Package org.apache.crunch.impl.mr

Examples of org.apache.crunch.impl.mr.MRPipeline.readTextFile()

142
143
144
145
146
147
148
149
150
151
152
   * another.
   */
  @Test
  public void testFusedMappersObjectReuseBug() throws IOException {
    Pipeline pipeline = new MRPipeline(MultipleOutputIT.class, tmpDir.getDefaultConfiguration());
    PCollection<StringWrapper> stringWrappers = pipeline.readTextFile(tmpDir.copyResourceFileName("set2.txt"))
        .parallelDo(new StringWrapper.StringToStringWrapperMapFn(), Avros.reflects(StringWrapper.class));

    PCollection<String> stringsA = stringWrappers.parallelDo(new AppendFn("A"), stringWrappers.getPType())
        .parallelDo(new StringWrapper.StringWrapperToStringMapFn(), Writables.strings());
    PCollection<String> stringsB = stringWrappers.parallelDo(new AppendFn("B"), stringWrappers.getPType())
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
      return 1;
    }
    // Create an object to coordinate pipeline creation and execution.
    Pipeline pipeline = new MRPipeline(AverageBytesByIP.class, getConf());
    // Reference a given text file as a collection of Strings.
    PCollection<String> lines = pipeline.readTextFile(args[0]);

    // Aggregator used for summing up response size and count
    Aggregator<Pair<Long, Long>> agg = pairAggregator(SUM_LONGS(), SUM_LONGS());

    // Table of (ip, sum(response size), count)
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
      return 1;
    }
    // Create an object to coordinate pipeline creation and execution.
    Pipeline pipeline = new MRPipeline(TotalBytesByIP.class, getConf());
    // Reference a given text file as a collection of Strings.
    PCollection<String> lines = pipeline.readTextFile(args[0]);

    // Aggregator used for summing up response size
    Aggregator<Long> agg = Aggregators.SUM_LONGS();

    // Table of (ip, sum(response size))
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
      return 1;
    }
    // Create an object to coordinate pipeline creation and execution.
    Pipeline pipeline = new MRPipeline(WordCount.class, getConf());
    // Reference a given text file as a collection of Strings.
    PCollection<String> lines = pipeline.readTextFile(args[0]);

    // Define a function that splits each line in a PCollection of Strings into
    // a
    // PCollection made up of the individual words in the file.
    PCollection<String> words = lines.parallelDo(new DoFn<String, String>() {
View Full Code Here
150
151
152
153
154
155
156
157
158
159
160
  @Test
  public void testAvroReflectSortPair() throws IOException {
    Pipeline pipeline = new MRPipeline(SortIT.class, tmpDir.getDefaultConfiguration());
    pipeline.enableDebug();
    String rsrc = tmpDir.copyResourceFileName("set2.txt");
    PCollection<Pair<String, StringWrapper>> in = pipeline.readTextFile(rsrc)
        .parallelDo(new MapFn<String, Pair<String, StringWrapper>>() {

          @Override
          public Pair<String, StringWrapper> map(String input) {
            return Pair.of(input, wrap(input));
View Full Code Here
171
172
173
174
175
176
177
178
179
180
181
  }

  @Test
  public void testAvroReflectSortTable() throws IOException {
    Pipeline pipeline = new MRPipeline(SortIT.class, tmpDir.getDefaultConfiguration());
    PTable<String, StringWrapper> unsorted = pipeline.readTextFile(tmpDir.copyResourceFileName("set2.txt")).parallelDo(
        new MapFn<String, Pair<String, StringWrapper>>() {

          @Override
          public Pair<String, StringWrapper> map(String input) {
            return Pair.of(input, wrap(input));
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
      return 1;
    }
    // Create an object to coordinate pipeline creation and execution.
    Pipeline pipeline = new MRPipeline(SecondarySortExample.class, getConf());
    // Reference a given text file as a collection of Strings.
    PCollection<String> lines = pipeline.readTextFile(args[0]);

    // Define a function that parses each line in a PCollection of Strings into
    // a pair of pairs, the first of which will be grouped by (first member) and
    // the sorted by (second memeber). The second pair is payload which can be
    // passed in an Iterable object.
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
        // Create an object to coordinate pipeline creation and execution.
        Pipeline pipeline = new MRPipeline(WordCount.class, getConf());

        // Reference a given text file as a collection of Strings.
        PCollection<String> lines = pipeline.readTextFile(inputPath);

        // Define a function that splits each line in a PCollection of Strings into
        // a PCollection made up of the individual words in the file.
        // The second argument sets the serialization format.
        PCollection<String> words = lines.parallelDo(new Tokenizer(), Writables.strings());
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
  @Test
  public void testWritables() throws Exception {
    Pipeline pipeline = new MRPipeline(AggregateIT.class, tmpDir.getDefaultConfiguration());
    String shakesInputPath = tmpDir.copyResourceFileName("shakes.txt");
    PCollection<String> shakes = pipeline.readTextFile(shakesInputPath);
    runMinMax(shakes, WritableTypeFamily.getInstance());
    pipeline.done();
  }

  @Test
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
  @Test
  public void testAvro() throws Exception {
    Pipeline pipeline = new MRPipeline(AggregateIT.class, tmpDir.getDefaultConfiguration());
    String shakesInputPath = tmpDir.copyResourceFileName("shakes.txt");
    PCollection<String> shakes = pipeline.readTextFile(shakesInputPath);
    runMinMax(shakes, AvroTypeFamily.getInstance());
    pipeline.done();
  }

  @Test
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.