Search in sources :

Example 21 with DimensionsSpec

use of io.druid.data.input.impl.DimensionsSpec in project druid by druid-io.

the class BatchDeltaIngestionTest method makeHadoopDruidIndexerConfig.

private HadoopDruidIndexerConfig makeHadoopDruidIndexerConfig(Map<String, Object> inputSpec, File tmpDir) throws Exception {
    HadoopDruidIndexerConfig config = new HadoopDruidIndexerConfig(new HadoopIngestionSpec(new DataSchema("website", MAPPER.convertValue(new StringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host")), null, null), null, ImmutableList.of("timestamp", "host", "host2", "visited_num")), null), Map.class), new AggregatorFactory[] { new LongSumAggregatorFactory("visited_sum", "visited_num"), new HyperUniquesAggregatorFactory("unique_hosts", "host2") }, new UniformGranularitySpec(Granularities.DAY, Granularities.NONE, ImmutableList.of(INTERVAL_FULL)), MAPPER), new HadoopIOConfig(inputSpec, null, tmpDir.getCanonicalPath()), new HadoopTuningConfig(tmpDir.getCanonicalPath(), null, null, null, null, null, false, false, false, false, null, false, false, null, null, null, false, false)));
    config.setShardSpecs(ImmutableMap.<Long, List<HadoopyShardSpec>>of(INTERVAL_FULL.getStartMillis(), ImmutableList.of(new HadoopyShardSpec(new HashBasedNumberedShardSpec(0, 1, null, HadoopDruidIndexerConfig.JSON_MAPPER), 0))));
    config = HadoopDruidIndexerConfig.fromSpec(config.getSchema());
    return config;
}
Also used : HashBasedNumberedShardSpec(io.druid.timeline.partition.HashBasedNumberedShardSpec) LongSumAggregatorFactory(io.druid.query.aggregation.LongSumAggregatorFactory) DataSchema(io.druid.segment.indexing.DataSchema) UniformGranularitySpec(io.druid.segment.indexing.granularity.UniformGranularitySpec) CSVParseSpec(io.druid.data.input.impl.CSVParseSpec) StringInputRowParser(io.druid.data.input.impl.StringInputRowParser) TimestampSpec(io.druid.data.input.impl.TimestampSpec) HyperUniquesAggregatorFactory(io.druid.query.aggregation.hyperloglog.HyperUniquesAggregatorFactory) DimensionsSpec(io.druid.data.input.impl.DimensionsSpec) Map(java.util.Map) ImmutableMap(com.google.common.collect.ImmutableMap)

Example 22 with DimensionsSpec

use of io.druid.data.input.impl.DimensionsSpec in project druid by druid-io.

the class DefaultOfflineAppenderatorFactoryTest method testBuild.

@Test
public void testBuild() throws IOException, SegmentNotWritableException {
    Injector injector = Initialization.makeInjectorWithModules(GuiceInjectors.makeStartupInjector(), ImmutableList.<Module>of(new Module() {

        @Override
        public void configure(Binder binder) {
            binder.bindConstant().annotatedWith(Names.named("serviceName")).to("druid/tool");
            binder.bindConstant().annotatedWith(Names.named("servicePort")).to(9999);
            binder.bind(DruidProcessingConfig.class).toInstance(new DruidProcessingConfig() {

                @Override
                public String getFormatString() {
                    return "processing-%s";
                }

                @Override
                public int intermediateComputeSizeBytes() {
                    return 100 * 1024 * 1024;
                }

                @Override
                public int getNumThreads() {
                    return 1;
                }

                @Override
                public int columnCacheSizeBytes() {
                    return 25 * 1024 * 1024;
                }
            });
            binder.bind(ColumnConfig.class).to(DruidProcessingConfig.class);
        }
    }));
    ObjectMapper objectMapper = injector.getInstance(ObjectMapper.class);
    AppenderatorFactory defaultOfflineAppenderatorFactory = objectMapper.reader(AppenderatorFactory.class).readValue("{\"type\":\"offline\"}");
    final Map<String, Object> parserMap = objectMapper.convertValue(new MapInputRowParser(new JSONParseSpec(new TimestampSpec("ts", "auto", null), new DimensionsSpec(null, null, null), null, null)), Map.class);
    DataSchema schema = new DataSchema("dataSourceName", parserMap, new AggregatorFactory[] { new CountAggregatorFactory("count"), new LongSumAggregatorFactory("met", "met") }, new UniformGranularitySpec(Granularities.MINUTE, Granularities.NONE, null), objectMapper);
    RealtimeTuningConfig tuningConfig = new RealtimeTuningConfig(75000, null, null, temporaryFolder.newFolder(), null, null, null, null, null, null, 0, 0, null, null);
    try (Appenderator appenderator = defaultOfflineAppenderatorFactory.build(schema, tuningConfig, new FireDepartmentMetrics())) {
        Assert.assertEquals("dataSourceName", appenderator.getDataSource());
        Assert.assertEquals(null, appenderator.startJob());
        SegmentIdentifier identifier = new SegmentIdentifier("dataSourceName", new Interval("2000/2001"), "A", new LinearShardSpec(0));
        Assert.assertEquals(0, ((AppenderatorImpl) appenderator).getRowsInMemory());
        appenderator.add(identifier, AppenderatorTest.IR("2000", "bar", 1), Suppliers.ofInstance(Committers.nil()));
        Assert.assertEquals(1, ((AppenderatorImpl) appenderator).getRowsInMemory());
        appenderator.add(identifier, AppenderatorTest.IR("2000", "baz", 1), Suppliers.ofInstance(Committers.nil()));
        Assert.assertEquals(2, ((AppenderatorImpl) appenderator).getRowsInMemory());
        appenderator.close();
        Assert.assertEquals(0, ((AppenderatorImpl) appenderator).getRowsInMemory());
    }
}
Also used : ColumnConfig(io.druid.segment.column.ColumnConfig) MapInputRowParser(io.druid.data.input.impl.MapInputRowParser) LinearShardSpec(io.druid.timeline.partition.LinearShardSpec) LongSumAggregatorFactory(io.druid.query.aggregation.LongSumAggregatorFactory) Binder(com.google.inject.Binder) UniformGranularitySpec(io.druid.segment.indexing.granularity.UniformGranularitySpec) Injector(com.google.inject.Injector) TimestampSpec(io.druid.data.input.impl.TimestampSpec) JSONParseSpec(io.druid.data.input.impl.JSONParseSpec) ObjectMapper(com.fasterxml.jackson.databind.ObjectMapper) RealtimeTuningConfig(io.druid.segment.indexing.RealtimeTuningConfig) DataSchema(io.druid.segment.indexing.DataSchema) FireDepartmentMetrics(io.druid.segment.realtime.FireDepartmentMetrics) CountAggregatorFactory(io.druid.query.aggregation.CountAggregatorFactory) DimensionsSpec(io.druid.data.input.impl.DimensionsSpec) Module(com.google.inject.Module) DruidProcessingConfig(io.druid.query.DruidProcessingConfig) Interval(org.joda.time.Interval) Test(org.junit.Test)

Example 23 with DimensionsSpec

use of io.druid.data.input.impl.DimensionsSpec in project druid by druid-io.

the class EventReceiverFirehoseTest method setUp.

@Before
public void setUp() throws Exception {
    req = EasyMock.createMock(HttpServletRequest.class);
    eventReceiverFirehoseFactory = new EventReceiverFirehoseFactory(SERVICE_NAME, CAPACITY, null, new DefaultObjectMapper(), new DefaultObjectMapper(), register);
    firehose = (EventReceiverFirehoseFactory.EventReceiverFirehose) eventReceiverFirehoseFactory.connect(new MapInputRowParser(new JSONParseSpec(new TimestampSpec("timestamp", "auto", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("d1")), null, null), null, null)));
}
Also used : HttpServletRequest(javax.servlet.http.HttpServletRequest) MapInputRowParser(io.druid.data.input.impl.MapInputRowParser) TimestampSpec(io.druid.data.input.impl.TimestampSpec) DimensionsSpec(io.druid.data.input.impl.DimensionsSpec) DefaultObjectMapper(io.druid.jackson.DefaultObjectMapper) JSONParseSpec(io.druid.data.input.impl.JSONParseSpec) Before(org.junit.Before)

Example 24 with DimensionsSpec

use of io.druid.data.input.impl.DimensionsSpec in project druid by druid-io.

the class EventReceiverFirehoseTest method testDuplicateRegistering.

@Test(expected = ISE.class)
public void testDuplicateRegistering() throws IOException {
    EventReceiverFirehoseFactory eventReceiverFirehoseFactory2 = new EventReceiverFirehoseFactory(SERVICE_NAME, CAPACITY, null, new DefaultObjectMapper(), new DefaultObjectMapper(), register);
    EventReceiverFirehoseFactory.EventReceiverFirehose firehose2 = (EventReceiverFirehoseFactory.EventReceiverFirehose) eventReceiverFirehoseFactory2.connect(new MapInputRowParser(new JSONParseSpec(new TimestampSpec("timestamp", "auto", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("d1")), null, null), null, null)));
}
Also used : MapInputRowParser(io.druid.data.input.impl.MapInputRowParser) TimestampSpec(io.druid.data.input.impl.TimestampSpec) DimensionsSpec(io.druid.data.input.impl.DimensionsSpec) DefaultObjectMapper(io.druid.jackson.DefaultObjectMapper) JSONParseSpec(io.druid.data.input.impl.JSONParseSpec) Test(org.junit.Test)

Example 25 with DimensionsSpec

use of io.druid.data.input.impl.DimensionsSpec in project druid by druid-io.

the class IngestSegmentFirehoseTest method createTestIndex.

private void createTestIndex(File segmentDir) throws Exception {
    List<String> rows = Lists.newArrayList("2014102200,host1,10", "2014102200,host2,20", "2014102200,host3,30", "2014102201,host1,10", "2014102201,host2,20", "2014102201,host3,30", "2014102202,host1,10", "2014102202,host2,20", "2014102202,host3,30");
    StringInputRowParser parser = new StringInputRowParser(new CSVParseSpec(new TimestampSpec("timestamp", "yyyyMMddHH", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("host")), null, null), null, ImmutableList.of("timestamp", "host", "visited")), Charsets.UTF_8.toString());
    AggregatorFactory[] aggregators = new AggregatorFactory[] { new LongSumAggregatorFactory("visited_sum", "visited") };
    IncrementalIndex index = null;
    try {
        index = new OnheapIncrementalIndex(0, Granularities.NONE, aggregators, true, true, true, 5000);
        for (String line : rows) {
            index.add(parser.parse(line));
        }
        indexMerger.persist(index, segmentDir, new IndexSpec());
    } finally {
        if (index != null) {
            index.close();
        }
    }
}
Also used : IndexSpec(io.druid.segment.IndexSpec) IncrementalIndex(io.druid.segment.incremental.IncrementalIndex) OnheapIncrementalIndex(io.druid.segment.incremental.OnheapIncrementalIndex) CSVParseSpec(io.druid.data.input.impl.CSVParseSpec) StringInputRowParser(io.druid.data.input.impl.StringInputRowParser) TimestampSpec(io.druid.data.input.impl.TimestampSpec) LongSumAggregatorFactory(io.druid.query.aggregation.LongSumAggregatorFactory) OnheapIncrementalIndex(io.druid.segment.incremental.OnheapIncrementalIndex) DimensionsSpec(io.druid.data.input.impl.DimensionsSpec) AggregatorFactory(io.druid.query.aggregation.AggregatorFactory) LongSumAggregatorFactory(io.druid.query.aggregation.LongSumAggregatorFactory)

Aggregations

DimensionsSpec (io.druid.data.input.impl.DimensionsSpec)41 TimestampSpec (io.druid.data.input.impl.TimestampSpec)29 JSONParseSpec (io.druid.data.input.impl.JSONParseSpec)16 StringInputRowParser (io.druid.data.input.impl.StringInputRowParser)16 OnheapIncrementalIndex (io.druid.segment.incremental.OnheapIncrementalIndex)16 Test (org.junit.Test)14 IncrementalIndex (io.druid.segment.incremental.IncrementalIndex)13 AggregatorFactory (io.druid.query.aggregation.AggregatorFactory)11 MapBasedInputRow (io.druid.data.input.MapBasedInputRow)10 CountAggregatorFactory (io.druid.query.aggregation.CountAggregatorFactory)10 DateTime (org.joda.time.DateTime)9 DoubleSumAggregatorFactory (io.druid.query.aggregation.DoubleSumAggregatorFactory)8 LongSumAggregatorFactory (io.druid.query.aggregation.LongSumAggregatorFactory)8 DataSchema (io.druid.segment.indexing.DataSchema)8 UniformGranularitySpec (io.druid.segment.indexing.granularity.UniformGranularitySpec)8 File (java.io.File)8 Map (java.util.Map)8 SpatialDimensionSchema (io.druid.data.input.impl.SpatialDimensionSchema)7 CSVParseSpec (io.druid.data.input.impl.CSVParseSpec)6 StringDimensionSchema (io.druid.data.input.impl.StringDimensionSchema)6