Package org.apache.hadoop.io.SequenceFile

Examples of org.apache.hadoop.io.SequenceFile.Writer

47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
  public void testJavaSerialization() throws Exception {
    Path file = new Path(System.getProperty("test.build.data",".") +
        "/test.seq");
   
    fs.delete(file, true);
    Writer writer = SequenceFile.createWriter(fs, conf, file, Long.class,
        String.class);
   
    writer.append(1L, "one");
    writer.append(2L, "two");
   
    writer.close();
   
    Reader reader = new Reader(fs, file, conf);
    assertEquals(1L, reader.next((Object) null));
    assertEquals("one", reader.getCurrentValue((Object) null));
    assertEquals(2L, reader.next((Object) null));
View Full Code Here
101
102
103
104
105
106
107
108
109
110
  /**
   *
   * Finds out the cluster directory of the vector and writes it into the specified cluster.
   */
  private void putVectorInRespectiveCluster(String clusterId, WeightedVectorWritable point) throws IOException {
    Writer writer = findWriterForVector(clusterId);
    postProcessedClusterDirectories.put(clusterId,
                                        PathDirectory.getClusterPathForClusterId(clusterPostProcessorOutput, clusterId));
    writeVectorToCluster(writer, point);
  }
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
  /**
   * Finds out the path in cluster where the point is supposed to be written.
   */
  private Writer findWriterForVector(String clusterId) throws IOException {
    Path clusterDirectory = PathDirectory.getClusterPathForClusterId(clusterPostProcessorOutput, clusterId);
    Writer writer = writersForClusters.get(clusterId);
    if (writer == null) {
      Path pathToWrite = new Path(clusterDirectory, new Path("part-m-0"));
      writer = new Writer(fileSystem, conf, pathToWrite, LongWritable.class, VectorWritable.class);
      writersForClusters.put(clusterId, writer);
    }
    return writer;
  }
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
    // store the output in a sequence file
    Path base = getTestTempDirPath("testdata");
    FileSystem fs = base.getFileSystem(conf);

    Path outputFile = new Path(base, "PartialBuilderTest.seq");
    Writer writer = SequenceFile.createWriter(fs, conf, outputFile,
        TreeID.class, MapredOutput.class);

    try {
      for (int index = 0; index < NUM_TREES; index++) {
        writer.append(keys[index], values[index]);
      }
    } finally {
      Closeables.closeQuietly(writer);
    }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
    FlumeConfiguration conf = FlumeConfiguration.get();
    Path path = new Path("hdfs://localhost/testfile");
    FileSystem hdfs = path.getFileSystem(conf);
    hdfs.deleteOnExit(path);

    Writer w = SequenceFile.createWriter(hdfs, conf, path,
        WriteableEventKey.class, WriteableEvent.class);
    b.mark("hdfs_fileopen_started");

    Event e = null;
    while ((e = mem.next()) != null) {
      // writing
      w.append(new WriteableEventKey(e), new WriteableEvent(e));
    }
    w.close();
    b.mark("seqfile_hdfs_write");

    hdfs.close();
    b.done();
  }
View Full Code Here
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
  }

  private void createFile(File dir, String fileName, int key, int count) throws IOException {
    File file = new File(dir, fileName);

    Writer writer = SequenceFile.createWriter(FileSystem.get(job), job, new Path(file.getAbsolutePath()), Text.class, IntWritable.class);

    Text text = new Text(Integer.toString(key));
    IntWritable value = new IntWritable();

    for (int i = 0, j = 0; i < count; i++, j = j == 9 ? 0 : j + 1) {
      value.set(j);

      writer.append(text, value);
    }

    writer.close();
  }
View Full Code Here
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
      writer.close();
    } else {
      CustomWritable key = new CustomWritable();
      CustomWritable value = new CustomWritable();

      Writer writer = SequenceFile.createWriter(getFileSystem(), getFileSystem().getConf(), path, CustomWritable.class,
          CustomWritable.class, CompressionType.BLOCK, defaultCodec);

      for (int k = 1, v = 100 * fileNum + 1; k <= fileNum; k++, v++) {
        key.set(k);
        value.set(v);

        writer.append(key, value);
      }

      writer.close();
    }
  }
View Full Code Here
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
99
100
101
102
103
  }

  @Test
  public void partition() throws IOException {

    Writer writer = SequenceFile.createWriter(fs, job, partitionMap, Text.class, IntWritable.class);

    Text key = new Text();
    IntWritable partNum = new IntWritable();

    key.set("bucket-1");
    partNum.set(0);
    writer.append(key, partNum);

    key.set("bucket-2");
    partNum.set(0);
    writer.append(key, partNum);

    key.set("bucket-3");
    partNum.set(1);
    writer.append(key, partNum);

    key.set("bucket-4");
    partNum.set(2);
    writer.append(key, partNum);

    key.set("bucket-5");
    partNum.set(2);
    writer.append(key, partNum);

    key.set("bucket-6");
    partNum.set(2);
    writer.append(key, partNum);

    writer.close();

    job.setNumReduceTasks(3);


    partitioner.configure(job);
View Full Code Here
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194

  @Test
  public void partitionWithFewerPartitionsThanReduceTasks() throws IOException {

    Writer writer = SequenceFile.createWriter(fs, job, partitionMap, Text.class, IntWritable.class);

    Text key = new Text();
    IntWritable partNum = new IntWritable();

    key.set("bucket-1");
    partNum.set(0);
    writer.append(key, partNum);

    key.set("bucket-2");
    partNum.set(0);
    writer.append(key, partNum);

    key.set("bucket-3");
    partNum.set(1);
    writer.append(key, partNum);

    key.set("bucket-4");
    partNum.set(2);
    writer.append(key, partNum);

    key.set("bucket-5");
    partNum.set(2);
    writer.append(key, partNum);

    key.set("bucket-6");
    partNum.set(2);
    writer.append(key, partNum);

    writer.close();

    job.setNumReduceTasks(40);


    partitioner.configure(job);
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
  }

  @Test
  public void noDupes() throws IOException {

    Writer writer = SequenceFile.createWriter(fs, job, partitionMap, Text.class, IntWritable.class);

    Text key = new Text();
    IntWritable value = new IntWritable();

    key.set("bucket-1");
    value.set(0);
    writer.append(key, value);

    key.set("bucket-2");
    value.set(0);
    writer.append(key, value);

    key.set("bucket-2");
    value.set(1);
    writer.append(key, value);

    writer.close();

    job.setNumReduceTasks(3);

    try {
      partitioner.configure(job);
View Full Code Here
TOP

Related Classes of org.apache.hadoop.io.SequenceFile.Writer

  • com.cloudera.flume.handlers.hdfs.DFSEventSink
  • com.cloudera.flume.handlers.hdfs.TestDFSWrite
  • com.cloudera.flume.PerfHdfsIO
  • com.digitalpebble.behemoth.SerializationTest
  • com.m6d.filecrush.crush.Crush
  • com.m6d.filecrush.crush.CrushPartitionerTest
  • com.m6d.filecrush.crush.CrushReducerParameterizedTest
  • com.m6d.filecrush.crush.CrushStandAloneSequenceFileTest
  • com.m6d.filecrush.crush.integration.CrushMapReduceTest
  • net.sf.katta.indexing.SequenceFileCreator
    • 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.