Update vendored DuckDB sources to e79a6b6c07

CMakeLists.txt

@@ -351,52 +351,52 @@ set(DUCKDB_SRC_FILES
   src/duckdb/third_party/zstd/dict/divsufsort.cpp
   src/duckdb/third_party/zstd/dict/fastcover.cpp
   src/duckdb/third_party/zstd/dict/zdict.cpp
-  src/duckdb/extension/core_functions/lambda_functions.cpp
-  src/duckdb/extension/core_functions/function_list.cpp
   src/duckdb/extension/core_functions/core_functions_extension.cpp
-  src/duckdb/ub_extension_core_functions_aggregate_distributive.cpp
+  src/duckdb/extension/core_functions/function_list.cpp
+  src/duckdb/extension/core_functions/lambda_functions.cpp
   src/duckdb/ub_extension_core_functions_aggregate_nested.cpp
-  src/duckdb/ub_extension_core_functions_aggregate_regression.cpp
+  src/duckdb/ub_extension_core_functions_aggregate_distributive.cpp
   src/duckdb/ub_extension_core_functions_aggregate_algebraic.cpp
+  src/duckdb/ub_extension_core_functions_aggregate_regression.cpp
   src/duckdb/ub_extension_core_functions_aggregate_holistic.cpp
-  src/duckdb/ub_extension_core_functions_scalar_string.cpp
+  src/duckdb/ub_extension_core_functions_scalar_generic.cpp
   src/duckdb/extension/core_functions/scalar/bit/bitstring.cpp
-  src/duckdb/extension/core_functions/scalar/operators/bitwise.cpp
-  src/duckdb/extension/core_functions/scalar/enum/enum_functions.cpp
+  src/duckdb/ub_extension_core_functions_scalar_string.cpp
+  src/duckdb/ub_extension_core_functions_scalar_debug.cpp
   src/duckdb/ub_extension_core_functions_scalar_map.cpp
-  src/duckdb/ub_extension_core_functions_scalar_random.cpp
-  src/duckdb/extension/core_functions/scalar/math/numeric.cpp
-  src/duckdb/ub_extension_core_functions_scalar_union.cpp
-  src/duckdb/ub_extension_core_functions_scalar_generic.cpp
   src/duckdb/ub_extension_core_functions_scalar_struct.cpp
-  src/duckdb/ub_extension_core_functions_scalar_list.cpp
+  src/duckdb/extension/core_functions/scalar/operators/bitwise.cpp
+  src/duckdb/ub_extension_core_functions_scalar_union.cpp
   src/duckdb/ub_extension_core_functions_scalar_array.cpp
-  src/duckdb/ub_extension_core_functions_scalar_debug.cpp
   src/duckdb/ub_extension_core_functions_scalar_blob.cpp
+  src/duckdb/extension/core_functions/scalar/enum/enum_functions.cpp
+  src/duckdb/ub_extension_core_functions_scalar_random.cpp
   src/duckdb/ub_extension_core_functions_scalar_date.cpp
+  src/duckdb/ub_extension_core_functions_scalar_list.cpp
+  src/duckdb/extension/core_functions/scalar/math/numeric.cpp
+  src/duckdb/extension/parquet/parquet_file_metadata_cache.cpp
+  src/duckdb/extension/parquet/parquet_field_id.cpp
   src/duckdb/extension/parquet/parquet_writer.cpp
-  src/duckdb/extension/parquet/zstd_file_system.cpp
+  src/duckdb/extension/parquet/parquet_column_schema.cpp
+  src/duckdb/extension/parquet/parquet_multi_file_info.cpp
+  src/duckdb/extension/parquet/parquet_metadata.cpp
   src/duckdb/extension/parquet/parquet_crypto.cpp
-  src/duckdb/extension/parquet/parquet_reader.cpp
   src/duckdb/extension/parquet/parquet_timestamp.cpp
-  src/duckdb/extension/parquet/parquet_float16.cpp
-  src/duckdb/extension/parquet/parquet_statistics.cpp
-  src/duckdb/extension/parquet/parquet_shredding.cpp
-  src/duckdb/extension/parquet/parquet_geometry.cpp
-  src/duckdb/extension/parquet/parquet_multi_file_info.cpp
-  src/duckdb/extension/parquet/column_reader.cpp
-  src/duckdb/extension/parquet/parquet_field_id.cpp
   src/duckdb/extension/parquet/parquet_extension.cpp
-  src/duckdb/extension/parquet/parquet_column_schema.cpp
   src/duckdb/extension/parquet/column_writer.cpp
-  src/duckdb/extension/parquet/parquet_file_metadata_cache.cpp
   src/duckdb/extension/parquet/serialize_parquet.cpp
-  src/duckdb/extension/parquet/parquet_metadata.cpp
+  src/duckdb/extension/parquet/parquet_reader.cpp
+  src/duckdb/extension/parquet/column_reader.cpp
+  src/duckdb/extension/parquet/parquet_float16.cpp
+  src/duckdb/extension/parquet/zstd_file_system.cpp
+  src/duckdb/extension/parquet/parquet_shredding.cpp
+  src/duckdb/extension/parquet/parquet_geometry.cpp
+  src/duckdb/extension/parquet/parquet_statistics.cpp
+  src/duckdb/ub_extension_parquet_writer.cpp
+  src/duckdb/ub_extension_parquet_writer_variant.cpp
   src/duckdb/ub_extension_parquet_decoder.cpp
   src/duckdb/ub_extension_parquet_reader.cpp
   src/duckdb/ub_extension_parquet_reader_variant.cpp
-  src/duckdb/ub_extension_parquet_writer.cpp
-  src/duckdb/ub_extension_parquet_writer_variant.cpp
   src/duckdb/third_party/parquet/parquet_types.cpp
   src/duckdb/third_party/thrift/thrift/protocol/TProtocol.cpp
   src/duckdb/third_party/thrift/thrift/transport/TTransportException.cpp
@@ -436,31 +436,31 @@ set(DUCKDB_SRC_FILES
   src/duckdb/third_party/brotli/enc/static_dict.cpp
   src/duckdb/third_party/brotli/enc/utf8_util.cpp
   src/duckdb/extension/icu/./icu_extension.cpp
+  src/duckdb/extension/icu/./icu-table-range.cpp
+  src/duckdb/extension/icu/./icu-list-range.cpp
   src/duckdb/extension/icu/./icu-strptime.cpp
-  src/duckdb/extension/icu/./icu-datepart.cpp
-  src/duckdb/extension/icu/./icu-makedate.cpp
-  src/duckdb/extension/icu/./icu-datefunc.cpp
+  src/duckdb/extension/icu/./icu-datetrunc.cpp
   src/duckdb/extension/icu/./icu-current.cpp
   src/duckdb/extension/icu/./icu-timezone.cpp
-  src/duckdb/extension/icu/./icu-table-range.cpp
-  src/duckdb/extension/icu/./icu-dateadd.cpp
-  src/duckdb/extension/icu/./icu-timebucket.cpp
   src/duckdb/extension/icu/./icu-datesub.cpp
-  src/duckdb/extension/icu/./icu-datetrunc.cpp
-  src/duckdb/extension/icu/./icu-list-range.cpp
+  src/duckdb/extension/icu/./icu-timebucket.cpp
+  src/duckdb/extension/icu/./icu-makedate.cpp
+  src/duckdb/extension/icu/./icu-dateadd.cpp
+  src/duckdb/extension/icu/./icu-datepart.cpp
+  src/duckdb/extension/icu/./icu-datefunc.cpp
   src/duckdb/ub_extension_icu_third_party_icu_common.cpp
   src/duckdb/ub_extension_icu_third_party_icu_i18n.cpp
   src/duckdb/extension/icu/third_party/icu/stubdata/stubdata.cpp
-  src/duckdb/extension/json/json_reader.cpp
-  src/duckdb/extension/json/json_functions.cpp
-  src/duckdb/extension/json/json_extension.cpp
+  src/duckdb/extension/json/serialize_json.cpp
   src/duckdb/extension/json/json_scan.cpp
+  src/duckdb/extension/json/json_reader.cpp
   src/duckdb/extension/json/json_multi_file_info.cpp
-  src/duckdb/extension/json/json_enums.cpp
-  src/duckdb/extension/json/serialize_json.cpp
   src/duckdb/extension/json/json_common.cpp
-  src/duckdb/extension/json/json_deserializer.cpp
+  src/duckdb/extension/json/json_enums.cpp
   src/duckdb/extension/json/json_serializer.cpp
+  src/duckdb/extension/json/json_extension.cpp
+  src/duckdb/extension/json/json_functions.cpp
+  src/duckdb/extension/json/json_deserializer.cpp
   src/duckdb/ub_extension_json_json_functions.cpp
   src/duckdb/generated_extension_loader_package_build.cpp)
 

src/duckdb/extension/core_functions/aggregate/holistic/mode.cpp

@@ -1,17 +1,11 @@
 #include "duckdb/common/exception.hpp"
 #include "duckdb/common/uhugeint.hpp"
-#include "duckdb/common/vector_operations/vector_operations.hpp"
-#include "duckdb/common/operator/comparison_operators.hpp"
 #include "duckdb/common/types/column/column_data_collection.hpp"
 #include "core_functions/aggregate/distributive_functions.hpp"
 #include "core_functions/aggregate/holistic_functions.hpp"
-#include "duckdb/planner/expression/bound_aggregate_expression.hpp"
-#include "duckdb/common/unordered_map.hpp"
 #include "duckdb/common/owning_string_map.hpp"
 #include "duckdb/function/create_sort_key.hpp"
 #include "duckdb/function/aggregate/sort_key_helpers.hpp"
-#include "duckdb/common/algorithm.hpp"
-#include <functional>
 
 // MODE( <expr1> )
 // Returns the most frequent value for the values within expr1.
@@ -44,6 +38,18 @@ struct ModeStandard {
 	static RESULT_TYPE Assign(Vector &result, INPUT_TYPE input) {
 		return RESULT_TYPE(input);
 	}
+
+	static void Destroy(T *mode) {
+	}
+
+	static T *Update(T *mode, const T &key) {
+		if (!mode) {
+			mode = new T(key);
+		}
+		*mode = key;
+
+		return mode;
+	}
 };
 
 struct ModeString {
@@ -60,6 +66,42 @@ struct ModeString {
 	static RESULT_TYPE Assign(Vector &result, INPUT_TYPE input) {
 		return StringVector::AddStringOrBlob(result, input);
 	}
+
+	static void Destroy(string_t *mode) {
+		if (mode && !mode->IsInlined()) {
+			delete[] mode->GetData();
+			mode->SetPointer(nullptr);
+		}
+	}
+
+	static string_t *Update(string_t *mode, const string_t &key) {
+		if (key.IsInlined()) {
+			Destroy(mode);
+			if (!mode) {
+				mode = new string_t(nullptr, 0);
+			}
+			*mode = key;
+			return mode;
+		}
+
+		// non-inlined string, need to allocate space for it somehow
+		const auto len = key.GetSize();
+		char *ptr;
+		if (!mode || mode->GetSize() < len) {
+			// we cannot fit this into the current slot - destroy it and re-allocate
+			Destroy(mode);
+			if (!mode) {
+				mode = new string_t(nullptr, 0);
+			}
+			ptr = new char[len];
+		} else {
+			// this fits into the current slot - take over the pointer
+			ptr = mode->GetDataWriteable();
+		}
+		memcpy(ptr, key.GetData(), len);
+		*mode = string_t(ptr, UnsafeNumericCast<uint32_t>(len));
+		return mode;
+	}
 };
 
 template <class KEY_TYPE, class TYPE_OP>
@@ -92,6 +134,7 @@ struct ModeState {
 			delete frequency_map;
 		}
 		if (mode) {
+			TYPE_OP::Destroy(mode);
 			delete mode;
 		}
 		if (scan) {
@@ -163,11 +206,7 @@ struct ModeState {
 		if (new_count > count) {
 			valid = true;
 			count = new_count;
-			if (mode) {
-				*mode = key;
-			} else {
-				mode = new KEY_TYPE(key);
-			}
+			Update(key);
 		}
 	}
 
@@ -183,6 +222,10 @@ struct ModeState {
 		}
 	}
 
+	void Update(const KEY_TYPE &key) {
+		mode = TYPE_OP::Update(mode, key);
+	}
+
 	typename Counts::const_iterator Scan() const {
 		//! Initialize control variables to first variable of the frequency map
 		auto highest_frequency = frequency_map->begin();
@@ -363,7 +406,7 @@ struct ModeFunction : TypedModeFunction<TYPE_OP> {
 			// Rescan
 			auto highest_frequency = state.Scan();
 			if (highest_frequency != state.frequency_map->end()) {
-				*(state.mode) = highest_frequency->first;
+				state.Update(highest_frequency->first);
 				state.count = highest_frequency->second.count;
 				state.valid = (state.count > 0);
 			}

src/duckdb/extension/core_functions/function_list.cpp

@@ -196,6 +196,7 @@ static const StaticFunctionDefinition core_functions[] = {
 	DUCKDB_SCALAR_FUNCTION_SET(GenerateSeriesFun),
 	DUCKDB_SCALAR_FUNCTION(GetBitFun),
 	DUCKDB_SCALAR_FUNCTION(GetCurrentTimestampFun),
+	DUCKDB_SCALAR_FUNCTION(GetTypeFun),
 	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(GradeUpFun),
 	DUCKDB_SCALAR_FUNCTION_SET(GreatestFun),
 	DUCKDB_SCALAR_FUNCTION_SET(GreatestCommonDivisorFun),
@@ -266,6 +267,7 @@ static const StaticFunctionDefinition core_functions[] = {
 	DUCKDB_SCALAR_FUNCTION_SET(MakeTimestampFun),
 	DUCKDB_SCALAR_FUNCTION_SET(MakeTimestampMsFun),
 	DUCKDB_SCALAR_FUNCTION_SET(MakeTimestampNsFun),
+	DUCKDB_SCALAR_FUNCTION(MakeTypeFun),
 	DUCKDB_SCALAR_FUNCTION_SET(MapFun),
 	DUCKDB_SCALAR_FUNCTION(MapConcatFun),
 	DUCKDB_SCALAR_FUNCTION(MapEntriesFun),

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

@@ -85,6 +85,26 @@ struct TypeOfFun {
 	static ScalarFunction GetFunction();
 };
 
+struct GetTypeFun {
+	static constexpr const char *Name = "get_type";
+	static constexpr const char *Parameters = "expression";
+	static constexpr const char *Description = "Returns the type of the result of the expression";
+	static constexpr const char *Example = "get_type('abc')";
+	static constexpr const char *Categories = "";
+
+	static ScalarFunction GetFunction();
+};
+
+struct MakeTypeFun {
+	static constexpr const char *Name = "make_type";
+	static constexpr const char *Parameters = "name,...";
+	static constexpr const char *Description = "Construct a type from its name and optional parameters";
+	static constexpr const char *Example = "make_type('DECIMAL', 10, 2)";
+	static constexpr const char *Categories = "";
+
+	static ScalarFunction GetFunction();
+};
+
 struct CanCastImplicitlyFun {
 	static constexpr const char *Name = "can_cast_implicitly";
 	static constexpr const char *Parameters = "source_type,target_type";

src/duckdb/extension/core_functions/lambda_functions.cpp

@@ -5,6 +5,7 @@
 
 #include "duckdb/planner/expression/bound_function_expression.hpp"
 #include "duckdb/planner/expression/bound_cast_expression.hpp"
+#include "duckdb/planner/expression/bound_lambda_expression.hpp"
 
 namespace duckdb {
 

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

@@ -517,7 +517,8 @@ unique_ptr<BaseStatistics> DateTruncStatistics(vector<BaseStatistics> &child_sta
 	auto result = NumericStats::CreateEmpty(min_value.type());
 	NumericStats::SetMin(result, min_value);
 	NumericStats::SetMax(result, max_value);
-	result.CopyValidity(child_stats[0]);
+
+	result.CombineValidity(child_stats[0], child_stats[1]);
 	return result.ToUnique();
 }