Package org.apache.crunch

Examples of org.apache.crunch.Pipeline.readTextFile()

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
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
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
107
108
109
110
111
112
113
114
115
116
117
  @Test
  public void testCollectUrls() throws Exception {
    Pipeline p = new MRPipeline(AggregateIT.class, tmpDir.getDefaultConfiguration());
    String urlsInputPath = tmpDir.copyResourceFileName("urls.txt");
    PTable<String, Collection<String>> urls = Aggregate.collectValues(p.readTextFile(urlsInputPath).parallelDo(
        new SplitFn(), tableOf(strings(), strings())));
    for (Pair<String, Collection<String>> e : urls.materialize()) {
      String key = e.first();
      int expectedSize = 0;
      if ("www.A.com".equals(key)) {
View Full Code Here
139
140
141
142
143
144
145
146
147
148
149
  }

  @Test
  public void testCollectValues_Writables() throws IOException {
    Pipeline pipeline = new MRPipeline(AggregateIT.class, tmpDir.getDefaultConfiguration());
    Map<Integer, Collection<Text>> collectionMap = pipeline.readTextFile(tmpDir.copyResourceFileName("set2.txt"))
        .parallelDo(new MapStringToTextPair(), Writables.tableOf(Writables.ints(), Writables.writables(Text.class)))
        .collectValues().materializeToMap();

    assertEquals(1, collectionMap.size());
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
  @Test
  public void testCollectValues_Avro() throws IOException {

    MapStringToEmployeePair mapFn = new MapStringToEmployeePair();
    Pipeline pipeline = new MRPipeline(AggregateIT.class, tmpDir.getDefaultConfiguration());
    Map<Integer, Collection<Employee>> collectionMap = pipeline.readTextFile(tmpDir.copyResourceFileName("set2.txt"))
        .parallelDo(mapFn, Avros.tableOf(Avros.ints(), Avros.records(Employee.class))).collectValues()
        .materializeToMap();

    assertEquals(1, collectionMap.size());
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
  public transient TemporaryPath tmpDir = TemporaryPaths.create();

  @Test
  public void testReflection() throws IOException {
    Pipeline pipeline = new MRPipeline(AvroReflectIT.class, tmpDir.getDefaultConfiguration());
    PCollection<StringWrapper> stringWrapperCollection = pipeline.readTextFile(tmpDir.copyResourceFileName("set1.txt"))
        .parallelDo(new MapFn<String, StringWrapper>() {

          @Override
          public StringWrapper map(String input) {
            StringWrapper stringWrapper = new StringWrapper();
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.