Package org.apache.hadoop.mapreduce

Examples of org.apache.hadoop.mapreduce.RecordReader

272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
    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);

    // First value is first filename.
    assertTrue(rr.nextKeyValue());
    assertEquals("file1", rr.getCurrentValue().toString());

    // The inner RR will return false, because it only emits one (k, v) pair.
    // But there's another sub-split to process. This returns true to us.
    assertTrue(rr.nextKeyValue());
   
    // And the 2nd rr will have its initialize method called correctly.
    assertEquals("file2", rr.getCurrentValue().toString());
   
    // But after both child RR's have returned their singleton (k, v), this
    // should also return false.
    assertFalse(rr.nextKeyValue());
  }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
                testFile.length(), null);
        System.out.println("reading Gremlin Kryo file " + testFile.getAbsolutePath() + " (" + testFile.length() + " bytes)");

        KryoInputFormat inputFormat = ReflectionUtils.newInstance(KryoInputFormat.class, conf);
        TaskAttemptContext job = new TaskAttemptContext(conf, new TaskAttemptID());
        RecordReader reader = inputFormat.createRecordReader(split, job);

        ByteArrayOutputStream bos = new ByteArrayOutputStream();
        try (DataOutputStream dos = new DataOutputStream(bos)) {
            KryoOutputFormat outputFormat = new KryoOutputFormat();
            RecordWriter writer = outputFormat.getRecordWriter(job, dos);

            float lastProgress = -1f;
            int count = 0;
            boolean foundKeyValue = false;
            while (reader.nextKeyValue()) {
                //System.out.println("" + reader.getProgress() + "> " + reader.getCurrentKey() + ": " + reader.getCurrentValue());
                count++;
                float progress = reader.getProgress();
                assertTrue(progress >= lastProgress);
                assertEquals(NullWritable.class, reader.getCurrentKey().getClass());
                GiraphComputeVertex v = (GiraphComputeVertex) reader.getCurrentValue();
                writer.write(NullWritable.get(), v);

                Vertex vertex = v.getBaseVertex();
                assertEquals(Integer.class, vertex.id().getClass());
View Full Code Here
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
                testFile.length(), null);
        System.out.println("reading GraphSON adjacency file " + testFile.getAbsolutePath() + " (" + testFile.length() + " bytes)");

        GraphSONInputFormat inputFormat = ReflectionUtils.newInstance(GraphSONInputFormat.class, conf);
        TaskAttemptContext job = new TaskAttemptContext(conf, new TaskAttemptID());
        RecordReader reader = inputFormat.createRecordReader(split, job);

        ByteArrayOutputStream bos = new ByteArrayOutputStream();
        try (DataOutputStream dos = new DataOutputStream(bos)) {
            GraphSONOutputFormat outputFormat = new GraphSONOutputFormat();
            RecordWriter writer = outputFormat.getRecordWriter(job, dos);

            float lastProgress = -1f;
            int count = 0;
            boolean foundKeyValue = false;
            while (reader.nextKeyValue()) {
                //System.out.println("" + reader.getProgress() + "> " + reader.getCurrentKey() + ": " + reader.getCurrentValue());
                count++;
                float progress = reader.getProgress();
                assertTrue(progress >= lastProgress);
                assertEquals(NullWritable.class, reader.getCurrentKey().getClass());
                GiraphComputeVertex v = (GiraphComputeVertex) reader.getCurrentValue();
                writer.write(NullWritable.get(), v);

                Vertex vertex = v.getBaseVertex();
                assertEquals(Integer.class, vertex.id().getClass());
View Full Code Here
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
    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",
      rr.getCurrentKey().toString());

    // Switch the active context for the RecordReader...
    Configuration conf2 = new Configuration();
    conf2.set(DUMMY_KEY, "STATE2");
    TaskAttemptContext context2 = new TaskAttemptContextImpl(conf2, taskId);
    rr.initialize(split, context2);

    // And verify that the new context is updated into the child record reader.
    assertEquals("Invalid secondary dummy key value", "STATE2",
      rr.getCurrentKey().toString());
  }
View Full Code Here
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
    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);

    // First value is first filename.
    assertTrue(rr.nextKeyValue());
    assertEquals("file1", rr.getCurrentValue().toString());

    // The inner RR will return false, because it only emits one (k, v) pair.
    // But there's another sub-split to process. This returns true to us.
    assertTrue(rr.nextKeyValue());
   
    // And the 2nd rr will have its initialize method called correctly.
    assertEquals("file2", rr.getCurrentValue().toString());
   
    // But after both child RR's have returned their singleton (k, v), this
    // should also return false.
    assertFalse(rr.nextKeyValue());
  }
View Full Code Here
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
    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",
      rr.getCurrentKey().toString());

    // Switch the active context for the RecordReader...
    Configuration conf2 = new Configuration();
    conf2.set(DUMMY_KEY, "STATE2");
    TaskAttemptContext context2 = new TaskAttemptContextImpl(conf2, taskId);
    rr.initialize(split, context2);

    // And verify that the new context is updated into the child record reader.
    assertEquals("Invalid secondary dummy key value", "STATE2",
      rr.getCurrentKey().toString());
  }
View Full Code Here
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
    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);

    // First value is first filename.
    assertTrue(rr.nextKeyValue());
    assertEquals("file1", rr.getCurrentValue().toString());

    // The inner RR will return false, because it only emits one (k, v) pair.
    // But there's another sub-split to process. This returns true to us.
    assertTrue(rr.nextKeyValue());
   
    // And the 2nd rr will have its initialize method called correctly.
    assertEquals("file2", rr.getCurrentValue().toString());
   
    // But after both child RR's have returned their singleton (k, v), this
    // should also return false.
    assertFalse(rr.nextKeyValue());
  }
View Full Code Here
92
93
94
95
96
97
98
99
100
101
    CombineFileSplit combineSplit = (CombineFileSplit) split;

    // Use CombineFileRecordReader since this can handle CombineFileSplits
    // and instantiate another RecordReader in a loop; do this with the
    // CombineShimRecordReader.
    RecordReader rr = new CombineFileRecordReader(combineSplit, context,
        CombineShimRecordReader.class);

    return rr;
  }
View Full Code Here
89
90
91
92
93
94
95
96
97
98
    CombineFileSplit combineSplit = (CombineFileSplit) split;

    // Use CombineFileRecordReader since this can handle CombineFileSplits
    // and instantiate another RecordReader in a loop; do this with the
    // CombineShimRecordReader.
    RecordReader rr = new CombineFileRecordReader(combineSplit, context,
        CombineShimRecordReader.class);

    return rr;
  }
View Full Code Here
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
    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",
      rr.getCurrentKey().toString());

    // Switch the active context for the RecordReader...
    Configuration conf2 = new Configuration();
    conf2.set(DUMMY_KEY, "STATE2");
    TaskAttemptContext context2 = new TaskAttemptContextImpl(conf2, taskId);
    rr.initialize(split, context2);

    // And verify that the new context is updated into the child record reader.
    assertEquals("Invalid secondary dummy key value", "STATE2",
      rr.getCurrentKey().toString());
  }
View Full Code Here
TOP

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

  • com.endgame.binarypig.loaders.AbstractExecutingLoaderTest
  • com.endgame.binarypig.loaders.BinarySequenceFileLoaderTest
  • com.facebook.giraph.hive.impl.input.benchmark.InputBenchmark
  • com.tinkerpop.gremlin.giraph.structure.io.graphson.GraphSONRecordReaderWriterTest
  • com.tinkerpop.gremlin.giraph.structure.io.kryo.KryoRecordReaderWriterTest
  • com.twitter.elephantbird.pig.load.TestLocationAsTuple
  • org.apache.hadoop.mapreduce.lib.chain.Chain
  • org.apache.hadoop.mapreduce.lib.input.TestCombineFileInputFormat
  • org.apache.hcatalog.mapreduce.HCatBaseInputFormat
  • org.apache.howl.mapreduce.HowlInputFormat
    • 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.