Examples with MultipleIntervalSegmentSpec org.apache.druid.query.spec.MultipleIntervalSegmentSpec used on opensource projects

Example 96 with MultipleIntervalSegmentSpec

use of org.apache.druid.query.spec.MultipleIntervalSegmentSpec in project druid by druid-io.

the class BloomFilterSqlAggregatorTest method testEmptyTimeseriesResults.

@Test
public void testEmptyTimeseriesResults() throws Exception {
    // makes empty bloom filters
    cannotVectorize();
    BloomKFilter expected1 = new BloomKFilter(TEST_NUM_ENTRIES);
    BloomKFilter expected2 = new BloomKFilter(TEST_NUM_ENTRIES);
    testQuery("SELECT\n" + "BLOOM_FILTER(dim1, 1000),\n" + "BLOOM_FILTER(l1, 1000)\n" + "FROM numfoo where dim2 = 0", ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE3).intervals(new MultipleIntervalSegmentSpec(ImmutableList.of(Filtration.eternity()))).granularity(Granularities.ALL).filters(BaseCalciteQueryTest.bound("dim2", "0", "0", false, false, null, StringComparators.NUMERIC)).aggregators(ImmutableList.of(new BloomFilterAggregatorFactory("a0:agg", new DefaultDimensionSpec("dim1", "a0:dim1"), TEST_NUM_ENTRIES), new BloomFilterAggregatorFactory("a1:agg", new DefaultDimensionSpec("l1", "a1:l1", ColumnType.LONG), TEST_NUM_ENTRIES))).context(BaseCalciteQueryTest.QUERY_CONTEXT_DEFAULT).build()), ImmutableList.of(new Object[] { CalciteTests.getJsonMapper().writeValueAsString(expected1), CalciteTests.getJsonMapper().writeValueAsString(expected2) }));
}

Example 97 with MultipleIntervalSegmentSpec

use of org.apache.druid.query.spec.MultipleIntervalSegmentSpec in project druid by druid-io.

the class BloomFilterSqlAggregatorTest method testBloomFilterAggExtractionFn.

@Test
public void testBloomFilterAggExtractionFn() throws Exception {
    cannotVectorize();
    BloomKFilter expected1 = new BloomKFilter(TEST_NUM_ENTRIES);
    for (InputRow row : CalciteTests.ROWS1_WITH_NUMERIC_DIMS) {
        String raw = NullHandling.emptyToNullIfNeeded((String) row.getRaw("dim1"));
        // empty string extractionFn produces null
        if (raw == null || "".equals(raw)) {
            expected1.addBytes(null, 0, 0);
        } else {
            expected1.addString(raw.substring(0, 1));
        }
    }
    testQuery("SELECT\n" + "BLOOM_FILTER(SUBSTRING(dim1, 1, 1), 1000)\n" + "FROM numfoo", ImmutableList.of(Druids.newTimeseriesQueryBuilder().dataSource(CalciteTests.DATASOURCE3).intervals(new MultipleIntervalSegmentSpec(ImmutableList.of(Filtration.eternity()))).granularity(Granularities.ALL).aggregators(ImmutableList.of(new BloomFilterAggregatorFactory("a0:agg", new ExtractionDimensionSpec("dim1", "a0:dim1", new SubstringDimExtractionFn(0, 1)), TEST_NUM_ENTRIES))).context(BaseCalciteQueryTest.QUERY_CONTEXT_DEFAULT).build()), ImmutableList.of(new Object[] { CalciteTests.getJsonMapper().writeValueAsString(expected1) }));
}

Example 98 with MultipleIntervalSegmentSpec

use of org.apache.druid.query.spec.MultipleIntervalSegmentSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testMergeResults.

@Test
public void testMergeResults() {
    GroupByQuery.Builder builder = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setInterval("2011-04-02/2011-04-04").setDimensions(new DefaultDimensionSpec("quality", "alias")).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(new PeriodGranularity(new Period("P1M"), null, null));
    final GroupByQuery fullQuery = builder.build();
    final GroupByQuery allGranQuery = builder.copy().setGranularity(Granularities.ALL).build();
    QueryRunner mergedRunner = factory.getToolchest().mergeResults(new QueryRunner<ResultRow>() {

        @Override
        public Sequence<ResultRow> run(QueryPlus<ResultRow> queryPlus, ResponseContext responseContext) {
            // simulate two daily segments
            final QueryPlus queryPlus1 = queryPlus.withQuery(queryPlus.getQuery().withQuerySegmentSpec(new MultipleIntervalSegmentSpec(Collections.singletonList(Intervals.of("2011-04-02/2011-04-03")))));
            final QueryPlus queryPlus2 = queryPlus.withQuery(queryPlus.getQuery().withQuerySegmentSpec(new MultipleIntervalSegmentSpec(Collections.singletonList(Intervals.of("2011-04-03/2011-04-04")))));
            return new MergeSequence(queryPlus.getQuery().getResultOrdering(), Sequences.simple(Arrays.asList(runner.run(queryPlus1, responseContext), runner.run(queryPlus2, responseContext))));
        }
    });
    List<ResultRow> expectedResults = Arrays.asList(makeRow(fullQuery, "2011-04-01", "alias", "automotive", "rows", 2L, "idx", 269L), makeRow(fullQuery, "2011-04-01", "alias", "business", "rows", 2L, "idx", 217L), makeRow(fullQuery, "2011-04-01", "alias", "entertainment", "rows", 2L, "idx", 319L), makeRow(fullQuery, "2011-04-01", "alias", "health", "rows", 2L, "idx", 216L), makeRow(fullQuery, "2011-04-01", "alias", "mezzanine", "rows", 6L, "idx", 4420L), makeRow(fullQuery, "2011-04-01", "alias", "news", "rows", 2L, "idx", 221L), makeRow(fullQuery, "2011-04-01", "alias", "premium", "rows", 6L, "idx", 4416L), makeRow(fullQuery, "2011-04-01", "alias", "technology", "rows", 2L, "idx", 177L), makeRow(fullQuery, "2011-04-01", "alias", "travel", "rows", 2L, "idx", 243L));
    ResponseContext context = ResponseContext.createEmpty();
    TestHelper.assertExpectedObjects(expectedResults, mergedRunner.run(QueryPlus.wrap(fullQuery)), "merged");
    List<ResultRow> allGranExpectedResults = Arrays.asList(makeRow(allGranQuery, "2011-04-02", "alias", "automotive", "rows", 2L, "idx", 269L), makeRow(allGranQuery, "2011-04-02", "alias", "business", "rows", 2L, "idx", 217L), makeRow(allGranQuery, "2011-04-02", "alias", "entertainment", "rows", 2L, "idx", 319L), makeRow(allGranQuery, "2011-04-02", "alias", "health", "rows", 2L, "idx", 216L), makeRow(allGranQuery, "2011-04-02", "alias", "mezzanine", "rows", 6L, "idx", 4420L), makeRow(allGranQuery, "2011-04-02", "alias", "news", "rows", 2L, "idx", 221L), makeRow(allGranQuery, "2011-04-02", "alias", "premium", "rows", 6L, "idx", 4416L), makeRow(allGranQuery, "2011-04-02", "alias", "technology", "rows", 2L, "idx", 177L), makeRow(allGranQuery, "2011-04-02", "alias", "travel", "rows", 2L, "idx", 243L));
    TestHelper.assertExpectedObjects(allGranExpectedResults, mergedRunner.run(QueryPlus.wrap(allGranQuery)), "merged");
}

Example 99 with MultipleIntervalSegmentSpec

use of org.apache.druid.query.spec.MultipleIntervalSegmentSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testVirtualColumnFilterOnInnerQuery.

@Test
public void testVirtualColumnFilterOnInnerQuery() {
    GroupByQuery subquery = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias")).setLimitSpec(new DefaultLimitSpec(Collections.singletonList(new OrderByColumnSpec("alias", OrderByColumnSpec.Direction.DESCENDING)), 12)).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    GroupByQuery query = makeQueryBuilder().setDataSource(subquery).setQuerySegmentSpec(new MultipleIntervalSegmentSpec(ImmutableList.of(Intervals.of("2011-04-01T00:00:00.000Z/2011-04-01T23:58:00.000Z"), Intervals.of("2011-04-02T00:00:00.000Z/2011-04-03T00:00:00.000Z")))).setDimensions(new DefaultDimensionSpec("alias", "alias")).setVirtualColumns(new ExpressionVirtualColumn("v", "case_searched(idx > 1000, 1, 0)", ColumnType.LONG, TestExprMacroTable.INSTANCE)).setDimFilter(new BoundDimFilter("v", "0", null, true, false, null, null, StringComparators.NUMERIC)).setLimitSpec(new DefaultLimitSpec(Collections.singletonList(new OrderByColumnSpec("alias", OrderByColumnSpec.Direction.DESCENDING)), 15)).setAggregatorSpecs(new LongSumAggregatorFactory("rows", "rows"), new LongSumAggregatorFactory("idx", "idx")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", "premium", "rows", 3L, "idx", 2900L), makeRow(query, "2011-04-01", "alias", "mezzanine", "rows", 3L, "idx", 2870L), makeRow(query, "2011-04-02", "alias", "premium", "rows", 3L, "idx", 2505L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "virtual column filter on inner query");
}

Example 100 with MultipleIntervalSegmentSpec

use of org.apache.druid.query.spec.MultipleIntervalSegmentSpec in project druid by druid-io.

the class GroupByLimitPushDownInsufficientBufferTest method testPartialLimitPushDownMergeForceAggs.

@Test
public void testPartialLimitPushDownMergeForceAggs() {
    // 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())), (QueryToolChest) toolChest);
    QueryRunner<ResultRow> theRunner2 = new FinalizeResultsQueryRunner<>(toolChest.mergeResults(tooSmallGroupByFactory.mergeRunners(executorService, getRunner2())), (QueryToolChest) toolChest);
    QueryRunner<ResultRow> theRunner3 = 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(0, 1000000)));
    GroupByQuery query = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("dimA", null)).setAggregatorSpecs(new LongSumAggregatorFactory("metA", "metA")).setLimitSpec(new DefaultLimitSpec(Collections.singletonList(new OrderByColumnSpec("metA", OrderByColumnSpec.Direction.DESCENDING, StringComparators.NUMERIC)), 3)).setGranularity(Granularities.ALL).setContext(ImmutableMap.of(GroupByQueryConfig.CTX_KEY_FORCE_LIMIT_PUSH_DOWN, true)).build();
    Sequence<ResultRow> queryResult = theRunner3.run(QueryPlus.wrap(query), ResponseContext.createEmpty());
    List<ResultRow> results = queryResult.toList();
    ResultRow expectedRow0 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "1970-01-01T00:00:00.000Z", "dimA", "zortaxx", "metA", 999L);
    ResultRow expectedRow1 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "1970-01-01T00:00:00.000Z", "dimA", "foo", "metA", 200L);
    ResultRow expectedRow2 = GroupByQueryRunnerTestHelper.createExpectedRow(query, "1970-01-01T00:00:00.000Z", "dimA", "mango", "metA", 190L);
    Assert.assertEquals(3, results.size());
    Assert.assertEquals(expectedRow0, results.get(0));
    Assert.assertEquals(expectedRow1, results.get(1));
    Assert.assertEquals(expectedRow2, results.get(2));
}