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

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

Introduction

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

Prototype

public JobConf(boolean loadDefaults) 

Source Link

Document

A new map/reduce configuration where the behavior of reading from the default resources can be turned off.

Usage

From source file:com.facebook.presto.hive.orc.DwrfRecordCursorProvider.java

License:Apache License

@Override
public Optional<HiveRecordCursor> createHiveRecordCursor(String clientId, Configuration configuration,
        ConnectorSession session, Path path, long start, long length, Properties schema,
        List<HiveColumnHandle> columns, List<HivePartitionKey> partitionKeys,
        TupleDomain<HiveColumnHandle> effectivePredicate, DateTimeZone hiveStorageTimeZone,
        TypeManager typeManager) {//from   w ww  .j a va 2 s.  co m
    if (!isDeserializerClass(schema, OrcSerde.class)) {
        return Optional.empty();
    }

    StructObjectInspector rowInspector = getTableObjectInspector(schema);
    if (rowInspector.getAllStructFieldRefs().stream()
            .anyMatch(field -> hasDateType(field.getFieldObjectInspector()))) {
        throw new IllegalArgumentException("DWRF does not support DATE type");
    }

    ReaderWriterProfiler.setProfilerOptions(configuration);

    RecordReader recordReader;
    try {
        FileSystem fileSystem = path.getFileSystem(configuration);
        Reader reader = OrcFile.createReader(fileSystem, path, new JobConf(configuration));
        boolean[] include = findIncludedColumns(reader.getTypes(), columns);
        recordReader = reader.rows(start, length, include);
    } catch (Exception e) {
        throw Throwables.propagate(e);
    }

    return Optional.<HiveRecordCursor>of(new DwrfHiveRecordCursor(recordReader, length, schema, partitionKeys,
            columns, hiveStorageTimeZone, typeManager));
}

From source file:com.facebook.presto.hive.util.ConfigurationUtils.java

License:Apache License

public static JobConf toJobConf(Configuration conf) {
    if (conf instanceof JobConf) {
        return (JobConf) conf;
    }/*from w ww  . j  av  a2s.c  om*/
    return new JobConf(conf);
}

From source file:com.facebook.presto.rcfile.RcFileTester.java

License:Apache License

private static DataSize writeRcFileColumnOld(File outputFile, Format format, Compression compression, Type type,
        Iterator<?> values) throws Exception {
    ObjectInspector columnObjectInspector = getJavaObjectInspector(type);
    RecordWriter recordWriter = createRcFileWriterOld(outputFile, compression, columnObjectInspector);

    SettableStructObjectInspector objectInspector = createSettableStructObjectInspector("test",
            columnObjectInspector);//from w ww . j  a  v a2 s.com
    Object row = objectInspector.create();

    List<StructField> fields = ImmutableList.copyOf(objectInspector.getAllStructFieldRefs());
    @SuppressWarnings("deprecation")
    Serializer serializer = format.createSerializer();

    Properties tableProperties = new Properties();
    tableProperties.setProperty("columns", "test");
    tableProperties.setProperty("columns.types", objectInspector.getTypeName());
    serializer.initialize(new JobConf(false), tableProperties);

    while (values.hasNext()) {
        Object value = values.next();
        value = preprocessWriteValueOld(type, value);
        objectInspector.setStructFieldData(row, fields.get(0), value);

        Writable record = serializer.serialize(row, objectInspector);
        recordWriter.write(record);
    }

    recordWriter.close(false);
    return new DataSize(outputFile.length(), BYTE).convertToMostSuccinctDataSize();
}

From source file:com.facebook.presto.rcfile.RcFileTester.java

License:Apache License

private static RecordWriter createRcFileWriterOld(File outputFile, Compression compression,
        ObjectInspector columnObjectInspector) throws IOException {
    JobConf jobConf = new JobConf(false);
    Optional<String> codecName = compression.getCodecName();
    if (codecName.isPresent()) {
        jobConf.set(COMPRESS_CODEC, codecName.get());
    }//from  w  ww  .  ja  va  2s .c o m

    return new RCFileOutputFormat().getHiveRecordWriter(jobConf, new Path(outputFile.toURI()), Text.class,
            codecName.isPresent(), createTableProperties("test", columnObjectInspector.getTypeName()), () -> {
            });
}

From source file:com.github.dryangkun.hbase.tidx.hive.HBaseStorageHandler.java

License:Apache License

@Override
public void configureJobConf(TableDesc tableDesc, JobConf jobConf) {
    try {/*from  w w w .j  a  v  a 2 s. c  o m*/
        HBaseSerDe.configureJobConf(tableDesc, jobConf);
        /*
         * HIVE-6356
         * The following code change is only needed for hbase-0.96.0 due to HBASE-9165, and
         * will not be required once Hive bumps up its hbase version). At that time , we will
         * only need TableMapReduceUtil.addDependencyJars(jobConf) here.
         */
        if (counterClass != null) {
            TableMapReduceUtil.addDependencyJars(jobConf, HBaseStorageHandler.class, TableInputFormatBase.class,
                    counterClass);
        } else {
            TableMapReduceUtil.addDependencyJars(jobConf, HBaseStorageHandler.class,
                    TableInputFormatBase.class);
        }
        if (HiveConf.getVar(jobConf, HiveConf.ConfVars.HIVE_HBASE_SNAPSHOT_NAME) != null) {
            // There is an extra dependency on MetricsRegistry for snapshot IF.
            TableMapReduceUtil.addDependencyJars(jobConf, MetricsRegistry.class);
        }
        Set<String> merged = new LinkedHashSet<String>(jobConf.getStringCollection("tmpjars"));

        Job copy = new Job(jobConf);
        TableMapReduceUtil.addDependencyJars(copy);
        merged.addAll(copy.getConfiguration().getStringCollection("tmpjars"));
        jobConf.set("tmpjars", StringUtils.arrayToString(merged.toArray(new String[0])));

        // Get credentials using the configuration instance which has HBase properties
        JobConf hbaseJobConf = new JobConf(getConf());
        org.apache.hadoop.hbase.mapred.TableMapReduceUtil.initCredentials(hbaseJobConf);
        ShimLoader.getHadoopShims().mergeCredentials(jobConf, hbaseJobConf);
    } catch (Exception e) {
        throw new RuntimeException(e);
    }
}

From source file:com.github.gaoyangthu.core.hbase.ConfigurationUtils.java

License:Apache License

/**
 * Creates a new {@link org.apache.hadoop.conf.Configuration} based on the given arguments.
 * /*w  w  w  .  j a  v a  2s.com*/
 * @param original initial configuration to read from. May be null. 
 * @param properties properties object to add to the newly created configuration. May be null.
 * @return newly created configuration based on the input parameters.
 */
public static Configuration createFrom(Configuration original, Properties properties) {
    Configuration cfg = null;
    if (original != null) {
        cfg = (original instanceof JobConf ? new JobConf(original) : new Configuration(original));
    } else {
        cfg = new JobConf();
    }
    addProperties(cfg, properties);
    return cfg;
}

From source file:com.github.gaoyangthu.demo.mapred.dancing.DistributedPentomino.java

License:Apache License

public int run(String[] args) throws Exception {
    JobConf conf;/*ww  w .  j  a  va 2  s.  c  om*/
    int depth = 5;
    int width = 9;
    int height = 10;
    Class<? extends Pentomino> pentClass;
    if (args.length == 0) {
        System.out.println("Usage: pentomino <output> [-depth #] [-height #] [-width #]");
        ToolRunner.printGenericCommandUsage(System.out);
        return -1;
    }

    conf = new JobConf(getConf());

    // Pick up the parameters, should the user set these
    width = conf.getInt("pent.width", width);
    height = conf.getInt("pent.height", height);
    depth = conf.getInt("pent.depth", depth);
    pentClass = conf.getClass("pent.class", OneSidedPentomino.class, Pentomino.class);

    for (int i = 0; i < args.length; i++) {
        if (args[i].equalsIgnoreCase("-depth")) {
            depth = Integer.parseInt(args[++i].trim());
        } else if (args[i].equalsIgnoreCase("-height")) {
            height = Integer.parseInt(args[++i].trim());
        } else if (args[i].equalsIgnoreCase("-width")) {
            width = Integer.parseInt(args[++i].trim());
        }
    }

    // Set parameters for MR tasks to pick up either which way the user sets
    // them or not
    conf.setInt("pent.width", width);
    conf.setInt("pent.height", height);
    conf.setInt("pent.depth", depth);

    Path output = new Path(args[0]);
    Path input = new Path(output + "_input");
    FileSystem fileSys = FileSystem.get(conf);
    try {
        FileInputFormat.setInputPaths(conf, input);
        FileOutputFormat.setOutputPath(conf, output);
        conf.setJarByClass(PentMap.class);

        conf.setJobName("dancingElephant");
        Pentomino pent = ReflectionUtils.newInstance(pentClass, conf);
        pent.initialize(width, height);
        createInputDirectory(fileSys, input, pent, depth);

        // the keys are the prefix strings
        conf.setOutputKeyClass(Text.class);
        // the values are puzzle solutions
        conf.setOutputValueClass(Text.class);

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

        conf.setNumMapTasks(2000);
        conf.setNumReduceTasks(1);

        JobClient.runJob(conf);
    } finally {
        fileSys.delete(input, true);
    }
    return 0;
}

From source file:com.google.mr4c.hadoop.MR4CMRJobTest.java

License:Open Source License

private JobConf newJobConf() {
    JobConf jobConf = new JobConf(false);
    jobConf.clear(); // just in case;
    return jobConf;
}

From source file:com.google.mr4c.hadoop.yarn.YarnTestBinding.java

License:Open Source License

public JobConf createTestMRJobConf() throws IOException {
    if (m_mrCluster == null) {
        startMrCluster();/*from ww  w.  j a va2s. c o  m*/
    }
    JobConf job = new JobConf(m_mrCluster.getConfig());
    job.setJarByClass(AlgoRunner.class);
    return job;
}

From source file:com.hadoop.examples.geolocation.GeoLocationJob.java

License:Apache License

/**
 * @param args//w  ww .j  av a 2 s . com
 */
public static void main(String[] args) throws Exception {
    JobConf conf = new JobConf(GeoLocationJob.class);
    conf.setJobName("geolocationgroup");

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

    conf.setMapperClass(GeoLocationMapper.class);
    conf.setReducerClass(GeoLocationReducer.class);

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

    FileInputFormat.setInputPaths(conf, new Path(args[0]));
    FileOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);

}