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

Introduction

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

Prototype

public void setOutputFormat(Class<? extends OutputFormat> theClass) 

Source Link

Document

Set the OutputFormat implementation for the map-reduce job.

Usage

From source file:com.liveramp.hank.cascading.DomainBuilderTap.java

License:Apache License

public void sinkConfInit(FlowProcess<JobConf> process, JobConf conf) {
    super.sinkConfInit(process, conf);
    // Output Format
    conf.setOutputFormat(this.outputFormatClass);
    // Output Committer
    conf.setOutputCommitter(DomainBuilderOutputCommitter.class);
    // Set this tap's Domain name locally in the conf
    if (conf.get(DomainBuilderAbstractOutputFormat.CONF_PARAM_HANK_DOMAIN_NAME) != null) {
        throw new RuntimeException("Trying to set domain name configuration parameter to " + domainName
                + " but it was previously set to "
                + conf.get(DomainBuilderAbstractOutputFormat.CONF_PARAM_HANK_DOMAIN_NAME));
    } else {//from   w  w w .  ja  v  a 2 s.co m
        conf.set(DomainBuilderAbstractOutputFormat.CONF_PARAM_HANK_DOMAIN_NAME, domainName);
    }
}

---

From source file:com.liveramp.hank.hadoop.AbstractHadoopDomainBuilder.java

License:Apache License

private void configureJobCommon(DomainBuilderProperties properties, int versionNumber, int numPartitions,
        JobConf conf) throws IOException {
    // Hank specific configuration
    properties.setJobConfProperties(conf, versionNumber);
    // Output Committer
    conf.setOutputCommitter(DomainBuilderOutputCommitter.class);
    // Output path (set to tmp output path)
    FileOutputFormat.setOutputPath(conf, new Path(properties.getTmpOutputPath(versionNumber)));
    // Output format
    conf.setOutputFormat(properties.getOutputFormatClass());
    // Num reduce tasks
    conf.setNumReduceTasks(numPartitions);
}

---

From source file:com.manning.hip.ch4.joins.improved.impl.OptimizedDataJoinJob.java

License:Apache License

public static JobConf createDataJoinJob(String args[]) throws IOException {

    String inputDir = args[0];//from ww  w .j  ava 2 s  .c  om
    String outputDir = args[1];
    Class inputFormat = SequenceFileInputFormat.class;
    if (args[2].compareToIgnoreCase("text") != 0) {
        System.out.println("Using SequenceFileInputFormat: " + args[2]);
    } else {
        System.out.println("Using TextInputFormat: " + args[2]);
        inputFormat = TextInputFormat.class;
    }
    int numOfReducers = Integer.parseInt(args[3]);
    Class mapper = getClassByName(args[4]);
    Class reducer = getClassByName(args[5]);
    Class mapoutputValueClass = getClassByName(args[6]);
    Class outputFormat = TextOutputFormat.class;
    Class outputValueClass = Text.class;
    if (args[7].compareToIgnoreCase("text") != 0) {
        System.out.println("Using SequenceFileOutputFormat: " + args[7]);
        outputFormat = SequenceFileOutputFormat.class;
        outputValueClass = getClassByName(args[7]);
    } else {
        System.out.println("Using TextOutputFormat: " + args[7]);
    }
    long maxNumOfValuesPerGroup = 100;
    String jobName = "";
    if (args.length > 8) {
        maxNumOfValuesPerGroup = Long.parseLong(args[8]);
    }
    if (args.length > 9) {
        jobName = args[9];
    }
    Configuration defaults = new Configuration();
    JobConf job = new JobConf(defaults, OptimizedDataJoinJob.class);
    job.setJobName("DataJoinJob: " + jobName);

    FileSystem fs = FileSystem.get(defaults);
    fs.delete(new Path(outputDir));
    FileInputFormat.setInputPaths(job, inputDir);

    job.setInputFormat(inputFormat);

    job.setMapperClass(mapper);
    FileOutputFormat.setOutputPath(job, new Path(outputDir));
    job.setOutputFormat(outputFormat);
    SequenceFileOutputFormat.setOutputCompressionType(job, SequenceFile.CompressionType.BLOCK);
    job.setMapOutputKeyClass(CompositeKey.class);
    job.setMapOutputValueClass(mapoutputValueClass);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(outputValueClass);
    job.setReducerClass(reducer);

    job.setPartitionerClass(CompositeKeyPartitioner.class);
    job.setOutputKeyComparatorClass(CompositeKeyComparator.class);
    job.setOutputValueGroupingComparator(CompositeKeyOnlyComparator.class);

    job.setNumMapTasks(1);
    job.setNumReduceTasks(numOfReducers);
    job.setLong("datajoin.maxNumOfValuesPerGroup", maxNumOfValuesPerGroup);
    return job;
}

---

From source file:com.maxpoint.cascading.avro.AvroScheme.java

License:Open Source License

@Override
public void sinkConfInit(FlowProcess<JobConf> process,
        Tap<JobConf, RecordReader<AvroWrapper<Record>, Writable>, OutputCollector<AvroWrapper<Record>, Writable>> tap,
        JobConf conf) {
    conf.set(AvroJob.OUTPUT_SCHEMA, dataSchema.toString());
    conf.setOutputFormat(AvroOutputFormat.class);
    conf.setOutputKeyClass(AvroWrapper.class);

    // set compression
    AvroOutputFormat.setDeflateLevel(conf, 6);
    AvroJob.setOutputCodec(conf, DataFileConstants.DEFLATE_CODEC);
    AvroOutputFormat.setSyncInterval(conf, 1048576);
}

---

From source file:com.mh2c.WikipediaDumpLoaderDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    // arg checks

    JobConf conf = new JobConf(getClass());
    conf.setJobName("WP dump loader");

    // Set the mapper class, but skip the reduce phase
    conf.setMapperClass(WikipediaDumpLoaderMapper.class);
    conf.setNumReduceTasks(0);//from   ww  w .ja va  2s . co m
    // The object key/value pairs are text
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(Text.class);

    // Stream XML into the job
    conf.setInputFormat(StreamInputFormat.class);
    StreamInputFormat.addInputPath(conf, new Path(args[0]));
    // Use the XML record reader, with each page as one record
    conf.set("stream.recordreader.class", "org.apache.hadoop.streaming.StreamXmlRecordReader");
    conf.set("stream.recordreader.begin", "<page>");
    conf.set("stream.recordreader.end", "</page>");
    // Emit sequence files
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    SequenceFileOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);
    return 0;
}

---

From source file:com.mh2c.WikipediaWordCountDriver.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    // arg checks

    JobConf conf = new JobConf(getClass());
    conf.setJobName("WP word count");

    // Set the mapper and reducer classes, and use the reducer as a combiner
    conf.setMapperClass(WikipediaWordCountMapper.class);
    conf.setReducerClass(WikipediaWordCountReducer.class);
    conf.setCombinerClass(WikipediaWordCountReducer.class);
    // The object key/value pairs are text words and integer counts
    conf.setOutputKeyClass(Text.class);
    conf.setOutputValueClass(IntWritable.class);

    // Read in sequence files
    conf.setInputFormat(SequenceFileInputFormat.class);
    SequenceFileInputFormat.addInputPath(conf, new Path(args[0]));
    // Emit ordinary text files
    conf.setOutputFormat(TextOutputFormat.class);
    TextOutputFormat.setOutputPath(conf, new Path(args[1]));

    JobClient.runJob(conf);/* w w w.  j a  va2 s  . com*/
    return 0;
}

---

From source file:com.mongodb.hadoop.examples.treasury.TreasuryYieldXMLConfigV2.java

License:Apache License

public int run(final String[] args) throws Exception {
    final Configuration conf = getConf();
    final JobConf job = new JobConf(conf);
    job.setReducerClass(TreasuryYieldReducerV2.class);
    job.setMapperClass(TreasuryYieldMapperV2.class);
    job.setOutputFormat(MongoOutputFormat.class);
    job.setOutputKeyClass(MongoConfigUtil.getOutputKey(conf));
    job.setOutputValueClass(MongoConfigUtil.getOutputValue(conf));
    job.setMapOutputKeyClass(MongoConfigUtil.getMapperOutputKey(conf));
    job.setMapOutputValueClass(MongoConfigUtil.getMapperOutputValue(conf));
    job.setInputFormat(MongoInputFormat.class);
    JobClient.runJob(job);/*from ww  w.  ja v a  2s .c  o m*/
    return 0;
}

---

From source file:com.mongodb.hadoop.util.MongoTool.java

License:Apache License

private int runMapredJob(final Configuration conf) {
    final JobConf job = new JobConf(conf, getClass());
    /**//from w ww .  j  av a2  s . com
     * Any arguments specified with -D <property>=<value>
     * on the CLI will be picked up and set here
     * They override any XML level values
     * Note that -D<space> is important - no space will
     * not work as it gets picked up by Java itself
     */
    // TODO - Do we need to set job name somehow more specifically?
    // This may or may not be correct/sane
    job.setJarByClass(getClass());
    final Class<? extends org.apache.hadoop.mapred.Mapper> mapper = MapredMongoConfigUtil.getMapper(conf);

    LOG.debug("Mapper Class: " + mapper);
    LOG.debug("Input URI: " + conf.get(MapredMongoConfigUtil.INPUT_URI));
    job.setMapperClass(mapper);
    Class<? extends org.apache.hadoop.mapred.Reducer> combiner = MapredMongoConfigUtil.getCombiner(conf);
    if (combiner != null) {
        job.setCombinerClass(combiner);
    }
    job.setReducerClass(MapredMongoConfigUtil.getReducer(conf));

    job.setOutputFormat(MapredMongoConfigUtil.getOutputFormat(conf));
    job.setOutputKeyClass(MapredMongoConfigUtil.getOutputKey(conf));
    job.setOutputValueClass(MapredMongoConfigUtil.getOutputValue(conf));
    job.setInputFormat(MapredMongoConfigUtil.getInputFormat(conf));
    Class mapOutputKeyClass = MapredMongoConfigUtil.getMapperOutputKey(conf);
    Class mapOutputValueClass = MapredMongoConfigUtil.getMapperOutputValue(conf);

    if (mapOutputKeyClass != null) {
        job.setMapOutputKeyClass(mapOutputKeyClass);
    }
    if (mapOutputValueClass != null) {
        job.setMapOutputValueClass(mapOutputValueClass);
    }

    /**
     * Determines if the job will run verbosely e.g. print debug output
     * Only works with foreground jobs
     */
    final boolean verbose = MapredMongoConfigUtil.isJobVerbose(conf);
    /**
     * Run job in foreground aka wait for completion or background?
     */
    final boolean background = MapredMongoConfigUtil.isJobBackground(conf);
    try {
        RunningJob runningJob = JobClient.runJob(job);
        if (background) {
            LOG.info("Setting up and running MapReduce job in background.");
            return 0;
        } else {
            LOG.info("Setting up and running MapReduce job in foreground, will wait for results.  {Verbose? "
                    + verbose + "}");
            runningJob.waitForCompletion();
            return 0;
        }
    } catch (final Exception e) {
        LOG.error("Exception while executing job... ", e);
        return 1;
    }

}

---

From source file:com.mycompany.mavenproject1.App.java

public static void main(String[] args) throws IOException {

    // give time to attach debugger
    try {/*from   w  w  w .j  a  v a  2 s.c om*/
        Thread.sleep(8000);
    } catch (InterruptedException ex) {
        Logger.getLogger(App.class.getName()).log(Level.SEVERE, null, ex);
    }

    JobConf conf = new JobConf(App.class);

    // purge existing output file
    FileSystem fs = FileSystem.get(conf);
    fs.delete(new Path(args[1]), true); // delete file, true for recursive 

    conf.setJobName("wordcount");

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

    conf.setMapperClass(Map.class);
    conf.setCombinerClass(Reduce.class);
    conf.setReducerClass(Reduce.class);

    conf.setInputFormat(WholeFileInputFormat.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);
}

---

From source file:com.mycompany.MyHadoopSamples1.TransposeJob.java

License:Apache License

public static Configuration buildTransposeJobConf(Configuration initialConf, Path matrixInputPath,
        Path matrixOutputPath, int numInputRows) throws IOException {
    JobConf conf = new JobConf(initialConf, TransposeJob.class);
    conf.setJobName("TransposeJob: " + matrixInputPath + " transpose -> " + matrixOutputPath);
    FileSystem fs = FileSystem.get(conf);
    matrixInputPath = fs.makeQualified(matrixInputPath);
    matrixOutputPath = fs.makeQualified(matrixOutputPath);
    conf.setInt(NUM_ROWS_KEY, numInputRows);

    FileInputFormat.addInputPath(conf, matrixInputPath);
    conf.setInputFormat(SequenceFileInputFormat.class);
    FileOutputFormat.setOutputPath(conf, matrixOutputPath);
    System.out.println("OUTPUT --> " + matrixOutputPath.toString());
    conf.setMapperClass(TransposeMapper.class);
    conf.setMapOutputKeyClass(IntWritable.class);
    conf.setMapOutputValueClass(VectorWritable.class);
    conf.setCombinerClass(MergeVectorsCombiner.class);
    conf.setReducerClass(MergeVectorsReducer.class);
    conf.setOutputFormat(SequenceFileOutputFormat.class);
    conf.setOutputKeyClass(IntWritable.class);
    conf.setOutputValueClass(VectorWritable.class);
    return conf;//from  w  w  w  .ja  v  a  2 s  .com
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »