Package org.apache.crunch

Examples of org.apache.crunch.Pipeline

37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
import static org.junit.Assert.assertEquals;

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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
    fs.delete(TEMP_DIR, true);
  }

  @Test
  public void testHFileTarget() throws Exception {
    Pipeline pipeline = new MRPipeline(HFileTargetIT.class, HBASE_TEST_UTILITY.getConfiguration());
    Path inputPath = copyResourceFileToHDFS("shakes.txt");
    Path outputPath = getTempPathOnHDFS("out");

    PCollection<String> shakespeare = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PCollection<String> words = split(shakespeare, "\\s+");
    PTable<String, Long> wordCounts = words.count();
    pipeline.write(convertToKeyValues(wordCounts), ToHBase.hfile(outputPath));

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

    FileSystem fs = FileSystem.get(HBASE_TEST_UTILITY.getConfiguration());
    KeyValue kv = readFromHFiles(fs, outputPath, "and");
    assertEquals(427L, Bytes.toLong(kv.getValue()));
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
    assertEquals(427L, Bytes.toLong(kv.getValue()));
  }

  @Test
  public void testBulkLoad() throws Exception {
    Pipeline pipeline = new MRPipeline(HFileTargetIT.class, HBASE_TEST_UTILITY.getConfiguration());
    Path inputPath = copyResourceFileToHDFS("shakes.txt");
    Path outputPath = getTempPathOnHDFS("out");
    HTable testTable = createTable(26);

    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());

    new LoadIncrementalHFiles(HBASE_TEST_UTILITY.getConfiguration())
        .doBulkLoad(outputPath, testTable);
View Full Code Here
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
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
    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
267
268
269
270
271
272
273
274
275
  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
276
277
278
279
280
281
282
283
284
  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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
    fs.delete(TEMP_DIR, true);
  }

  @Test
  public void testHFileTarget() throws Exception {
    Pipeline pipeline = new MRPipeline(HFileTargetIT.class, HBASE_TEST_UTILITY.getConfiguration());
    Path inputPath = copyResourceFileToHDFS("shakes.txt");
    Path outputPath = getTempPathOnHDFS("out");

    PCollection<String> shakespeare = pipeline.read(At.textFile(inputPath, Writables.strings()));
    PCollection<String> words = split(shakespeare, "\\s+");
    PTable<String, Long> wordCounts = words.count();
    pipeline.write(convertToKeyValues(wordCounts), ToHBase.hfile(outputPath));

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

    FileSystem fs = FileSystem.get(HBASE_TEST_UTILITY.getConfiguration());
    KeyValue kv = readFromHFiles(fs, outputPath, "and");
    assertEquals(427L, Bytes.toLong(kv.getValue()));
View Full Code Here
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
    assertEquals(427L, Bytes.toLong(kv.getValue()));
  }

  @Test
  public void testBulkLoad() throws Exception {
    Pipeline pipeline = new MRPipeline(HFileTargetIT.class, HBASE_TEST_UTILITY.getConfiguration());
    Path inputPath = copyResourceFileToHDFS("shakes.txt");
    Path outputPath = getTempPathOnHDFS("out");
    HTable testTable = createTable(26);

    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());

    new LoadIncrementalHFiles(HBASE_TEST_UTILITY.getConfiguration())
        .doBulkLoad(outputPath, testTable);
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.