Search in sources :

Example 1 with SeekableStreamStartSequenceNumbers

use of org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers in project druid by druid-io.

the class KafkaIndexTaskTest method testMultipleParseExceptionsFailure.

@Test(timeout = 60_000L)
public void testMultipleParseExceptionsFailure() throws Exception {
    reportParseExceptions = false;
    maxParseExceptions = 2;
    maxSavedParseExceptions = 2;
    // Insert data
    insertData();
    final KafkaIndexTask task = createTask(null, new KafkaIndexTaskIOConfig(0, "sequence0", new SeekableStreamStartSequenceNumbers<>(topic, ImmutableMap.of(0, 2L), ImmutableSet.of()), new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 10L)), kafkaServer.consumerProperties(), KafkaSupervisorIOConfig.DEFAULT_POLL_TIMEOUT_MILLIS, true, null, null, INPUT_FORMAT));
    final ListenableFuture<TaskStatus> future = runTask(task);
    TaskStatus status = future.get();
    // Wait for task to exit
    Assert.assertEquals(TaskState.FAILED, status.getStatusCode());
    IndexTaskTest.checkTaskStatusErrorMsgForParseExceptionsExceeded(status);
    // Check metrics
    Assert.assertEquals(3, task.getRunner().getRowIngestionMeters().getProcessed());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getProcessedWithError());
    Assert.assertEquals(3, task.getRunner().getRowIngestionMeters().getUnparseable());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getThrownAway());
    // Check published metadata
    Assert.assertEquals(ImmutableList.of(), publishedDescriptors());
    Assert.assertNull(newDataSchemaMetadata());
    IngestionStatsAndErrorsTaskReportData reportData = getTaskReportData();
    Map<String, Object> expectedMetrics = ImmutableMap.of(RowIngestionMeters.BUILD_SEGMENTS, ImmutableMap.of(RowIngestionMeters.PROCESSED, 3, RowIngestionMeters.PROCESSED_WITH_ERROR, 0, RowIngestionMeters.UNPARSEABLE, 3, RowIngestionMeters.THROWN_AWAY, 0));
    Assert.assertEquals(expectedMetrics, reportData.getRowStats());
    List<LinkedHashMap> parseExceptionReports = (List<LinkedHashMap>) reportData.getUnparseableEvents().get(RowIngestionMeters.BUILD_SEGMENTS);
    List<String> expectedMessages = Arrays.asList("Unable to parse [] as the intermediateRow resulted in empty input row (Record: 1)", "Unable to parse row [unparseable] (Record: 1)");
    List<String> actualMessages = parseExceptionReports.stream().map((r) -> {
        return ((List<String>) r.get("details")).get(0);
    }).collect(Collectors.toList());
    Assert.assertEquals(expectedMessages, actualMessages);
    List<String> expectedInputs = Arrays.asList("", "unparseable");
    List<String> actualInputs = parseExceptionReports.stream().map((r) -> {
        return (String) r.get("input");
    }).collect(Collectors.toList());
    Assert.assertEquals(expectedInputs, actualInputs);
}
Also used : JsonProperty(com.fasterxml.jackson.annotation.JsonProperty) SegmentCacheManagerFactory(org.apache.druid.indexing.common.SegmentCacheManagerFactory) DirectQueryProcessingPool(org.apache.druid.query.DirectQueryProcessingPool) Arrays(java.util.Arrays) LookupNodeService(org.apache.druid.discovery.LookupNodeService) TestDataSegmentAnnouncer(org.apache.druid.indexing.test.TestDataSegmentAnnouncer) DataSourceMetadata(org.apache.druid.indexing.overlord.DataSourceMetadata) Map(java.util.Map) NamedType(com.fasterxml.jackson.databind.jsontype.NamedType) ScanQueryQueryToolChest(org.apache.druid.query.scan.ScanQueryQueryToolChest) ExpressionTransform(org.apache.druid.segment.transform.ExpressionTransform) AppenderatorsManager(org.apache.druid.segment.realtime.appenderator.AppenderatorsManager) NoopJoinableFactory(org.apache.druid.segment.join.NoopJoinableFactory) NoopIndexingServiceClient(org.apache.druid.client.indexing.NoopIndexingServiceClient) AfterClass(org.junit.AfterClass) Execs(org.apache.druid.java.util.common.concurrent.Execs) InputFormat(org.apache.druid.data.input.InputFormat) IngestionStatsAndErrorsTaskReportData(org.apache.druid.indexing.common.IngestionStatsAndErrorsTaskReportData) CacheConfig(org.apache.druid.client.cache.CacheConfig) TimeseriesQuery(org.apache.druid.query.timeseries.TimeseriesQuery) Set(java.util.Set) StringDimensionSchema(org.apache.druid.data.input.impl.StringDimensionSchema) StandardCharsets(java.nio.charset.StandardCharsets) Executors(java.util.concurrent.Executors) InputRow(org.apache.druid.data.input.InputRow) TaskState(org.apache.druid.indexer.TaskState) Stream(java.util.stream.Stream) TestDerbyConnector(org.apache.druid.metadata.TestDerbyConnector) TaskActionClientFactory(org.apache.druid.indexing.common.actions.TaskActionClientFactory) RowIngestionMetersFactory(org.apache.druid.segment.incremental.RowIngestionMetersFactory) TestingCluster(org.apache.curator.test.TestingCluster) TestBroker(org.apache.druid.indexing.kafka.test.TestBroker) TransformSpec(org.apache.druid.segment.transform.TransformSpec) DataSegmentPusher(org.apache.druid.segment.loading.DataSegmentPusher) Iterables(com.google.common.collect.Iterables) DoubleSumAggregatorFactory(org.apache.druid.query.aggregation.DoubleSumAggregatorFactory) SeekableStreamIndexTaskTestBase(org.apache.druid.indexing.seekablestream.SeekableStreamIndexTaskTestBase) DruidNodeAnnouncer(org.apache.druid.discovery.DruidNodeAnnouncer) RunWith(org.junit.runner.RunWith) TaskAuditLogConfig(org.apache.druid.indexing.common.actions.TaskAuditLogConfig) InputRowListPlusRawValues(org.apache.druid.data.input.InputRowListPlusRawValues) InputRowSchema(org.apache.druid.data.input.InputRowSchema) TaskStatus(org.apache.druid.indexer.TaskStatus) ScanQuery(org.apache.druid.query.scan.ScanQuery) KafkaSupervisorIOConfig(org.apache.druid.indexing.kafka.supervisor.KafkaSupervisorIOConfig) LinkedHashMap(java.util.LinkedHashMap) LocalDataSegmentPusherConfig(org.apache.druid.segment.loading.LocalDataSegmentPusherConfig) SupervisorManager(org.apache.druid.indexing.overlord.supervisor.SupervisorManager) AuthTestUtils(org.apache.druid.server.security.AuthTestUtils) CachePopulatorStats(org.apache.druid.client.cache.CachePopulatorStats) Nullable(javax.annotation.Nullable) Before(org.junit.Before) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) TaskToolboxFactory(org.apache.druid.indexing.common.TaskToolboxFactory) Executor(java.util.concurrent.Executor) DataSegmentServerAnnouncer(org.apache.druid.server.coordination.DataSegmentServerAnnouncer) QueryRunnerFactoryConglomerate(org.apache.druid.query.QueryRunnerFactoryConglomerate) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) Test(org.junit.Test) IOException(java.io.IOException) EasyMock(org.easymock.EasyMock) File(java.io.File) ExecutionException(java.util.concurrent.ExecutionException) Futures(com.google.common.util.concurrent.Futures) KafkaRecordEntity(org.apache.druid.data.input.kafka.KafkaRecordEntity) TreeMap(java.util.TreeMap) DefaultQueryRunnerFactoryConglomerate(org.apache.druid.query.DefaultQueryRunnerFactoryConglomerate) DruidNode(org.apache.druid.server.DruidNode) QueryRunnerFactory(org.apache.druid.query.QueryRunnerFactory) DefaultGenericQueryMetricsFactory(org.apache.druid.query.DefaultGenericQueryMetricsFactory) Assert(org.junit.Assert) DataSchema(org.apache.druid.segment.indexing.DataSchema) Module(com.fasterxml.jackson.databind.Module) QueryPlus(org.apache.druid.query.QueryPlus) TaskConfig(org.apache.druid.indexing.common.config.TaskConfig) LongDimensionSchema(org.apache.druid.data.input.impl.LongDimensionSchema) LocalTaskActionClientFactory(org.apache.druid.indexing.common.actions.LocalTaskActionClientFactory) TimeoutException(java.util.concurrent.TimeoutException) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) SeekableStreamSupervisor(org.apache.druid.indexing.seekablestream.supervisor.SeekableStreamSupervisor) SimpleModule(com.fasterxml.jackson.databind.module.SimpleModule) Druids(org.apache.druid.query.Druids) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) Task(org.apache.druid.indexing.common.task.Task) After(org.junit.After) ServerType(org.apache.druid.server.coordination.ServerType) TypeReference(com.fasterxml.jackson.core.type.TypeReference) CloseableIterator(org.apache.druid.java.util.common.parsers.CloseableIterator) NoopChatHandlerProvider(org.apache.druid.segment.realtime.firehose.NoopChatHandlerProvider) DerbyMetadataStorageActionHandlerFactory(org.apache.druid.metadata.DerbyMetadataStorageActionHandlerFactory) Parameterized(org.junit.runners.Parameterized) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) DateTimes(org.apache.druid.java.util.common.DateTimes) ImmutableSet(com.google.common.collect.ImmutableSet) ImmutableMap(com.google.common.collect.ImmutableMap) ScanResultValue(org.apache.druid.query.scan.ScanResultValue) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) Status(org.apache.druid.indexing.seekablestream.SeekableStreamIndexTaskRunner.Status) StringUtils(org.apache.druid.java.util.common.StringUtils) ScanQueryEngine(org.apache.druid.query.scan.ScanQueryEngine) Collectors(java.util.stream.Collectors) LockGranularity(org.apache.druid.indexing.common.LockGranularity) QuerySegmentSpec(org.apache.druid.query.spec.QuerySegmentSpec) TestUtils(org.apache.druid.indexing.common.TestUtils) ExprMacroTable(org.apache.druid.math.expr.ExprMacroTable) IndexerSQLMetadataStorageCoordinator(org.apache.druid.metadata.IndexerSQLMetadataStorageCoordinator) Objects(java.util.Objects) DataNodeService(org.apache.druid.discovery.DataNodeService) List(java.util.List) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) Header(org.apache.kafka.common.header.Header) InputEntityReader(org.apache.druid.data.input.InputEntityReader) ServiceEmitter(org.apache.druid.java.util.emitter.service.ServiceEmitter) SegmentHandoffNotifierFactory(org.apache.druid.segment.handoff.SegmentHandoffNotifierFactory) MetadataTaskStorage(org.apache.druid.indexing.overlord.MetadataTaskStorage) MapCache(org.apache.druid.client.cache.MapCache) Logger(org.apache.druid.java.util.common.logger.Logger) MoreExecutors(com.google.common.util.concurrent.MoreExecutors) TimeseriesQueryEngine(org.apache.druid.query.timeseries.TimeseriesQueryEngine) ProducerRecord(org.apache.kafka.clients.producer.ProducerRecord) ListenableFuture(com.google.common.util.concurrent.ListenableFuture) BeforeClass(org.junit.BeforeClass) SingleFileTaskReportFileWriter(org.apache.druid.indexing.common.SingleFileTaskReportFileWriter) TaskStorageConfig(org.apache.druid.indexing.common.config.TaskStorageConfig) MapBasedInputRow(org.apache.druid.data.input.MapBasedInputRow) HashMap(java.util.HashMap) RowIngestionMeters(org.apache.druid.segment.incremental.RowIngestionMeters) TaskActionToolbox(org.apache.druid.indexing.common.actions.TaskActionToolbox) HashSet(java.util.HashSet) ScanQueryConfig(org.apache.druid.query.scan.ScanQueryConfig) KafkaProducer(org.apache.kafka.clients.producer.KafkaProducer) ImmutableList(com.google.common.collect.ImmutableList) FloatDimensionSchema(org.apache.druid.data.input.impl.FloatDimensionSchema) Query(org.apache.druid.query.Query) NoopEmitter(org.apache.druid.java.util.emitter.core.NoopEmitter) ScanQueryRunnerFactory(org.apache.druid.query.scan.ScanQueryRunnerFactory) KafkaSupervisor(org.apache.druid.indexing.kafka.supervisor.KafkaSupervisor) RowIngestionMetersTotals(org.apache.druid.segment.incremental.RowIngestionMetersTotals) KafkaStringHeaderFormat(org.apache.druid.data.input.kafkainput.KafkaStringHeaderFormat) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) SegmentHandoffNotifier(org.apache.druid.segment.handoff.SegmentHandoffNotifier) Period(org.joda.time.Period) TestAppenderatorsManager(org.apache.druid.indexing.common.task.TestAppenderatorsManager) TaskLockbox(org.apache.druid.indexing.overlord.TaskLockbox) EmittingLogger(org.apache.druid.java.util.emitter.EmittingLogger) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest) TimeseriesQueryQueryToolChest(org.apache.druid.query.timeseries.TimeseriesQueryQueryToolChest) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) JsonProcessingException(com.fasterxml.jackson.core.JsonProcessingException) TestDataSegmentKiller(org.apache.druid.indexing.test.TestDataSegmentKiller) Granularities(org.apache.druid.java.util.common.granularity.Granularities) TimeUnit(java.util.concurrent.TimeUnit) Rule(org.junit.Rule) KafkaInputFormat(org.apache.druid.data.input.kafkainput.KafkaInputFormat) MonitorScheduler(org.apache.druid.java.util.metrics.MonitorScheduler) JsonCreator(com.fasterxml.jackson.annotation.JsonCreator) LocalDataSegmentPusher(org.apache.druid.segment.loading.LocalDataSegmentPusher) AsyncFunction(com.google.common.util.concurrent.AsyncFunction) SegmentDescriptor(org.apache.druid.query.SegmentDescriptor) TimeseriesQueryRunnerFactory(org.apache.druid.query.timeseries.TimeseriesQueryRunnerFactory) InputEntity(org.apache.druid.data.input.InputEntity) Collections(java.util.Collections) SeekableStreamIndexTaskRunner(org.apache.druid.indexing.seekablestream.SeekableStreamIndexTaskRunner) TemporaryFolder(org.junit.rules.TemporaryFolder) IngestionStatsAndErrorsTaskReportData(org.apache.druid.indexing.common.IngestionStatsAndErrorsTaskReportData) TaskStatus(org.apache.druid.indexer.TaskStatus) LinkedHashMap(java.util.LinkedHashMap) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) List(java.util.List) ImmutableList(com.google.common.collect.ImmutableList) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) Test(org.junit.Test) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest)

Example 2 with SeekableStreamStartSequenceNumbers

use of org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers in project druid by druid-io.

the class KafkaIndexTaskTest method testKafkaInputFormat.

@Test(timeout = 60_000L)
public void testKafkaInputFormat() throws Exception {
    // Insert data
    insertData(Iterables.limit(records, 3));
    final KafkaIndexTask task = createTask(null, new DataSchema("test_ds", new TimestampSpec("timestamp", "iso", null), new DimensionsSpec(Arrays.asList(new StringDimensionSchema("dim1"), new StringDimensionSchema("dim1t"), new StringDimensionSchema("dim2"), new LongDimensionSchema("dimLong"), new FloatDimensionSchema("dimFloat"), new StringDimensionSchema("kafka.testheader.encoding"))), new AggregatorFactory[] { new DoubleSumAggregatorFactory("met1sum", "met1"), new CountAggregatorFactory("rows") }, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, null), null), new KafkaIndexTaskIOConfig(0, "sequence0", new SeekableStreamStartSequenceNumbers<>(topic, ImmutableMap.of(0, 0L), ImmutableSet.of()), new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 5L)), kafkaServer.consumerProperties(), KafkaSupervisorIOConfig.DEFAULT_POLL_TIMEOUT_MILLIS, true, null, null, KAFKA_INPUT_FORMAT));
    Assert.assertTrue(task.supportsQueries());
    final ListenableFuture<TaskStatus> future = runTask(task);
    while (countEvents(task) != 3) {
        Thread.sleep(25);
    }
    Assert.assertEquals(Status.READING, task.getRunner().getStatus());
    final QuerySegmentSpec interval = OBJECT_MAPPER.readValue("\"2008/2012\"", QuerySegmentSpec.class);
    List<ScanResultValue> scanResultValues = scanData(task, interval);
    // verify that there are no records indexed in the rollbacked time period
    Assert.assertEquals(3, Iterables.size(scanResultValues));
    int i = 0;
    for (ScanResultValue result : scanResultValues) {
        final Map<String, Object> event = ((List<Map<String, Object>>) result.getEvents()).get(0);
        Assert.assertEquals("application/json", event.get("kafka.testheader.encoding"));
        Assert.assertEquals("y", event.get("dim2"));
    }
    // insert remaining data
    insertData(Iterables.skip(records, 3));
    // Wait for task to exit
    Assert.assertEquals(TaskState.SUCCESS, future.get().getStatusCode());
    // Check metrics
    Assert.assertEquals(4, task.getRunner().getRowIngestionMeters().getProcessed());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getUnparseable());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getThrownAway());
}
Also used : DoubleSumAggregatorFactory(org.apache.druid.query.aggregation.DoubleSumAggregatorFactory) LongDimensionSchema(org.apache.druid.data.input.impl.LongDimensionSchema) FloatDimensionSchema(org.apache.druid.data.input.impl.FloatDimensionSchema) DoubleSumAggregatorFactory(org.apache.druid.query.aggregation.DoubleSumAggregatorFactory) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) TaskStatus(org.apache.druid.indexer.TaskStatus) StringDimensionSchema(org.apache.druid.data.input.impl.StringDimensionSchema) DataSchema(org.apache.druid.segment.indexing.DataSchema) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) CountAggregatorFactory(org.apache.druid.query.aggregation.CountAggregatorFactory) ScanResultValue(org.apache.druid.query.scan.ScanResultValue) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) QuerySegmentSpec(org.apache.druid.query.spec.QuerySegmentSpec) List(java.util.List) ImmutableList(com.google.common.collect.ImmutableList) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) Test(org.junit.Test) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest)

Example 3 with SeekableStreamStartSequenceNumbers

use of org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers in project druid by druid-io.

the class KafkaIndexTaskTest method testRunOneTaskTwoPartitions.

@Test(timeout = 60_000L)
public void testRunOneTaskTwoPartitions() throws Exception {
    final KafkaIndexTask task = createTask(null, new KafkaIndexTaskIOConfig(0, "sequence0", new SeekableStreamStartSequenceNumbers<>(topic, ImmutableMap.of(0, 2L, 1, 0L), ImmutableSet.of()), new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 5L, 1, 2L)), kafkaServer.consumerProperties(), KafkaSupervisorIOConfig.DEFAULT_POLL_TIMEOUT_MILLIS, true, null, null, INPUT_FORMAT));
    final ListenableFuture<TaskStatus> future = runTask(task);
    // Insert data
    insertData();
    // Wait for tasks to exit
    Assert.assertEquals(TaskState.SUCCESS, future.get().getStatusCode());
    // Check metrics
    Assert.assertEquals(5, task.getRunner().getRowIngestionMeters().getProcessed());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getUnparseable());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getThrownAway());
    // Check published segments & metadata
    SegmentDescriptorAndExpectedDim1Values desc1 = sdd("2010/P1D", 0, ImmutableList.of("c"));
    SegmentDescriptorAndExpectedDim1Values desc2 = sdd("2011/P1D", 0, ImmutableList.of("d", "e", "h"));
    // desc3 will not be created in KafkaIndexTask (0.12.x) as it does not create per Kafka partition Druid segments
    @SuppressWarnings("unused") SegmentDescriptor desc3 = sd("2011/P1D", 1);
    SegmentDescriptorAndExpectedDim1Values desc4 = sdd("2012/P1D", 0, ImmutableList.of("g"));
    assertEqualsExceptVersion(ImmutableList.of(desc1, desc2, desc4), publishedDescriptors());
    Assert.assertEquals(new KafkaDataSourceMetadata(new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 5L, 1, 2L))), newDataSchemaMetadata());
}
Also used : SegmentDescriptor(org.apache.druid.query.SegmentDescriptor) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) TaskStatus(org.apache.druid.indexer.TaskStatus) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) Test(org.junit.Test) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest)

Example 4 with SeekableStreamStartSequenceNumbers

use of org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers in project druid by druid-io.

the class KafkaIndexTaskTest method testRunWithTransformSpec.

@Test(timeout = 60_000L)
public void testRunWithTransformSpec() throws Exception {
    final KafkaIndexTask task = createTask(null, NEW_DATA_SCHEMA.withTransformSpec(new TransformSpec(new SelectorDimFilter("dim1", "b", null), ImmutableList.of(new ExpressionTransform("dim1t", "concat(dim1,dim1)", ExprMacroTable.nil())))), new KafkaIndexTaskIOConfig(0, "sequence0", new SeekableStreamStartSequenceNumbers<>(topic, ImmutableMap.of(0, 0L), ImmutableSet.of()), new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 5L)), kafkaServer.consumerProperties(), KafkaSupervisorIOConfig.DEFAULT_POLL_TIMEOUT_MILLIS, true, null, null, INPUT_FORMAT));
    final ListenableFuture<TaskStatus> future = runTask(task);
    // Wait for the task to start reading
    while (task.getRunner().getStatus() != Status.READING) {
        Thread.sleep(10);
    }
    // Insert data
    insertData();
    // Wait for task to exit
    Assert.assertEquals(TaskState.SUCCESS, future.get().getStatusCode());
    // Check metrics
    Assert.assertEquals(1, task.getRunner().getRowIngestionMeters().getProcessed());
    Assert.assertEquals(0, task.getRunner().getRowIngestionMeters().getUnparseable());
    Assert.assertEquals(4, task.getRunner().getRowIngestionMeters().getThrownAway());
    // Check published metadata
    final List<SegmentDescriptor> publishedDescriptors = publishedDescriptors();
    assertEqualsExceptVersion(ImmutableList.of(sdd("2009/P1D", 0)), publishedDescriptors);
    Assert.assertEquals(new KafkaDataSourceMetadata(new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of(0, 5L))), newDataSchemaMetadata());
    // Check segments in deep storage
    Assert.assertEquals(ImmutableList.of("b"), readSegmentColumn("dim1", publishedDescriptors.get(0)));
    Assert.assertEquals(ImmutableList.of("bb"), readSegmentColumn("dim1t", publishedDescriptors.get(0)));
}
Also used : SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) SegmentDescriptor(org.apache.druid.query.SegmentDescriptor) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) ExpressionTransform(org.apache.druid.segment.transform.ExpressionTransform) TaskStatus(org.apache.druid.indexer.TaskStatus) TransformSpec(org.apache.druid.segment.transform.TransformSpec) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) Test(org.junit.Test) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest)

Example 5 with SeekableStreamStartSequenceNumbers

use of org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers in project druid by druid-io.

the class KafkaIndexTaskTest method testSerde.

@Test
public void testSerde() throws Exception {
    // This is both a serde test and a regression test for https://github.com/apache/druid/issues/7724.
    final KafkaIndexTask task = createTask("taskid", NEW_DATA_SCHEMA.withTransformSpec(new TransformSpec(null, ImmutableList.of(new ExpressionTransform("beep", "nofunc()", ExprMacroTable.nil())))), new KafkaIndexTaskIOConfig(0, "sequence", new SeekableStreamStartSequenceNumbers<>(topic, ImmutableMap.of(), ImmutableSet.of()), new SeekableStreamEndSequenceNumbers<>(topic, ImmutableMap.of()), ImmutableMap.of(), KafkaSupervisorIOConfig.DEFAULT_POLL_TIMEOUT_MILLIS, true, null, null, INPUT_FORMAT));
    final Task task1 = OBJECT_MAPPER.readValue(OBJECT_MAPPER.writeValueAsBytes(task), Task.class);
    Assert.assertEquals(task, task1);
}
Also used : Task(org.apache.druid.indexing.common.task.Task) SeekableStreamStartSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers) ExpressionTransform(org.apache.druid.segment.transform.ExpressionTransform) TransformSpec(org.apache.druid.segment.transform.TransformSpec) SeekableStreamEndSequenceNumbers(org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers) Test(org.junit.Test) IndexTaskTest(org.apache.druid.indexing.common.task.IndexTaskTest)

Aggregations

SeekableStreamStartSequenceNumbers (org.apache.druid.indexing.seekablestream.SeekableStreamStartSequenceNumbers)22 SeekableStreamEndSequenceNumbers (org.apache.druid.indexing.seekablestream.SeekableStreamEndSequenceNumbers)18 Test (org.junit.Test)17 Task (org.apache.druid.indexing.common.task.Task)13 ImmutableMap (com.google.common.collect.ImmutableMap)12 HashMap (java.util.HashMap)12 Map (java.util.Map)12 TreeMap (java.util.TreeMap)12 IndexTaskTest (org.apache.druid.indexing.common.task.IndexTaskTest)12 TaskStatus (org.apache.druid.indexer.TaskStatus)11 RealtimeIndexTask (org.apache.druid.indexing.common.task.RealtimeIndexTask)8 KinesisDataSourceMetadata (org.apache.druid.indexing.kinesis.KinesisDataSourceMetadata)7 SegmentDescriptor (org.apache.druid.query.SegmentDescriptor)7 ExpressionTransform (org.apache.druid.segment.transform.ExpressionTransform)7 TransformSpec (org.apache.druid.segment.transform.TransformSpec)7 ImmutableList (com.google.common.collect.ImmutableList)6 ImmutableSet (com.google.common.collect.ImmutableSet)6 HashSet (java.util.HashSet)6 List (java.util.List)6 Set (java.util.Set)6