Examples of DatasetRepository

com.cloudera.cdk.data.DatasetRepository

A logical repository (storage system) of {@link Dataset}s.

Implementations of {@code DatasetRepository} are storage systems that containzero or more {@link Dataset}s. A repository acts as a factory, as well as a registry, of datasets. Users can {@link #create(String,DatasetDescriptor)} anew {@link Dataset} with a name and schema, or retrieve a handle to anexisting dataset, by name, by way of the {@link #load(String)} method. Whilenot expressly forbidden, most repositories are expected to support only a single concrete {@link Dataset} implementation.

No guarantees are made as to the durability, reliability, or availability of the underlying storage. That is, a {@code DatasetRepository} could be ondisk, in memory, or some combination. See the implementation class for details about the guarantees it provides.

Implementations of {@link DatasetRepository} are immutable.
@see Dataset @see DatasetDescriptor
org.kitesdk.data.DatasetRepository
org.kitesdk.data.spi.DatasetRepository

A logical repository (storage system) of {@link Dataset}s.

Implementations of {@code DatasetRepository} are storage systems that containzero or more {@link Dataset}s. A repository acts as a factory, as well as a registry, of datasets. You can {@link #create(String,String,DatasetDescriptor)} anew {@link Dataset} with a name and schema, or retrieve a handle to anexisting dataset, by name, by way of the {@link #load(String,String)} method. Whilenot expressly forbidden, most repositories are expected to support only a single concrete {@link Dataset} implementation.

No guarantees are made as to the durability, reliability, or availability of the underlying storage. That is, a {@code DatasetRepository} could be ondisk, in memory, or some combination. See the implementation class for details about the guarantees it provides.

Implementations of {@link DatasetRepository} are immutable.
@see Dataset @see DatasetDescriptor
org.openrdf.repository.dataset.DatasetRepository

Examples of org.kitesdk.data.spi.DatasetRepository

    command.datasets = Lists.newArrayList(source, dest);


    int rc = command.run();
    Assert.assertEquals("Should return success", 0, rc);


    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:" + repoUri);
    int size = DatasetTestUtilities.datasetSize(repo.load("default", dest));
    Assert.assertEquals("Should contain copied records", 6, size);


    verify(console).info("Added {} records to \"{}\"", 6l, dest);
    verifyNoMoreInteractions(console);
  }

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    command.datasets = Lists.newArrayList(source, dest);


    int rc = command.run();
    Assert.assertEquals("Should return success", 0, rc);


    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:" + repoUri);
    FileSystemDataset<GenericData.Record> ds =
        (FileSystemDataset<GenericData.Record>) repo.<GenericData.Record>
            load("default", dest);
    int size = DatasetTestUtilities.datasetSize(ds);
    Assert.assertEquals("Should contain copied records", 6, size);


    Assert.assertEquals("Should produce 1 files",

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    command.datasets = Lists.newArrayList(source, dest);


    int rc = command.run();
    Assert.assertEquals("Should return success", 0, rc);


    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:" + repoUri);
    FileSystemDataset<GenericData.Record> ds =
        (FileSystemDataset<GenericData.Record>) repo.<GenericData.Record>
            load("default", dest);
    int size = DatasetTestUtilities.datasetSize(ds);
    Assert.assertEquals("Should contain copied records", 6, size);


    Assert.assertEquals("Should produce 3 files",

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

        .build(), Object.class);


    int rc = command.run();
    Assert.assertEquals("Should return success", 0, rc);


    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:" + repoUri);
    FileSystemDataset<GenericData.Record> ds =
        (FileSystemDataset<GenericData.Record>) repo.<GenericData.Record>
            load("default", "dest_partitioned");
    int size = DatasetTestUtilities.datasetSize(ds);
    Assert.assertEquals("Should contain copied records", 6, size);


    Assert.assertEquals("Should produce 2 partitions",

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    }
  }


  @Test
  public void testExternal() {
    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:hive:/tmp/data");
    repo.delete("ns", "test");
    repo.create("ns", "test", descriptor);


    Dataset<GenericRecord> ds = Datasets.load("dataset:hive:/tmp/data/ns/test");


    Assert.assertNotNull("Should load dataset", ds);
    Assert.assertTrue(ds instanceof FileSystemDataset);
    Assert.assertEquals("Locations should match",
        URI.create("hdfs://" + hdfsAuth + "/tmp/data/ns/test"),
        ds.getDescriptor().getLocation());
    Assert.assertEquals("Descriptors should match",
        repo.load("ns", "test").getDescriptor(), ds.getDescriptor());


    repo.delete("ns", "test");
  }

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    repo.delete("ns", "test");
  }


  @Test
  public void testExternalRoot() {
    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:hive:/");
    repo.delete("ns", "test");
    repo.create("ns", "test", descriptor);


    Dataset<GenericRecord> ds = Datasets.load("dataset:hive:/ns/test");


    Assert.assertNotNull("Should load dataset", ds);
    Assert.assertTrue(ds instanceof FileSystemDataset);
    Assert.assertEquals("Locations should match",
        URI.create("hdfs://" + hdfsAuth + "/ns/test"),
        ds.getDescriptor().getLocation());
    Assert.assertEquals("Descriptors should match",
        repo.load("ns", "test").getDescriptor(), ds.getDescriptor());


    repo.delete("ns", "test");
  }

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    repo.delete("ns", "test");
  }


  @Test
  public void testExternalRelative() {
    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:hive:data");
    repo.delete("ns", "test");
    repo.create("ns", "test", descriptor);


    Dataset<GenericRecord> ds = Datasets.load("dataset:hive:data/ns/test");


    Assert.assertNotNull("Should load dataset", ds);
    Assert.assertTrue(ds instanceof FileSystemDataset);
    Path cwd = getDFS().makeQualified(new Path("."));
    Assert.assertEquals("Locations should match",
        new Path(cwd, "data/ns/test").toUri(), ds.getDescriptor().getLocation());
    Assert.assertEquals("Descriptors should match",
        repo.load("ns", "test").getDescriptor(), ds.getDescriptor());


    repo.delete("ns", "test");
  }

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    repo.delete("ns", "test");
  }


  @Test
  public void testManaged() {
    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:hive");
    repo.delete("ns", "test");
    repo.create("ns", "test", descriptor);


    Dataset<GenericRecord> ds = Datasets.load("dataset:hive?dataset=test&namespace=ns");


    Assert.assertNotNull("Should load dataset", ds);
    Assert.assertTrue(ds instanceof FileSystemDataset);
    Assert.assertEquals("Descriptors should match",
        repo.load("ns", "test").getDescriptor(), ds.getDescriptor());


    repo.delete("ns", "test");
  }

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    Assert.assertEquals("string", columns.get(10).getType());
  }


  @Test
  public void testManagedDatasetCreation() {
    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:hive");
    repo.delete("ns", "records"); // ensure it does not already exist
    repo.create("ns", "records", descriptor);
    repo.delete("ns", "records"); // clean up
  }

View Full Code Here

Examples of org.kitesdk.data.spi.DatasetRepository

    repo.delete("ns", "records"); // clean up
  }


  @Test
  public void testExternalDatasetCreation() {
    DatasetRepository repo = DatasetRepositories.repositoryFor("repo:hive:target/");
    repo.delete("ns", "records"); // ensure it does not already exist
    repo.create("ns", "records", descriptor);
    repo.delete("ns", "records"); // clean up
  }

View Full Code Here

0 1 2 3 4 5

TOP

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.