfo(job.getConfiguration(), args[2], args[3].getBytes(), urlTable,
                new Authorizations());

        job.setMapperClass(MapperClass.class);
        job.setMapOutputKeyClass(Key.class);
        job.setMapOutputValueClass(Value.class);

        job.setReducerClass(ReducerClass.class);
        job.setNumReduceTasks(Integer.parseInt(args[4]));

        job.setOutputFormatClass(AccumuloOutputFormat.class);
        job.setOutputKeyClass(Key.class);
        job.setOutputValueClass(Value.class);

        AccumuloOutputFormat.setZooKeeperInstance(job.getConfiguration(), args[0], args[1]);
        AccumuloOutputFormat.setOutputInfo(job.getConfiguration(), args[2], args[3].getBytes(), true, urlTable);

        job.waitForCompletion(true);

        return job.isSuccessful() ? 0 : 1;
    } catch (IOException e) {
        if (e.getMessage() != null) {
            log.error(e.getMessage());
        } else {
            log.error(e.getStackTrace());
        }
    } catch (InterruptedException e) {
        if (e.getMessage() != null) {
            log.error(e.getMessage());
        } else {
            log.error(e.getStackTrace());
        }
    } catch (ClassNotFoundException e) {
        if (e.getMessage() != null) {
            log.error(e.getMessage());
        } else {
            log.error(e.getStackTrace());
        }
    }
    return 1;
}