Package org.apache.crunch

Examples of org.apache.crunch.Pipeline

190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
  }

  /** See CRUNCH-251 */
  @Test
  public void testMultipleHFileTargets() throws Exception {
    Pipeline pipeline = new MRPipeline(HFileTargetIT.class, HBASE_TEST_UTILITY.getConfiguration());
    Path inputPath = copyResourceFileToHDFS("shakes.txt");
    Path outputPath1 = getTempPathOnHDFS("out1");
    Path outputPath2 = getTempPathOnHDFS("out2");
    HTable table1 = createTable(26);
    HTable table2 = createTable(26);
    LoadIncrementalHFiles loader = new LoadIncrementalHFiles(HBASE_TEST_UTILITY.getConfiguration());

    PCollection<String> shakespeare = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PCollection<String> words = split(shakespeare, "\\s+");
    PCollection<String> shortWords = words.filter(SHORT_WORD_FILTER);
    PCollection<String> longWords = words.filter(FilterFns.not(SHORT_WORD_FILTER));
    PTable<String, Long> shortWordCounts = shortWords.count();
    PTable<String, Long> longWordCounts = longWords.count();
    HFileUtils.writePutsToHFilesForIncrementalLoad(
        convertToPuts(shortWordCounts),
        table1,
        outputPath1);
    HFileUtils.writePutsToHFilesForIncrementalLoad(
        convertToPuts(longWordCounts),
        table2,
        outputPath2);

    PipelineResult result = pipeline.run();
    assertTrue(result.succeeded());

    loader.doBulkLoad(outputPath1, table1);
    loader.doBulkLoad(outputPath2, table2);

View Full Code Here
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
  @Test
  public void testHFileUsesFamilyConfig() throws Exception {
    DataBlockEncoding newBlockEncoding = DataBlockEncoding.PREFIX;
    assertNotSame(newBlockEncoding, DataBlockEncoding.valueOf(HColumnDescriptor.DEFAULT_DATA_BLOCK_ENCODING));

    Pipeline pipeline = new MRPipeline(HFileTargetIT.class, HBASE_TEST_UTILITY.getConfiguration());
    Path inputPath = copyResourceFileToHDFS("shakes.txt");
    Path outputPath = getTempPathOnHDFS("out");
    HColumnDescriptor hcol = new HColumnDescriptor(TEST_FAMILY);
    hcol.setDataBlockEncoding(newBlockEncoding);
    HTable testTable = createTable(26, hcol);

    PCollection<String> shakespeare = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PCollection<String> words = split(shakespeare, "\\s+");
    PTable<String,Long> wordCounts = words.count();
    PCollection<Put> wordCountPuts = convertToPuts(wordCounts);
    HFileUtils.writePutsToHFilesForIncrementalLoad(
        wordCountPuts,
        testTable,
        outputPath);

    PipelineResult result = pipeline.run();
    assertTrue(result.succeeded());

    int hfilesCount = 0;
    Configuration conf = HBASE_TEST_UTILITY.getConfiguration();
    FileSystem fs = outputPath.getFileSystem(conf);
View Full Code Here
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
140
    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);
    PTable<String, String> result = textExtracted.groupByKey()
        .combineValues(Aggregators.STRING_CONCAT(" ",  true));

    // 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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
 
  private <T> void testSourceTarget(PType<T> ptype, T expected) {
    Path inputPath = new Path(tempPath, "input.orc");
    Path outputPath = new Path(tempPath, "output");
   
    Pipeline pipeline = new MRPipeline(OrcFileSourceTargetIT.class, conf);
    OrcFileSource<T> source = new OrcFileSource<T>(inputPath, ptype);
    PCollection<T> rows = pipeline.read(source);
    List<T> result = Lists.newArrayList(rows.materialize());
   
    assertEquals(Lists.newArrayList(expected), result);
   
    OrcFileTarget target = new OrcFileTarget(outputPath);
    pipeline.write(rows, target);
   
    assertTrue(pipeline.done().succeeded());
   
    OrcFileReaderFactory<T> reader = new OrcFileReaderFactory<T>(ptype);
    List<T> newResult = Lists.newArrayList(reader.read(fs, inputPath));
   
    assertEquals(Lists.newArrayList(expected), newResult);
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
 
  @Test
  public void testColumnPruning() throws IOException {
    generateInputData();
   
    Pipeline pipeline = new MRPipeline(OrcFileSourceTargetIT.class, conf);
    int[] readColumns = {0, 1};
    OrcFileSource<Person> source = new OrcFileSource<Person>(new Path(tempPath, "input.orc"),
        Orcs.reflects(Person.class), readColumns);
    PCollection<Person> rows = pipeline.read(source);
    List<Person> result = Lists.newArrayList(rows.materialize());
   
    Person expected = new Person("Alice", 23, null);
    assertEquals(Lists.newArrayList(expected), result);
  }
View Full Code Here
142
143
144
145
146
147
148
149
150
151
152
153
154
    writer.write(s2);
    writer.write(s3);
    writer.write(s4);
    writer.close();
   
    Pipeline pipeline = new MRPipeline(OrcFileSourceTargetIT.class, conf);
    OrcFileSource<Person> source = new OrcFileSource<Person>(inputPath, Orcs.reflects(Person.class));
    PCollection<Person> rows = pipeline.read(source);
    PTable<Person, Long> count = rows.count();

    List<Pair<Person, Long>> result = Lists.newArrayList(count.materialize());
    List<Pair<Person, Long>> expected = Lists.newArrayList(
        Pair.of(new Person("Alice", 23, Arrays.asList("444-333-9999")), 1L),
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
    List<KeyValue> kvs = generateKeyValues(100);
    Path inputPath = tmpDir.getPath("in");
    Path outputPath = tmpDir.getPath("out");
    writeKeyValuesToHFile(inputPath, kvs);

    Pipeline pipeline = new MRPipeline(HFileSourceIT.class, conf);
    PCollection<KeyValue> in = pipeline.read(FromHBase.hfile(inputPath));
    PCollection<String> texts = in.parallelDo(new MapFn<KeyValue, String>() {
      @Override
      public String map(KeyValue input) {
        return input.toString();
      }
    }, strings());
    texts.write(To.textFile(outputPath));
    PipelineResult result = pipeline.run();
    assertTrue(result.succeeded());

    List<String> lines = FileUtils.readLines(new File(outputPath.toString(), "part-m-00000"));
    assertEquals(kvs.size(), lines.size());
    for (int i = 0; i < kvs.size(); i++) {
View Full Code Here
268
269
270
271
272
273
274
275
276
  private List<Result> doTestScanHFiles(List<KeyValue> kvs, Scan scan) throws IOException {
    Path inputPath = tmpDir.getPath("in");
    writeKeyValuesToHFile(inputPath, kvs);

    Pipeline pipeline = new MRPipeline(HFileSourceIT.class, conf);
    PCollection<Result> results = HFileUtils.scanHFiles(pipeline, inputPath, scan);
    return ImmutableList.copyOf(results.materialize());
  }
View Full Code Here
277
278
279
280
281
282
283
284
285
  private List<KeyValue> doTestReadHFiles(List<KeyValue> kvs, Scan scan) throws IOException {
    Path inputPath = tmpDir.getPath("in");
    writeKeyValuesToHFile(inputPath, kvs);

    Pipeline pipeline = new MRPipeline(HFileSourceIT.class, conf);
    PCollection<KeyValue> results = pipeline.read(FromHBase.hfile(inputPath));
    return ImmutableList.copyOf(results.materialize());
  }
View Full Code Here
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
54
55
56
public class CountersTest {

  @Test
  public void counterTest() throws Exception {
    Pipeline pipeline = MemPipeline.getInstance();

    // Single row PCollection.
    PCollection<String> objects = MemPipeline.collectionOf(Arrays.asList(new String[]{"hello world"}));
    System.out.println("Objects: " + ((MemCollection) objects).getCollection());

    // Counter creating Map.
    PCollection<String> objects2 = objects.parallelDo("Create counters",
        new MapFn<String, String>() {
          @Override
          public String map(String input) {
            for(int i = 0; i < 200; ++i) {
              this.increment("testCounter", String.valueOf(i));
            }
            return input;
          }
        },
        Writables.strings()
    );

    // Run it!
    pipeline.done();
    System.out.println("Objects2: " + ((MemCollection) objects2).getCollection());
  }
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.