Package com.cloudera.cdk.data

Examples of com.cloudera.cdk.data.PartitionStrategy$Builder

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
141
142
143
144
  }

  @Test
  @SuppressWarnings("deprecation")
  public void testPartitionedWriterSingle() throws IOException {
    PartitionStrategy partitionStrategy = new PartitionStrategy.Builder().hash(
      "username", 2).build();

    FileSystemDataset<Record> ds = new FileSystemDataset.Builder()
        .name("partitioned-users")
        .configuration(getConfiguration())
        .descriptor(new DatasetDescriptor.Builder()
            .schema(USER_SCHEMA)
            .format(format)
            .location(testDirectory)
            .partitionStrategy(partitionStrategy)
            .build())
        .build();

    Assert.assertTrue("Dataset is partitioned", ds.getDescriptor()
      .isPartitioned());
    Assert.assertEquals(partitionStrategy, ds.getDescriptor()
      .getPartitionStrategy());

    writeTestUsers(ds, 10);
    Assert.assertTrue("Partitioned directory 0 exists",
      fileSystem.exists(new Path(testDirectory, "username=0")));
    Assert.assertTrue("Partitioned directory 1 exists",
      fileSystem.exists(new Path(testDirectory, "username=1")));
    checkTestUsers(ds, 10);
    PartitionKey key0 = partitionStrategy.partitionKey(0);
    PartitionKey key1 = partitionStrategy.partitionKey(1);
    int total = readTestUsersInPartition(ds, key0, null)
      + readTestUsersInPartition(ds, key1, null);
    Assert.assertEquals(10, total);

    testPartitionKeysAreEqual(ds, key0, key1);
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
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
  }

  @Test
  @SuppressWarnings("deprecation")
  public void testPartitionedWriterDouble() throws IOException {
    PartitionStrategy partitionStrategy = new PartitionStrategy.Builder()
      .hash("username", 2).hash("email", 3).build();

    FileSystemDataset<Record> ds = new FileSystemDataset.Builder()
        .name("partitioned-users")
        .configuration(getConfiguration())
        .descriptor(new DatasetDescriptor.Builder()
            .schema(USER_SCHEMA)
            .format(format)
            .location(testDirectory)
            .partitionStrategy(partitionStrategy)
            .build())
        .build();

    Assert.assertTrue("Dataset is partitioned", ds.getDescriptor()
      .isPartitioned());
    Assert.assertEquals(partitionStrategy, ds.getDescriptor()
      .getPartitionStrategy());

    writeTestUsers(ds, 10);
    checkTestUsers(ds, 10);
    PartitionKey key0 = Accessor.getDefault().newPartitionKey(0);
    PartitionKey key1 = Accessor.getDefault().newPartitionKey(1);
    int total = readTestUsersInPartition(ds, key0, "email")
      + readTestUsersInPartition(ds, key0, "email");
    Assert.assertEquals(10, total);

    total = 0;
    for (int i1 = 0; i1 < 2; i1++) {
      for (int i2 = 0; i2 < 3; i2++) {
        String part = "username=" + i1 + "/email=" + i2;
        Assert.assertTrue("Partitioned directory " + part + " exists",
          fileSystem.exists(new Path(testDirectory, part)));
        total += readTestUsersInPartition(ds,
          partitionStrategy.partitionKey(i1, i2), null);
      }
    }
    Assert.assertEquals(10, total);

    testPartitionKeysAreEqual(ds, key0, key1);
View Full Code Here
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
  }

  @Test
  @SuppressWarnings("deprecation")
  public void testGetPartitionReturnsNullIfNoAutoCreate() throws IOException {
    PartitionStrategy partitionStrategy = new PartitionStrategy.Builder().hash(
      "username", 2).build();

    FileSystemDataset<Record> ds = new FileSystemDataset.Builder()
        .name("partitioned-users")
        .configuration(getConfiguration())
        .descriptor(new DatasetDescriptor.Builder()
            .schema(USER_SCHEMA)
            .format(format)
            .location(testDirectory)
            .partitionStrategy(partitionStrategy)
            .build())
        .build();

    Assert
      .assertNull(ds.getPartition(partitionStrategy.partitionKey(1), false));
  }
View Full Code Here
228
229
230
231
232
233
234
235
236
237
238
  }

  @Test
  @SuppressWarnings("deprecation")
  public void testWriteToSubpartition() throws IOException {
    PartitionStrategy partitionStrategy = new PartitionStrategy.Builder()
      .hash("username", "username_part", 2).hash("email", 3).build();

    FileSystemDataset<Record> ds = new FileSystemDataset.Builder()
        .name("partitioned-users")
        .configuration(getConfiguration())
View Full Code Here
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
  }

  @Test
  @SuppressWarnings("deprecation")
  public void testDropPartition() throws IOException {
    PartitionStrategy partitionStrategy = new PartitionStrategy.Builder()
      .hash("username", 2).build();

    FileSystemDataset<Record> ds = new FileSystemDataset.Builder()
        .name("partitioned-users")
        .configuration(getConfiguration())
        .descriptor(new DatasetDescriptor.Builder()
            .schema(USER_SCHEMA)
            .format(format)
            .location(testDirectory)
            .partitionStrategy(partitionStrategy)
            .build())
        .build();

    writeTestUsers(ds, 10);

    Assert.assertTrue(
      fileSystem.isDirectory(new Path(testDirectory, "username=0")));
    Assert.assertTrue(
      fileSystem.isDirectory(new Path(testDirectory, "username=1")));

    ds.dropPartition(partitionStrategy.partitionKey(0));
    Assert.assertFalse(
      fileSystem.isDirectory(new Path(testDirectory, "username=0")));

    ds.dropPartition(partitionStrategy.partitionKey(1));
    Assert.assertFalse(
      fileSystem.isDirectory(new Path(testDirectory, "username=1")));

    DatasetException caught = null;

    try {
      ds.dropPartition(partitionStrategy.partitionKey(0));
    } catch (DatasetException e) {
      caught = e;
    }

    Assert.assertNotNull(caught);
View Full Code Here
30
31
32
33
34
35
36
37
38
39
40
41
  @Test
  public void testPartitionStrategy() {
    String expr = "hash(\"username\", \"username_part\", 2)";
    PartitionExpression expression = new PartitionExpression(expr, true);

    PartitionStrategy strategy = expression.evaluate();
    List<FieldPartitioner> fieldPartitioners = strategy.getFieldPartitioners();
    Assert.assertEquals(1, fieldPartitioners.size());
    FieldPartitioner fp = fieldPartitioners.get(0);
    Assert.assertEquals(HashFieldPartitioner.class, fp.getClass());
    Assert.assertEquals("username", fp.getSourceName());
    Assert.assertEquals("username_part", fp.getName());
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
59
  public void testSubpartitionStrategy() {
    String expr = "[hash(\"username\", \"username_part\", 2), hash(\"username2\", " +
        "\"username2_part\", 3)]";
    PartitionExpression expression = new PartitionExpression(expr, true);

    PartitionStrategy strategy = expression.evaluate();
    List<FieldPartitioner> fieldPartitioners = strategy.getFieldPartitioners();
    Assert.assertEquals(2, fieldPartitioners.size());

    FieldPartitioner fp0 = fieldPartitioners.get(0);
    Assert.assertEquals(HashFieldPartitioner.class, fp0.getClass());
    Assert.assertEquals("username_part", fp0.getName());
View Full Code Here
70
71
72
73
74
75
76
77
78
79
80
81
  @Test
  public void testMixedSubpartitionStrategy() {
    String expr = "[year(\"timestamp\", \"year\"), minute(\"timestamp\", \"minute\")]";
    PartitionExpression expression = new PartitionExpression(expr, true);

    PartitionStrategy strategy = expression.evaluate();
    List<FieldPartitioner> fieldPartitioners = strategy.getFieldPartitioners();
    Assert.assertEquals(2, fieldPartitioners.size());

    FieldPartitioner fp0 = fieldPartitioners.get(0);
    Assert.assertEquals(YearFieldPartitioner.class, fp0.getClass());
    Assert.assertEquals("timestamp", fp0.getSourceName());
View Full Code Here
98
99
100
101
102
103
104
105
106
107
108
109
110
111
        Formats.AVRO, repo.load(NAME).getDescriptor().getFormat());
  }

  @Test
  public void testUpdateFailsWithPartitionStrategyChange() {
    PartitionStrategy ps1 = new PartitionStrategy.Builder()
        .hash("username", 2)
        .build();
    PartitionStrategy ps2 = new PartitionStrategy.Builder()
        .hash("username", 2)
        .hash("email", 3)
        .build();

    Dataset<Record> dataset = repo.create(NAME,
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
  }

  @Test
  @SuppressWarnings("deprecation")
  public void testPartitionedSourceAndTarget() throws IOException {
    PartitionStrategy partitionStrategy = new PartitionStrategy.Builder().hash(
        "username", 2).build();

    Dataset<Record> inputDataset = repo.create("in", new DatasetDescriptor.Builder()
        .schema(USER_SCHEMA).partitionStrategy(partitionStrategy).build());
    Dataset<Record> outputDataset = repo.create("out", new DatasetDescriptor.Builder()
        .schema(USER_SCHEMA).partitionStrategy(partitionStrategy).build());

    writeTestUsers(inputDataset, 10);

    PartitionKey key = partitionStrategy.partitionKey(0);
    Dataset<Record> inputPart0 = inputDataset.getPartition(key, false);
    Dataset<Record> outputPart0 = outputDataset.getPartition(key, true);

    Pipeline pipeline = new MRPipeline(TestCrunchDatasets.class);
    PCollection<GenericData.Record> data = pipeline.read(
View Full Code Here
TOP

Related Classes of com.cloudera.cdk.data.PartitionStrategy$Builder

  • ch.grengine.code.groovy.DefaultGroovyCompilerFactory
  • ch.grengine.source.DefaultSourceFactory
  • co.cask.tigon.sql.internal.DefaultGDATField
  • com.asakusafw.utils.java.model.syntax.Expression
  • com.asakusafw.utils.java.model.syntax.ModelFactory
  • com.asakusafw.utils.java.model.util.ImportBuilder
  • com.asakusafw.utils.java.model.util.TypeBuilder
  • com.basho.riak.client.api.cap.Quorum
  • com.basho.riak.client.cap.Quorum
  • com.cloudera.cdk.data.filesystem.FileSystemDataset
    • 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.