Package cascading.tap.hadoop

Examples of cascading.tap.hadoop.Hfs$CombinedInputFormat

424
425
426
427
428
429
430
431
432
433
434
  @Test
  public void testFlowID() throws Exception
    {
    Tap source = new Lfs( new TextLine(), "input/path" );
    Tap sink = new Hfs( new TextLine(), "output/path", true );

    Pipe pipe = new Pipe( "test" );

    Map<Object, Object> props = getProperties();
    Flow flow1 = getPlatform().getFlowConnector( props ).connect( source, sink, pipe );
View Full Code Here
446
447
448
449
450
451
452
453
454
455
456
  @Test
  public void testCopyConfig() throws Exception
    {
    Tap source = new Lfs( new TextLine(), "input/path" );
    Tap sink = new Hfs( new TextLine(), "output/path", true );

    Pipe pipe = new Pipe( "test" );

    Configuration conf = ( (BaseHadoopPlatform) getPlatform() ).getConfiguration();
View Full Code Here
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
  public void testAsGroupByValue() throws Exception {
    FileSystem.get(new Configuration()).delete(new Path("/tmp/input"), true);
    FileSystem.get(new Configuration()).delete(new Path("/tmp/output"), true);

    Tap t = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/input");
    TupleEntryCollector tec = t.openForWrite(new HadoopFlowProcess(new JobConf()));

    HashSet<Tuple> expectedTuples = new HashSet<Tuple>(){{
      add(new Tuple(Example.Person.newBuilder().setName("bryan").setId(1).build()));
      add(new Tuple(Example.Person.newBuilder().setName("lucas").setId(2).build()));
    }};

    for (Tuple tuple : expectedTuples) {
      tec.add(tuple);
    }

    tec.close();

    Pipe inPipe = new Pipe("input");
    Pipe injectedPipe = new Each(inPipe, Fields.NONE, new Insert(new Fields("key"), 7), new Fields("key", "value"));
    Pipe groupByPipe = new GroupBy(injectedPipe, new Fields("key"));

    Hfs sink = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/output");
    Map<Object, Object> properties = new HashMap<Object, Object>(){{
      put("io.serializations", new JobConf().get("io.serializations") + "," + ProtobufSerialization.class.getName());
    }};
    new HadoopFlowConnector(properties).connect(t, sink, groupByPipe).complete();

    TupleEntryIterator tei = sink.openForRead(new HadoopFlowProcess(new JobConf()));
    Set<Tuple> tuples = new HashSet<Tuple>();
    while (tei.hasNext()) {
      tuples.add(tei.next().getTupleCopy());
    }
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
  public void testAsGroupByKey() throws Exception {
    FileSystem.get(new Configuration()).delete(new Path("/tmp/input"), true);
    FileSystem.get(new Configuration()).delete(new Path("/tmp/output"), true);

    Tap t = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/input");
    TupleEntryCollector tec = t.openForWrite(new HadoopFlowProcess(new JobConf()));

    HashSet<Tuple> expectedTuples = new HashSet<Tuple>(){{
      add(new Tuple(Example.Person.newBuilder().setName("bryan").setId(1).build()));
      add(new Tuple(Example.Person.newBuilder().setName("lucas").setId(2).build()));
    }};

    for (Tuple tuple : expectedTuples) {
      tec.add(tuple);
    }

    tec.close();

    Pipe inPipe = new Pipe("input");
    Pipe groupByPipe = new GroupBy(inPipe, new Fields("value"));

    Hfs sink = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/output");
    Map<Object, Object> properties = new HashMap<Object, Object>(){{
      put("io.serializations",
          new JobConf().get("io.serializations") + "," + ProtobufSerialization.class.getName());
    }};
    new HadoopFlowConnector(properties).connect(t, sink, groupByPipe).complete();

    TupleEntryIterator tei = sink.openForRead(new HadoopFlowProcess(new JobConf()));
    Set<Tuple> tuples = new HashSet<Tuple>();
    while (tei.hasNext()) {
      tuples.add(tei.next().getTupleCopy());
    }
View Full Code Here
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
    List<Tuple> expected = new ArrayList<Tuple>();
    expected.add(fixture("bryan", "bryan.duxbury@mail.com", 1));
    expected.add(fixture("lucas", "lucas@mail.com", 2));
    expected.add(fixture("vida", null, 3));

    Tap inputTap = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/input");
    TupleEntryCollector tec = inputTap.openForWrite(new HadoopFlowProcess(), null);

    for (Tuple t : expected) {
      tec.add(new TupleEntry(new Fields("value"), t));
    }
    tec.close();

    // read results back out
    Tap outputTap = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/input");
    TupleEntryIterator iter = outputTap.openForRead(new HadoopFlowProcess(), null);
    List<Tuple> tuples = new ArrayList<Tuple>();
    while (iter.hasNext()) {
      tuples.add(iter.next().getTupleCopy());
    }
View Full Code Here
99
100
101
102
103
104
105
106
107
108
109
110
111
    Pipe p = new Each("input", new ExtractProto(Example.Partnership.class, "leader.name"));

    final String INPUT_PATH = "/tmp/ExtractProtoTest/input";
    final String OUTPUT_PATH = "/tmp/ExtractProtoTest/output";

    Hfs inputTap = new Hfs(new ProtobufScheme("partnership", Example.Partnership.class),
        INPUT_PATH);
    Hfs outputTap = new Hfs(new ProtobufScheme("leader.name", Example.Partnership.class),
        OUTPUT_PATH);

    // make sure the input path exists
    inputTap.openForWrite(new HadoopFlowProcess()).close();
    // make sure the output path does not exist
View Full Code Here
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
  public void testInFlow() throws Exception {
    FileSystem.get(new Configuration()).delete(new Path("/tmp/input"), true);
    FileSystem.get(new Configuration()).delete(new Path("/tmp/output"), true);

    Hfs inTap = new Hfs(new ProtobufScheme("value", Example.Person.class), "/tmp/input");
    TupleEntryCollector collector = inTap.openForWrite(new HadoopFlowProcess());
    collector.add(new TupleEntry(new Fields("value"), new Tuple(BRYAN.build())));
    collector.add(new TupleEntry(new Fields("value"), new Tuple(LUCAS.build())));
    collector.close();

    Pipe inPipe = new Pipe("in");
    Pipe p = new Each(inPipe, new Fields("value"), new ExpandProto(Example.Person.class), new Fields("id", "name", "email", "position"));

    Hfs sink = new Hfs(new TextLine(), "/tmp/output");
    new HadoopFlowConnector().connect(inTap, sink, p).complete();

    TupleEntryIterator iter = sink.openForRead(new HadoopFlowProcess());
    List<Tuple> results = new ArrayList<Tuple>();
    while (iter.hasNext()) {
      results.add(iter.next().getTupleCopy());
    }
    assertEquals(2, results.size());
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
135
      JobConf conf = (JobConf) flowProcess.getConfigCopy();

      try {
        LOG.info("HLL counter found " + approxCounter.cardinality() + " distinct keys");

        Hfs tap = new Hfs(new SequenceFile(new Fields("bytes")), BloomProps.getApproxCountsDir(conf));
        TupleEntryCollector out = tap.openForWrite(new HadoopFlowProcess(conf));
        out.add(new Tuple(new BytesWritable(approxCounter.getBytes())));
        out.close();

      } catch (IOException e) {
        throw new RuntimeException("couldn't write approximate counts to side bucket", e);
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
      String partsRoot = BloomProps.getBloomFilterPartsDir(conf);
      maxHashes = BloomProps.getMaxBloomHashes(conf);
      minHashes = BloomProps.getMinBloomHashes(conf);

      for (int i = minHashes; i <= maxHashes; i++) {
        Hfs tap = new Hfs(new SequenceFile(new Fields("split", "filter")), partsRoot + "/" + i + "/");
        numHashesToCollector.put(i, tap.openForWrite(new HadoopFlowProcess(conf)));
      }

    } catch (IOException e) {
      throw new RuntimeException(e);
    }
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
  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());
        for (long i = 0; i < curSet.numBits(); i++) {
View Full Code Here
TOP

Related Classes of cascading.tap.hadoop.Hfs$CombinedInputFormat

  • cascading.flow.hadoop.BuildJobsHadoopPlatformTest
  • cascading.flow.hadoop.FlowPlatformTest
  • cascading.flow.hadoop.MapReduceFlow
  • cascading.flow.hadoop.MapReduceFlowPlatformTest
  • cascading.flow.hadoop.planner.rule.scopeexpression.EquivalentTapsScopeExpression
  • cascading.flow.hadoop.util.HadoopMRUtil
  • cascading.flow.hadoop.util.HadoopUtil
  • cascading.lingual.platform.hadoop.HadoopDefaultFactory
  • cascading.lingual.platform.hadoop.HadoopPlatformBroker
  • cascading.lingual.platform.hadoop2.Hadoop2MR1DefaultFactory
    • 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.