Package org.apache.crunch

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

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
45
46
47
48
49
50
51
52
53
54
55
      return 1;
    }
    // Create an object to coordinate pipeline creation and execution.
    Pipeline pipeline = new MRPipeline(TotalWordCount.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<Long> numberOfWords = lines.parallelDo(new DoFn<String, Long>() {
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
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(AverageBytesByIP.class, getConf());
    // Reference a given text file as a collection of Strings.
    PCollection<String> lines = pipeline.readTextFile(args[0]);

    // Combiner used for summing up response size and count
    CombineFn<String, Pair<Long, Long>> stringPairOfLongsSumCombiner = CombineFn.pairAggregator(CombineFn.SUM_LONGS,
        CombineFn.SUM_LONGS);
View Full Code Here
56
57
58
59
60
61
62
63
64
65
66
      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]);

    // Combiner used for summing up response size
    CombineFn<String, Long> longSumCombiner = CombineFn.SUM_LONGS();

    // Table of (ip, sum(response size))
View Full Code Here
148
149
150
151
152
153
154
155
156
157
158
  @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
169
170
171
172
173
174
175
176
177
178
179
  }

  @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
59
60
61
62
63
64
65
66
67
68
69
    new File(infilename).getParentFile().mkdirs();

    writeFile(expected, infilename);

    Pipeline memPipeline = MemPipeline.getInstance();
    PCollection<String> memPColl = memPipeline.readTextFile(infilename);
    Target memTarget = new TextFileTarget(memOutFilename);
    memPipeline.write(memPColl, memTarget, WriteMode.OVERWRITE);
    memPipeline.run();
    File outDir = new File(memOutFilename);
    File actualMemOut = null;
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
      }
    }
    String actualMemText = Files.readFirstLine(actualMemOut, Charsets.UTF_8);

    Pipeline mrPipeline = new MRPipeline(getClass());
    PCollection<String> mrPColl = mrPipeline.readTextFile(infilename);
    Target mrTarget = new TextFileTarget(mrOutFilename);
    mrPipeline.write(mrPColl, mrTarget, WriteMode.OVERWRITE);
    mrPipeline.run();
    String actualMrText = Files.readFirstLine(new File(mrOutFilename + "/part-m-00000"), Charsets.UTF_8);
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
  @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
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.