Package com.cloudera.crunch

Examples of com.cloudera.crunch.Pipeline

22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
public class SortCrunchTest implements Serializable {
 
  @Test
  public void test() throws IOException {
    Pipeline pipeline = new MRPipeline(SortCrunchTest.class);
    PCollection<String> records = pipeline.readTextFile("sort/A");
   
    PCollection<Pair<Integer, Integer>> pairs = records.parallelDo(new DoFn<String, Pair<Integer, Integer>>() {
      @Override
      public void process(String input, Emitter<Pair<Integer, Integer>> emitter) {
        Iterator<String> split = Splitter.on('\t').split(input).iterator();
        String l = split.next();
        String r = split.next();
        emitter.emit(Pair.of(Integer.parseInt(l), Integer.parseInt(r)));
      }
    }, pairs(ints(), ints()));
   
    PCollection<Pair<Integer, Integer>> sorted = Sort.sortPairs(pairs, by(1, ASCENDING), by(2, DESCENDING));
   
    pipeline.writeTextFile(sorted, "output-sorted");
    pipeline.run();
  }
View Full Code Here
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
 
  private static final int MISSING = 9999;
 
  @Test
  public void test() throws IOException {
    Pipeline pipeline = new MRPipeline(MaxTemperatureCrunchTest.class);
    PCollection<String> records = pipeline.readTextFile("input");
   
    PTable<String, Integer> maxTemps = records
      .parallelDo(toYearTempPairsFn(), tableOf(strings(), ints()))
      .groupByKey()
      .combineValues(CombineFn.<String> MAX_INTS());
   
    pipeline.writeTextFile(maxTemps, "output");
    pipeline.run();
  }
View Full Code Here
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
public class JoinCrunchTest implements Serializable {
 
  @Test
  public void test() throws IOException {
    Pipeline pipeline = new MRPipeline(JoinCrunchTest.class);
    PCollection<String> a = pipeline.readTextFile("join/A");
    PCollection<String> b = pipeline.readTextFile("join/B");
   
    PTable<String, String> aTable = a.parallelDo(new DoFn<String, Pair<String, String>>() {
    @Override
    public void process(String input, Emitter<Pair<String, String>> emitter) {
      Iterator<String> split = Splitter.on('\t').split(input).iterator();
      emitter.emit(Pair.of(split.next(), split.next()));
    }
  }, tableOf(strings(),strings()));

    PTable<String, String> bTable = b.parallelDo(new DoFn<String, Pair<String, String>>() {
    @Override
    public void process(String input, Emitter<Pair<String, String>> emitter) {
      Iterator<String> split = Splitter.on('\t').split(input).iterator();
      String l = split.next();
      String r = split.next();
      emitter.emit(Pair.of(r, l));
    }
  }, tableOf(strings(),strings()));
   
    PTable<String, Pair<String, String>> join = Join.join(aTable, bTable);
   
    pipeline.writeTextFile(join, "output-joined");
    pipeline.run();
  }
View Full Code Here
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
public class CogroupCrunchTest implements Serializable {
 
  @Test
  public void test() throws IOException {
    Pipeline pipeline = new MRPipeline(CogroupCrunchTest.class);
    PCollection<String> a = pipeline.readTextFile("join/A");
    PCollection<String> b = pipeline.readTextFile("join/B");
   
    PTable<String, String> aTable = a.parallelDo(new DoFn<String, Pair<String, String>>() {
    @Override
    public void process(String input, Emitter<Pair<String, String>> emitter) {
      Iterator<String> split = Splitter.on('\t').split(input).iterator();
      emitter.emit(Pair.of(split.next(), split.next()));
    }
  }, tableOf(strings(),strings()));

    PTable<String, String> bTable = b.parallelDo(new DoFn<String, Pair<String, String>>() {
    @Override
    public void process(String input, Emitter<Pair<String, String>> emitter) {
      Iterator<String> split = Splitter.on('\t').split(input).iterator();
      String l = split.next();
      String r = split.next();
      emitter.emit(Pair.of(r, l));
    }
  }, tableOf(strings(),strings()));
   
    PTable<String, Pair<Collection<String>, Collection<String>>> cogroup = Cogroup.cogroup(aTable, bTable);
   
    pipeline.writeTextFile(cogroup, "output-cogrouped");
    pipeline.run();
  }
View Full Code Here
TOP

Related Classes of com.cloudera.crunch.Pipeline

  • crunch.CogroupCrunchTest
  • crunch.JoinCrunchTest
  • crunch.MaxTemperatureCrunchTest
  • crunch.SortCrunchTest
    • 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.