Examples of SequenceFile

Examples of cascading.scheme.hadoop.SequenceFile

75
76
77
78
79
80
81
82
83
84
85
  private static BloomFilter mergeBloomParts(String tapPath, long numBloomBits, long splitSize, int numBloomHashes, long numElems) throws IOException {
    FixedSizeBitSet bitSet = new FixedSizeBitSet(numBloomBits);

    if (FileSystemHelper.getFS().exists(new Path(tapPath))) {
      Hfs tap = new Hfs(new SequenceFile(new Fields("split", "filter")), tapPath);
      TupleEntryIterator itr = tap.openForRead(CascadingUtil.get().getFlowProcess());
      while (itr.hasNext()) {
        TupleEntry cur = itr.next();
        long split = cur.getLong(0);
        FixedSizeBitSet curSet = new FixedSizeBitSet(splitSize, ((BytesWritable) cur.getObject(1)).getBytes());
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

161
162
163
164
165
166
167
168
169
170
171
  private static long getApproxDistinctKeysCount(JobConf conf, String partsDir) throws IOException, CardinalityMergeException {
    if (!FileSystemHelper.getFS().exists(new Path(partsDir))) {
      return 0;
    }

    Hfs approxCountsTap = new Hfs(new SequenceFile(new Fields("bytes")), partsDir);

    TupleEntryIterator in = approxCountsTap.openForRead(CascadingUtil.get().getFlowProcess());
    List<HyperLogLog> countParts = new LinkedList<HyperLogLog>();

    long totalSum = 0;
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

44
45
46
47
48
49
50
51
52
53
54
    Map<String, Tap> sources = new HashMap<String, Tap>();
    sources.put("source1", ExampleFixtures.SOURCE_TAP_1);
    sources.put("source2", ExampleFixtures.SOURCE_TAP_2);

    String outputDir = args[0];
    Hfs sink = new Hfs(new SequenceFile(new Fields("field1", "field2", "field3", "field4")), outputDir);

    Pipe source1 = new Pipe("source1");
    Pipe source2 = new Pipe("source2");

    Pipe joined = new BloomJoin(source1, new Fields("field1"), source2, new Fields("field3"));
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

38
39
40
41
42
43
44
45
46
47
48
      System.out.println("Usage: hadoop jar cascading_ext.job.jar com.liveramp.cascading_ext.example.SimpleFlowExample <output dir>");
      return;
    }

    String outputDir = args[0];
    Hfs sink = new Hfs(new SequenceFile(new Fields("field1", "field2", "field3", "field4")), outputDir);

    Pipe source1 = new Pipe("source1");

    Pipe source2 = new Pipe("source2");
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

46
47
48
49
50
51
52
53
54
55
56
      System.out.println("Usage: hadoop jar cascading_ext.job.jar com.liveramp.cascading_ext.example.BloomJoinExampleWithoutCascadingUtil <output dir>");
      return;
    }

    String outputDir = args[0];
    Hfs sink = new Hfs(new SequenceFile(new Fields("field1", "field2", "field3", "field4")), outputDir);

    Pipe source1 = new Pipe("source1");

    Pipe source2 = new Pipe("source2");
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

78
79
80
81
82
83
84
85
86
87
88
      System.out.println("Usage: hadoop jar cascading_ext.job.jar com.liveramp.cascading_ext.example.FlowWithCustomCascadingUtil <output dir>");
      return;
    }

    String outputDir = args[0];
    Hfs sink = new Hfs(new SequenceFile(new Fields("field1", "field2", "field3", "field4")), outputDir);

    Pipe source1 = new Pipe("source1");

    Pipe source2 = new Pipe("source2");
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

40
41
42
43
44
45
46
47
48
49
50
51
  private Tap<JobConf, ?, ?> inputRhs;

  @Before
  public void setUp() throws IOException {

    inputLhs = new Hfs(new SequenceFile(new Fields("a", "b")), getTestRoot() + "/lhs");
    inputRhs = new Hfs(new SequenceFile(new Fields("c", "d")), getTestRoot() + "/rhs");

    TapHelper.writeToTap(inputLhs,
        new Tuple("1", "A"),
        new Tuple("1", "B"),
        new Tuple("1", "C"),
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

59
60
61
62
63
64
65
66
67
68
69
        new Tuple("2", "G"));
  }

  @Test
  public void checkLimits() throws IOException {
    Tap<JobConf, ?, ?> output = new Hfs(new SequenceFile(new Fields("a", "b", "d")), getTestRoot() + "/output");

    Pipe lhs = new Pipe("lhs");

    Pipe rhs = new Pipe("rhs");
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

47
48
49
50
51
52
53
54
55
56
57
      new Fields("in"));

    Pipe pipe = new Pipe("batch-pipe");
    pipe = new Each(pipe, new AnnotateWithSizeOfCurrentBatch(4));

    Tap<JobConf, RecordReader, OutputCollector> dst = new Lfs(new SequenceFile(OUT_FIELD), getTestRoot()+"/out");

    Flow f = CascadingUtil.get().getFlowConnector().connect(src, dst, pipe);
    f.complete();

    TupleEntryIterator tupleEntryIterator = dst.openForRead(CascadingUtil.get().getFlowProcess());
View Full Code Here

Examples of cascading.scheme.hadoop.SequenceFile

29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
  private final String OUTPUT_PATH = getTestRoot() + "/output";

  @Test
  public void testSimpleCombiner() throws IOException {

    Hfs source = new Hfs(new SequenceFile(new Fields("key", "value")), INPUT_PATH);
    TupleEntryCollector tc = source.openForWrite(CascadingUtil.get().getFlowProcess());
    tc.add(new Tuple("k0", 1));
    tc.add(new Tuple("k0", 2));
    tc.add(new Tuple("k1", 1));
    tc.add(new Tuple("k1", -3));
    tc.add(new Tuple("k1", 10));
    tc.close();

    Tap sink = new Hfs(new SequenceFile(new Fields("key", "sum")), OUTPUT_PATH);

    Pipe pipe = new Pipe("pipe");
    pipe = Combiner.assembly(pipe, new SimpleAggregator(), new Fields("key"), new Fields("value"), new Fields("sum"));

    CascadingUtil.get().getFlowConnector().connect(source, sink, pipe).complete();
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.