Examples with GeneratorSchemaInfo org.apache.druid.segment.generator.GeneratorSchemaInfo used on opensource projects

Example 11 with GeneratorSchemaInfo

use of org.apache.druid.segment.generator.GeneratorSchemaInfo 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 12 with GeneratorSchemaInfo

use of org.apache.druid.segment.generator.GeneratorSchemaInfo in project druid by druid-io.

the class ExpressionVectorSelectorBenchmark method setup.

@Setup(Level.Trial)
public void setup() {
    this.closer = Closer.create();
    final GeneratorSchemaInfo schemaInfo = GeneratorBasicSchemas.SCHEMA_MAP.get("expression-testbench");
    final DataSegment dataSegment = DataSegment.builder().dataSource("foo").interval(schemaInfo.getDataInterval()).version("1").shardSpec(new LinearShardSpec(0)).size(0).build();
    final SegmentGenerator segmentGenerator = closer.register(new SegmentGenerator());
    this.index = closer.register(segmentGenerator.generate(dataSegment, schemaInfo, Granularities.HOUR, rowsPerSegment));
    Expr parsed = Parser.parse(expression, ExprMacroTable.nil());
    outputType = parsed.getOutputType(new ColumnInspector() {

        @Nullable
        @Override
        public ColumnCapabilities getColumnCapabilities(String column) {
            return QueryableIndexStorageAdapter.getColumnCapabilities(index, column);
        }
    });
    checkSanity();
}

Example 13 with GeneratorSchemaInfo

use of org.apache.druid.segment.generator.GeneratorSchemaInfo in project druid by druid-io.

the class GroupByTypeInterfaceBenchmark method setupQueries.

private void setupQueries() {
    // queries for the basic schema
    Map<String, GroupByQuery> basicQueries = new LinkedHashMap<>();
    GeneratorSchemaInfo basicSchema = GeneratorBasicSchemas.SCHEMA_MAP.get("basic");
    {
        // basic.A
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        queryAggs.add(new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"));
        GroupByQuery queryString = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("dimSequential", null)).setAggregatorSpecs(queryAggs).setGranularity(Granularity.fromString(queryGranularity)).build();
        GroupByQuery queryLongFloat = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("metLongUniform", null), new DefaultDimensionSpec("metFloatNormal", null)).setAggregatorSpecs(queryAggs).setGranularity(Granularity.fromString(queryGranularity)).build();
        GroupByQuery queryLong = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("metLongUniform", null)).setAggregatorSpecs(queryAggs).setGranularity(Granularity.fromString(queryGranularity)).build();
        GroupByQuery queryFloat = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("metFloatNormal", null)).setAggregatorSpecs(queryAggs).setGranularity(Granularity.fromString(queryGranularity)).build();
        basicQueries.put("string", queryString);
        basicQueries.put("longFloat", queryLongFloat);
        basicQueries.put("long", queryLong);
        basicQueries.put("float", queryFloat);
    }
    {
        // basic.nested
        QuerySegmentSpec intervalSpec = new MultipleIntervalSegmentSpec(Collections.singletonList(basicSchema.getDataInterval()));
        List<AggregatorFactory> queryAggs = new ArrayList<>();
        queryAggs.add(new LongSumAggregatorFactory("sumLongSequential", "sumLongSequential"));
        GroupByQuery subqueryA = GroupByQuery.builder().setDataSource("blah").setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("dimSequential", null), new DefaultDimensionSpec("dimZipf", null)).setAggregatorSpecs(queryAggs).setGranularity(Granularities.DAY).build();
        GroupByQuery queryA = GroupByQuery.builder().setDataSource(subqueryA).setQuerySegmentSpec(intervalSpec).setDimensions(new DefaultDimensionSpec("dimSequential", null)).setAggregatorSpecs(queryAggs).setGranularity(Granularities.WEEK).build();
        basicQueries.put("nested", queryA);
    }
    SCHEMA_QUERY_MAP.put("basic", basicQueries);
}

Example 14 with GeneratorSchemaInfo

use of org.apache.druid.segment.generator.GeneratorSchemaInfo in project druid by druid-io.

the class ExpressionAggregationBenchmark method setup.

@Setup(Level.Trial)
public void setup() {
    this.closer = Closer.create();
    final GeneratorSchemaInfo schemaInfo = new GeneratorSchemaInfo(ImmutableList.of(GeneratorColumnSchema.makeNormal("x", ValueType.FLOAT, false, 1, 0d, 0d, 10000d, false), GeneratorColumnSchema.makeNormal("y", ValueType.FLOAT, false, 1, 0d, 0d, 10000d, false)), ImmutableList.of(), Intervals.of("2000/P1D"), false);
    final DataSegment dataSegment = DataSegment.builder().dataSource("foo").interval(schemaInfo.getDataInterval()).version("1").shardSpec(new LinearShardSpec(0)).size(0).build();
    final SegmentGenerator segmentGenerator = closer.register(new SegmentGenerator());
    this.index = closer.register(segmentGenerator.generate(dataSegment, schemaInfo, Granularities.NONE, rowsPerSegment));
    this.javaScriptAggregatorFactory = new JavaScriptAggregatorFactory("name", ImmutableList.of("x", "y"), "function(current,x,y) { if (x > 0) { return current + x + 1 } else { return current + y + 1 } }", "function() { return 0 }", "function(a,b) { return a + b }", JavaScriptConfig.getEnabledInstance());
    this.expressionAggregatorFactory = new DoubleSumAggregatorFactory("name", null, "if(x>0,1.0+x,y+1)", TestExprMacroTable.INSTANCE);
}

Example 15 with GeneratorSchemaInfo

use of org.apache.druid.segment.generator.GeneratorSchemaInfo in project druid by druid-io.

the class ExpressionFilterBenchmark method setup.

@Setup(Level.Trial)
public void setup() {
    this.closer = Closer.create();
    final GeneratorSchemaInfo schemaInfo = new GeneratorSchemaInfo(ImmutableList.of(GeneratorColumnSchema.makeEnumerated("x", ValueType.STRING, false, 3, null, Arrays.asList("Apple", "Orange", "Xylophone", "Corundum", null), Arrays.asList(0.2, 0.25, 0.15, 0.10, 0.3)), GeneratorColumnSchema.makeEnumerated("y", ValueType.STRING, false, 4, null, Arrays.asList("Hello", "World", "Foo", "Bar", "Baz"), Arrays.asList(0.2, 0.25, 0.15, 0.10, 0.3))), ImmutableList.of(), Intervals.of("2000/P1D"), false);
    final DataSegment dataSegment = DataSegment.builder().dataSource("foo").interval(schemaInfo.getDataInterval()).version("1").shardSpec(new LinearShardSpec(0)).size(0).build();
    final SegmentGenerator segmentGenerator = closer.register(new SegmentGenerator());
    this.index = closer.register(segmentGenerator.generate(dataSegment, schemaInfo, Granularities.NONE, rowsPerSegment));
    expressionFilter = new ExpressionDimFilter("array_contains(x, ['Orange', 'Xylophone'])", TestExprMacroTable.INSTANCE);
    nativeFilter = new AndDimFilter(new SelectorDimFilter("x", "Orange", null), new SelectorDimFilter("x", "Xylophone", null));
}