Package org.apache.crunch

Examples of org.apache.crunch.Pipeline

54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
      System.err.println();
      GenericOptionsParser.printGenericCommandUsage(System.err);
      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))
    PTable<String, Long> ipAddrResponseSize = lines
        .parallelDo(extractIPResponseSize, Writables.tableOf(Writables.strings(), Writables.longs())).groupByKey()
        .combineValues(longSumCombiner);

    pipeline.writeTextFile(ipAddrResponseSize, args[1]);
    // Execute the pipeline as a MapReduce.
    PipelineResult result = pipeline.done();

    return result.succeeded() ? 0 : 1;
  }
View Full Code Here
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
137
138
139
    createTable(configuration, TABLE_TARGET, Bytes.toString(COLUMN_FAMILY_TARGET));

    putInHbase(putList, configuration);

    // We create the pipeline which will handle most of the job.
    Pipeline pipeline = new MRPipeline(WordAggregationHBase.class, HBaseConfiguration.create());

    // The scan which will retrieve the data from the source in hbase.
    Scan scan = new Scan();
    scan.addColumn(COLUMN_FAMILY_SOURCE, COLUMN_QUALIFIER_SOURCE_PLAY);
    scan.addColumn(COLUMN_FAMILY_SOURCE, COLUMN_QUALIFIER_SOURCE_QUOTE);

    // Our hbase source
    HBaseSourceTarget source = new HBaseSourceTarget(TABLE_SOURCE, scan);

    // Our source, in a format which can be use by crunch
    PTable<ImmutableBytesWritable, Result> rawText = pipeline.read(source);

    // We process the data from the source HTable then concatenate all data
    // with the same rowkey
    PTable<String, String> textExtracted = extractText(rawText);
    CombineFn<String, String> stringConcatCombine = CombineFn.STRING_CONCAT(" ", true);
    PTable<String, String> result = textExtracted.groupByKey().combineValues(stringConcatCombine);

    // We create the collection of puts from the concatenated datas
    PCollection<Put> resultPut = createPut(result);

    // We write the puts in hbase, in the target table
    pipeline.write(resultPut, new HBaseTarget(TABLE_TARGET));

    pipeline.done();
    return 0;
  }
View Full Code Here
145
146
147
148
149
150
151
152
153
154
155
156
157
158
        new ColumnOrder[] { by(1, ASCENDING), by(2, DESCENDING) }, new String[] { "A", "this doc has this text" });
  }

  @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
168
169
170
171
172
173
174
175
176
177
178
179
    assertEquals(expected, Lists.newArrayList(sorted.materialize()));
  }

  @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
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
  public void testSecondarySortWritables() throws Exception {
    runSecondarySort(WritableTypeFamily.getInstance());
  }

  public void runSecondarySort(PTypeFamily ptf) throws Exception {
    Pipeline p = new MRPipeline(SecondarySortIT.class, tempDir.getDefaultConfiguration());
    String inputFile = tempDir.copyResourceFileName("secondary_sort_input.txt");
   
    PTable<String, Pair<Integer, Integer>> in = p.read(From.textFile(inputFile))
        .parallelDo(new MapFn<String, Pair<String, Pair<Integer, Integer>>>() {
          @Override
          public Pair<String, Pair<Integer, Integer>> map(String input) {
            String[] pieces = input.split(",");
            return Pair.of(pieces[0],
                Pair.of(Integer.valueOf(pieces[1].trim()), Integer.valueOf(pieces[2].trim())));
          }
        }, ptf.tableOf(ptf.strings(), ptf.pairs(ptf.ints(), ptf.ints())));
    Iterable<String> lines = SecondarySort.sortAndApply(in, new MapFn<Pair<String, Iterable<Pair<Integer, Integer>>>, String>() {
      @Override
      public String map(Pair<String, Iterable<Pair<Integer, Integer>>> input) {
        Joiner j = Joiner.on(',');
        return j.join(input.first(), j.join(input.second()));
      }
    }, ptf.strings()).materialize();
    assertEquals(ImmutableList.of("one,[-5,10],[1,1],[2,-3]", "three,[0,-1]", "two,[1,7],[2,6],[4,5]"),
        ImmutableList.copyOf(lines));
    p.done();
  }
View Full Code Here
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
import static org.junit.Assert.assertFalse;

public class AvroPathPerKeyIT extends CrunchTestSupport implements Serializable {
  @Test
  public void testOutputFilePerKey() throws Exception {
    Pipeline p = new MRPipeline(AvroPathPerKeyIT.class, tempDir.getDefaultConfiguration());
    Path outDir = tempDir.getPath("out");
    p.read(From.textFile(tempDir.copyResourceFileName("docs.txt")))
        .parallelDo(new MapFn<String, Pair<String, String>>() {
          @Override
          public Pair<String, String> map(String input) {
            String[] p = input.split("\t");
            return Pair.of(p[0], p[1]);
          }
        }, Avros.tableOf(Avros.strings(), Avros.strings()))
        .groupByKey()
        .write(new AvroPathPerKeyTarget(outDir));
    p.done();

    Set<String> names = Sets.newHashSet();
    FileSystem fs = outDir.getFileSystem(tempDir.getDefaultConfiguration());
    for (FileStatus fstat : fs.listStatus(outDir)) {
      names.add(fstat.getPath().getName());
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
    assertEquals("part-r-00000.avro", bStat[0].getPath().getName());
  }

  @Test
  public void testOutputFilePerKey_NothingToOutput() throws Exception {
    Pipeline p = new MRPipeline(AvroPathPerKeyIT.class, tempDir.getDefaultConfiguration());
    Path outDir = tempDir.getPath("out");

    p.read(From.textFile(tempDir.copyResourceFileName("docs.txt")))
        .parallelDo(new MapFn<String, Pair<String, String>>() {
          @Override
          public Pair<String, String> map(String input) {
            String[] p = input.split("\t");
            return Pair.of(p[0], p[1]);
          }
        }, Avros.tableOf(Avros.strings(), Avros.strings()))
        .filter(FilterFns.<Pair<String, String>>REJECT_ALL())
        .groupByKey()
        .write(new AvroPathPerKeyTarget(outDir));
    p.done();

    FileSystem fs = outDir.getFileSystem(tempDir.getDefaultConfiguration());
    assertFalse(fs.exists(outDir));
  }
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
  @Test
  public void testInputFromMapReduceKeyValueFile_Generic() throws InterruptedException, IOException, ClassNotFoundException {

    Path keyValuePath = produceMapReduceOutputFile();

    Pipeline pipeline = new MRPipeline(AvroKeyValueIT.class, tempDir.getDefaultConfiguration());
    PTable<Person, Integer> personTable = pipeline.read(
        From.avroTableFile(keyValuePath, Avros.tableOf(Avros.specifics(Person.class), Avros.ints())));

    org.apache.crunch.Pair<Person, Integer> firstEntry = Iterables.getFirst(personTable.materialize(), null);

    assertEquals("a", firstEntry.first().getName().toString());
    assertEquals(Integer.valueOf(1), firstEntry.second());

    pipeline.done();

  }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
  @Test
  public void testInputFromMapRedKeyValueFile_Specific() throws IOException {
    Path keyValuePath = produceMapRedOutputFile();

    Pipeline pipeline = new MRPipeline(AvroKeyValueIT.class, tempDir.getDefaultConfiguration());
    PTable<Person, Integer> personTable = pipeline.read(
        From.avroTableFile(keyValuePath, Avros.keyValueTableOf(Avros.specifics(Person.class), Avros.ints())));

    org.apache.crunch.Pair<Person, Integer> firstEntry = Iterables.getFirst(personTable.materialize(), null);

    assertEquals("a", firstEntry.first().getName().toString());
    assertEquals(Integer.valueOf(1), firstEntry.second());

    // Verify that deep copying on this PType works as well
    PTableType<Person, Integer> tableType = Avros.keyValueTableOf(Avros.specifics(Person.class), Avros.ints());
    tableType.initialize(tempDir.getDefaultConfiguration());
    org.apache.crunch.Pair<Person, Integer> detachedPair = tableType.getDetachedValue(firstEntry);
    assertEquals(firstEntry, detachedPair);

    pipeline.done();
  }
View Full Code Here
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
  @Test
  public void testInputFromMapRedKeyValueFile_Reflect() throws IOException {
    Path keyValuePath = produceMapRedOutputFile();

    Pipeline pipeline = new MRPipeline(AvroKeyValueIT.class, tempDir.getDefaultConfiguration());
    PTable<ReflectedPerson, Integer> personTable = pipeline.read(
        From.avroTableFile(keyValuePath, Avros.keyValueTableOf(Avros.reflects(ReflectedPerson.class), Avros.ints())));

    org.apache.crunch.Pair<ReflectedPerson, Integer> firstEntry = Iterables.getFirst(personTable.materialize(), null);

    assertEquals("a", firstEntry.first().getName().toString());
    assertEquals(Integer.valueOf(1), firstEntry.second());

    // Verify that deep copying on this PType works as well
    PTableType<ReflectedPerson, Integer> tableType =
        Avros.keyValueTableOf(Avros.reflects(ReflectedPerson.class), Avros.ints());
    tableType.initialize(tempDir.getDefaultConfiguration());
    org.apache.crunch.Pair<ReflectedPerson, Integer> detachedPair = tableType.getDetachedValue(firstEntry);
    assertEquals(firstEntry, detachedPair);

    pipeline.done();
  }
View Full Code Here
TOP

Related Classes of org.apache.crunch.Pipeline

  • $.WordCount
  • com.cloudera.cdk.data.crunch.TestCrunchDatasets
  • org.apache.bigtop.bigpetstore.etl.CrunchETL
  • org.apache.crunch.contrib.io.jdbc.DataBaseSourceIT
  • org.apache.crunch.examples.AverageBytesByIP
  • org.apache.crunch.examples.SecondarySortExample
  • org.apache.crunch.examples.TotalBytesByIP
  • org.apache.crunch.examples.TotalWordCount
  • org.apache.crunch.examples.WordAggregationHBase
  • org.apache.crunch.examples.WordCount
    • 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.