Jackie-Jiang commented on code in PR #13146:
URL: https://github.com/apache/pinot/pull/13146#discussion_r1602189909
##########
pinot-common/src/main/java/org/apache/pinot/common/request/context/FunctionContext.java:
##########
@@ -35,12 +35,14 @@ public enum Type {
private final Type _type;
private String _functionName;
private final List<ExpressionContext> _arguments;
+ private final boolean _isDistinct;
- public FunctionContext(Type type, String functionName,
List<ExpressionContext> arguments) {
+ public FunctionContext(Type type, String functionName,
List<ExpressionContext> arguments, boolean isDistinct) {
Review Comment:
This is single-stage engine context. Do we need to push this to the single
stage side? I think we will need to collect all records for a partition,
sorting the records, then apply the distinct and aggregation?
##########
pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/array/ListAggFunction.java:
##########
@@ -0,0 +1,214 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.pinot.core.query.aggregation.function.array;
+
+import it.unimi.dsi.fastutil.objects.ObjectArrayList;
+import java.util.Map;
+import org.apache.commons.lang3.StringUtils;
+import org.apache.pinot.common.request.context.ExpressionContext;
+import org.apache.pinot.common.utils.DataSchema;
+import org.apache.pinot.core.common.BlockValSet;
+import org.apache.pinot.core.query.aggregation.AggregationResultHolder;
+import org.apache.pinot.core.query.aggregation.ObjectAggregationResultHolder;
+import
org.apache.pinot.core.query.aggregation.function.BaseSingleInputAggregationFunction;
+import org.apache.pinot.core.query.aggregation.groupby.GroupByResultHolder;
+import
org.apache.pinot.core.query.aggregation.groupby.ObjectGroupByResultHolder;
+import org.apache.pinot.segment.spi.AggregationFunctionType;
+import org.roaringbitmap.RoaringBitmap;
+
+
+public class ListAggFunction
+ extends BaseSingleInputAggregationFunction<ObjectArrayList<String>,
String> {
+
+ private final String _separator;
+ private final boolean _nullHandlingEnabled;
+ private final boolean _isDistinct;
+
+ public ListAggFunction(ExpressionContext expression, String separator,
boolean isDistinct,
+ boolean nullHandlingEnabled) {
+ super(expression);
+ _separator = separator;
+ _isDistinct = isDistinct;
+ _nullHandlingEnabled = nullHandlingEnabled;
+ }
+
+ @Override
+ public AggregationFunctionType getType() {
+ return AggregationFunctionType.LISTAGG;
+ }
+
+ @Override
+ public AggregationResultHolder createAggregationResultHolder() {
+ return new ObjectAggregationResultHolder();
+ }
+
+ @Override
+ public GroupByResultHolder createGroupByResultHolder(int initialCapacity,
int maxCapacity) {
+ return new ObjectGroupByResultHolder(initialCapacity, maxCapacity);
+ }
+
+ @Override
+ public void aggregate(int length, AggregationResultHolder
aggregationResultHolder,
+ Map<ExpressionContext, BlockValSet> blockValSetMap) {
+ ObjectArrayList<String> valueSet = aggregationResultHolder.getResult();
+ if (valueSet == null) {
+ valueSet = new ObjectArrayList<>();
+ aggregationResultHolder.setValue(valueSet);
+ }
+ BlockValSet blockValSet = blockValSetMap.get(_expression);
+ String[] values = blockValSet.getStringValuesSV();
+ if (_nullHandlingEnabled) {
+ RoaringBitmap nullBitmap = blockValSet.getNullBitmap();
+ if (nullBitmap != null && !nullBitmap.isEmpty()) {
+ aggregateArrayWithNull(length, valueSet, values, nullBitmap);
+ return;
+ }
+ }
+ aggregateArray(length, valueSet, values);
+ }
+
+ private void aggregateArray(int length, ObjectArrayList<String> valueSet,
String[] values) {
+ for (int i = 0; i < length; i++) {
+ String value = values[i];
+ if (_isDistinct && valueSet.contains(value)) {
Review Comment:
This is `O(n)` contains, which will be extremely slow
##########
pinot-query-planner/src/main/java/org/apache/pinot/query/planner/plannode/AggregateNode.java:
##########
@@ -42,6 +45,12 @@ public class AggregateNode extends AbstractPlanNode {
private List<RexExpression> _groupSet;
@ProtoProperties
private AggType _aggType;
+ @ProtoProperties
+ private List<RexExpression> _collationKey = ImmutableList.of();
+ @ProtoProperties
+ private List<RelFieldCollation.Direction> _collationDirection =
ImmutableList.of();
+ @ProtoProperties
+ private List<RelFieldCollation.NullDirection> _collationNullDirection =
ImmutableList.of();
Review Comment:
Do you put them as 3 separate list because we cannot serialize
`RelFieldCollation` properly? Some comments will help
##########
pinot-core/src/main/java/org/apache/pinot/core/query/aggregation/function/array/ListAggFunction.java:
##########
@@ -0,0 +1,214 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.pinot.core.query.aggregation.function.array;
+
+import it.unimi.dsi.fastutil.objects.ObjectArrayList;
+import java.util.Map;
+import org.apache.commons.lang3.StringUtils;
+import org.apache.pinot.common.request.context.ExpressionContext;
+import org.apache.pinot.common.utils.DataSchema;
+import org.apache.pinot.core.common.BlockValSet;
+import org.apache.pinot.core.query.aggregation.AggregationResultHolder;
+import org.apache.pinot.core.query.aggregation.ObjectAggregationResultHolder;
+import
org.apache.pinot.core.query.aggregation.function.BaseSingleInputAggregationFunction;
+import org.apache.pinot.core.query.aggregation.groupby.GroupByResultHolder;
+import
org.apache.pinot.core.query.aggregation.groupby.ObjectGroupByResultHolder;
+import org.apache.pinot.segment.spi.AggregationFunctionType;
+import org.roaringbitmap.RoaringBitmap;
+
+
+public class ListAggFunction
Review Comment:
Do we need to implement it as a single-stage aggregation? I think it should
follow the way how window function is implemented
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
