Skip to content

add support for filtered projections #18342

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
clintropolis merged 10 commits into from
Aug 7, 2025
Merged

add support for filtered projections #18342

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
58a4cbd
add support for filtered projections
clintropolis Jul 30, 2025
b47b5e5
fix style
clintropolis Jul 30, 2025
280c8ce
remove mistake
clintropolis Jul 30, 2025
b591181
move match logic into Projections instead of living in Schema, WIP
clintropolis Aug 4, 2025
4d4a748
Merge remote-tracking branch 'upstream/master' into filtered-projections
clintropolis Aug 6, 2025
af66e88
move tests
clintropolis Aug 6, 2025
dcf8e2f
builders, improvements, fixes, etc
clintropolis Aug 7, 2025
2efc1a2
cleanup
clintropolis Aug 7, 2025
ba255d9
cleanup
clintropolis Aug 7, 2025
7a78c7b
move inner classes
clintropolis Aug 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
90 changes: 52 additions & 38 deletions benchmarks/src/test/java/org/apache/druid/benchmark/query/SqlBenchmarkDatasets.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,6 @@
import org.apache.druid.query.aggregation.datasketches.theta.SketchMergeAggregatorFactory;
import org.apache.druid.query.expression.TestExprMacroTable;
import org.apache.druid.segment.AutoTypeColumnSchema;
import org.apache.druid.segment.VirtualColumns;
import org.apache.druid.segment.generator.GeneratorBasicSchemas;
import org.apache.druid.segment.generator.GeneratorSchemaInfo;
import org.apache.druid.segment.transform.ExpressionTransform;
Expand Down Expand Up @@ -162,34 +161,47 @@ public class SqlBenchmarkDatasets
makeDimensionsSpec(expressionsSchema),
expressionsSchema.getAggsArray(),
Arrays.asList(
new AggregateProjectionSpec(
"string2_hourly_sums_hll",
VirtualColumns.create(
Granularities.toVirtualColumn(Granularities.HOUR, "__gran")
),
Arrays.asList(
new StringDimensionSchema("string2"),
new LongDimensionSchema("__gran")
),
new AggregatorFactory[]{
new LongSumAggregatorFactory("long4_sum", "long4"),
new DoubleSumAggregatorFactory("double2_sum", "double2"),
new HllSketchBuildAggregatorFactory("hll_string5", "string5", null, null, null, false, true)
}
),
new AggregateProjectionSpec(
"string2_long2_sums",
VirtualColumns.EMPTY,
Arrays.asList(
new StringDimensionSchema("string2"),
new LongDimensionSchema("long2")
),
new AggregatorFactory[]{
new LongSumAggregatorFactory("long4_sum", "long4"),
new DoubleSumAggregatorFactory("double2_sum", "double2"),
new HllSketchBuildAggregatorFactory("hll_string5", "string5", null, null, null, false, true)
}
)
AggregateProjectionSpec.builder("string2_hourly_sums_hll")
.virtualColumns(
Granularities.toVirtualColumn(Granularities.HOUR, "__gran")
)
.groupingColumns(
new StringDimensionSchema("string2"),
new LongDimensionSchema("__gran")
)
.aggregators(
new LongSumAggregatorFactory("long4_sum", "long4"),
new DoubleSumAggregatorFactory("double2_sum", "double2"),
new HllSketchBuildAggregatorFactory(
"hll_string5",
"string5",
null,
null,
null,
false,
true
)
)
.build(),
AggregateProjectionSpec.builder("string2_long2_sums")
.groupingColumns(
new StringDimensionSchema("string2"),
new LongDimensionSchema("long2")
)
.aggregators(
new LongSumAggregatorFactory("long4_sum", "long4"),
new DoubleSumAggregatorFactory("double2_sum", "double2"),
new HllSketchBuildAggregatorFactory(
"hll_string5",
"string5",
null,
null,
null,
false,
true
)
)
.build()
),
Granularities.NONE
)
Expand Down Expand Up @@ -407,15 +419,17 @@ public BenchmarkSchema asAutoDimensions()
),
aggregators,
projections.stream()
.map(projection -> new AggregateProjectionSpec(
projection.getName(),
projection.getVirtualColumns(),
projection.getGroupingColumns()
.stream()
.map(dim -> new AutoTypeColumnSchema(dim.getName(), null))
.collect(Collectors.toList()),
projection.getAggregators()
)).collect(Collectors.toList()),
.map(
projection ->
AggregateProjectionSpec.builder(projection)
.groupingColumns(
projection.getGroupingColumns()
.stream()
.map(dim -> new AutoTypeColumnSchema(dim.getName(), null))
.collect(Collectors.toList())
)
.build()
).collect(Collectors.toList()),
queryGranularity
);
}
Expand Down
64 changes: 35 additions & 29 deletions ...-core/datasketches/src/test/java/org/apache/druid/segment/DatasketchesProjectionTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,6 @@
import org.apache.druid.java.util.common.io.Closer;
import org.apache.druid.query.DruidProcessingConfig;
import org.apache.druid.query.QueryContexts;
import org.apache.druid.query.aggregation.AggregatorFactory;
import org.apache.druid.query.aggregation.datasketches.hll.HllSketchBuildAggregatorFactory;
import org.apache.druid.query.aggregation.datasketches.hll.HllSketchHolder;
import org.apache.druid.query.aggregation.datasketches.hll.HllSketchModule;
Expand Down Expand Up @@ -98,36 +97,43 @@ public class DatasketchesProjectionTest extends InitializedNullHandlingTest
private static final Closer CLOSER = Closer.create();

private static final List<AggregateProjectionSpec> PROJECTIONS = Collections.singletonList(
new AggregateProjectionSpec(
"a_projection",
VirtualColumns.create(
Granularities.toVirtualColumn(Granularities.HOUR, "__gran")
),
Arrays.asList(
new LongDimensionSchema("__gran"),
new StringDimensionSchema("a")
),
new AggregatorFactory[]{
new HllSketchBuildAggregatorFactory("_b_hll", "b", null, null, null, null, false),
new SketchMergeAggregatorFactory("_b_theta", "b", null, null, false, null),
new DoublesSketchAggregatorFactory("_d_doubles", "d", null),
new ArrayOfDoublesSketchAggregatorFactory("_bcd_aod", "b", null, Arrays.asList("c", "d"), null),
new KllDoublesSketchAggregatorFactory("_d_kll", "d", null, null)
}
)
AggregateProjectionSpec.builder("a_projection")
.virtualColumns(
Granularities.toVirtualColumn(Granularities.HOUR, "__gran")
)
.groupingColumns(
new LongDimensionSchema("__gran"),
new StringDimensionSchema("a")
)
.aggregators(
new HllSketchBuildAggregatorFactory("_b_hll", "b", null, null, null, null, false),
new SketchMergeAggregatorFactory("_b_theta", "b", null, null, false, null),
new DoublesSketchAggregatorFactory("_d_doubles", "d", null),
new ArrayOfDoublesSketchAggregatorFactory(
"_bcd_aod",
"b",
null,
Arrays.asList("c", "d"),
null
),
new KllDoublesSketchAggregatorFactory("_d_kll", "d", null, null)
)
.build()
);

private static final List<AggregateProjectionSpec> AUTO_PROJECTIONS = PROJECTIONS.stream().map(projection -> {
return new AggregateProjectionSpec(
projection.getName(),
projection.getVirtualColumns(),
projection.getGroupingColumns()
.stream()
.map(x -> new AutoTypeColumnSchema(x.getName(), null))
.collect(Collectors.toList()),
projection.getAggregators()
);
}).collect(Collectors.toList());
private static final List<AggregateProjectionSpec> AUTO_PROJECTIONS =
PROJECTIONS.stream()
.map(
projection ->
AggregateProjectionSpec.builder(projection)
.groupingColumns(
projection.getGroupingColumns()
.stream()
.map(x -> new AutoTypeColumnSchema(x.getName(), null))
.collect(Collectors.toList())
)
.build()
).collect(Collectors.toList());

@Parameterized.Parameters(name = "name: {0}, sortByDim: {3}, autoSchema: {4}")
public static Collection<?> constructorFeeder()
Expand Down
27 changes: 10 additions & 17 deletions ...s-core/druid-catalog/src/test/java/org/apache/druid/catalog/storage/TableManagerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,9 +40,7 @@
import org.apache.druid.jackson.DefaultObjectMapper;
import org.apache.druid.java.util.common.granularity.Granularities;
import org.apache.druid.metadata.TestDerbyConnector;
import org.apache.druid.query.aggregation.AggregatorFactory;
import org.apache.druid.query.aggregation.CountAggregatorFactory;
import org.apache.druid.segment.VirtualColumns;
import org.junit.After;
import org.junit.Before;
import org.junit.Rule;
Expand Down Expand Up @@ -94,21 +92,16 @@ public void tearDown()
public void testCreate() throws DuplicateKeyException, NotFoundException
{
final DatasourceProjectionMetadata projectionMetadata = new DatasourceProjectionMetadata(
new AggregateProjectionSpec(
"projection",
VirtualColumns.create(
Granularities.toVirtualColumn(
Granularities.HOUR,
Granularities.GRANULARITY_VIRTUAL_COLUMN_NAME
)
),
ImmutableList.of(
new StringDimensionSchema("dim")
),
new AggregatorFactory[]{
new CountAggregatorFactory("count")
}
)
AggregateProjectionSpec.builder("projection")
.virtualColumns(
Granularities.toVirtualColumn(
Granularities.HOUR,
Granularities.GRANULARITY_VIRTUAL_COLUMN_NAME
)
)
.groupingColumns(new StringDimensionSchema("dim"))
.aggregators(new CountAggregatorFactory("count"))
.build()
);

List<Object> jsonProjectionSpec = JSON_MAPPER.convertValue(ImmutableList.of(projectionMetadata), List.class);
Expand Down
Loading
Loading