use of io.druid.indexer.HadoopIngestionSpec in project druid by druid-io.
the class OrcIndexGeneratorJobTest method setUp.
@Before
public void setUp() throws Exception {
mapper = HadoopDruidIndexerConfig.JSON_MAPPER;
mapper.registerSubtypes(new NamedType(HashBasedNumberedShardSpec.class, "hashed"));
dataRoot = temporaryFolder.newFolder("data");
outputRoot = temporaryFolder.newFolder("output");
File dataFile = writeDataToLocalOrcFile(dataRoot, data);
HashMap<String, Object> inputSpec = new HashMap<String, Object>();
inputSpec.put("paths", dataFile.getCanonicalPath());
inputSpec.put("type", "static");
inputSpec.put("inputFormat", "org.apache.hadoop.hive.ql.io.orc.OrcNewInputFormat");
config = new HadoopDruidIndexerConfig(new HadoopIngestionSpec(new DataSchema(dataSourceName, mapper.convertValue(inputRowParser, Map.class), aggs, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, ImmutableList.of(this.interval)), mapper), new HadoopIOConfig(ImmutableMap.copyOf(inputSpec), null, outputRoot.getCanonicalPath()), new HadoopTuningConfig(outputRoot.getCanonicalPath(), null, null, null, null, null, false, false, false, false, //verifies that set num reducers is ignored
ImmutableMap.of(JobContext.NUM_REDUCES, "0"), false, true, null, true, null, false, false)));
config.setShardSpecs(loadShardSpecs(shardInfoForEachSegment));
config = HadoopDruidIndexerConfig.fromSpec(config.getSchema());
}
use of io.druid.indexer.HadoopIngestionSpec in project druid by druid-io.
the class TaskSerdeTest method testHadoopIndexTaskSerde.
@Test
public void testHadoopIndexTaskSerde() throws Exception {
final HadoopIndexTask task = new HadoopIndexTask(null, new HadoopIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[0], new UniformGranularitySpec(Granularities.DAY, null, ImmutableList.of(new Interval("2010-01-01/P1D"))), jsonMapper), new HadoopIOConfig(ImmutableMap.<String, Object>of("paths", "bar"), null, null), null), null, null, "blah", jsonMapper, null);
final String json = jsonMapper.writeValueAsString(task);
final HadoopIndexTask task2 = (HadoopIndexTask) jsonMapper.readValue(json, Task.class);
Assert.assertEquals("foo", task.getDataSource());
Assert.assertEquals(task.getId(), task2.getId());
Assert.assertEquals(task.getGroupId(), task2.getGroupId());
Assert.assertEquals(task.getDataSource(), task2.getDataSource());
Assert.assertEquals(task.getSpec().getTuningConfig().getJobProperties(), task2.getSpec().getTuningConfig().getJobProperties());
Assert.assertEquals("blah", task.getClasspathPrefix());
Assert.assertEquals("blah", task2.getClasspathPrefix());
}
Aggregations