Package org.apache.crunch.impl.spark

Examples of org.apache.crunch.impl.spark.SparkPipeline

118
119
120
121
122
123
124
    runMapsideLeftOuterJoin(new SparkPipeline("local", "mapside"), false);
  }

  @Test
  public void testMapsideJoin_LeftOuterJoin_Materialized() throws IOException {
    runMapsideLeftOuterJoin(new SparkPipeline("local", "mapside"), true);
  }
View Full Code Here
52
53
54
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
  @Test
  public void testUnionOfGroupedOutputAndNonGroupedOutput() throws IOException {
    String inputPath = tempDir.copyResourceFileName("set1.txt");
    String inputPath2 = tempDir.copyResourceFileName("set2.txt");

    Pipeline pipeline = new SparkPipeline("local", "unionresults");

    PCollection<String> set1Lines = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PCollection<Pair<String, Long>> set1Lengths = set1Lines.parallelDo(new StringLengthMapFn(),
        Writables.pairs(Writables.strings(), Writables.longs()));
    PCollection<Pair<String, Long>> set2Counts = pipeline.read(At.textFile(inputPath2, Writables.strings())).count();

    PCollection<Pair<String, Long>> union = set1Lengths.union(set2Counts);

    Set<Pair<String, Long>> unionValues = Sets.newHashSet(union.materialize());
    assertEquals(7, unionValues.size());

    Set<Pair<String, Long>> expectedPairs = Sets.newHashSet();
    expectedPairs.add(Pair.of("b", 10L));
    expectedPairs.add(Pair.of("c", 10L));
    expectedPairs.add(Pair.of("a", 10L));
    expectedPairs.add(Pair.of("e", 10L));
    expectedPairs.add(Pair.of("a", 1L));
    expectedPairs.add(Pair.of("c", 1L));
    expectedPairs.add(Pair.of("d", 1L));

    assertEquals(expectedPairs, unionValues);

    pipeline.done();
  }
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
  public void testMultiGroupBy() throws Exception {
    String inputPath = tempDir.copyResourceFileName("set1.txt");
    String inputPath2 = tempDir.copyResourceFileName("set2.txt");
    String output = tempDir.getFileName("output");

    Pipeline pipeline = new SparkPipeline("local", "multigroupby");

    PCollection<String> set1Lines = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PCollection<Pair<String, Long>> set1Lengths = set1Lines.parallelDo(new StringLengthMapFn(),
        Writables.pairs(Writables.strings(), Writables.longs()));
    PTable<String, Long> set2Counts = pipeline.read(At.textFile(inputPath2, Writables.strings())).count();
    PTables.asPTable(set2Counts.union(set1Lengths)).groupByKey().ungroup()
        .write(At.sequenceFile(output, Writables.strings(), Writables.longs()));
    PipelineResult res = pipeline.done();
    assertEquals(4, res.getStageResults().get(0).getCounterValue("my", "counter"));
  }
View Full Code Here
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
127
128
129
130
131
132
133
134
135
136
  public void testMultiWrite() throws Exception {
    String inputPath = tempDir.copyResourceFileName("set1.txt");
    String inputPath2 = tempDir.copyResourceFileName("set2.txt");
    String output = tempDir.getFileName("output");

    Pipeline pipeline = new SparkPipeline("local", "multiwrite");

    PCollection<String> set1Lines = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PTable<String, Long> set1Lengths = set1Lines.parallelDo(new StringLengthMapFn(),
        Writables.tableOf(Writables.strings(), Writables.longs()));
    PTable<String, Long> set2Counts = pipeline.read(At.textFile(inputPath2, Writables.strings())).count();

    TableSourceTarget<String, Long> inter = At.sequenceFile(output, Writables.strings(), Writables.longs());
    set1Lengths.write(inter);
    set2Counts.write(inter, Target.WriteMode.APPEND);

    pipeline.run();

    PTable<String, Long> in = pipeline.read(inter);
    Set<Pair<String, Long>> values = Sets.newHashSet(in.materialize());
    assertEquals(7, values.size());

    Set<Pair<String, Long>> expectedPairs = Sets.newHashSet();
    expectedPairs.add(Pair.of("b", 10L));
    expectedPairs.add(Pair.of("c", 10L));
    expectedPairs.add(Pair.of("a", 10L));
    expectedPairs.add(Pair.of("e", 10L));
    expectedPairs.add(Pair.of("a", 1L));
    expectedPairs.add(Pair.of("c", 1L));
    expectedPairs.add(Pair.of("d", 1L));

    assertEquals(expectedPairs, values);

    pipeline.done();
  }
View Full Code Here
45
46
47
48
49
50
51
52
  @Rule
  public transient TemporaryPath tmpDir = new TemporaryPath();

  @Test
  public void testWritableSortAsc() throws Exception {
    runSingle(new SparkPipeline("local", "sort"), WritableTypeFamily.getInstance(), Sort.Order.ASCENDING,
        "A\tand this text as well");
  }
View Full Code Here
51
52
53
54
55
56
57
58
        "A\tand this text as well");
  }

  @Test
  public void testWritableSortDesc() throws Exception {
    runSingle(new SparkPipeline("local", "sort"), WritableTypeFamily.getInstance(), Sort.Order.DESCENDING,
        "B\tthis doc has some text");
  }
View Full Code Here
57
58
59
60
61
62
63
64
        "B\tthis doc has some text");
  }

  @Test
  public void testWritableSortAscDesc() throws Exception {
    runPair(new SparkPipeline("local", "sort"), WritableTypeFamily.getInstance(), by(1, ASCENDING), by(2, DESCENDING), "A",
        "this doc has this text");
  }
View Full Code Here
63
64
65
66
67
68
69
70
        "this doc has this text");
  }

  @Test
  public void testWritableSortSecondDescFirstAsc() throws Exception {
    runPair(new SparkPipeline("local", "sort"), WritableTypeFamily.getInstance(), by(2, DESCENDING), by(1, ASCENDING), "A",
        "this doc has this text");
  }
View Full Code Here
69
70
71
72
73
74
75
76
        "this doc has this text");
  }

  @Test
  public void testWritableSortTripleAscDescAsc() throws Exception {
    runTriple(new SparkPipeline("local", "sort"), WritableTypeFamily.getInstance(), by(1, ASCENDING), by(2, DESCENDING),
        by(3, ASCENDING), "A", "this", "doc");
  }
View Full Code Here
75
76
77
78
79
80
81
82
        by(3, ASCENDING), "A", "this", "doc");
  }

  @Test
  public void testWritableSortQuadAscDescAscDesc() throws Exception {
    runQuad(new SparkPipeline("local", "sort"), WritableTypeFamily.getInstance(), by(1, ASCENDING), by(2, DESCENDING),
        by(3, ASCENDING), by(4, DESCENDING), "A", "this", "doc", "has");
  }
View Full Code Here
TOP

Related Classes of org.apache.crunch.impl.spark.SparkPipeline

  • org.apache.crunch.impl.spark.collect.SparkCollectFactory
  • org.apache.crunch.PipelineExecution
  • org.apache.crunch.PipelineResult
  • org.apache.crunch.SkipPTypesIT
  • org.apache.crunch.SparkAggregatorIT
  • org.apache.crunch.SparkCogroupIT
  • org.apache.crunch.SparkEmptyPCollectionIT
  • org.apache.crunch.SparkMapsideJoinIT
  • org.apache.crunch.SparkPageRankIT
  • org.apache.crunch.SparkPipelineCallableIT
    • 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.