Search in sources :

Example 61 with TimestampSpec

use of org.apache.druid.data.input.impl.TimestampSpec in project druid by druid-io.

the class InputSourceSamplerTest method testMissingValueTimestampSpec.

@Test
public void testMissingValueTimestampSpec() throws IOException {
    final TimestampSpec timestampSpec = new TimestampSpec(null, null, DateTimes.of("1970"));
    final DimensionsSpec dimensionsSpec = new DimensionsSpec(null);
    final DataSchema dataSchema = createDataSchema(timestampSpec, dimensionsSpec, null, null, null);
    final InputSource inputSource = createInputSource(getTestRows(), dataSchema);
    final InputFormat inputFormat = createInputFormat();
    SamplerResponse response = inputSourceSampler.sample(inputSource, inputFormat, dataSchema, null);
    Assert.assertEquals(6, response.getNumRowsRead());
    Assert.assertEquals(6, response.getNumRowsIndexed());
    Assert.assertEquals(6, response.getData().size());
    List<SamplerResponseRow> data = response.getData();
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(0), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 0L).put("t", "2019-04-22T12:00").put("dim2", null).put("dim1", "foo").put("met1", "1").build(), null, null), data.get(0));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(1), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 0L).put("t", "2019-04-22T12:00").put("dim2", null).put("dim1", "foo").put("met1", "2").build(), null, null), data.get(1));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(2), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 0L).put("t", "2019-04-22T12:01").put("dim2", null).put("dim1", "foo").put("met1", "3").build(), null, null), data.get(2));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(3), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 0L).put("t", "2019-04-22T12:00").put("dim2", null).put("dim1", "foo2").put("met1", "4").build(), null, null), data.get(3));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(4), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 0L).put("t", "2019-04-22T12:00").put("dim2", "bar").put("dim1", "foo").put("met1", "5").build(), null, null), data.get(4));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(5), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 0L).put("t", "bad_timestamp").put("dim2", null).put("dim1", "foo").put("met1", "6").build(), null, null), data.get(5));
}
Also used : DataSchema(org.apache.druid.segment.indexing.DataSchema) RecordSupplierInputSource(org.apache.druid.indexing.seekablestream.RecordSupplierInputSource) InlineInputSource(org.apache.druid.data.input.impl.InlineInputSource) InputSource(org.apache.druid.data.input.InputSource) JsonInputFormat(org.apache.druid.data.input.impl.JsonInputFormat) InputFormat(org.apache.druid.data.input.InputFormat) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) SamplerResponse(org.apache.druid.client.indexing.SamplerResponse) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) SamplerResponseRow(org.apache.druid.client.indexing.SamplerResponse.SamplerResponseRow) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 62 with TimestampSpec

use of org.apache.druid.data.input.impl.TimestampSpec in project druid by druid-io.

the class RecordSupplierInputSourceTest method testRead.

@Test
public void testRead() throws IOException {
    final RandomCsvSupplier supplier = new RandomCsvSupplier();
    final InputSource inputSource = new RecordSupplierInputSource<>("topic", supplier, false);
    final List<String> colNames = IntStream.range(0, NUM_COLS).mapToObj(i -> StringUtils.format("col_%d", i)).collect(Collectors.toList());
    final InputFormat inputFormat = new CsvInputFormat(colNames, null, null, false, 0);
    final InputSourceReader reader = inputSource.reader(new InputRowSchema(new TimestampSpec("col_0", "auto", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(colNames.subList(1, colNames.size()))), ColumnsFilter.all()), inputFormat, temporaryFolder.newFolder());
    int read = 0;
    try (CloseableIterator<InputRow> iterator = reader.read()) {
        for (; read < NUM_ROWS && iterator.hasNext(); read++) {
            final InputRow inputRow = iterator.next();
            Assert.assertEquals(DateTimes.of(TIMESTAMP_STRING), inputRow.getTimestamp());
            Assert.assertEquals(NUM_COLS - 1, inputRow.getDimensions().size());
        }
    }
    Assert.assertEquals(NUM_ROWS, read);
    Assert.assertTrue(supplier.isClosed());
}
Also used : IntStream(java.util.stream.IntStream) StreamPartition(org.apache.druid.indexing.seekablestream.common.StreamPartition) RecordSupplier(org.apache.druid.indexing.seekablestream.common.RecordSupplier) OrderedPartitionableRecord(org.apache.druid.indexing.seekablestream.common.OrderedPartitionableRecord) Random(java.util.Random) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) InputRowSchema(org.apache.druid.data.input.InputRowSchema) ArrayList(java.util.ArrayList) InputSource(org.apache.druid.data.input.InputSource) Map(java.util.Map) ThreadLocalRandom(java.util.concurrent.ThreadLocalRandom) InputSourceReader(org.apache.druid.data.input.InputSourceReader) CloseableIterator(org.apache.druid.java.util.common.parsers.CloseableIterator) Nullable(javax.annotation.Nullable) DateTimes(org.apache.druid.java.util.common.DateTimes) ColumnsFilter(org.apache.druid.data.input.ColumnsFilter) InputFormat(org.apache.druid.data.input.InputFormat) Collection(java.util.Collection) StringUtils(org.apache.druid.java.util.common.StringUtils) Set(java.util.Set) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test) IOException(java.io.IOException) NotNull(javax.validation.constraints.NotNull) Maps(com.google.common.collect.Maps) Collectors(java.util.stream.Collectors) InputRow(org.apache.druid.data.input.InputRow) List(java.util.List) Rule(org.junit.Rule) ByteEntity(org.apache.druid.data.input.impl.ByteEntity) RandomStringUtils(org.apache.commons.lang3.RandomStringUtils) Assert(org.junit.Assert) Collections(java.util.Collections) TemporaryFolder(org.junit.rules.TemporaryFolder) InputSource(org.apache.druid.data.input.InputSource) InputSourceReader(org.apache.druid.data.input.InputSourceReader) InputFormat(org.apache.druid.data.input.InputFormat) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) InputRow(org.apache.druid.data.input.InputRow) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) InputRowSchema(org.apache.druid.data.input.InputRowSchema) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 63 with TimestampSpec

use of org.apache.druid.data.input.impl.TimestampSpec in project druid by druid-io.

the class InputSourceSamplerTest method testWithTransformsAutoDimensions.

@Test
public void testWithTransformsAutoDimensions() throws IOException {
    final TimestampSpec timestampSpec = new TimestampSpec("t", null, null);
    final DimensionsSpec dimensionsSpec = new DimensionsSpec(null);
    final TransformSpec transformSpec = new TransformSpec(null, ImmutableList.of(new ExpressionTransform("dim1PlusBar", "concat(dim1, 'bar')", TestExprMacroTable.INSTANCE)));
    final AggregatorFactory[] aggregatorFactories = { new LongSumAggregatorFactory("met1", "met1") };
    final GranularitySpec granularitySpec = new UniformGranularitySpec(Granularities.DAY, Granularities.HOUR, true, null);
    final DataSchema dataSchema = createDataSchema(timestampSpec, dimensionsSpec, aggregatorFactories, granularitySpec, transformSpec);
    final InputSource inputSource = createInputSource(getTestRows(), dataSchema);
    final InputFormat inputFormat = createInputFormat();
    SamplerResponse response = inputSourceSampler.sample(inputSource, inputFormat, dataSchema, null);
    Assert.assertEquals(6, response.getNumRowsRead());
    Assert.assertEquals(5, response.getNumRowsIndexed());
    Assert.assertEquals(4, response.getData().size());
    List<SamplerResponseRow> data = response.getData();
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(0), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo").put("dim2", null).put("met1", 6L).build(), null, null), data.get(0));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(3), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo2").put("dim2", null).put("met1", 4L).build(), null, null), data.get(1));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(4), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo").put("dim2", "bar").put("met1", 5L).build(), null, null), data.get(2));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(5), null, true, getUnparseableTimestampString()), data.get(3));
}
Also used : RecordSupplierInputSource(org.apache.druid.indexing.seekablestream.RecordSupplierInputSource) InlineInputSource(org.apache.druid.data.input.impl.InlineInputSource) InputSource(org.apache.druid.data.input.InputSource) SamplerResponse(org.apache.druid.client.indexing.SamplerResponse) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) TransformSpec(org.apache.druid.segment.transform.TransformSpec) DataSchema(org.apache.druid.segment.indexing.DataSchema) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) GranularitySpec(org.apache.druid.segment.indexing.granularity.GranularitySpec) JsonInputFormat(org.apache.druid.data.input.impl.JsonInputFormat) InputFormat(org.apache.druid.data.input.InputFormat) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) SamplerResponseRow(org.apache.druid.client.indexing.SamplerResponse.SamplerResponseRow) ExpressionTransform(org.apache.druid.segment.transform.ExpressionTransform) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 64 with TimestampSpec

use of org.apache.druid.data.input.impl.TimestampSpec in project druid by druid-io.

the class InputSourceSamplerTest method testWithNoRollup.

@Test
public void testWithNoRollup() throws IOException {
    final TimestampSpec timestampSpec = new TimestampSpec("t", null, null);
    final DimensionsSpec dimensionsSpec = new DimensionsSpec(null);
    final AggregatorFactory[] aggregatorFactories = { new LongSumAggregatorFactory("met1", "met1") };
    final GranularitySpec granularitySpec = new UniformGranularitySpec(Granularities.DAY, Granularities.HOUR, false, null);
    final DataSchema dataSchema = createDataSchema(timestampSpec, dimensionsSpec, aggregatorFactories, granularitySpec, null);
    final InputSource inputSource = createInputSource(getTestRows(), dataSchema);
    final InputFormat inputFormat = createInputFormat();
    SamplerResponse response = inputSourceSampler.sample(inputSource, inputFormat, dataSchema, null);
    Assert.assertEquals(6, response.getNumRowsRead());
    Assert.assertEquals(5, response.getNumRowsIndexed());
    Assert.assertEquals(6, response.getData().size());
    List<SamplerResponseRow> data = response.getData();
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(0), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo").put("dim2", null).put("met1", 1L).build(), null, null), data.get(0));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(1), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo").put("dim2", null).put("met1", 2L).build(), null, null), data.get(1));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(2), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo").put("dim2", null).put("met1", 3L).build(), null, null), data.get(2));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(3), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo2").put("dim2", null).put("met1", 4L).build(), null, null), data.get(3));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(4), new SamplerTestUtils.MapAllowingNullValuesBuilder<String, Object>().put("__time", 1555934400000L).put("dim1", "foo").put("dim2", "bar").put("met1", 5L).build(), null, null), data.get(4));
    assertEqualsSamplerResponseRow(new SamplerResponseRow(getRawColumns().get(5), null, true, getUnparseableTimestampString()), data.get(5));
}
Also used : RecordSupplierInputSource(org.apache.druid.indexing.seekablestream.RecordSupplierInputSource) InlineInputSource(org.apache.druid.data.input.impl.InlineInputSource) InputSource(org.apache.druid.data.input.InputSource) SamplerResponse(org.apache.druid.client.indexing.SamplerResponse) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) AggregatorFactory(org.apache.druid.query.aggregation.AggregatorFactory) DataSchema(org.apache.druid.segment.indexing.DataSchema) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) UniformGranularitySpec(org.apache.druid.segment.indexing.granularity.UniformGranularitySpec) GranularitySpec(org.apache.druid.segment.indexing.granularity.GranularitySpec) JsonInputFormat(org.apache.druid.data.input.impl.JsonInputFormat) InputFormat(org.apache.druid.data.input.InputFormat) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) SamplerResponseRow(org.apache.druid.client.indexing.SamplerResponse.SamplerResponseRow) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 65 with TimestampSpec

use of org.apache.druid.data.input.impl.TimestampSpec in project druid by druid-io.

the class OssInputSourceTest method testReader.

@Test
public void testReader() throws IOException {
    EasyMock.reset(OSSCLIENT);
    expectListObjects(PREFIXES.get(0), ImmutableList.of(EXPECTED_URIS.get(0)), CONTENT);
    expectListObjects(EXPECTED_URIS.get(1), ImmutableList.of(EXPECTED_URIS.get(1)), CONTENT);
    expectGetObject(EXPECTED_URIS.get(0));
    expectGetObject(EXPECTED_URIS.get(1));
    EasyMock.replay(OSSCLIENT);
    OssInputSource inputSource = new OssInputSource(OSSCLIENT, INPUT_DATA_CONFIG, null, ImmutableList.of(PREFIXES.get(0), EXPECTED_URIS.get(1)), null, null);
    InputRowSchema someSchema = new InputRowSchema(new TimestampSpec("time", "auto", null), new DimensionsSpec(DimensionsSpec.getDefaultSchemas(ImmutableList.of("dim1", "dim2"))), ColumnsFilter.all());
    InputSourceReader reader = inputSource.reader(someSchema, new CsvInputFormat(ImmutableList.of("time", "dim1", "dim2"), "|", false, null, 0), temporaryFolder.newFolder());
    CloseableIterator<InputRow> iterator = reader.read();
    while (iterator.hasNext()) {
        InputRow nextRow = iterator.next();
        Assert.assertEquals(NOW, nextRow.getTimestamp());
        Assert.assertEquals("hello", nextRow.getDimension("dim1").get(0));
        Assert.assertEquals("world", nextRow.getDimension("dim2").get(0));
    }
    EasyMock.verify(OSSCLIENT);
}
Also used : InputSourceReader(org.apache.druid.data.input.InputSourceReader) TimestampSpec(org.apache.druid.data.input.impl.TimestampSpec) InputRow(org.apache.druid.data.input.InputRow) DimensionsSpec(org.apache.druid.data.input.impl.DimensionsSpec) CsvInputFormat(org.apache.druid.data.input.impl.CsvInputFormat) InputRowSchema(org.apache.druid.data.input.InputRowSchema) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Aggregations

TimestampSpec (org.apache.druid.data.input.impl.TimestampSpec)154 DimensionsSpec (org.apache.druid.data.input.impl.DimensionsSpec)113 Test (org.junit.Test)110 DataSchema (org.apache.druid.segment.indexing.DataSchema)49 InputRow (org.apache.druid.data.input.InputRow)47 InitializedNullHandlingTest (org.apache.druid.testing.InitializedNullHandlingTest)41 UniformGranularitySpec (org.apache.druid.segment.indexing.granularity.UniformGranularitySpec)39 InputRowSchema (org.apache.druid.data.input.InputRowSchema)37 InputEntityReader (org.apache.druid.data.input.InputEntityReader)33 AggregatorFactory (org.apache.druid.query.aggregation.AggregatorFactory)32 JSONPathSpec (org.apache.druid.java.util.common.parsers.JSONPathSpec)30 JSONParseSpec (org.apache.druid.data.input.impl.JSONParseSpec)29 ArrayList (java.util.ArrayList)28 CsvInputFormat (org.apache.druid.data.input.impl.CsvInputFormat)28 StringInputRowParser (org.apache.druid.data.input.impl.StringInputRowParser)27 LongSumAggregatorFactory (org.apache.druid.query.aggregation.LongSumAggregatorFactory)27 JSONPathFieldSpec (org.apache.druid.java.util.common.parsers.JSONPathFieldSpec)25 InputRowListPlusRawValues (org.apache.druid.data.input.InputRowListPlusRawValues)21 DoubleSumAggregatorFactory (org.apache.druid.query.aggregation.DoubleSumAggregatorFactory)21 ArbitraryGranularitySpec (org.apache.druid.segment.indexing.granularity.ArbitraryGranularitySpec)20