Search in sources :

Example 1 with TimeFormatExtractionFn

use of org.apache.druid.query.extraction.TimeFormatExtractionFn in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByNestedDoubleTimeExtractionFnWithLongOutputTypes.

@Test
public void testGroupByNestedDoubleTimeExtractionFnWithLongOutputTypes() {
    // Cannot vectorize due to extraction dimension spec.
    cannotVectorize();
    if (config.getDefaultStrategy().equals(GroupByStrategySelector.STRATEGY_V1)) {
        expectedException.expect(UnsupportedOperationException.class);
        expectedException.expectMessage("GroupBy v1 only supports dimensions with an outputType of STRING.");
    }
    GroupByQuery subquery = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, "time_day", ColumnType.LONG, new TimeFormatExtractionFn(null, null, null, Granularities.DAY, true))).setDimFilter(new SelectorDimFilter("quality", "technology", null)).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    GroupByQuery outerQuery = makeQueryBuilder().setDataSource(subquery).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("alias", "alias"), new ExtractionDimensionSpec("time_day", "time_week", ColumnType.LONG, new TimeFormatExtractionFn(null, null, null, Granularities.WEEK, true))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT).setGranularity(QueryRunnerTestHelper.ALL_GRAN).build();
    List<ResultRow> expectedResults = Collections.singletonList(makeRow(outerQuery, "2011-04-01", "alias", "technology", "time_week", 1301270400000L, "rows", 2L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, outerQuery);
    TestHelper.assertExpectedObjects(expectedResults, results, "extraction-fn");
}
Also used : TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) ExtractionDimensionSpec(org.apache.druid.query.dimension.ExtractionDimensionSpec) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 2 with TimeFormatExtractionFn

use of org.apache.druid.query.extraction.TimeFormatExtractionFn in project druid by druid-io.

the class GroupByLimitPushDownMultiNodeMergeTest method testPartialLimitPushDownMerge.

@Test
public void testPartialLimitPushDownMerge() {
    // one segment's results use limit push down, the other doesn't because of insufficient buffer capacity
    QueryToolChest<ResultRow, GroupByQuery> toolChest = groupByFactory.getToolchest();
    QueryRunner<ResultRow> theRunner = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(groupByFactory.mergeRunners(executorService, getRunner1(0))), (QueryToolChest) toolChest);
    QueryRunner<ResultRow> theRunner2 = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(groupByFactory2.mergeRunners(executorService, getRunner2(1))), (QueryToolChest) toolChest);
    QueryRunner<ResultRow> finalRunner = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(new QueryRunner<ResultRow>() {

        @Override
        public Sequence<ResultRow> run(QueryPlus<ResultRow> queryPlus, ResponseContext responseContext) {
            return Sequences.simple(ImmutableList.of(theRunner.run(queryPlus, responseContext), theRunner2.run(queryPlus, responseContext))).flatMerge(Function.identity(), queryPlus.getQuery().getResultOrdering());
        }
    }), (QueryToolChest) toolChest);
    QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(Intervals.utc(1500000000000L, 1600000000000L)));
    GroupByQuery query = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("dimA", "dimA"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, "hour", ColumnType.LONG, new TimeFormatExtractionFn(null, null, null, new PeriodGranularity(new Period("PT1H"), null, DateTimeZone.UTC), true))).setAggregatorSpecs(new LongSumAggregatorFactory("metASum", "metA")).setLimitSpec(new DefaultLimitSpec(Arrays.asList(new OrderByColumnSpec("hour", OrderByColumnSpec.Direction.ASCENDING, StringComparators.NUMERIC), new OrderByColumnSpec("dimA", OrderByColumnSpec.Direction.ASCENDING)), 1000)).setContext(ImmutableMap.of(GroupByQueryConfig.CTX_KEY_APPLY_LIMIT_PUSH_DOWN, true)).setGranularity(Granularities.ALL).build();
    Sequence<ResultRow> queryResult = finalRunner.run(QueryPlus.wrap(query), ResponseContext.createEmpty());
    List<ResultRow> results = queryResult.toList();
    ResultRow expectedRow0 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "mango", "hour", 1505260800000L, "metASum", 26L);
    ResultRow expectedRow1 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "pomegranate", "hour", 1505260800000L, "metASum", 7113L);
    ResultRow expectedRow2 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "mango", "hour", 1505264400000L, "metASum", 10L);
    ResultRow expectedRow3 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "2017-07-14T02:40:00.000Z", "dimA", "pomegranate", "hour", 1505264400000L, "metASum", 7726L);
    Assert.assertEquals(4, results.size());
    Assert.assertEquals(expectedRow0, results.get(0));
    Assert.assertEquals(expectedRow1, results.get(1));
    Assert.assertEquals(expectedRow2, results.get(2));
    Assert.assertEquals(expectedRow3, results.get(3));
}
Also used : TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) DefaultLimitSpec(org.apache.druid.query.groupby.orderby.DefaultLimitSpec) PeriodGranularity(org.apache.druid.java.util.common.granularity.PeriodGranularity) LongSumAggregatorFactory(org.apache.druid.query.aggregation.LongSumAggregatorFactory) Period(org.joda.time.Period) MultipleIntervalSegmentSpec(org.apache.druid.query.spec.MultipleIntervalSegmentSpec) QueryRunner(org.apache.druid.query.QueryRunner) FinalizeResultsQueryRunner(org.apache.druid.query.FinalizeResultsQueryRunner) BySegmentQueryRunner(org.apache.druid.query.BySegmentQueryRunner) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) OrderByColumnSpec(org.apache.druid.query.groupby.orderby.OrderByColumnSpec) FinalizeResultsQueryRunner(org.apache.druid.query.FinalizeResultsQueryRunner) ResponseContext(org.apache.druid.query.context.ResponseContext) QuerySegmentSpec(org.apache.druid.query.spec.QuerySegmentSpec) QueryPlus(org.apache.druid.query.QueryPlus) ExtractionDimensionSpec(org.apache.druid.query.dimension.ExtractionDimensionSpec) Test(org.junit.Test)

Example 3 with TimeFormatExtractionFn

use of org.apache.druid.query.extraction.TimeFormatExtractionFn in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByTimeExtractionWithNulls.

@Test
public void testGroupByTimeExtractionWithNulls() {
    // Cannot vectorize due to extraction dimension specs.
    cannotVectorize();
    final DimExtractionFn nullWednesdays = new DimExtractionFn() {

        @Override
        public String apply(String dimValue) {
            if ("Wednesday".equals(dimValue)) {
                return null;
            } else {
                return dimValue;
            }
        }

        @Override
        public byte[] getCacheKey() {
            throw new UnsupportedOperationException();
        }

        @Override
        public boolean preservesOrdering() {
            return false;
        }

        @Override
        public ExtractionType getExtractionType() {
            return ExtractionType.MANY_TO_ONE;
        }
    };
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).setDimensions(new DefaultDimensionSpec("market", "market"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, "dayOfWeek", new CascadeExtractionFn(new ExtractionFn[] { new TimeFormatExtractionFn("EEEE", null, null, null, false), nullWednesdays }))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, QueryRunnerTestHelper.INDEX_DOUBLE_SUM).setPostAggregatorSpecs(Collections.singletonList(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT)).setGranularity(QueryRunnerTestHelper.ALL_GRAN).setDimFilter(new OrDimFilter(Arrays.asList(new SelectorDimFilter("market", "spot", null), new SelectorDimFilter("market", "upfront", null)))).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "1970-01-01", "dayOfWeek", null, "market", "spot", "index", 14271.368591308594, "rows", 126L, "addRowsIndexConstant", 14398.368591308594), makeRow(query, "1970-01-01", "dayOfWeek", "Friday", "market", "spot", "index", 13219.574157714844, "rows", 117L, "addRowsIndexConstant", 13337.574157714844), makeRow(query, "1970-01-01", "dayOfWeek", "Monday", "market", "spot", "index", 13557.738830566406, "rows", 117L, "addRowsIndexConstant", 13675.738830566406), makeRow(query, "1970-01-01", "dayOfWeek", "Saturday", "market", "spot", "index", 13493.751281738281, "rows", 117L, "addRowsIndexConstant", 13611.751281738281), makeRow(query, "1970-01-01", "dayOfWeek", "Sunday", "market", "spot", "index", 13585.541015625, "rows", 117L, "addRowsIndexConstant", 13703.541015625), makeRow(query, "1970-01-01", "dayOfWeek", "Thursday", "market", "spot", "index", 14279.127197265625, "rows", 126L, "addRowsIndexConstant", 14406.127197265625), makeRow(query, "1970-01-01", "dayOfWeek", "Tuesday", "market", "spot", "index", 13199.471435546875, "rows", 117L, "addRowsIndexConstant", 13317.471435546875), makeRow(query, "1970-01-01", "dayOfWeek", null, "market", "upfront", "index", 28985.5751953125, "rows", 28L, "addRowsIndexConstant", 29014.5751953125), makeRow(query, "1970-01-01", "dayOfWeek", "Friday", "market", "upfront", "index", 27297.8623046875, "rows", 26L, "addRowsIndexConstant", 27324.8623046875), makeRow(query, "1970-01-01", "dayOfWeek", "Monday", "market", "upfront", "index", 27619.58447265625, "rows", 26L, "addRowsIndexConstant", 27646.58447265625), makeRow(query, "1970-01-01", "dayOfWeek", "Saturday", "market", "upfront", "index", 27820.83154296875, "rows", 26L, "addRowsIndexConstant", 27847.83154296875), makeRow(query, "1970-01-01", "dayOfWeek", "Sunday", "market", "upfront", "index", 24791.223876953125, "rows", 26L, "addRowsIndexConstant", 24818.223876953125), makeRow(query, "1970-01-01", "dayOfWeek", "Thursday", "market", "upfront", "index", 28562.748901367188, "rows", 28L, "addRowsIndexConstant", 28591.748901367188), makeRow(query, "1970-01-01", "dayOfWeek", "Tuesday", "market", "upfront", "index", 26968.280639648438, "rows", 26L, "addRowsIndexConstant", 26995.280639648438));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "time-extraction");
}
Also used : TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) CascadeExtractionFn(org.apache.druid.query.extraction.CascadeExtractionFn) RegexDimExtractionFn(org.apache.druid.query.extraction.RegexDimExtractionFn) StringFormatExtractionFn(org.apache.druid.query.extraction.StringFormatExtractionFn) LookupExtractionFn(org.apache.druid.query.lookup.LookupExtractionFn) CascadeExtractionFn(org.apache.druid.query.extraction.CascadeExtractionFn) StrlenExtractionFn(org.apache.druid.query.extraction.StrlenExtractionFn) SubstringDimExtractionFn(org.apache.druid.query.extraction.SubstringDimExtractionFn) ExtractionFn(org.apache.druid.query.extraction.ExtractionFn) DimExtractionFn(org.apache.druid.query.extraction.DimExtractionFn) JavaScriptExtractionFn(org.apache.druid.query.extraction.JavaScriptExtractionFn) SearchQuerySpecDimExtractionFn(org.apache.druid.query.extraction.SearchQuerySpecDimExtractionFn) TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) OrDimFilter(org.apache.druid.query.filter.OrDimFilter) RegexDimExtractionFn(org.apache.druid.query.extraction.RegexDimExtractionFn) SubstringDimExtractionFn(org.apache.druid.query.extraction.SubstringDimExtractionFn) DimExtractionFn(org.apache.druid.query.extraction.DimExtractionFn) SearchQuerySpecDimExtractionFn(org.apache.druid.query.extraction.SearchQuerySpecDimExtractionFn) ExtractionDimensionSpec(org.apache.druid.query.dimension.ExtractionDimensionSpec) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 4 with TimeFormatExtractionFn

use of org.apache.druid.query.extraction.TimeFormatExtractionFn in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByTimeExtractionNamedUnderUnderTime.

@Test
public void testGroupByTimeExtractionNamedUnderUnderTime() {
    expectedException.expect(IAE.class);
    expectedException.expectMessage("'__time' cannot be used as an output name for dimensions, aggregators, or post-aggregators.");
    makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).setDimensions(new DefaultDimensionSpec("market", "market"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, ColumnHolder.TIME_COLUMN_NAME, new TimeFormatExtractionFn("EEEE", null, null, null, false))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, QueryRunnerTestHelper.INDEX_DOUBLE_SUM).setPostAggregatorSpecs(Collections.singletonList(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT)).setGranularity(QueryRunnerTestHelper.ALL_GRAN).setDimFilter(new OrDimFilter(Arrays.asList(new SelectorDimFilter("market", "spot", null), new SelectorDimFilter("market", "upfront", null)))).setLimitSpec(new DefaultLimitSpec(ImmutableList.of(), 1)).build();
}
Also used : TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) DefaultLimitSpec(org.apache.druid.query.groupby.orderby.DefaultLimitSpec) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) OrDimFilter(org.apache.druid.query.filter.OrDimFilter) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) ExtractionDimensionSpec(org.apache.druid.query.dimension.ExtractionDimensionSpec) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Example 5 with TimeFormatExtractionFn

use of org.apache.druid.query.extraction.TimeFormatExtractionFn in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByTimeExtraction.

@Test
public void testGroupByTimeExtraction() {
    // Cannot vectorize due to extraction dimension spec.
    cannotVectorize();
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FULL_ON_INTERVAL_SPEC).setDimensions(new DefaultDimensionSpec("market", "market"), new ExtractionDimensionSpec(ColumnHolder.TIME_COLUMN_NAME, "dayOfWeek", new TimeFormatExtractionFn("EEEE", null, null, null, false))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, QueryRunnerTestHelper.INDEX_DOUBLE_SUM).setPostAggregatorSpecs(Collections.singletonList(QueryRunnerTestHelper.ADD_ROWS_INDEX_CONSTANT)).setGranularity(QueryRunnerTestHelper.ALL_GRAN).setDimFilter(new OrDimFilter(Arrays.asList(new SelectorDimFilter("market", "spot", null), new SelectorDimFilter("market", "upfront", null)))).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "1970-01-01", "dayOfWeek", "Friday", "market", "spot", "index", 13219.574157714844, "rows", 117L, "addRowsIndexConstant", 13337.574157714844), makeRow(query, "1970-01-01", "dayOfWeek", "Monday", "market", "spot", "index", 13557.738830566406, "rows", 117L, "addRowsIndexConstant", 13675.738830566406), makeRow(query, "1970-01-01", "dayOfWeek", "Saturday", "market", "spot", "index", 13493.751281738281, "rows", 117L, "addRowsIndexConstant", 13611.751281738281), makeRow(query, "1970-01-01", "dayOfWeek", "Sunday", "market", "spot", "index", 13585.541015625, "rows", 117L, "addRowsIndexConstant", 13703.541015625), makeRow(query, "1970-01-01", "dayOfWeek", "Thursday", "market", "spot", "index", 14279.127197265625, "rows", 126L, "addRowsIndexConstant", 14406.127197265625), makeRow(query, "1970-01-01", "dayOfWeek", "Tuesday", "market", "spot", "index", 13199.471435546875, "rows", 117L, "addRowsIndexConstant", 13317.471435546875), makeRow(query, "1970-01-01", "dayOfWeek", "Wednesday", "market", "spot", "index", 14271.368591308594, "rows", 126L, "addRowsIndexConstant", 14398.368591308594), makeRow(query, "1970-01-01", "dayOfWeek", "Friday", "market", "upfront", "index", 27297.8623046875, "rows", 26L, "addRowsIndexConstant", 27324.8623046875), makeRow(query, "1970-01-01", "dayOfWeek", "Monday", "market", "upfront", "index", 27619.58447265625, "rows", 26L, "addRowsIndexConstant", 27646.58447265625), makeRow(query, "1970-01-01", "dayOfWeek", "Saturday", "market", "upfront", "index", 27820.83154296875, "rows", 26L, "addRowsIndexConstant", 27847.83154296875), makeRow(query, "1970-01-01", "dayOfWeek", "Sunday", "market", "upfront", "index", 24791.223876953125, "rows", 26L, "addRowsIndexConstant", 24818.223876953125), makeRow(query, "1970-01-01", "dayOfWeek", "Thursday", "market", "upfront", "index", 28562.748901367188, "rows", 28L, "addRowsIndexConstant", 28591.748901367188), makeRow(query, "1970-01-01", "dayOfWeek", "Tuesday", "market", "upfront", "index", 26968.280639648438, "rows", 26L, "addRowsIndexConstant", 26995.280639648438), makeRow(query, "1970-01-01", "dayOfWeek", "Wednesday", "market", "upfront", "index", 28985.5751953125, "rows", 28L, "addRowsIndexConstant", 29014.5751953125));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "time-extraction");
}
Also used : TimeFormatExtractionFn(org.apache.druid.query.extraction.TimeFormatExtractionFn) SelectorDimFilter(org.apache.druid.query.filter.SelectorDimFilter) OrDimFilter(org.apache.druid.query.filter.OrDimFilter) DefaultDimensionSpec(org.apache.druid.query.dimension.DefaultDimensionSpec) ExtractionDimensionSpec(org.apache.druid.query.dimension.ExtractionDimensionSpec) InitializedNullHandlingTest(org.apache.druid.testing.InitializedNullHandlingTest) Test(org.junit.Test)

Aggregations

TimeFormatExtractionFn (org.apache.druid.query.extraction.TimeFormatExtractionFn)12 ExtractionDimensionSpec (org.apache.druid.query.dimension.ExtractionDimensionSpec)9 Test (org.junit.Test)9 DefaultDimensionSpec (org.apache.druid.query.dimension.DefaultDimensionSpec)8 SelectorDimFilter (org.apache.druid.query.filter.SelectorDimFilter)7 InitializedNullHandlingTest (org.apache.druid.testing.InitializedNullHandlingTest)7 OrDimFilter (org.apache.druid.query.filter.OrDimFilter)5 List (java.util.List)3 ExtractionFn (org.apache.druid.query.extraction.ExtractionFn)3 StrlenExtractionFn (org.apache.druid.query.extraction.StrlenExtractionFn)3 ImmutableList (com.google.common.collect.ImmutableList)2 ArrayList (java.util.ArrayList)2 BitSet (java.util.BitSet)2 TimeUnit (java.util.concurrent.TimeUnit)2 NullHandling (org.apache.druid.common.config.NullHandling)2 Intervals (org.apache.druid.java.util.common.Intervals)2 Granularities (org.apache.druid.java.util.common.granularity.Granularities)2 Sequence (org.apache.druid.java.util.common.guava.Sequence)2 Closer (org.apache.druid.java.util.common.io.Closer)2 LongSumAggregatorFactory (org.apache.druid.query.aggregation.LongSumAggregatorFactory)2