Package org.kitesdk.data

Examples of org.kitesdk.data.DatasetDescriptor$Builder

220
221
222
223
224
225
226
227
228
229
230
        Datasets.delete("dataset:hive:/tmp/datasets/test"));
    Assert.assertFalse("Delete should return false if there is no dataset",
        Datasets.delete("dataset:hive:/tmp/datasets/test"));

    // recreate the default.test dataset, but with a different storage location
    DatasetDescriptor doNotDelete = new DatasetDescriptor.Builder(descriptor)
        .location(URI.create("file:/tmp/datasets/default/test"))
        .build();
    metastore.createTable(HiveUtils.tableForDescriptor(
        "default", "test", doNotDelete, true));
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
public class AvroKeyEntitySchemaParser implements
    KeyEntitySchemaParser<AvroKeySchema, AvroEntitySchema> {

  @Override
  public AvroKeySchema parseKeySchema(String rawSchema) {
    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaLiteral(rawSchema)
        .build();
    return new AvroKeySchema(
        descriptor.getSchema(), descriptor.getPartitionStrategy());
  }
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
    Dataset<GenericRecord> inputDataset = repo.create("default", "in",
        new DatasetDescriptor.Builder()
        .schemaLiteral(testGenericEntity).build());

    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaLiteral(testGenericEntity)
        .build();
    Dataset<GenericRecord> outputDataset = repo.create("default", datasetName, descriptor);

    DatasetWriter<GenericRecord> writer = inputDataset.newWriter();
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
    Dataset<GenericRecord> inputDataset = repo.create("default", "in",
        new DatasetDescriptor.Builder()
            .schemaLiteral(testGenericEntity).build());

    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaLiteral(testGenericEntity)
        .build();
    Dataset<GenericRecord> outputDataset = repo.create("default", datasetName, descriptor);

    DatasetKeyInputFormat.configure(job).readFrom(inputDataset);
View Full Code Here
91
92
93
94
95
96
97
98
99
100
101
102
  @Override
  public AvroKeySchema parseKeySchema(String rawSchema,
      PartitionStrategy partitionStrategy) {
    // use DatasetDescriptor.Builder because it checks consistency
    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaLiteral(rawSchema)
        .partitionStrategy(partitionStrategy)
        .build();
    return new AvroKeySchema(
        descriptor.getSchema(), descriptor.getPartitionStrategy());
  }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
        descriptor.getSchema(), descriptor.getPartitionStrategy());
  }

  @Override
  public AvroEntitySchema parseEntitySchema(String rawSchema) {
    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaLiteral(rawSchema)
        .build();
    return new AvroEntitySchema(
        descriptor.getSchema(), rawSchema, descriptor.getColumnMapping());
  }
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
  @Override
  public AvroEntitySchema parseEntitySchema(String rawSchema,
      ColumnMapping columnMapping) {
    // use DatasetDescriptor.Builder because it checks consistency
    DatasetDescriptor descriptor = new DatasetDescriptor.Builder()
        .schemaLiteral(rawSchema)
        .columnMapping(columnMapping)
        .build();
    return new AvroEntitySchema(
        descriptor.getSchema(), rawSchema, descriptor.getColumnMapping());
  }
View Full Code Here
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
  public boolean delete(String namespace, String name) {
    Preconditions.checkArgument(DEFAULT_NAMESPACE.equals(namespace),
        "Non-default namespaces are not supported");
    Preconditions.checkNotNull(name, "Dataset name cannot be null");

    DatasetDescriptor descriptor;
    try {
      descriptor = load(namespace, name);
    } catch (DatasetNotFoundException e) {
      return false;
    }
    Preconditions.checkState(descriptor.isColumnMapped(),
        "[BUG] Existing descriptor has no column mapping");

    String tableName = getTableName(name);
    String entityName = getEntityName(name);

    schemaManager.deleteSchema(tableName, entityName);

    // TODO: this may delete columns for other entities if they share column families
    // TODO: https://issues.cloudera.org/browse/CDK-145, https://issues.cloudera.org/browse/CDK-146
    for (String columnFamily : descriptor.getColumnMapping().getRequiredColumnFamilies()) {
      try {
        hbaseAdmin.disableTable(tableName);
        try {
          hbaseAdmin.deleteColumn(tableName, columnFamily);
        } finally {
View Full Code Here
45
46
47
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
      if (resolved.equals(namespace)) {
        // the requested dataset already exists
        throw new DatasetExistsException(
            "Metadata already exists for dataset: " + namespace + "." + name);
      } else {
        DatasetDescriptor loaded = load(resolved, name);
        // replacing old default.name table
        LOG.warn("Creating table managed table {}.{}: replaces default.{}",
            new Object[]{namespace, name, name});
        // validate that the new metadata can read the existing data
        Compatibility.checkUpdate(loaded, descriptor);
        // if the table in the default namespace matches, then the location is
        // either null (and should be set to the existing) or matches. either
        // way, use the loaded location.
        location = loaded.getLocation();
      }
    }

    LOG.info("Creating a managed Hive table named: " + name);

    boolean isExternal = (location != null);

    DatasetDescriptor toCreate = descriptor;
    if (isExternal) {
      // add the location to the descriptor that will be used
      toCreate = new DatasetDescriptor.Builder(descriptor)
          .location(location)
          .build();
    }

    // construct the table metadata from a descriptor
    Table table = HiveUtils.tableForDescriptor(
        namespace, name, toCreate, isExternal);

    // create it
    getMetaStoreUtil().createTable(table);

    // load the created table to get the final data location
    Table newTable = getMetaStoreUtil().getTable(namespace, name);

    DatasetDescriptor newDescriptor = new DatasetDescriptor.Builder(descriptor)
        .location(newTable.getSd().getLocation())
        .build();

    if (isExternal) {
      FileSystemUtil.ensureLocationExists(newDescriptor, conf);
View Full Code Here
71
72
73
74
75
76
77
78
79
80
81
      }
    }

    LOG.info("Creating an external Hive table: {}.{}", namespace, name);

    DatasetDescriptor newDescriptor = descriptor;

    if (descriptor.getLocation() == null) {
      // create a new descriptor with the dataset's location
      newDescriptor = new DatasetDescriptor.Builder(descriptor)
          .location(pathForDataset(namespace, name))
View Full Code Here
TOP

Related Classes of org.kitesdk.data.DatasetDescriptor$Builder

  • 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.fasterxml.jackson.databind.JsonNode
  • com.fasterxml.jackson.databind.ObjectMapper
  • com.google.gwt.autobean.shared.AutoBean.PropertyName
  • com.google.javascript.rhino.JSDocInfo
  • com.google.javascript.rhino.Node
    • 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.