Skip to content

GroupBy: Fix offsets on outer queries. #17837

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
abhishekagarwal87 merged 1 commit into from
Mar 27, 2025
Merged

GroupBy: Fix offsets on outer queries. #17837

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 8 additions & 1 deletion processing/src/main/java/org/apache/druid/query/groupby/GroupingEngine.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -597,7 +597,7 @@ public Sequence<ResultRow> processSubqueryResult(
GroupByRowProcessor.ResultSupplier resultSupplier = null;

try {
final GroupByQuery queryToRun;
GroupByQuery queryToRun;

if (wasQueryPushedDown) {
// If the query was pushed down, filters would have been applied downstream, so skip it here.
Expand All @@ -607,6 +607,13 @@ public Sequence<ResultRow> processSubqueryResult(
queryToRun = query;
}

if (queryToRun.getLimitSpec() instanceof DefaultLimitSpec) {
// If the query has an offset, incorporate it into the limit before processing subquery results.
// This allows limit pushdown to work properly during processing. Later on, we'll use the GroupByQuery's
// postProcessingFn to apply the offset.
queryToRun = queryToRun.withLimitSpec(((DefaultLimitSpec) queryToRun.getLimitSpec()).withOffsetToLimit());
}

resultSupplier = GroupByRowProcessor.process(
queryToRun,
wasQueryPushedDown ? queryToRun : subquery,
Expand Down
33 changes: 33 additions & 0 deletions processing/src/test/java/org/apache/druid/query/groupby/GroupByQueryRunnerTest.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6569,6 +6569,39 @@ public void testSubqueryWithPostAggregators()
TestHelper.assertExpectedObjects(expectedResults, results, "subquery-postaggs");
}

@Test
public void testSubqueryWithOuterOffsetAndLimit()
{
// Granularity != ALL requires time-ordering.
assumeTimeOrdered();

final GroupByQuery subquery = makeQueryBuilder()
.setDataSource(QueryRunnerTestHelper.DATA_SOURCE)
.setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD)
.setDimensions(new DefaultDimensionSpec("quality", "alias"))
.setAggregatorSpecs(QueryRunnerTestHelper.ROWS_COUNT)
.setGranularity(QueryRunnerTestHelper.DAY_GRAN)
.build();

final GroupByQuery query = makeQueryBuilder()
.setDataSource(subquery)
.setQuerySegmentSpec(QueryRunnerTestHelper.FIRST_TO_THIRD)
.setDimensions(new DefaultDimensionSpec("alias", "alias"))
.setAggregatorSpecs(new LongSumAggregatorFactory("rows", "rows"))
.setGranularity(QueryRunnerTestHelper.DAY_GRAN)
.setLimitSpec(new DefaultLimitSpec(null, 1, 2))
.build();

List<ResultRow> expectedResults = Arrays.asList(
makeRow(query, "2011-04-01", "alias", "business", "rows", 1L),
makeRow(query, "2011-04-01", "alias", "entertainment", "rows", 1L)
);

// Subqueries are handled by the ToolChest
Iterable<ResultRow> results = GroupByQueryRunnerTestHelper.runQuery(factory, runner, query);
TestHelper.assertExpectedObjects(expectedResults, results, "subquery-postaggs");
}

@Test
public void testSubqueryWithPostAggregatorsAndHaving()
{
Expand Down
Loading