Examples of org.apache.hadoop.mapreduce.InputFormat

org.apache.hadoop.mapreduce.InputFormat
InputFormat describes the input-specification for a Map-Reduce job.
The Map-Reduce framework relies on the InputFormat of the job to:
1. Validate the input-specification of the job.
2. Split-up the input file(s) into logical {@link InputSplit}s, each of which is then assigned to an individual {@link Mapper}.
3. Provide the {@link RecordReader} implementation to be used to gleaninput records from the logical InputSplit for processing by the {@link Mapper}.
The default behavior of file-based {@link InputFormat}s, typically sub-classes of {@link FileInputFormat}, is to split the input into logical {@link InputSplit}s based on the total size, in bytes, of the input files. However, the {@link FileSystem} blocksize of the input files is treated as an upper bound for input splits. A lower bound on the split size can be set via mapred.min.split.size.

Clearly, logical splits based on input-size is insufficient for many applications since record boundaries are to respected. In such cases, the application has to also implement a {@link RecordReader} on whom lies theresponsibility to respect record-boundaries and present a record-oriented view of the logical InputSplit to the individual task. @see InputSplit @see RecordReader @see FileInputFormat

   */
  @SuppressWarnings("unchecked") // getInputFormat, getOutputKeyComparator
  public static <K,V> void writePartitionFile(Job job, Sampler<K,V> sampler) 
      throws IOException, ClassNotFoundException, InterruptedException {
    Configuration conf = job.getConfiguration();
    final InputFormat inf = 
        ReflectionUtils.newInstance(job.getInputFormatClass(), conf);
    int numPartitions = job.getNumReduceTasks();
    K[] samples = sampler.getSample(inf, job);
    LOG.info("Using " + samples.length + " samples");
    RawComparator<K> comparator =

View Full Code Here

    conf1.set(DUMMY_KEY, "STATE1");
    TaskAttemptContext context1 = new TaskAttemptContextImpl(conf1, taskId);


    // This will create a CombineFileRecordReader that itself contains a
    // DummyRecordReader.
    InputFormat inputFormat = new ChildRRInputFormat();


    Path [] files = { new Path("file1") };
    long [] lengths = { 1 };


    CombineFileSplit split = new CombineFileSplit(files, lengths);


    RecordReader rr = inputFormat.createRecordReader(split, context1);
    assertTrue("Unexpected RR type!", rr instanceof CombineFileRecordReader);


    // Verify that the initial configuration is the one being used.
    // Right after construction the dummy key should have value "STATE1"
    assertEquals("Invalid initial dummy key value", "STATE1",

View Full Code Here

    Configuration conf = new Configuration();
    TaskAttemptContext context = new TaskAttemptContextImpl(conf, taskId);


    // This will create a CombineFileRecordReader that itself contains a
    // DummyRecordReader.
    InputFormat inputFormat = new ChildRRInputFormat();


    Path [] files = { new Path("file1"), new Path("file2") };
    long [] lengths = { 1, 1 };


    CombineFileSplit split = new CombineFileSplit(files, lengths);
    RecordReader rr = inputFormat.createRecordReader(split, context);
    assertTrue("Unexpected RR type!", rr instanceof CombineFileRecordReader);


    // first initialize() call comes from MapTask. We'll do it here.
    rr.initialize(split, context);

View Full Code Here

    }
  }
  
  public void testGetInputFormat() throws IOException
  {
    InputFormat f = underTest.getInputFormat();
    assertEquals(f.getClass(), SequenceFileInputFormat.class);
  }

View Full Code Here

    assertTrue(reader == underTest.reader);
  }
  
  public void testGetInputFormat() throws IOException
  {
    InputFormat f = underTest.getInputFormat();
    assertEquals(f.getClass(), SequenceFileInputFormat.class);
  }

View Full Code Here

        PigInputFormat.mergeSplitSpecificConf(loadFunc, pigSplit, conf);
        
        // for backward compatibility
        PigInputFormat.sJob = conf;
        
        InputFormat inputFormat = loadFunc.getInputFormat();
        
        return new PigRecordReader(inputFormat, pigSplit, loadFunc, context);
    }

View Full Code Here

                        inputSpecificJob);
                // The above setLocation call could write to the conf within
                // the inputSpecificJob - use this updated conf
                
                // get the InputFormat from it and ask for splits
                InputFormat inpFormat = loadFunc.getInputFormat();
                List<InputSplit> oneInputSplits = inpFormat.getSplits(
                        HadoopShims.createJobContext(inputSpecificJob.getConfiguration(), 
                                jobcontext.getJobID()));
                List<InputSplit> oneInputPigSplits = getPigSplits(
                        oneInputSplits, i, inpTargets.get(i), fs.getDefaultBlockSize(), combinable, confClone);
                splits.addAll(oneInputPigSplits);

View Full Code Here

                            LoadFunc loader = (LoadFunc) PigContext
                            .instantiateFuncFromSpec(ld.getLFile()
                                    .getFuncSpec());
                            Job job = new Job(conf);
                            loader.setLocation(location, job);
                            InputFormat inf = loader.getInputFormat();
                            List<InputSplit> splits = inf.getSplits(HadoopShims.cloneJobContext(job));
                            List<List<InputSplit>> results = MapRedUtil
                            .getCombinePigSplits(splits, fs
                                    .getDefaultBlockSize(), conf);
                            numFiles += results.size();
                        } else {

View Full Code Here

      writer.write("str1" + " " + "str2" + " " + "30" + " " + "4000" + "\n");
    }
    writer.close();


    Schema schema = new Schema("schema", Fields.parse("a:string, b:string, c:int, d:long"));
    InputFormat inputFormat = new TupleTextInputFormat(schema, false, false, ' ',
        TupleTextInputFormat.NO_QUOTE_CHARACTER, TupleTextInputFormat.NO_ESCAPE_CHARACTER,
        FieldSelector.NONE, TupleTextInputFormat.NO_NULL_STRING);


    Configuration conf = getConf();
    conf.setLong("mapred.min.split.size", 10 * 1024);

View Full Code Here

  }


  @Test
  public void testInputCompression() throws Exception {
    Schema schema = new Schema("schema", Fields.parse("a:string, b:string, c:int, d:long"));
    InputFormat inputFormat = new TupleTextInputFormat(schema, false, false, ' ',
        TupleTextInputFormat.NO_QUOTE_CHARACTER, TupleTextInputFormat.NO_ESCAPE_CHARACTER,
        FieldSelector.NONE, TupleTextInputFormat.NO_NULL_STRING);


    Configuration conf = getConf();
    FileSystem fS = FileSystem.get(conf);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.hadoop.mapreduce.InputFormat

bulkimport.BulkImportJobExample$VerboseInputSampler

com.datasalt.pangool.tuplemr.mapred.lib.input.DelegatingInputFormat

com.datasalt.pangool.tuplemr.mapred.lib.output.TestTupleTextInputOutputFormat

com.endgame.binarypig.loaders.AbstractExecutingLoaderTest

com.endgame.binarypig.loaders.BinarySequenceFileLoaderTest

org.apache.hadoop.hbase.mapreduce.hadoopbackport.InputSampler

org.apache.hadoop.mapreduce.lib.input.DelegatingInputFormat

org.apache.hadoop.mapreduce.lib.input.MultipleInputs

org.apache.hadoop.mapreduce.lib.input.TestCombineFileInputFormat

org.apache.hadoop.mapreduce.lib.partition.InputSampler

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.