Merge branch 'main' into main

Author: eramitmittal

.github/workflows/Java.yml

@@ -20,7 +20,9 @@ jobs:
           fetch-depth: 0
           ref: ${{ inputs.git_ref }}
 
-      - run: make format-check
+      - run: |
+          python3 -m pip install --user clang_format==11.0.1
+          make format-check
 
   java-linux-amd64:
     name: Java Linux (amd64)

CMakeLists.txt

@@ -22,6 +22,21 @@ struct AvgState {
 	}
 };
 
+struct IntervalAvgState {
+	int64_t count;
+	interval_t value;
+
+	void Initialize() {
+		this->count = 0;
+		this->value = interval_t();
+	}
+
+	void Combine(const IntervalAvgState &other) {
+		this->count += other.count;
+		this->value = AddOperator::Operation<interval_t, interval_t, interval_t>(this->value, other.value);
+	}
+};
+
 struct KahanAvgState {
 	uint64_t count;
 	double value;
@@ -105,6 +120,20 @@ struct IntegerAverageOperationHugeint : public BaseSumOperation<AverageSetOperat
 	}
 };
 
+struct DiscreteAverageOperation : public BaseSumOperation<AverageSetOperation, AddToHugeint> {
+	template <class T, class STATE>
+	static void Finalize(STATE &state, T &target, AggregateFinalizeData &finalize_data) {
+		if (state.count == 0) {
+			finalize_data.ReturnNull();
+		} else {
+			uint64_t remainder;
+			target = Hugeint::Cast<T>(Hugeint::DivModPositive(state.value, state.count, remainder));
+			// Round the result
+			target += (remainder > (state.count / 2));
+		}
+	}
+};
+
 struct HugeintAverageOperation : public BaseSumOperation<AverageSetOperation, HugeintAdd> {
 	template <class T, class STATE>
 	static void Finalize(STATE &state, T &target, AggregateFinalizeData &finalize_data) {
@@ -139,6 +168,45 @@ struct KahanAverageOperation : public BaseSumOperation<AverageSetOperation, Kaha
 	}
 };
 
+struct IntervalAverageOperation : public BaseSumOperation<AverageSetOperation, IntervalAdd> {
+	// Override BaseSumOperation::Initialize because
+	// IntervalAvgState does not have an assignment constructor from 0
+	static void Initialize(IntervalAvgState &state) {
+		AverageSetOperation::Initialize<IntervalAvgState>(state);
+	}
+
+	template <class RESULT_TYPE, class STATE>
+	static void Finalize(STATE &state, RESULT_TYPE &target, AggregateFinalizeData &finalize_data) {
+		if (state.count == 0) {
+			finalize_data.ReturnNull();
+		} else {
+			// DivideOperator does not borrow fractions right,
+			// TODO: Maybe it should?
+			// Copy PG implementation.
+			const auto &value = state.value;
+			const auto count = UnsafeNumericCast<int64_t>(state.count);
+
+			target.months = value.months / count;
+			auto months_remainder = value.months % count;
+
+			target.days = value.days / count;
+			auto days_remainder = value.days % count;
+
+			target.micros = value.micros / count;
+			auto micros_remainder = value.micros % count;
+
+			//	Shift the remainders right
+			months_remainder *= Interval::DAYS_PER_MONTH;
+			target.days += months_remainder / count;
+			days_remainder += months_remainder % count;
+
+			days_remainder *= Interval::MICROS_PER_DAY;
+			micros_remainder += days_remainder / count;
+			target.micros += micros_remainder;
+		}
+	}
+};
+
 AggregateFunction GetAverageAggregate(PhysicalType type) {
 	switch (type) {
 	case PhysicalType::INT16: {
@@ -157,6 +225,10 @@ AggregateFunction GetAverageAggregate(PhysicalType type) {
 		return AggregateFunction::UnaryAggregate<AvgState<hugeint_t>, hugeint_t, double, HugeintAverageOperation>(
 		    LogicalType::HUGEINT, LogicalType::DOUBLE);
 	}
+	case PhysicalType::INTERVAL: {
+		return AggregateFunction::UnaryAggregate<IntervalAvgState, interval_t, interval_t, IntervalAverageOperation>(
+		    LogicalType::INTERVAL, LogicalType::INTERVAL);
+	}
 	default:
 		throw InternalException("Unimplemented average aggregate");
 	}
@@ -183,8 +255,17 @@ AggregateFunctionSet AvgFun::GetFunctions() {
 	avg.AddFunction(GetAverageAggregate(PhysicalType::INT32));
 	avg.AddFunction(GetAverageAggregate(PhysicalType::INT64));
 	avg.AddFunction(GetAverageAggregate(PhysicalType::INT128));
+	avg.AddFunction(GetAverageAggregate(PhysicalType::INTERVAL));
 	avg.AddFunction(AggregateFunction::UnaryAggregate<AvgState<double>, double, double, NumericAverageOperation>(
 	    LogicalType::DOUBLE, LogicalType::DOUBLE));
+
+	avg.AddFunction(AggregateFunction::UnaryAggregate<AvgState<hugeint_t>, int64_t, int64_t, DiscreteAverageOperation>(
+	    LogicalType::TIMESTAMP, LogicalType::TIMESTAMP));
+	avg.AddFunction(AggregateFunction::UnaryAggregate<AvgState<hugeint_t>, int64_t, int64_t, DiscreteAverageOperation>(
+	    LogicalType::TIMESTAMP_TZ, LogicalType::TIMESTAMP_TZ));
+	avg.AddFunction(AggregateFunction::UnaryAggregate<AvgState<hugeint_t>, int64_t, int64_t, DiscreteAverageOperation>(
+	    LogicalType::TIME, LogicalType::TIME));
+
 	return avg;
 }
 

src/duckdb/extension/core_functions/aggregate/algebraic/avg.cpp

@@ -266,6 +266,7 @@ static const StaticFunctionDefinition core_functions[] = {
 	DUCKDB_SCALAR_FUNCTION(MapConcatFun),
 	DUCKDB_SCALAR_FUNCTION(MapEntriesFun),
 	DUCKDB_SCALAR_FUNCTION(MapExtractFun),
+	DUCKDB_SCALAR_FUNCTION(MapExtractValueFun),
 	DUCKDB_SCALAR_FUNCTION(MapFromEntriesFun),
 	DUCKDB_SCALAR_FUNCTION(MapKeysFun),
 	DUCKDB_SCALAR_FUNCTION(MapValuesFun),

src/duckdb/extension/core_functions/function_list.cpp

@@ -8,9 +8,11 @@
 
 #pragma once
 
-#include "duckdb/common/common.hpp"
-#include "duckdb/common/types.hpp"
-#include "duckdb/common/types/vector.hpp"
+#include "duckdb/common/types/hugeint.hpp"
+#include "duckdb/common/operator/add.hpp"
+#include "duckdb/common/operator/multiply.hpp"
+#include "duckdb/function/aggregate_state.hpp"
+#include "duckdb/common/operator/cast_operators.hpp"
 
 namespace duckdb {
 
@@ -77,6 +79,20 @@ struct HugeintAdd {
 	}
 };
 
+struct IntervalAdd {
+	template <class STATE, class T>
+	static void AddNumber(STATE &state, T input) {
+		state.value = AddOperator::Operation<interval_t, interval_t, interval_t>(state.value, input);
+	}
+
+	template <class STATE, class T>
+	static void AddConstant(STATE &state, T input, idx_t count) {
+		const auto count64 = Cast::Operation<idx_t, int64_t>(count);
+		input = MultiplyOperator::Operation<interval_t, int64_t, interval_t>(input, count64);
+		state.value = AddOperator::Operation<interval_t, interval_t, interval_t>(state.value, input);
+	}
+};
+
 struct KahanAdd {
 	template <class STATE, class T>
 	static void AddNumber(STATE &state, T input) {

src/duckdb/extension/core_functions/include/core_functions/aggregate/sum_helpers.hpp

@@ -57,6 +57,15 @@ struct ElementAtFun {
 	static constexpr const char *Name = "element_at";
 };
 
+struct MapExtractValueFun {
+	static constexpr const char *Name = "map_extract_value";
+	static constexpr const char *Parameters = "map,key";
+	static constexpr const char *Description = "Returns the value for a given key or NULL if the key is not contained in the map. The type of the key provided in the second parameter must match the type of the map’s keys else an error is returned";
+	static constexpr const char *Example = "map_extract_value(map(['key'], ['val']), 'key')";
+
+	static ScalarFunction GetFunction();
+};
+
 struct MapFromEntriesFun {
 	static constexpr const char *Name = "map_from_entries";
 	static constexpr const char *Parameters = "map";

src/duckdb/extension/core_functions/include/core_functions/scalar/map_functions.hpp

@@ -6,6 +6,7 @@
 #include "duckdb/main/client_context.hpp"
 #include "duckdb/planner/expression/bound_function_expression.hpp"
 #include "duckdb/transaction/meta_transaction.hpp"
+#include "duckdb/planner/expression/bound_cast_expression.hpp"
 
 namespace duckdb {
 

src/duckdb/extension/core_functions/scalar/date/current.cpp

@@ -18,8 +18,8 @@ static void CanCastImplicitlyFunction(DataChunk &args, ExpressionState &state, V
 }
 
 unique_ptr<Expression> BindCanCastImplicitlyExpression(FunctionBindExpressionInput &input) {
-	auto &source_type = input.function.children[0]->return_type;
-	auto &target_type = input.function.children[1]->return_type;
+	auto &source_type = input.children[0]->return_type;
+	auto &target_type = input.children[1]->return_type;
 	if (source_type.id() == LogicalTypeId::UNKNOWN || source_type.id() == LogicalTypeId::SQLNULL ||
 	    target_type.id() == LogicalTypeId::UNKNOWN || target_type.id() == LogicalTypeId::SQLNULL) {
 		// parameter - unknown return type

src/duckdb/extension/core_functions/scalar/generic/can_implicitly_cast.cpp

@@ -10,7 +10,7 @@ static void TypeOfFunction(DataChunk &args, ExpressionState &state, Vector &resu
 }
 
 unique_ptr<Expression> BindTypeOfFunctionExpression(FunctionBindExpressionInput &input) {
-	auto &return_type = input.function.children[0]->return_type;
+	auto &return_type = input.children[0]->return_type;
 	if (return_type.id() == LogicalTypeId::UNKNOWN || return_type.id() == LogicalTypeId::SQLNULL) {
 		// parameter - unknown return type
 		return nullptr;