Package org.apache.hadoop.mapred

Examples of org.apache.hadoop.mapred.InputSplit

222
223
224
225
226
227
228
229
230
231
232
    secondOutput = new PartialOutputCollector(total);
    Reporter reporter = Reporter.NULL;
    long slowest = 0; // duration of slowest map

    for (int partition = 0; partition < splits.length; partition++) {
      InputSplit split = splits[partition];
      RecordReader<LongWritable, Text> reader = input.getRecordReader(split,
          job, reporter);

      LongWritable key = reader.createKey();
      Text value = reader.createValue();
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    Step0OutputCollector collector = new Step0OutputCollector(numMaps);
    Reporter reporter = Reporter.NULL;

    for (int p = 0; p < numMaps; p++) {
      InputSplit split = sorted[p];
      RecordReader<LongWritable, Text> reader = input.getRecordReader(split, job, reporter);

      LongWritable key = reader.createKey();
      Text value = reader.createValue();
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
    Step0Output[] values = new Step0Output[numMaps];
   
    int[] expectedIds = new int[numMaps];
   
    for (int p = 0; p < numMaps; p++) {
      InputSplit split = sorted[p];
      RecordReader<LongWritable, Text> reader = input.getRecordReader(split, job, reporter);

      LongWritable key = reader.createKey();
      Text value = reader.createValue();
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
    HBaseTestingUtility.SeenRowTracker rowTracker =
      new HBaseTestingUtility.SeenRowTracker(startRow, stopRow);

    for (int i = 0; i < splits.length; i++) {
      // validate input split
      InputSplit split = splits[i];
      Assert.assertTrue(split instanceof TableSnapshotInputFormat.TableSnapshotRegionSplit);

      // validate record reader
      OutputCollector collector = mock(OutputCollector.class);
      Reporter reporter = mock(Reporter.class);
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
  public void testSerializedPayload() throws IOException {

    Configuration conf = new Configuration(false);
    conf.setBoolean(MRJobConfig.MR_TEZ_INPUT_INITIALIZER_SERIALIZE_EVENT_PAYLAOD, true);
    ByteString confByteString = MRHelpers.createByteStringFromConf(conf);
    InputSplit split1 = new InputSplitForTest(1);
    InputSplit split2 = new InputSplitForTest(2);
    MRSplitProto proto1 = MRHelpers.createSplitProto(split1);
    MRSplitProto proto2 = MRHelpers.createSplitProto(split2);
    MRSplitsProto.Builder splitsProtoBuilder = MRSplitsProto.newBuilder();
    splitsProtoBuilder.addSplits(proto1);
    splitsProtoBuilder.addSplits(proto2);
    MRInputUserPayloadProto.Builder payloadProto = MRInputUserPayloadProto.newBuilder();
    payloadProto.setSplits(splitsProtoBuilder.build());
    payloadProto.setConfigurationBytes(confByteString);
    byte[] userPayload = payloadProto.build().toByteArray();

    TezRootInputInitializerContext context = new TezRootInputInitializerContextForTest(userPayload);
    MRInputSplitDistributor splitDist = new MRInputSplitDistributor();

    List<Event> events = splitDist.initialize(context);

    assertEquals(3, events.size());
    assertTrue(events.get(0) instanceof RootInputUpdatePayloadEvent);
    assertTrue(events.get(1) instanceof RootInputDataInformationEvent);
    assertTrue(events.get(2) instanceof RootInputDataInformationEvent);

    RootInputDataInformationEvent diEvent1 = (RootInputDataInformationEvent) (events.get(1));
    RootInputDataInformationEvent diEvent2 = (RootInputDataInformationEvent) (events.get(2));

    assertNull(diEvent1.getDeserializedUserPayload());
    assertNull(diEvent2.getDeserializedUserPayload());

    assertNotNull(diEvent1.getUserPayload());
    assertNotNull(diEvent2.getUserPayload());

    MRSplitProto event1Proto = MRSplitProto.parseFrom(diEvent1.getUserPayload());
    InputSplit is1 = MRInput.getOldSplitDetailsFromEvent(event1Proto, new Configuration());
    assertTrue(is1 instanceof InputSplitForTest);
    assertEquals(1, ((InputSplitForTest) is1).identifier);

    MRSplitProto event2Proto = MRSplitProto.parseFrom(diEvent2.getUserPayload());
    InputSplit is2 = MRInput.getOldSplitDetailsFromEvent(event2Proto, new Configuration());
    assertTrue(is2 instanceof InputSplitForTest);
    assertEquals(2, ((InputSplitForTest) is2).identifier);
  }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
  public void testDeserializedPayload() throws IOException {

    Configuration conf = new Configuration(false);
    conf.setBoolean(MRJobConfig.MR_TEZ_INPUT_INITIALIZER_SERIALIZE_EVENT_PAYLAOD, false);
    ByteString confByteString = MRHelpers.createByteStringFromConf(conf);
    InputSplit split1 = new InputSplitForTest(1);
    InputSplit split2 = new InputSplitForTest(2);
    MRSplitProto proto1 = MRHelpers.createSplitProto(split1);
    MRSplitProto proto2 = MRHelpers.createSplitProto(split2);
    MRSplitsProto.Builder splitsProtoBuilder = MRSplitsProto.newBuilder();
    splitsProtoBuilder.addSplits(proto1);
    splitsProtoBuilder.addSplits(proto2);
View Full Code Here
185
186
187
188
189
190
191
192
    outMeta.close();
  }

  public static void generateInputSplit(FileSystem fs, Path workDir, JobConf jobConf, Path mapInput) throws IOException {
    jobConf.setInputFormat(SequenceFileInputFormat.class);
    InputSplit split = createInputSplit(fs, workDir, jobConf, mapInput);
    writeSplitFiles(fs, jobConf, split);
  }
View Full Code Here
951
952
953
954
955
956
957
958
959
    }

    Deserializer<InputSplit> deserializer = serializationFactory
        .getDeserializer(clazz);
    deserializer.open(splitProto.getSplitBytes().newInput());
    InputSplit inputSplit = deserializer.deserialize(null);
    deserializer.close();
    return inputSplit;
  }
View Full Code Here
178
179
180
181
182
183
184
185
186
187
188
    // Initialize input in-line since it sets parameters which may be used by the processor.
    // Done only for MRInput.
    // TODO use new method in MRInput to get required info
    //input.initialize(job, master);
   
    InputSplit inputSplit = input.getOldInputSplit();
   
    updateJobWithSplit(job, inputSplit);

    RecordReader in = new OldRecordReader(input);
View Full Code Here
182
183
184
185
186
187
188
189
    outMeta.close();
  }

  public static void generateInputSplit(FileSystem fs, Path workDir, JobConf jobConf, Path mapInput) throws IOException {
    jobConf.setInputFormat(SequenceFileInputFormat.class);
    InputSplit split = createInputSplit(fs, workDir, jobConf, mapInput);
    writeSplitFiles(fs, jobConf, split);
  }
View Full Code Here
TOP

Related Classes of org.apache.hadoop.mapred.InputSplit

  • com.ebay.erl.mobius.core.mapred.MobiusInputSampler
  • com.sap.hadoop.windowing.io.TableWindowingInput
  • com.taobao.zeus.jobs.sub.tool.DataPreviewJob
  • org.apache.accumulo.core.client.mapred.AccumuloInputFormatTest
  • org.apache.drill.exec.store.hive.HiveSubScan
  • org.apache.hadoop.contrib.mongoreduce.MongoStreamInputFormat
  • org.apache.hadoop.hbase.mapred.TestTableSnapshotInputFormat
  • org.apache.hadoop.hive.accumulo.mr.TestHiveAccumuloTableInputFormat
  • org.apache.hadoop.hive.ql.exec.StatsNoJobTask
  • org.apache.hadoop.hive.ql.exec.StatsNoJobTask$StatsCollection
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.