This is an automated email from the ASF dual-hosted git repository.
rongr pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/pinot.git
The following commit(s) were added to refs/heads/master by this push:
new a4c3286018 add null handling to sketch group-by (#12259)
a4c3286018 is described below
commit a4c3286018a7aaa89873f40a04f3b912fe0e1104
Author: Rong Rong <[email protected]>
AuthorDate: Thu Jan 11 14:00:34 2024 -0800
add null handling to sketch group-by (#12259)
* add null handling to sketch group-by
* adding integration test for hitting the npe
---------
Co-authored-by: Rong Rong <[email protected]>
---
.../function/DistinctCountThetaSketchAggregationFunction.java | 8 ++++++++
.../pinot/integration/tests/custom/ThetaSketchTest.java | 11 +++++++++++
2 files changed, 19 insertions(+)
diff --git
a/pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/DistinctCountThetaSketchAggregationFunction.java
b/pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/DistinctCountThetaSketchAggregationFunction.java
index 4a9a846acd..9cef1d1931 100644
---
a/pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/DistinctCountThetaSketchAggregationFunction.java
+++
b/pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/DistinctCountThetaSketchAggregationFunction.java
@@ -964,6 +964,14 @@ public class DistinctCountThetaSketchAggregationFunction
@Override
public List<ThetaSketchAccumulator> extractGroupByResult(GroupByResultHolder
groupByResultHolder, int groupKey) {
List result = groupByResultHolder.getResult(groupKey);
+ if (result == null) {
+ int numSketches = _filterEvaluators.size() + 1;
+ List<ThetaSketchAccumulator> thetaSketchAccumulators = new
ArrayList<>(numSketches);
+ for (int i = 0; i < numSketches; i++) {
+ thetaSketchAccumulators.add(new
ThetaSketchAccumulator(_setOperationBuilder, _accumulatorThreshold));
+ }
+ return thetaSketchAccumulators;
+ }
if (result.get(0) instanceof Sketch) {
int numSketches = result.size();
diff --git
a/pinot-integration-tests/src/test/java/org/apache/pinot/integration/tests/custom/ThetaSketchTest.java
b/pinot-integration-tests/src/test/java/org/apache/pinot/integration/tests/custom/ThetaSketchTest.java
index 392ed8738c..e9b577d977 100644
---
a/pinot-integration-tests/src/test/java/org/apache/pinot/integration/tests/custom/ThetaSketchTest.java
+++
b/pinot-integration-tests/src/test/java/org/apache/pinot/integration/tests/custom/ThetaSketchTest.java
@@ -442,6 +442,17 @@ public class ThetaSketchTest extends
CustomDataQueryClusterIntegrationTest {
runAndAssert(query, expected);
}
+ // group by sketch with filter
+ {
+ String query = "select dimValue,
GET_THETA_SKETCH_ESTIMATE(THETA_SKETCH_INTERSECT( "
+ + " DISTINCT_COUNT_RAW_THETA_SKETCH(thetaSketchCol, '') FILTER
(WHERE dimName = 'gender'),"
+ + " DISTINCT_COUNT_RAW_THETA_SKETCH(thetaSketchCol, '') FILTER
(WHERE dimName != 'gender'))) "
+ + " FROM " + getTableName() + " GROUP BY dimValue";
+ ImmutableMap<String, Integer> expected =
+ ImmutableMap.of("Female", 0, "Male", 0, "Math", 0, "History", 0,
"Biology", 0);
+ runAndAssert(query, expected);
+ }
+
// group by gender
{
String query = "select dimValue,
distinctCountThetaSketch(thetaSketchCol) from " + getTableName()
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
