Examples with DataSchema io.druid.segment.indexing.DataSchema used on opensource projects

Example 6 with DataSchema

use of io.druid.segment.indexing.DataSchema in project druid by druid-io.

the class TaskSerdeTest method testIndexTaskSerde.

@Test
public void testIndexTaskSerde() throws Exception {
    final IndexTask task = new IndexTask(null, null, new IndexTask.IndexIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[] { new DoubleSumAggregatorFactory("met", "met") }, new UniformGranularitySpec(Granularities.DAY, null, ImmutableList.of(new Interval("2010-01-01/P2D"))), jsonMapper), new IndexTask.IndexIOConfig(new LocalFirehoseFactory(new File("lol"), "rofl", null), true, true), new IndexTask.IndexTuningConfig(10000, 10, 9999, null, indexSpec, 3, true, true, true)), null, jsonMapper);
    final String json = jsonMapper.writeValueAsString(task);
    // Just want to run the clock a bit to make sure the task id doesn't change
    Thread.sleep(100);
    final IndexTask task2 = (IndexTask) 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());
    IndexTask.IndexIOConfig taskIoConfig = task.getIngestionSchema().getIOConfig();
    IndexTask.IndexIOConfig task2IoConfig = task2.getIngestionSchema().getIOConfig();
    Assert.assertTrue(taskIoConfig.getFirehoseFactory() instanceof LocalFirehoseFactory);
    Assert.assertTrue(task2IoConfig.getFirehoseFactory() instanceof LocalFirehoseFactory);
    Assert.assertEquals(taskIoConfig.isAppendToExisting(), task2IoConfig.isAppendToExisting());
    Assert.assertEquals(taskIoConfig.isSkipFirehoseCaching(), task2IoConfig.isSkipFirehoseCaching());
    IndexTask.IndexTuningConfig taskTuningConfig = task.getIngestionSchema().getTuningConfig();
    IndexTask.IndexTuningConfig task2TuningConfig = task2.getIngestionSchema().getTuningConfig();
    Assert.assertEquals(taskTuningConfig.getBasePersistDirectory(), task2TuningConfig.getBasePersistDirectory());
    Assert.assertEquals(taskTuningConfig.getIndexSpec(), task2TuningConfig.getIndexSpec());
    Assert.assertEquals(taskTuningConfig.getIntermediatePersistPeriod(), task2TuningConfig.getIntermediatePersistPeriod());
    Assert.assertEquals(taskTuningConfig.getMaxPendingPersists(), task2TuningConfig.getMaxPendingPersists());
    Assert.assertEquals(taskTuningConfig.getMaxRowsInMemory(), task2TuningConfig.getMaxRowsInMemory());
    Assert.assertEquals(taskTuningConfig.getNumShards(), task2TuningConfig.getNumShards());
    Assert.assertEquals(taskTuningConfig.getTargetPartitionSize(), task2TuningConfig.getTargetPartitionSize());
    Assert.assertEquals(taskTuningConfig.isBuildV9Directly(), task2TuningConfig.isBuildV9Directly());
    Assert.assertEquals(taskTuningConfig.isForceExtendableShardSpecs(), task2TuningConfig.isForceExtendableShardSpecs());
    Assert.assertEquals(taskTuningConfig.isReportParseExceptions(), task2TuningConfig.isReportParseExceptions());
}

Example 7 with DataSchema

use of io.druid.segment.indexing.DataSchema in project druid by druid-io.

the class TaskSerdeTest method testIndexTaskwithResourceSerde.

@Test
public void testIndexTaskwithResourceSerde() throws Exception {
    final IndexTask task = new IndexTask(null, new TaskResource("rofl", 2), new IndexTask.IndexIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[] { new DoubleSumAggregatorFactory("met", "met") }, new UniformGranularitySpec(Granularities.DAY, null, ImmutableList.of(new Interval("2010-01-01/P2D"))), jsonMapper), new IndexTask.IndexIOConfig(new LocalFirehoseFactory(new File("lol"), "rofl", null), true, null), new IndexTask.IndexTuningConfig(10000, 10, null, null, indexSpec, 3, true, true, true)), null, jsonMapper);
    for (final Module jacksonModule : new FirehoseModule().getJacksonModules()) {
        jsonMapper.registerModule(jacksonModule);
    }
    final String json = jsonMapper.writeValueAsString(task);
    // Just want to run the clock a bit to make sure the task id doesn't change
    Thread.sleep(100);
    final IndexTask task2 = (IndexTask) jsonMapper.readValue(json, Task.class);
    Assert.assertEquals("foo", task.getDataSource());
    Assert.assertEquals(task.getId(), task2.getId());
    Assert.assertEquals(2, task.getTaskResource().getRequiredCapacity());
    Assert.assertEquals("rofl", task.getTaskResource().getAvailabilityGroup());
    Assert.assertEquals(task.getTaskResource().getRequiredCapacity(), task2.getTaskResource().getRequiredCapacity());
    Assert.assertEquals(task.getTaskResource().getAvailabilityGroup(), task2.getTaskResource().getAvailabilityGroup());
    Assert.assertEquals(task.getGroupId(), task2.getGroupId());
    Assert.assertEquals(task.getDataSource(), task2.getDataSource());
    Assert.assertTrue(task.getIngestionSchema().getIOConfig().getFirehoseFactory() instanceof LocalFirehoseFactory);
    Assert.assertTrue(task2.getIngestionSchema().getIOConfig().getFirehoseFactory() instanceof LocalFirehoseFactory);
}

Example 8 with DataSchema

use of io.druid.segment.indexing.DataSchema in project druid by druid-io.

the class TaskLifecycleTest method newRealtimeIndexTask.

private RealtimeIndexTask newRealtimeIndexTask() {
    String taskId = String.format("rt_task_%s", System.currentTimeMillis());
    DataSchema dataSchema = new DataSchema("test_ds", null, new AggregatorFactory[] { new LongSumAggregatorFactory("count", "rows") }, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, null), mapper);
    RealtimeIOConfig realtimeIOConfig = new RealtimeIOConfig(new MockFirehoseFactory(true), null, // PlumberSchool - Realtime Index Task always uses RealtimePlumber which is hardcoded in RealtimeIndexTask class
    null);
    RealtimeTuningConfig realtimeTuningConfig = new RealtimeTuningConfig(1000, new Period("P1Y"), //default window period of 10 minutes
    null, // base persist dir ignored by Realtime Index task
    null, null, null, null, null, null, null, 0, 0, null, null);
    FireDepartment fireDepartment = new FireDepartment(dataSchema, realtimeIOConfig, realtimeTuningConfig);
    return new RealtimeIndexTask(taskId, new TaskResource(taskId, 1), fireDepartment, null);
}

Example 9 with DataSchema

use of io.druid.segment.indexing.DataSchema in project druid by druid-io.

the class TaskLifecycleTest method testIndexTask.

@Test
public void testIndexTask() throws Exception {
    final Task indexTask = new IndexTask(null, null, new IndexTask.IndexIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[] { new DoubleSumAggregatorFactory("met", "met") }, new UniformGranularitySpec(Granularities.DAY, null, ImmutableList.of(new Interval("2010-01-01/P2D"))), mapper), new IndexTask.IndexIOConfig(new MockFirehoseFactory(false), false, null), new IndexTask.IndexTuningConfig(10000, 10, null, null, indexSpec, 3, true, true, true)), null, MAPPER);
    final Optional<TaskStatus> preRunTaskStatus = tsqa.getStatus(indexTask.getId());
    Assert.assertTrue("pre run task status not present", !preRunTaskStatus.isPresent());
    final TaskStatus mergedStatus = runTask(indexTask);
    final TaskStatus status = taskStorage.getStatus(indexTask.getId()).get();
    final List<DataSegment> publishedSegments = byIntervalOrdering.sortedCopy(mdc.getPublished());
    final List<DataSegment> loggedSegments = byIntervalOrdering.sortedCopy(tsqa.getInsertedSegments(indexTask.getId()));
    Assert.assertEquals("statusCode", TaskStatus.Status.SUCCESS, status.getStatusCode());
    Assert.assertEquals("merged statusCode", TaskStatus.Status.SUCCESS, mergedStatus.getStatusCode());
    Assert.assertEquals("segments logged vs published", loggedSegments, publishedSegments);
    Assert.assertEquals("num segments published", 2, mdc.getPublished().size());
    Assert.assertEquals("num segments nuked", 0, mdc.getNuked().size());
    Assert.assertEquals("segment1 datasource", "foo", publishedSegments.get(0).getDataSource());
    Assert.assertEquals("segment1 interval", new Interval("2010-01-01/P1D"), publishedSegments.get(0).getInterval());
    Assert.assertEquals("segment1 dimensions", ImmutableList.of("dim1", "dim2"), publishedSegments.get(0).getDimensions());
    Assert.assertEquals("segment1 metrics", ImmutableList.of("met"), publishedSegments.get(0).getMetrics());
    Assert.assertEquals("segment2 datasource", "foo", publishedSegments.get(1).getDataSource());
    Assert.assertEquals("segment2 interval", new Interval("2010-01-02/P1D"), publishedSegments.get(1).getInterval());
    Assert.assertEquals("segment2 dimensions", ImmutableList.of("dim1", "dim2"), publishedSegments.get(1).getDimensions());
    Assert.assertEquals("segment2 metrics", ImmutableList.of("met"), publishedSegments.get(1).getMetrics());
}

Example 10 with DataSchema

use of io.druid.segment.indexing.DataSchema in project druid by druid-io.

the class TaskLifecycleTest method testIndexTaskFailure.

@Test
public void testIndexTaskFailure() throws Exception {
    final Task indexTask = new IndexTask(null, null, new IndexTask.IndexIngestionSpec(new DataSchema("foo", null, new AggregatorFactory[] { new DoubleSumAggregatorFactory("met", "met") }, new UniformGranularitySpec(Granularities.DAY, null, ImmutableList.of(new Interval("2010-01-01/P1D"))), mapper), new IndexTask.IndexIOConfig(new MockExceptionalFirehoseFactory(), false, null), new IndexTask.IndexTuningConfig(10000, 10, null, null, indexSpec, 3, true, true, true)), null, MAPPER);
    final TaskStatus status = runTask(indexTask);
    Assert.assertEquals("statusCode", TaskStatus.Status.FAILED, status.getStatusCode());
    Assert.assertEquals("num segments published", 0, mdc.getPublished().size());
    Assert.assertEquals("num segments nuked", 0, mdc.getNuked().size());
}