duckdb 0.7.2-dev16.0 → 0.7.2-dev314.0

package/src/duckdb/src/function/aggregate/distributive/bitstring_agg.cpp

@@ -0,0 +1,254 @@
+#include "duckdb/function/aggregate/distributive_functions.hpp"
+#include "duckdb/common/exception.hpp"
+#include "duckdb/common/types/null_value.hpp"
+#include "duckdb/common/vector_operations/aggregate_executor.hpp"
+#include "duckdb/common/types/bit.hpp"
+#include "duckdb/storage/statistics/base_statistics.hpp"
+#include "duckdb/execution/expression_executor.hpp"
+#include "duckdb/common/types/cast_helpers.hpp"
+
+namespace duckdb {
+
+template <class INPUT_TYPE>
+struct BitAggState {
+	bool is_set;
+	string_t value;
+	INPUT_TYPE min;
+	INPUT_TYPE max;
+};
+
+struct BitstringAggBindData : public FunctionData {
+	Value min;
+	Value max;
+
+	BitstringAggBindData() {
+	}
+
+	BitstringAggBindData(Value min, Value max) : min(std::move(min)), max(std::move(max)) {
+	}
+
+	unique_ptr<FunctionData> Copy() const override {
+		return make_unique<BitstringAggBindData>(*this);
+	}
+
+	bool Equals(const FunctionData &other_p) const override {
+		auto &other = (BitstringAggBindData &)other_p;
+		if (min.IsNull() && other.min.IsNull() && max.IsNull() && other.max.IsNull()) {
+			return true;
+		}
+		if (Value::NotDistinctFrom(min, other.min) && Value::NotDistinctFrom(max, other.max)) {
+			return true;
+		}
+		return false;
+	}
+};
+
+struct BitStringAggOperation {
+	static constexpr const idx_t MAX_BIT_RANGE = 1000000000; // for now capped at 1 billion bits
+
+	template <class STATE>
+	static void Initialize(STATE *state) {
+		state->is_set = false;
+	}
+
+	template <class INPUT_TYPE, class STATE, class OP>
+	static void Operation(STATE *state, AggregateInputData &data, INPUT_TYPE *input, ValidityMask &mask, idx_t idx) {
+		auto bind_agg_data = (BitstringAggBindData *)data.bind_data;
+		if (!state->is_set) {
+			if (bind_agg_data->min.IsNull() || bind_agg_data->max.IsNull()) {
+				throw BinderException(
+				    "Could not retrieve required statistics. Alternatively, try by providing the statistics "
+				    "explicitly: BITSTRING_AGG(col, min, max) ");
+			}
+			state->min = bind_agg_data->min.GetValue<INPUT_TYPE>();
+			state->max = bind_agg_data->max.GetValue<INPUT_TYPE>();
+			idx_t bit_range =
+			    GetRange(bind_agg_data->min.GetValue<INPUT_TYPE>(), bind_agg_data->max.GetValue<INPUT_TYPE>());
+			if (bit_range > MAX_BIT_RANGE) {
+				throw OutOfRangeException(
+				    "The range between min and max value (%s <-> %s) is too large for bitstring aggregation",
+				    NumericHelper::ToString(state->min), NumericHelper::ToString(state->max));
+			}
+			idx_t len = Bit::ComputeBitstringLen(bit_range);
+			auto target = len > string_t::INLINE_LENGTH ? string_t(new char[len], len) : string_t(len);
+			Bit::SetEmptyBitString(target, bit_range);
+
+			state->value = target;
+			state->is_set = true;
+		}
+		if (input[idx] >= state->min && input[idx] <= state->max) {
+			Execute(state, input[idx], bind_agg_data->min.GetValue<INPUT_TYPE>());
+		} else {
+			throw OutOfRangeException("Value %s is outside of provided min and max range (%s <-> %s)",
+			                          NumericHelper::ToString(input[idx]), NumericHelper::ToString(state->min),
+			                          NumericHelper::ToString(state->max));
+		}
+	}
+
+	template <class INPUT_TYPE, class STATE, class OP>
+	static void ConstantOperation(STATE *state, AggregateInputData &aggr_input_data, INPUT_TYPE *input,
+	                              ValidityMask &mask, idx_t count) {
+		OP::template Operation<INPUT_TYPE, STATE, OP>(state, aggr_input_data, input, mask, 0);
+	}
+
+	template <class INPUT_TYPE>
+	static idx_t GetRange(INPUT_TYPE min, INPUT_TYPE max) {
+		return max - min + 1;
+	}
+
+	template <class INPUT_TYPE, class STATE>
+	static void Execute(STATE *state, INPUT_TYPE input, INPUT_TYPE min) {
+		Bit::SetBit(state->value, input - min, 1);
+	}
+
+	template <class STATE, class OP>
+	static void Combine(const STATE &source, STATE *target, AggregateInputData &) {
+		if (!source.is_set) {
+			return;
+		}
+		if (!target->is_set) {
+			Assign(target, source.value);
+			target->is_set = true;
+			target->min = source.min;
+			target->max = source.max;
+		} else {
+			Bit::BitwiseOr(source.value, target->value, target->value);
+		}
+	}
+
+	template <class INPUT_TYPE, class STATE>
+	static void Assign(STATE *state, INPUT_TYPE input) {
+		D_ASSERT(state->is_set == false);
+		if (input.IsInlined()) {
+			state->value = input;
+		} else { // non-inlined string, need to allocate space for it
+			auto len = input.GetSize();
+			auto ptr = new char[len];
+			memcpy(ptr, input.GetDataUnsafe(), len);
+			state->value = string_t(ptr, len);
+		}
+	}
+
+	template <class T, class STATE>
+	static void Finalize(Vector &result, AggregateInputData &, STATE *state, T *target, ValidityMask &mask, idx_t idx) {
+		if (!state->is_set) {
+			mask.SetInvalid(idx);
+		} else {
+			target[idx] = StringVector::AddStringOrBlob(result, state->value);
+		}
+	}
+
+	template <class STATE>
+	static void Destroy(STATE *state) {
+		if (state->is_set && !state->value.IsInlined()) {
+			delete[] state->value.GetDataUnsafe();
+		}
+	}
+
+	static bool IgnoreNull() {
+		return true;
+	}
+};
+
+template <>
+void BitStringAggOperation::Execute(BitAggState<hugeint_t> *state, hugeint_t input, hugeint_t min) {
+	idx_t val;
+	if (Hugeint::TryCast(input - min, val)) {
+		Bit::SetBit(state->value, val, 1);
+	} else {
+		throw OutOfRangeException("Range too large for bitstring aggregation");
+	}
+}
+
+template <>
+idx_t BitStringAggOperation::GetRange(hugeint_t min, hugeint_t max) {
+	idx_t val;
+	if (Hugeint::TryCast(max - min + 1, val)) {
+		return val;
+	} else {
+		throw OutOfRangeException("Range too large for bitstring aggregation");
+	}
+}
+
+unique_ptr<BaseStatistics> BitstringPropagateStats(ClientContext &context, BoundAggregateExpression &expr,
+                                                   AggregateStatisticsInput &input) {
+
+	if (!NumericStats::HasMinMax(input.child_stats[0])) {
+		throw BinderException("Could not retrieve required statistics. Alternatively, try by providing the statistics "
+		                      "explicitly: BITSTRING_AGG(col, min, max) ");
+	}
+	auto bind_agg_data = (BitstringAggBindData *)input.bind_data;
+	bind_agg_data->min = NumericStats::Min(input.child_stats[0]);
+	bind_agg_data->max = NumericStats::Max(input.child_stats[0]);
+	return nullptr;
+}
+
+unique_ptr<FunctionData> BindBitstringAgg(ClientContext &context, AggregateFunction &function,
+                                          vector<unique_ptr<Expression>> &arguments) {
+
+	if (arguments.size() == 3) {
+		auto min = ExpressionExecutor::EvaluateScalar(context, *arguments[1]);
+		auto max = ExpressionExecutor::EvaluateScalar(context, *arguments[2]);
+		Function::EraseArgument(function, arguments, 2);
+		Function::EraseArgument(function, arguments, 1);
+		return make_unique<BitstringAggBindData>(min, max);
+	}
+	return make_unique<BitstringAggBindData>();
+}
+
+template <class TYPE>
+static void BindBitString(AggregateFunctionSet &bitstring_agg, const LogicalTypeId &type) {
+	auto function =
+	    AggregateFunction::UnaryAggregateDestructor<BitAggState<TYPE>, TYPE, string_t, BitStringAggOperation>(
+	        type, LogicalType::BIT);
+	function.bind = BindBitstringAgg;              // create new a 'BitstringAggBindData'
+	function.statistics = BitstringPropagateStats; // stores min and max from column stats in BitstringAggBindData
+	bitstring_agg.AddFunction(function); // uses the BitstringAggBindData to access statistics for creating bitstring
+	function.arguments = {type, type, type};
+	function.statistics = nullptr; // min and max are provided as arguments
+	bitstring_agg.AddFunction(function);
+}
+
+void BitStringAggFun::GetBitStringAggregate(const LogicalType &type, AggregateFunctionSet &bitstring_agg) {
+	switch (type.id()) {
+	case LogicalType::TINYINT: {
+		return BindBitString<int8_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::SMALLINT: {
+		return BindBitString<int16_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::INTEGER: {
+		return BindBitString<int32_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::BIGINT: {
+		return BindBitString<int64_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::HUGEINT: {
+		return BindBitString<hugeint_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::UTINYINT: {
+		return BindBitString<uint8_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::USMALLINT: {
+		return BindBitString<uint16_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::UINTEGER: {
+		return BindBitString<uint32_t>(bitstring_agg, type.id());
+	}
+	case LogicalType::UBIGINT: {
+		return BindBitString<uint64_t>(bitstring_agg, type.id());
+	}
+	default:
+		throw InternalException("Unimplemented bitstring aggregate");
+	}
+}
+
+void BitStringAggFun::RegisterFunction(BuiltinFunctions &set) {
+	AggregateFunctionSet bitstring_agg("bitstring_agg");
+	for (auto &type : LogicalType::Integral()) {
+		GetBitStringAggregate(type, bitstring_agg);
+	}
+	set.AddFunction(bitstring_agg);
+}
+
+} // namespace duckdb

package/src/duckdb/src/function/aggregate/distributive/count.cpp

@@ -2,7 +2,6 @@
 #include "duckdb/common/vector_operations/vector_operations.hpp"
 #include "duckdb/function/aggregate/distributive_functions.hpp"
 #include "duckdb/planner/expression/bound_aggregate_expression.hpp"
-#include "duckdb/storage/statistics/validity_statistics.hpp"
 
 namespace duckdb {
 
@@ -100,9 +99,8 @@ AggregateFunction CountStarFun::GetFunction() {
 }
 
 unique_ptr<BaseStatistics> CountPropagateStats(ClientContext &context, BoundAggregateExpression &expr,
-                                               FunctionData *bind_data, vector<unique_ptr<BaseStatistics>> &child_stats,
-                                               NodeStatistics *node_stats) {
-	if (!expr.IsDistinct() && child_stats[0] && !child_stats[0]->CanHaveNull()) {
+                                               AggregateStatisticsInput &input) {
+	if (!expr.IsDistinct() && !input.child_stats[0].CanHaveNull()) {
 		// count on a column without null values: use count star
 		expr.function = CountStarFun::GetFunction();
 		expr.function.name = "count_star";

package/src/duckdb/src/function/aggregate/distributive/sum.cpp

@@ -2,7 +2,6 @@
 #include "duckdb/function/aggregate/sum_helpers.hpp"
 #include "duckdb/common/exception.hpp"
 #include "duckdb/common/types/decimal.hpp"
-#include "duckdb/storage/statistics/numeric_statistics.hpp"
 #include "duckdb/planner/expression/bound_aggregate_expression.hpp"
 #include "duckdb/function/aggregate/algebraic_functions.hpp"
 
@@ -52,9 +51,6 @@ struct DoubleSumOperation : public BaseSumOperation<SumSetOperation, ADD_OPERATO
 		if (!state->isset) {
 			mask.SetInvalid(idx);
 		} else {
-			if (!Value::DoubleIsFinite(state->value)) {
-				throw OutOfRangeException("SUM is out of range!");
-			}
 			target[idx] = state->value;
 		}
 	}
@@ -75,30 +71,29 @@ struct HugeintSumOperation : public BaseSumOperation<SumSetOperation, RegularAdd
 };
 
 unique_ptr<BaseStatistics> SumPropagateStats(ClientContext &context, BoundAggregateExpression &expr,
-                                             FunctionData *bind_data, vector<unique_ptr<BaseStatistics>> &child_stats,
-                                             NodeStatistics *node_stats) {
-	if (child_stats[0] && node_stats && node_stats->has_max_cardinality) {
-		auto &numeric_stats = (NumericStatistics &)*child_stats[0];
-		if (numeric_stats.min.IsNull() || numeric_stats.max.IsNull()) {
+                                             AggregateStatisticsInput &input) {
+	if (input.node_stats && input.node_stats->has_max_cardinality) {
+		auto &numeric_stats = input.child_stats[0];
+		if (!NumericStats::HasMinMax(numeric_stats)) {
 			return nullptr;
 		}
-		auto internal_type = numeric_stats.min.type().InternalType();
+		auto internal_type = numeric_stats.GetType().InternalType();
 		hugeint_t max_negative;
 		hugeint_t max_positive;
 		switch (internal_type) {
 		case PhysicalType::INT32:
-			max_negative = numeric_stats.min.GetValueUnsafe<int32_t>();
-			max_positive = numeric_stats.max.GetValueUnsafe<int32_t>();
+			max_negative = NumericStats::Min(numeric_stats).GetValueUnsafe<int32_t>();
+			max_positive = NumericStats::Max(numeric_stats).GetValueUnsafe<int32_t>();
 			break;
 		case PhysicalType::INT64:
-			max_negative = numeric_stats.min.GetValueUnsafe<int64_t>();
-			max_positive = numeric_stats.max.GetValueUnsafe<int64_t>();
+			max_negative = NumericStats::Min(numeric_stats).GetValueUnsafe<int64_t>();
+			max_positive = NumericStats::Max(numeric_stats).GetValueUnsafe<int64_t>();
 			break;
 		default:
 			throw InternalException("Unsupported type for propagate sum stats");
 		}
-		auto max_sum_negative = max_negative * hugeint_t(node_stats->max_cardinality);
-		auto max_sum_positive = max_positive * hugeint_t(node_stats->max_cardinality);
+		auto max_sum_negative = max_negative * hugeint_t(input.node_stats->max_cardinality);
+		auto max_sum_positive = max_positive * hugeint_t(input.node_stats->max_cardinality);
 		if (max_sum_positive >= NumericLimits<int64_t>::Maximum() ||
 		    max_sum_negative <= NumericLimits<int64_t>::Minimum()) {
 			// sum can potentially exceed int64_t bounds: use hugeint sum

package/src/duckdb/src/function/aggregate/distributive_functions.cpp

@@ -10,6 +10,7 @@ void BuiltinFunctions::RegisterDistributiveAggregates() {
 	Register<BitAndFun>();
 	Register<BitOrFun>();
 	Register<BitXorFun>();
+	Register<BitStringAggFun>();
 	Register<CountStarFun>();
 	Register<CountFun>();
 	Register<FirstFun>();

package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp

@@ -71,17 +71,25 @@ struct SortedAggregateBindData : public FunctionData {
 };
 
 struct SortedAggregateState {
-	static const idx_t BUFFER_CAPACITY = STANDARD_VECTOR_SIZE;
+	//! Default buffer size, optimised for small group to avoid blowing out memory.
+	static const idx_t BUFFER_CAPACITY = 16;
 
 	SortedAggregateState() : nsel(0) {
 	}
 
 	static inline void InitializeBuffer(DataChunk &chunk, const vector<LogicalType> &types) {
 		if (!chunk.ColumnCount() && !types.empty()) {
-			chunk.Initialize(Allocator::DefaultAllocator(), types);
+			chunk.Initialize(Allocator::DefaultAllocator(), types, BUFFER_CAPACITY);
 		}
 	}
 
+	//! Make sure the buffer is large enough for slicing
+	static inline void ResetBuffer(DataChunk &chunk, const vector<LogicalType> &types) {
+		chunk.Reset();
+		chunk.Destroy();
+		chunk.Initialize(Allocator::DefaultAllocator(), types);
+	}
+
 	void Flush(SortedAggregateBindData &order_bind) {
 		if (ordering) {
 			return;
@@ -90,10 +98,12 @@ struct SortedAggregateState {
 		ordering = make_unique<ColumnDataCollection>(order_bind.buffer_manager, order_bind.sort_types);
 		InitializeBuffer(sort_buffer, order_bind.sort_types);
 		ordering->Append(sort_buffer);
+		ResetBuffer(sort_buffer, order_bind.sort_types);
 
 		arguments = make_unique<ColumnDataCollection>(order_bind.buffer_manager, order_bind.arg_types);
 		InitializeBuffer(arg_buffer, order_bind.arg_types);
 		arguments->Append(arg_buffer);
+		ResetBuffer(arg_buffer, order_bind.arg_types);
 	}
 
 	void Update(SortedAggregateBindData &order_bind, DataChunk &sort_chunk, DataChunk &arg_chunk) {
@@ -101,7 +111,7 @@ struct SortedAggregateState {
 		InitializeBuffer(sort_buffer, order_bind.sort_types);
 		InitializeBuffer(arg_buffer, order_bind.arg_types);
 
-		if (sort_chunk.size() + sort_buffer.size() > BUFFER_CAPACITY) {
+		if (sort_chunk.size() + sort_buffer.size() > STANDARD_VECTOR_SIZE) {
 			Flush(order_bind);
 		}
 		if (ordering) {
@@ -118,7 +128,7 @@ struct SortedAggregateState {
 		InitializeBuffer(sort_buffer, order_bind.sort_types);
 		InitializeBuffer(arg_buffer, order_bind.arg_types);
 
-		if (nsel + sort_buffer.size() > BUFFER_CAPACITY) {
+		if (nsel + sort_buffer.size() > STANDARD_VECTOR_SIZE) {
 			Flush(order_bind);
 		}
 		if (ordering) {
@@ -276,6 +286,8 @@ struct SortedAggregateFunction {
 		auto &orders = order_bind->orders;
 		RowLayout payload_layout;
 		payload_layout.Initialize(order_bind->arg_types);
+		DataChunk chunk;
+		chunk.Initialize(Allocator::DefaultAllocator(), order_bind->arg_types);
 
 		//	 Reusable inner state
 		vector<data_t> agg_state(order_bind->function.state_size());
@@ -314,7 +326,6 @@ struct SortedAggregateFunction {
 					global_sort->CompleteMergeRound(false);
 				}
 
-				auto &chunk = state->arg_buffer;
 				PayloadScanner scanner(*global_sort);
 				for (;;) {
 					chunk.Reset();

package/src/duckdb/src/function/cast/bit_cast.cpp

@@ -9,8 +9,6 @@ BoundCastInfo DefaultCasts::BitCastSwitch(BindCastInput &input, const LogicalTyp
 	case LogicalTypeId::VARCHAR:
 		// bit to varchar
 		return BoundCastInfo(&VectorCastHelpers::StringCast<string_t, duckdb::CastFromBit>);
-	case LogicalTypeId::BLOB:
-		return DefaultCasts::ReinterpretCast;
 	default:
 		return DefaultCasts::TryVectorNullCast;
 	}

package/src/duckdb/src/function/cast/blob_cast.cpp

@@ -10,7 +10,6 @@ BoundCastInfo DefaultCasts::BlobCastSwitch(BindCastInput &input, const LogicalTy
 		// blob to varchar
 		return BoundCastInfo(&VectorCastHelpers::StringCast<string_t, duckdb::CastFromBlob>);
 	case LogicalTypeId::AGGREGATE_STATE:
-	case LogicalTypeId::BIT:
 		return DefaultCasts::ReinterpretCast;
 	default:
 		return DefaultCasts::TryVectorNullCast;

package/src/duckdb/src/function/scalar/bit/bitstring.cpp

@@ -0,0 +1,99 @@
+#include "duckdb/common/types/bit.hpp"
+#include "duckdb/function/scalar/bit_functions.hpp"
+#include "duckdb/common/types/cast_helpers.hpp"
+
+namespace duckdb {
+
+//===--------------------------------------------------------------------===//
+// BitStringFunction
+//===--------------------------------------------------------------------===//
+
+static void BitStringFunction(DataChunk &args, ExpressionState &state, Vector &result) {
+	BinaryExecutor::Execute<string_t, int32_t, string_t>(
+	    args.data[0], args.data[1], result, args.size(), [&](string_t input, int32_t n) {
+		    if (n < 0) {
+			    throw InvalidInputException("The bitstring length cannot be negative");
+		    }
+		    if ((idx_t)n < input.GetSize()) {
+			    throw InvalidInputException("Length must be equal or larger than input string");
+		    }
+		    idx_t len;
+		    Bit::TryGetBitStringSize(input, len, nullptr); // string verification
+
+		    len = Bit::ComputeBitstringLen(n);
+		    string_t target = StringVector::EmptyString(result, len);
+
+		    Bit::BitString(input, n, target);
+		    return target;
+	    });
+}
+
+void BitStringFun::RegisterFunction(BuiltinFunctions &set) {
+	// bitstring creates a new bitstring from varchar with a fixed-length
+	set.AddFunction(
+	    ScalarFunction("bitstring", {LogicalType::VARCHAR, LogicalType::INTEGER}, LogicalType::BIT, BitStringFunction));
+}
+
+//===--------------------------------------------------------------------===//
+// get_bit
+//===--------------------------------------------------------------------===//
+struct GetBitOperator {
+	template <class TA, class TB, class TR>
+	static inline TR Operation(TA input, TB n) {
+		if (n < 0 || (idx_t)n > Bit::BitLength(input) - 1) {
+			throw OutOfRangeException("bit index %s out of valid range (0..%s)", NumericHelper::ToString(n),
+			                          NumericHelper::ToString(Bit::BitLength(input) - 1));
+		}
+		return Bit::GetBit(input, n);
+	}
+};
+
+void GetBitFun::RegisterFunction(BuiltinFunctions &set) {
+	set.AddFunction(ScalarFunction("get_bit", {LogicalType::BIT, LogicalType::INTEGER}, LogicalType::INTEGER,
+	                               ScalarFunction::BinaryFunction<string_t, int32_t, int32_t, GetBitOperator>));
+}
+
+//===--------------------------------------------------------------------===//
+// set_bit
+//===--------------------------------------------------------------------===//
+static void SetBitOperation(DataChunk &args, ExpressionState &state, Vector &result) {
+	TernaryExecutor::Execute<string_t, int32_t, int32_t, string_t>(
+	    args.data[0], args.data[1], args.data[2], result, args.size(),
+	    [&](string_t input, int32_t n, int32_t new_value) {
+		    if (new_value != 0 && new_value != 1) {
+			    throw InvalidInputException("The new bit must be 1 or 0");
+		    }
+		    if (n < 0 || (idx_t)n > Bit::BitLength(input) - 1) {
+			    throw OutOfRangeException("bit index %s out of valid range (0..%s)", NumericHelper::ToString(n),
+			                              NumericHelper::ToString(Bit::BitLength(input) - 1));
+		    }
+		    string_t target = StringVector::EmptyString(result, input.GetSize());
+		    Bit::SetBit(input, n, new_value, target);
+		    return target;
+	    });
+}
+
+void SetBitFun::RegisterFunction(BuiltinFunctions &set) {
+	set.AddFunction(ScalarFunction("set_bit", {LogicalType::BIT, LogicalType::INTEGER, LogicalType::INTEGER},
+	                               LogicalType::BIT, SetBitOperation));
+}
+
+//===--------------------------------------------------------------------===//
+// bit_position
+//===--------------------------------------------------------------------===//
+struct BitPositionOperator {
+	template <class TA, class TB, class TR>
+	static inline TR Operation(TA substring, TB input) {
+		if (substring.GetSize() > input.GetSize()) {
+			return 0;
+		}
+		return Bit::BitPosition(substring, input);
+	}
+};
+
+void BitPositionFun::RegisterFunction(BuiltinFunctions &set) {
+	set.AddFunction(ScalarFunction("bit_position", {LogicalType::BIT, LogicalType::BIT}, LogicalType::INTEGER,
+	                               ScalarFunction::BinaryFunction<string_t, string_t, int32_t, BitPositionOperator>));
+}
+
+} // namespace duckdb

package/src/duckdb/src/function/scalar/date/date_diff.cpp

@@ -9,7 +9,6 @@
 #include "duckdb/common/vector_operations/ternary_executor.hpp"
 #include "duckdb/common/vector_operations/vector_operations.hpp"
 #include "duckdb/common/string_util.hpp"
-#include "duckdb/storage/statistics/numeric_statistics.hpp"
 
 namespace duckdb {
 

package/src/duckdb/src/function/scalar/date/date_part.cpp

@@ -9,7 +9,7 @@
 #include "duckdb/function/scalar/date_functions.hpp"
 #include "duckdb/function/scalar/nested_functions.hpp"
 #include "duckdb/planner/expression/bound_function_expression.hpp"
-#include "duckdb/storage/statistics/numeric_statistics.hpp"
+
 #include "duckdb/common/field_writer.hpp"
 
 namespace duckdb {
@@ -161,34 +161,27 @@ DatePartSpecifier GetDateTypePartSpecifier(const string &specifier, LogicalType
 }
 
 template <int64_t MIN, int64_t MAX>
-static unique_ptr<BaseStatistics> PropagateSimpleDatePartStatistics(vector<unique_ptr<BaseStatistics>> &child_stats) {
+static unique_ptr<BaseStatistics> PropagateSimpleDatePartStatistics(vector<BaseStatistics> &child_stats) {
 	// we can always propagate simple date part statistics
 	// since the min and max can never exceed these bounds
-	auto result = make_unique<NumericStatistics>(LogicalType::BIGINT, Value::BIGINT(MIN), Value::BIGINT(MAX),
-	                                             StatisticsType::LOCAL_STATS);
-	if (!child_stats[0]) {
-		// if there are no child stats, we don't know
-		result->validity_stats = make_unique<ValidityStatistics>(true);
-	} else if (child_stats[0]->validity_stats) {
-		result->validity_stats = child_stats[0]->validity_stats->Copy();
-	}
-	return std::move(result);
+	auto result = NumericStats::CreateEmpty(LogicalType::BIGINT);
+	result.CopyValidity(child_stats[0]);
+	NumericStats::SetMin(result, Value::BIGINT(MIN));
+	NumericStats::SetMax(result, Value::BIGINT(MAX));
+	return result.ToUnique();
 }
 
 struct DatePart {
 	template <class T, class OP>
-	static unique_ptr<BaseStatistics> PropagateDatePartStatistics(vector<unique_ptr<BaseStatistics>> &child_stats) {
+	static unique_ptr<BaseStatistics> PropagateDatePartStatistics(vector<BaseStatistics> &child_stats) {
 		// we can only propagate complex date part stats if the child has stats
-		if (!child_stats[0]) {
-			return nullptr;
-		}
-		auto &nstats = (NumericStatistics &)*child_stats[0];
-		if (nstats.min.IsNull() || nstats.max.IsNull()) {
+		auto &nstats = child_stats[0];
+		if (!NumericStats::HasMinMax(nstats)) {
 			return nullptr;
 		}
 		// run the operator on both the min and the max, this gives us the [min, max] bound
-		auto min = nstats.min.GetValueUnsafe<T>();
-		auto max = nstats.max.GetValueUnsafe<T>();
+		auto min = NumericStats::GetMinUnsafe<T>(nstats);
+		auto max = NumericStats::GetMaxUnsafe<T>(nstats);
 		if (min > max) {
 			return nullptr;
 		}
@@ -198,12 +191,11 @@ struct DatePart {
 		}
 		auto min_part = OP::template Operation<T, int64_t>(min);
 		auto max_part = OP::template Operation<T, int64_t>(max);
-		auto result = make_unique<NumericStatistics>(LogicalType::BIGINT, Value::BIGINT(min_part),
-		                                             Value::BIGINT(max_part), StatisticsType::LOCAL_STATS);
-		if (child_stats[0]->validity_stats) {
-			result->validity_stats = child_stats[0]->validity_stats->Copy();
-		}
-		return std::move(result);
+		auto result = NumericStats::CreateEmpty(LogicalType::BIGINT);
+		NumericStats::SetMin(result, Value::BIGINT(min_part));
+		NumericStats::SetMax(result, Value::BIGINT(max_part));
+		result.CopyValidity(child_stats[0]);
+		return result.ToUnique();
 	}
 
 	template <typename OP>

package/src/duckdb/src/function/scalar/date/date_sub.cpp

@@ -9,7 +9,6 @@
 #include "duckdb/common/vector_operations/ternary_executor.hpp"
 #include "duckdb/common/vector_operations/vector_operations.hpp"
 #include "duckdb/common/string_util.hpp"
-#include "duckdb/storage/statistics/numeric_statistics.hpp"
 
 namespace duckdb {