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

Introduction

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

Prototype

public void setCombinerClass(Class<? extends Reducer> cls) throws IllegalStateException 

Source Link

Document

Set the combiner class for the job.

Usage

From source file:com.cloudera.castagna.logparser.mr.StatusCodesStats.java

License:Apache License

@Override
public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.printf("Usage: %s [generic options] <input> <output>\n", getClass().getName());
        ToolRunner.printGenericCommandUsage(System.err);
        return -1;
    }//  w  w w  .j  av  a2s .  co m

    Configuration configuration = getConf();
    boolean useCompression = configuration.getBoolean(Constants.OPTION_USE_COMPRESSION,
            Constants.OPTION_USE_COMPRESSION_DEFAULT);

    if (useCompression) {
        configuration.setBoolean("mapred.compress.map.output", true);
        configuration.set("mapred.output.compression.type", "BLOCK");
        configuration.set("mapred.map.output.compression.codec", "org.apache.hadoop.io.compress.GzipCodec");
    }

    boolean overrideOutput = configuration.getBoolean(Constants.OPTION_OVERWRITE_OUTPUT,
            Constants.OPTION_OVERWRITE_OUTPUT_DEFAULT);
    FileSystem fs = FileSystem.get(new Path(args[1]).toUri(), configuration);
    if (overrideOutput) {
        fs.delete(new Path(args[1]), true);
    }

    Job job = Job.getInstance(configuration);
    job.setJobName(Constants.STATUS_CODES_STATS);
    job.setJarByClass(getClass());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setInputFormatClass(TextInputFormat.class);

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

    job.setCombinerClass(StatusCodesStatsCombiner.class);

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

    Utils.setReducers(job, configuration, log);

    job.setOutputFormatClass(TextOutputFormat.class);

    if (log.isDebugEnabled())
        Utils.log(job, log);

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

---

From source file:com.cloudera.hbase.WordCount.java

License:Open Source License

public int run(String[] args) throws Exception {
    if (args.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        return 2;
    }//w w w.jav  a2 s  . c o m

    Configuration conf = getConf();

    Job job = new Job(conf, "word count");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.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.cloudera.recordservice.examples.mapreduce.RecordCount.java

License:Apache License

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

    Job job = Job.getInstance(getConf());
    job.setJobName("recordcount");
    job.setJarByClass(RecordCount.class);
    job.setMapperClass(Map.class);
    job.setCombinerClass(Reduce.class);
    job.setReducerClass(Reduce.class);
    job.setNumReduceTasks(1);
    job.setOutputKeyClass(NullWritable.class);
    job.setOutputValueClass(LongWritable.class);

    RecordServiceConfig.setInputQuery(job.getConfiguration(), inputQuery);
    job.setInputFormatClass(RecordServiceInputFormat.class);
    job.setOutputFormatClass(TextOutputFormat.class);

    FileSystem fs = FileSystem.get(job.getConfiguration());
    Path outputPath = new Path(output);
    if (fs.exists(outputPath))
        fs.delete(outputPath, true);
    FileOutputFormat.setOutputPath(job, outputPath);

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

---

From source file:com.cloudera.sa.hbasebulkload.HBASEBulkLoadDriver.java

@Override
public int run(String[] args) throws Exception {
    Configuration config = getConf();
    args = new GenericOptionsParser(config, args).getRemainingArgs();

    if (args.length < 6) {
        /*System.out.println("hadoop jar HBASEBulkLoad.jar "
         + "com.cloudera.sa.hbasebulkload.HBASEBulkLoadDriver"
         + " <inputpath> <outputpath> <hbaseTable> <hbaseColumnFamily"
         + " \"<hbaseColumns (delimiter seperated)>\" <column delimiter>");*/
        ToolRunner.printGenericCommandUsage(System.out);
        return 2;
    }/*from ww w  .  jav  a 2  s . c o m*/

    String hbaseTab = args[2];
    String hbaseColumnFamily = args[3];
    String hbaseColumns = args[4];
    String hbaseColumnSeperator = args[5];
    config.set(HBASEBulkLoadConstants.HBASE_TABLE_KEY, hbaseTab.trim().toLowerCase(Locale.ENGLISH));
    config.set(HBASEBulkLoadConstants.HBASE_COLUMN_FAMILY_KEY, hbaseColumnFamily);
    config.set(HBASEBulkLoadConstants.HBASE_COLUMNS_KEY, hbaseColumns.trim().toLowerCase(Locale.ENGLISH));
    config.set(HBASEBulkLoadConstants.HBASE_COLUMN_SEPERATOR_KEY, hbaseColumnSeperator);
    System.out.println(2);
    Job job = Job.getInstance(config, this.getClass().getName() + "-" + hbaseTab);
    HBaseConfiguration.addHbaseResources(config);

    job.setInputFormatClass(TextInputFormat.class);
    job.setJarByClass(HBASEBulkLoadDriver.class);
    job.setMapperClass(HBASEBulkLoadKeyValueMapper.class);
    job.setMapOutputKeyClass(ImmutableBytesWritable.class);
    job.setMapOutputValueClass(Put.class);
    job.setCombinerClass(PutCombiner.class);
    job.setReducerClass(PutSortReducer.class);

    Connection connection = ConnectionFactory.createConnection(config);
    Table hTab = connection.getTable(TableName.valueOf(hbaseTab));

    FileSystem.get(getConf()).delete(new Path(args[1]), true);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    //job.setOutputFormatClass(HFileOutputFormat2.class);
    TableMapReduceUtil.initTableReducerJob(hTab.getName().getNameAsString(), null, job);
    //job.setNumReduceTasks(0);
    TableMapReduceUtil.addDependencyJars(job);
    HFileOutputFormat2.configureIncrementalLoadMap(job, hTab);

    int exitCode = job.waitForCompletion(true) ? HBASEBulkLoadConstants.SUCCESS
            : HBASEBulkLoadConstants.FAILURE;
    System.out.println(8);
    if (HBASEBulkLoadConstants.SUCCESS == exitCode) {
        LoadIncrementalHFiles loader = new LoadIncrementalHFiles(config);
        loader.doBulkLoad(new Path(args[1]), (HTable) hTab);
        connection.close();
    }
    return exitCode;
}

---

From source file:com.cloudera.sa.securewordcount.SecureWordCountDriver.java

@Override
public int run(String[] args) throws Exception {
    Configuration config = getConf();
    args = new GenericOptionsParser(config, args).getRemainingArgs();

    if (args.length < 2) {

        ToolRunner.printGenericCommandUsage(System.out);
        return 2;
    }/* w  ww  .  j av  a 2 s . c o  m*/
    Job job = Job.getInstance(config, this.getClass().getName() + "-wordcount");
    job.setJarByClass(SecureWordCountDriver.class);
    job.setInputFormatClass(TextInputFormat.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.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.cloudera.traffic.AveragerRunner.java

License:Apache License

public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    Job job = new Job(conf);
    job.setJarByClass(AveragerRunner.class);
    job.setMapperClass(AveragerMapper.class);
    job.setReducerClass(AveragerReducer.class);
    job.setCombinerClass(AveragerReducer.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(AverageWritable.class);
    job.setInputFormatClass(TextInputFormat.class);

    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

    job.waitForCompletion(true);// w  w w . ja  v a2 s . c  om
}

---

From source file:com.conversantmedia.mapreduce.example.WordCount.java

License:Apache License

public static void main(String[] args) {

    try {//from   ww w .j  a va  2s.co m
        Job job = Job.getInstance(new Configuration(), "WordCount v2");

        job.setInputFormatClass(FileInputFormat.class);
        job.setOutputFormatClass(FileOutputFormat.class);

        job.setMapperClass(WordCountMapper.class);
        job.setReducerClass(WordCountReducer.class);
        job.setCombinerClass(WordCountReducer.class);

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

        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.waitForCompletion(true);

    } catch (IOException | ClassNotFoundException | InterruptedException e) {
        e.printStackTrace();
    }
}

---

From source file:com.conversantmedia.mapreduce.tool.annotation.handler.CombinerInfoHandler.java

License:Apache License

@Override
@SuppressWarnings("rawtypes")
public void process(Annotation annotation, Job job, Object target) {
    CombinerInfo combine = (CombinerInfo) annotation;
    if (combine != null && combine.value() != org.apache.hadoop.mapreduce.Reducer.class) {
        Class<? extends Reducer> combinerClass = combine.value();
        job.setCombinerClass(combinerClass);
    }/*w ww . j a  va2s.co  m*/
}

---

From source file:com.datasalt.pangool.benchmark.wordcount.HadoopWordCount.java

License:Apache License

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);// w w w. java 2  s. c o  m
    }
    //conf.setBoolean("hadoop.security.authorization", false);
    //conf.set("hadoop.security.authentication","simple");
    Job job = new Job(conf, "word count");
    job.setJarByClass(HadoopWordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    HadoopUtils.deleteIfExists(FileSystem.get(conf), new Path(otherArgs[1]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    job.waitForCompletion(true);
}

---

From source file:com.datasalt.pangool.tuplemr.TupleMRBuilder.java

License:Apache License

public Job createJob() throws IOException, TupleMRException {

    failIfNull(tupleReducer, "Need to set a group handler");
    failIfEmpty(multipleInputs.getMultiInputs(), "Need to add at least one input");
    failIfNull(outputFormat, "Need to set output format");
    failIfNull(outputKeyClass, "Need to set outputKeyClass");
    failIfNull(outputValueClass, "Need to set outputValueClass");
    failIfNull(outputPath, "Need to set outputPath");

    // perform a deep copy of the Configuration
    this.conf = new Configuration(this.conf);

    TupleMRConfig tupleMRConf = buildConf();
    // Serialize PangoolConf in Hadoop Configuration
    instanceFilesCreated.addAll(TupleMRConfig.set(tupleMRConf, conf));
    Job job = (jobName == null) ? new Job(conf) : new Job(conf, jobName);
    if (tupleMRConf.getRollupFrom() != null) {
        job.setReducerClass(RollupReducer.class);
    } else {//  ww  w.jav a 2  s  . c  o  m
        job.setReducerClass(SimpleReducer.class);
    }

    if (tupleCombiner != null) {
        job.setCombinerClass(SimpleCombiner.class); // not rollup by now
        // Set Combiner Handler
        String uniqueName = UUID.randomUUID().toString() + '.' + "combiner-handler.dat";
        try {
            InstancesDistributor.distribute(tupleCombiner, uniqueName, job.getConfiguration());
            instanceFilesCreated.add(uniqueName);
            job.getConfiguration().set(SimpleCombiner.CONF_COMBINER_HANDLER, uniqueName);
        } catch (URISyntaxException e1) {
            throw new TupleMRException(e1);
        }
    }

    // Set Tuple Reducer
    try {
        String uniqueName = UUID.randomUUID().toString() + '.' + "group-handler.dat";
        InstancesDistributor.distribute(tupleReducer, uniqueName, job.getConfiguration());
        instanceFilesCreated.add(uniqueName);
        job.getConfiguration().set(SimpleReducer.CONF_REDUCER_HANDLER, uniqueName);
    } catch (URISyntaxException e1) {
        throw new TupleMRException(e1);
    }

    // Enabling serialization
    TupleSerialization.enableSerialization(job.getConfiguration());

    job.setJarByClass((jarByClass != null) ? jarByClass : tupleReducer.getClass());
    job.setMapOutputKeyClass(DatumWrapper.class);
    job.setMapOutputValueClass(NullWritable.class);
    job.setPartitionerClass(TupleHashPartitioner.class);
    job.setGroupingComparatorClass(GroupComparator.class);
    job.setSortComparatorClass(SortComparator.class);
    job.setOutputKeyClass(outputKeyClass);
    job.setOutputValueClass(outputValueClass);
    FileOutputFormat.setOutputPath(job, outputPath);
    instanceFilesCreated.addAll(multipleInputs.configureJob(job));
    instanceFilesCreated.addAll(namedOutputs.configureJob(job));
    // Configure a {@link ProxyOutputFormat} for Pangool's Multiple Outputs to
    // work: {@link PangoolMultipleOutput}
    String uniqueName = UUID.randomUUID().toString() + '.' + "out-format.dat";
    try {
        InstancesDistributor.distribute(outputFormat, uniqueName, conf);
        instanceFilesCreated.add(uniqueName);
    } catch (URISyntaxException e1) {
        throw new TupleMRException(e1);
    }
    job.getConfiguration().set(ProxyOutputFormat.PROXIED_OUTPUT_FORMAT_CONF, uniqueName);
    job.setOutputFormatClass(ProxyOutputFormat.class);

    return job;
}

---

• «
• 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
• »