Examples with ExtractionDimensionSpec org.apache.druid.query.dimension.ExtractionDimensionSpec used on opensource projects

Example 46 with ExtractionDimensionSpec

use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByNestedOuterExtractionFnOnFloatInner.

@Test
public void testGroupByNestedOuterExtractionFnOnFloatInner() {
    // 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.");
    }
    String jsFn = "function(obj) { return obj; }";
    ExtractionFn jsExtractionFn = new JavaScriptExtractionFn(jsFn, false, JavaScriptConfig.getEnabledInstance());
    GroupByQuery subquery = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias"), new ExtractionDimensionSpec("qualityFloat", "qf_inner", ColumnType.FLOAT, jsExtractionFn)).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("qf_inner", "qf_outer", ColumnType.FLOAT, jsExtractionFn)).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT).setGranularity(QueryRunnerTestHelper.ALL_GRAN).build();
    List<ResultRow> expectedResults = Collections.singletonList(makeRow(outerQuery, "2011-04-01", "alias", "technology", "qf_outer", 17000.0f, "rows", 2L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, outerQuery);
    TestHelper.assertExpectedObjects(expectedResults, results, "extraction-fn");
}

Example 47 with ExtractionDimensionSpec

use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByLongColumnWithExFn.

@Test
public void testGroupByLongColumnWithExFn() {
    // Cannot vectorize due to extraction dimension spec.
    cannotVectorize();
    if (config.getDefaultStrategy().equals(GroupByStrategySelector.STRATEGY_V1)) {
        expectedException.expect(UnsupportedOperationException.class);
        expectedException.expectMessage("GroupBy v1 does not support dimension selectors with unknown cardinality.");
    }
    String jsFn = "function(str) { return 'super-' + str; }";
    ExtractionFn jsExtractionFn = new JavaScriptExtractionFn(jsFn, false, JavaScriptConfig.getEnabledInstance());
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new ExtractionDimensionSpec("qualityLong", "ql_alias", jsExtractionFn)).setDimFilter(new SelectorDimFilter("quality", "entertainment", null)).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "ql_alias", "super-1200", "rows", 1L, "idx", 158L), makeRow(query, "2011-04-02", "ql_alias", "super-1200", "rows", 1L, "idx", 166L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "long-extraction");
}

Example 48 with ExtractionDimensionSpec

use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testBySegmentResultsUnOptimizedDimextraction.

@Test
public void testBySegmentResultsUnOptimizedDimextraction() {
    GroupByQuery.Builder builder = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setInterval("2011-04-02/2011-04-04").setDimensions(new ExtractionDimensionSpec("quality", "alias", new LookupExtractionFn(new MapLookupExtractor(ImmutableMap.of("mezzanine", "mezzanine0"), false), false, null, false, false))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(new PeriodGranularity(new Period("P1M"), null, null)).setDimFilter(new SelectorDimFilter("quality", "mezzanine", null)).setContext(ImmutableMap.of(QueryContexts.BY_SEGMENT_KEY, true));
    final GroupByQuery fullQuery = builder.build();
    int segmentCount = 32;
    Result<BySegmentResultValue> singleSegmentResult = new Result<>(DateTimes.of("2011-01-12T00:00:00.000Z"), new BySegmentResultValueClass<>(Collections.singletonList(makeRow(fullQuery, "2011-04-01", "alias", "mezzanine0", "rows", 6L, "idx", 4420L)), QueryRunnerTestHelper.SEGMENT_ID.toString(), Intervals.of("2011-04-02T00:00:00.000Z/2011-04-04T00:00:00.000Z")));
    List<Result> bySegmentResults = new ArrayList<>();
    for (int i = 0; i < segmentCount; i++) {
        bySegmentResults.add(singleSegmentResult);
    }
    QueryToolChest toolChest = factory.getToolchest();
    List<QueryRunner<ResultRow>> singleSegmentRunners = new ArrayList<>();
    for (int i = 0; i < segmentCount; i++) {
        singleSegmentRunners.add(toolChest.preMergeQueryDecoration(runner));
    }
    ExecutorService exec = Executors.newCachedThreadPool();
    QueryRunner theRunner = toolChest.postMergeQueryDecoration(new FinalizeResultsQueryRunner<>(toolChest.mergeResults(factory.mergeRunners(Executors.newCachedThreadPool(), singleSegmentRunners)), toolChest));
    TestHelper.assertExpectedObjects(bySegmentResults, theRunner.run(QueryPlus.wrap(fullQuery)), "bySegment");
    exec.shutdownNow();
}

Example 49 with ExtractionDimensionSpec

use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testGroupByNestedWithInnerQueryOutputNullNumerics.

@Test
public void testGroupByNestedWithInnerQueryOutputNullNumerics() {
    cannotVectorize();
    if (config.getDefaultStrategy().equals(GroupByStrategySelector.STRATEGY_V1)) {
        expectedException.expect(UnsupportedOperationException.class);
        expectedException.expectMessage("GroupBy v1 only supports dimensions with an outputType of STRING.");
    }
    // Following extractionFn will generate null value for one kind of quality
    ExtractionFn extractionFn = new SearchQuerySpecDimExtractionFn(new ContainsSearchQuerySpec("1200", false));
    GroupByQuery subquery = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("quality", "alias"), new ExtractionDimensionSpec("qualityLong", "ql_alias", ColumnType.LONG, extractionFn), new ExtractionDimensionSpec("qualityFloat", "qf_alias", ColumnType.FLOAT, extractionFn), new ExtractionDimensionSpec("qualityDouble", "qd_alias", ColumnType.DOUBLE, extractionFn)).setDimFilter(new InDimFilter("quality", Arrays.asList("entertainment", "business"), null)).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.DAY_GRAN).build();
    GroupByQuery outerQuery = makeQueryBuilder().setDataSource(subquery).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setDimensions(new DefaultDimensionSpec("ql_alias", "quallong", ColumnType.LONG), new DefaultDimensionSpec("qf_alias", "qualfloat", ColumnType.FLOAT), new DefaultDimensionSpec("qd_alias", "qualdouble", ColumnType.DOUBLE)).setAggregatorSpecs(new LongSumAggregatorFactory("ql_alias_sum", "ql_alias"), new DoubleSumAggregatorFactory("qf_alias_sum", "qf_alias"), new DoubleSumAggregatorFactory("qd_alias_sum", "qd_alias")).setGranularity(QueryRunnerTestHelper.ALL_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(outerQuery, "2011-04-01", "quallong", NullHandling.defaultLongValue(), "qualfloat", NullHandling.defaultFloatValue(), "qualdouble", NullHandling.defaultDoubleValue(), "ql_alias_sum", NullHandling.defaultLongValue(), "qf_alias_sum", NullHandling.defaultFloatValue(), "qd_alias_sum", NullHandling.defaultDoubleValue()), makeRow(outerQuery, "2011-04-01", "quallong", 1200L, "qualfloat", 12000.0, "qualdouble", 12000.0, "ql_alias_sum", 2400L, "qf_alias_sum", 24000.0, "qd_alias_sum", 24000.0));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, outerQuery);
    TestHelper.assertExpectedObjects(expectedResults, results, "numerics");
}

Example 50 with ExtractionDimensionSpec

use of org.apache.druid.query.dimension.ExtractionDimensionSpec in project druid by druid-io.

the class GroupByQueryRunnerTest method testExtractionStringSpecWithMultiValueVirtualDimAsInput.

@Test
public void testExtractionStringSpecWithMultiValueVirtualDimAsInput() {
    if (config.getDefaultStrategy().equals(GroupByStrategySelector.STRATEGY_V1)) {
        expectedException.expect(UnsupportedOperationException.class);
        expectedException.expectMessage("GroupBy v1 does not support dimension selectors with unknown cardinality");
    }
    cannotVectorize();
    GroupByQuery query = makeQueryBuilder().setDataSource(QueryRunnerTestHelper.DATA_SOURCE).setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD).setVirtualColumns(new ExpressionVirtualColumn("v0", "mv_to_array(placementish)", ColumnType.STRING_ARRAY, ExprMacroTable.nil())).setDimensions(new ExtractionDimensionSpec("v0", "alias", ColumnType.STRING, new SubstringDimExtractionFn(1, 1))).setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT, new LongSumAggregatorFactory("idx", "index")).setGranularity(QueryRunnerTestHelper.ALL_GRAN).build();
    List<ResultRow> expectedResults = Arrays.asList(makeRow(query, "2011-04-01", "alias", null, "rows", 26L, "idx", 12446L), makeRow(query, "2011-04-01", "alias", "r", "rows", 26L, "idx", 12446L));
    Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
    TestHelper.assertExpectedObjects(expectedResults, results, "multi-value-extraction-spec-as-string-dim-groupby-arrays");
}