Search in sources :

Example 71 with InputRow

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

the class S3InputSourceTest method testReaderRetriesOnSdkClientExceptionButNeverSucceedsThenThrows.

@Test(expected = SdkClientException.class)
public void testReaderRetriesOnSdkClientExceptionButNeverSucceedsThenThrows() throws Exception {
    EasyMock.reset(S3_CLIENT);
    expectListObjects(PREFIXES.get(0), ImmutableList.of(EXPECTED_URIS.get(0)), CONTENT);
    expectSdkClientException(EXPECTED_URIS.get(0));
    EasyMock.replay(S3_CLIENT);
    S3InputSource inputSource = new S3InputSource(SERVICE, SERVER_SIDE_ENCRYPTING_AMAZON_S3_BUILDER, INPUT_DATA_CONFIG, null, ImmutableList.of(PREFIXES.get(0)), null, null, // only have three retries since they are slow
    3);
    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(S3_CLIENT);
}
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)

Example 72 with InputRow

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

the class VarianceSqlAggregatorTest method testStdDevWithVirtualColumns.

@Test
public void testStdDevWithVirtualColumns() throws Exception {
    VarianceAggregatorCollector holder1 = new VarianceAggregatorCollector();
    VarianceAggregatorCollector holder2 = new VarianceAggregatorCollector();
    VarianceAggregatorCollector holder3 = new VarianceAggregatorCollector();
    for (InputRow row : CalciteTests.ROWS1_WITH_NUMERIC_DIMS) {
        Object raw1 = row.getRaw("d1");
        Object raw2 = row.getRaw("f1");
        Object raw3 = row.getRaw("l1");
        addToHolder(holder1, raw1, 7);
        addToHolder(holder2, raw2, 7);
        addToHolder(holder3, raw3, 7);
    }
    final List<Object[]> expectedResults = ImmutableList.of(new Object[] { Math.sqrt(holder1.getVariance(false)), (float) Math.sqrt(holder2.getVariance(false)), (long) Math.sqrt(holder3.getVariance(false)) });
    testQuery("SELECT\n" + "STDDEV(d1*7),\n" + "STDDEV(f1*7),\n" + "STDDEV(l1*7)\n" + "FROM numfoo", ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE3).intervals(new MultipleIntervalSegmentSpec(ImmutableList.of(Filtration.eternity()))).granularity(Granularities.ALL).virtualColumns(BaseCalciteQueryTest.expressionVirtualColumn("v0", "(\"d1\" * 7)", ColumnType.DOUBLE), BaseCalciteQueryTest.expressionVirtualColumn("v1", "(\"f1\" * 7)", ColumnType.FLOAT), BaseCalciteQueryTest.expressionVirtualColumn("v2", "(\"l1\" * 7)", ColumnType.LONG)).aggregators(ImmutableList.of(new VarianceAggregatorFactory("a0:agg", "v0", "sample", "double"), new VarianceAggregatorFactory("a1:agg", "v1", "sample", "float"), new VarianceAggregatorFactory("a2:agg", "v2", "sample", "long"))).postAggregators(new StandardDeviationPostAggregator("a0", "a0:agg", "sample"), new StandardDeviationPostAggregator("a1", "a1:agg", "sample"), new StandardDeviationPostAggregator("a2", "a2:agg", "sample")).context(BaseCalciteQueryTest.QUERY_CONTEXT_DEFAULT).build()), expectedResults);
}
Also used : VarianceAggregatorCollector(org.apache.druid.query.aggregation.variance.VarianceAggregatorCollector) StandardDeviationPostAggregator(org.apache.druid.query.aggregation.variance.StandardDeviationPostAggregator) InputRow(org.apache.druid.data.input.InputRow) MultipleIntervalSegmentSpec(org.apache.druid.query.spec.MultipleIntervalSegmentSpec) VarianceAggregatorFactory(org.apache.druid.query.aggregation.variance.VarianceAggregatorFactory) BaseCalciteQueryTest(org.apache.druid.sql.calcite.BaseCalciteQueryTest) Test(org.junit.Test)

Example 73 with InputRow

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

the class BatchDeltaIngestionTest method verifyRows.

private void verifyRows(List<ImmutableMap<String, Object>> expectedRows, List<InputRow> actualRows, List<String> expectedDimensions, List<String> expectedMetrics) {
    Assert.assertEquals(expectedRows.size(), actualRows.size());
    for (int i = 0; i < expectedRows.size(); i++) {
        Map<String, Object> expected = expectedRows.get(i);
        InputRow actual = actualRows.get(i);
        Assert.assertEquals(expected.get("time"), actual.getTimestamp());
        Assert.assertEquals(expectedDimensions, actual.getDimensions());
        expectedDimensions.forEach(s -> Assert.assertEquals(expected.get(s), actual.getDimension(s)));
        for (String metric : expectedMetrics) {
            Object actualValue = actual.getRaw(metric);
            if (actualValue instanceof HyperLogLogCollector) {
                Assert.assertEquals((Double) expected.get(metric), (Double) HyperUniquesAggregatorFactory.estimateCardinality(actualValue, false), 0.001);
            } else {
                Assert.assertEquals(expected.get(metric), actual.getMetric(metric));
            }
        }
    }
}
Also used : HyperLogLogCollector(org.apache.druid.hll.HyperLogLogCollector) InputRow(org.apache.druid.data.input.InputRow)

Example 74 with InputRow

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

the class VarianceSqlAggregatorTest method testVarSamp.

@Test
public void testVarSamp() throws Exception {
    VarianceAggregatorCollector holder1 = new VarianceAggregatorCollector();
    VarianceAggregatorCollector holder2 = new VarianceAggregatorCollector();
    VarianceAggregatorCollector holder3 = new VarianceAggregatorCollector();
    for (InputRow row : CalciteTests.ROWS1_WITH_NUMERIC_DIMS) {
        Object raw1 = row.getRaw("d1");
        Object raw2 = row.getRaw("f1");
        Object raw3 = row.getRaw("l1");
        addToHolder(holder1, raw1);
        addToHolder(holder2, raw2);
        addToHolder(holder3, raw3);
    }
    final List<Object[]> expectedResults = ImmutableList.of(new Object[] { holder1.getVariance(false), holder2.getVariance(false).floatValue(), holder3.getVariance(false).longValue() });
    testQuery("SELECT\n" + "VAR_SAMP(d1),\n" + "VAR_SAMP(f1),\n" + "VAR_SAMP(l1)\n" + "FROM numfoo", ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE3).intervals(new MultipleIntervalSegmentSpec(ImmutableList.of(Filtration.eternity()))).granularity(Granularities.ALL).aggregators(ImmutableList.of(new VarianceAggregatorFactory("a0:agg", "d1", "sample", "double"), new VarianceAggregatorFactory("a1:agg", "f1", "sample", "float"), new VarianceAggregatorFactory("a2:agg", "l1", "sample", "long"))).context(BaseCalciteQueryTest.QUERY_CONTEXT_DEFAULT).build()), expectedResults);
}
Also used : VarianceAggregatorCollector(org.apache.druid.query.aggregation.variance.VarianceAggregatorCollector) InputRow(org.apache.druid.data.input.InputRow) MultipleIntervalSegmentSpec(org.apache.druid.query.spec.MultipleIntervalSegmentSpec) VarianceAggregatorFactory(org.apache.druid.query.aggregation.variance.VarianceAggregatorFactory) BaseCalciteQueryTest(org.apache.druid.sql.calcite.BaseCalciteQueryTest) Test(org.junit.Test)

Example 75 with InputRow

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

the class VarianceSqlAggregatorTest method testVarPop.

@Test
public void testVarPop() throws Exception {
    VarianceAggregatorCollector holder1 = new VarianceAggregatorCollector();
    VarianceAggregatorCollector holder2 = new VarianceAggregatorCollector();
    VarianceAggregatorCollector holder3 = new VarianceAggregatorCollector();
    for (InputRow row : CalciteTests.ROWS1_WITH_NUMERIC_DIMS) {
        Object raw1 = row.getRaw("d1");
        Object raw2 = row.getRaw("f1");
        Object raw3 = row.getRaw("l1");
        addToHolder(holder1, raw1);
        addToHolder(holder2, raw2);
        addToHolder(holder3, raw3);
    }
    final List<Object[]> expectedResults = ImmutableList.of(new Object[] { holder1.getVariance(true), holder2.getVariance(true).floatValue(), holder3.getVariance(true).longValue() });
    testQuery("SELECT\n" + "VAR_POP(d1),\n" + "VAR_POP(f1),\n" + "VAR_POP(l1)\n" + "FROM numfoo", ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE3).intervals(new MultipleIntervalSegmentSpec(ImmutableList.of(Filtration.eternity()))).granularity(Granularities.ALL).aggregators(ImmutableList.of(new VarianceAggregatorFactory("a0:agg", "d1", "population", "double"), new VarianceAggregatorFactory("a1:agg", "f1", "population", "float"), new VarianceAggregatorFactory("a2:agg", "l1", "population", "long"))).context(BaseCalciteQueryTest.QUERY_CONTEXT_DEFAULT).build()), expectedResults);
}
Also used : VarianceAggregatorCollector(org.apache.druid.query.aggregation.variance.VarianceAggregatorCollector) InputRow(org.apache.druid.data.input.InputRow) MultipleIntervalSegmentSpec(org.apache.druid.query.spec.MultipleIntervalSegmentSpec) VarianceAggregatorFactory(org.apache.druid.query.aggregation.variance.VarianceAggregatorFactory) BaseCalciteQueryTest(org.apache.druid.sql.calcite.BaseCalciteQueryTest) Test(org.junit.Test)

Aggregations

InputRow (org.apache.druid.data.input.InputRow)266 Test (org.junit.Test)193 MapBasedInputRow (org.apache.druid.data.input.MapBasedInputRow)57 InputEntityReader (org.apache.druid.data.input.InputEntityReader)54 InputRowSchema (org.apache.druid.data.input.InputRowSchema)52 DimensionsSpec (org.apache.druid.data.input.impl.DimensionsSpec)52 TimestampSpec (org.apache.druid.data.input.impl.TimestampSpec)49 ArrayList (java.util.ArrayList)46 List (java.util.List)37 ImmutableList (com.google.common.collect.ImmutableList)33 JSONPathSpec (org.apache.druid.java.util.common.parsers.JSONPathSpec)33 InitializedNullHandlingTest (org.apache.druid.testing.InitializedNullHandlingTest)33 InputRowListPlusRawValues (org.apache.druid.data.input.InputRowListPlusRawValues)29 File (java.io.File)27 HadoopDruidIndexerConfig (org.apache.druid.indexer.HadoopDruidIndexerConfig)27 JSONPathFieldSpec (org.apache.druid.java.util.common.parsers.JSONPathFieldSpec)27 DateTime (org.joda.time.DateTime)24 Map (java.util.Map)23 IOException (java.io.IOException)18 Interval (org.joda.time.Interval)18