Package cascading.scheme.hadoop

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
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
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
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
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
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79

  @Test
  public void testSimpleCombinerWithMemoryLimit() 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("key0", 1));
    tc.add(new Tuple("key0", 2));
    tc.add(new Tuple("key1", 1));
    tc.add(new Tuple("key1", -3));
    tc.add(new Tuple("key0", 10));
    tc.close();

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

    Pipe pipe = new Pipe("pipe");
    pipe = new Each(pipe, Combiner.function(new SimpleAggregator(), new Fields("key"), new Fields("value"), new Fields("sum"), MemoryBoundLruHashMap.UNLIMITED_ITEM_CAPACITY, 100, new SimpleTupleMemoryUsageEstimator(), new LongMemoryUsageEstimator(), false));

    CascadingUtil.get().getFlowConnector().connect(source, sink, pipe).complete();
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
  }

  @Test
  public void testComplexCombiner() 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", 4));
    tc.add(new Tuple("k1", 10));
    tc.close();

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

    Pipe pipe = new Pipe("pipe");
    pipe = Combiner.assembly(pipe,
        new ComplexAggregator(),
        new Fields("key"),
View Full Code Here
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
  private final String INPUT_PATH = getTestRoot() + "/input";
  private final String OUTPUT_PATH = getTestRoot() + "/output";

  @Test
  public void testMain() 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", 10));
    tc.add(new Tuple("k1", -2));
    tc.add(new Tuple("k1", -9));
    tc.add(new Tuple("k2", -3));
    tc.add(new Tuple("k2", -6));
    tc.close();

    Tap sink = new Hfs(new SequenceFile(new Fields("key", "sum")), OUTPUT_PATH);
   
    Pipe pipe = new Pipe("pipe");
    pipe = Combiner.assembly(pipe, new SumExactAggregator(1), new Fields("key"), new Fields("value"), new Fields("sum"));

    CascadingUtil.get().getFlowConnector().connect(source, sink, pipe).complete();
View Full Code Here
40
41
42
43
44
45
46
  protected Hfs output;

  @Before
  public void setUp() throws Exception {
    output = new Hfs(new SequenceFile(new Fields("key", "key2", "lhs-value")), getTestRoot() + "/output");
  }
View Full Code Here
TOP

Related Classes of cascading.scheme.hadoop.SequenceFile

  • cascading.flow.hadoop.BuildJobsHadoopPlatformTest
  • cascading.tap.hadoop.HadoopTapPlatformTest
  • cascading.tap.hadoop.util.TempHfs
  • cascading.tuple.hadoop.SerializedPipesPlatformTest
  • cascading.tuple.Tuple
  • cascading.tuple.TupleEntry
  • com.liveramp.cascading_ext.assembly.BloomAssemblyTestCase
  • com.liveramp.cascading_ext.assembly.CreateBloomFilter$CollectKeyStats
  • com.liveramp.cascading_ext.assembly.TestBloomFilter
  • com.liveramp.cascading_ext.assembly.TestBloomJoin
    • 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.