Examples with InDimFilter org.apache.druid.query.filter.InDimFilter used on opensource projects

Example 26 with InDimFilter

use of org.apache.druid.query.filter.InDimFilter in project druid by druid-io.

the class FilteredAggregatorBenchmark method setup.

/**
 * Setup everything common for benchmarking both the incremental-index and the queriable-index.
 */
@Setup
public void setup() {
    log.info("SETUP CALLED AT " + System.currentTimeMillis());
    ComplexMetrics.registerSerde("hyperUnique", new HyperUniquesSerde());
    schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get(schema);
    generator = new DataGenerator(schemaInfo.getColumnSchemas(), RNG_SEED, schemaInfo.getDataInterval(), rowsPerSegment);
    filter = new OrDimFilter(Arrays.asList(new BoundDimFilter("dimSequential", "-1", "-1", true, true, null, null, StringComparators.ALPHANUMERIC), new RegexDimFilter("dimSequential", "X", null), new SearchQueryDimFilter("dimSequential", new ContainsSearchQuerySpec("X", false), null), new InDimFilter("dimSequential", Collections.singletonList("X"), null)));
    filteredMetric = new FilteredAggregatorFactory(new CountAggregatorFactory("rows"), filter);
    factory = new TimeseriesQueryRunnerFactory(new TimeseriesQueryQueryToolChest(), new TimeseriesQueryEngine(), QueryBenchmarkUtil.NOOP_QUERYWATCHER);
    GeneratorSchemaInfo basicSchema = GeneratorBasicSchemas.SCHEMA_MAP.get("basic");
    QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(basicSchema.getDataInterval()));
    List<AggregatorFactory> queryAggs = Collections.singletonList(filteredMetric);
    query = Druids.newTimeseriesQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).aggregators(queryAggs).descending(descending).build();
}

Example 27 with InDimFilter

use of org.apache.druid.query.filter.InDimFilter in project druid by druid-io.

the class IncrementalIndexReadBenchmark method readWithFilters.

@Benchmark
@BenchmarkMode(Mode.AverageTime)
@OutputTimeUnit(TimeUnit.MICROSECONDS)
public void readWithFilters(Blackhole blackhole) {
    DimFilter filter = new OrDimFilter(Arrays.asList(new BoundDimFilter("dimSequential", "-1", "-1", true, true, null, null, StringComparators.ALPHANUMERIC), new JavaScriptDimFilter("dimSequential", "function(x) { return false }", null, JavaScriptConfig.getEnabledInstance()), new RegexDimFilter("dimSequential", "X", null), new SearchQueryDimFilter("dimSequential", new ContainsSearchQuerySpec("X", false), null), new InDimFilter("dimSequential", Collections.singletonList("X"), null)));
    IncrementalIndexStorageAdapter sa = new IncrementalIndexStorageAdapter(incIndex);
    Sequence<Cursor> cursors = makeCursors(sa, filter);
    Cursor cursor = cursors.limit(1).toList().get(0);
    List<DimensionSelector> selectors = new ArrayList<>();
    selectors.add(makeDimensionSelector(cursor, "dimSequential"));
    selectors.add(makeDimensionSelector(cursor, "dimZipf"));
    selectors.add(makeDimensionSelector(cursor, "dimUniform"));
    selectors.add(makeDimensionSelector(cursor, "dimSequentialHalfNull"));
    cursor.reset();
    while (!cursor.isDone()) {
        for (DimensionSelector selector : selectors) {
            IndexedInts row = selector.getRow();
            blackhole.consume(selector.lookupName(row.get(0)));
        }
        cursor.advance();
    }
}

Example 28 with InDimFilter

use of org.apache.druid.query.filter.InDimFilter in project druid by druid-io.

the class SearchBenchmark method basicC.

private static SearchQueryBuilder basicC(final GeneratorSchemaInfo basicSchema) {
    final QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(basicSchema.getDataInterval()));
    final List<String> dimUniformFilterVals = new ArrayList<>();
    final int resultNum = (int) (100000 * 0.1);
    final int step = 100000 / resultNum;
    for (int i = 1; i < 100001 && dimUniformFilterVals.size() < resultNum; i += step) {
        dimUniformFilterVals.add(String.valueOf(i));
    }
    final String dimName = "dimUniform";
    final List<DimFilter> dimFilters = new ArrayList<>();
    dimFilters.add(new InDimFilter(dimName, dimUniformFilterVals, IdentityExtractionFn.getInstance()));
    dimFilters.add(new SelectorDimFilter(dimName, "3", StrlenExtractionFn.instance()));
    dimFilters.add(new BoundDimFilter(dimName, "100", "10000", true, true, true, new DimExtractionFn() {

        @Override
        public byte[] getCacheKey() {
            return new byte[] { 0xF };
        }

        @Override
        public String apply(String value) {
            return String.valueOf(Long.parseLong(value) + 1);
        }

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

        @Override
        public ExtractionType getExtractionType() {
            return ExtractionType.ONE_TO_ONE;
        }
    }, null));
    dimFilters.add(new InDimFilter(dimName, dimUniformFilterVals, new LowerExtractionFn(null)));
    dimFilters.add(new InDimFilter(dimName, dimUniformFilterVals, new UpperExtractionFn(null)));
    dimFilters.add(new InDimFilter(dimName, dimUniformFilterVals, new SubstringDimExtractionFn(1, 3)));
    return Druids.newSearchQueryBuilder().dataSource("blah").granularity(Granularities.ALL).intervals(intervalSpec).query("").dimensions(Collections.singletonList("dimUniform")).filters(new AndDimFilter(dimFilters));
}

Example 29 with InDimFilter

use of org.apache.druid.query.filter.InDimFilter in project druid by druid-io.

the class MultiValuedDimensionTest method testGroupByWithDimFilterEmptyResults.

@Test
public void testGroupByWithDimFilterEmptyResults() {
    GroupByQuery query = GroupByQuery.builder().setDataSource("xx").setQuerySegmentSpec(new LegacySegmentSpec("1970/3000")).setGranularity(Granularities.ALL).setDimensions(new DefaultDimensionSpec("tags", "tags")).setAggregatorSpecs(new CountAggregatorFactory("count")).setDimFilter(new InDimFilter("product", ImmutableList.of("product_5"), null)).setContext(context).build();
    Sequence<ResultRow> result = helper.runQueryOnSegmentsObjs(ImmutableList.of(new QueryableIndexSegment(queryableIndexNullSampler, SegmentId.dummy("sid1")), new IncrementalIndexSegment(incrementalIndexNullSampler, SegmentId.dummy("sid2"))), query);
    List<ResultRow> expectedResults = Collections.singletonList(GroupByQueryRunnerTestHelper.createExpectedRow(query, "1970-01-01T00:00:00.000Z", "tags", null, "count", 2L));
    TestHelper.assertExpectedObjects(expectedResults, result.toList(), "filter-empty");
}

Example 30 with InDimFilter

use of org.apache.druid.query.filter.InDimFilter 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");
}