Merge branch 'main' into duck_stl_allocator

lnkuiper · Sep 5, 2024 · cac5a82 · cac5a82
2 parents 988f3ca + a6e32b1
commit cac5a82
Show file tree

Hide file tree

Showing 55 changed files with 842 additions and 558 deletions.
diff --git a/.github/workflows/LinuxRelease.yml b/.github/workflows/LinuxRelease.yml
@@ -68,6 +68,7 @@ jobs:
     steps:
     - uses: actions/checkout@v3
       with:
+        fetch-depth: 0
         ref: ${{ inputs.git_ref }}
 
     - uses: ./.github/actions/manylinux_2014_setup

diff --git a/CMakeLists.txt b/CMakeLists.txt
@@ -215,6 +215,10 @@ if(${EXPLICIT_EXCEPTIONS})
   set(CXX_EXTRA "${CXX_EXTRA} -fexceptions")
 endif()
 
+if (UNSAFE_NUMERIC_CAST)
+  message(status "UNSAFE_NUMERIC_CAST")
+  add_definitions(-DUNSAFE_NUMERIC_CAST=1)
+endif()
 if (ENABLE_EXTENSION_AUTOLOADING)
   add_definitions(-DDUCKDB_EXTENSION_AUTOLOAD_DEFAULT=1)
 endif()

diff --git a/Makefile b/Makefile
@@ -94,7 +94,7 @@ endif
 ifneq (${ENABLE_EXTENSION_AUTOINSTALL}, "")
 	CMAKE_VARS:=${CMAKE_VARS} -DENABLE_EXTENSION_AUTOINSTALL=${ENABLE_EXTENSION_AUTOINSTALL}
 endif
-ifneq (${UNSAFE_NUMERIC_CAST}, "")
+ifneq (${UNSAFE_NUMERIC_CAST}, )
 	CMAKE_VARS:=${CMAKE_VARS} -DUNSAFE_NUMERIC_CAST=1
 endif
 ifeq (${BUILD_EXTENSIONS_ONLY}, 1)

diff --git a/src/common/arrow/arrow_appender.cpp b/src/common/arrow/arrow_appender.cpp
@@ -160,6 +160,16 @@ static void InitializeFunctionPointers(ArrowAppendData &append_data, const Logic
 		InitializeAppenderForType<ArrowScalarData<int64_t>>(append_data);
 		break;
 	case LogicalTypeId::UUID:
+		if (append_data.options.arrow_lossless_conversion) {
+			InitializeAppenderForType<ArrowScalarData<hugeint_t, hugeint_t, ArrowUUIDBlobConverter>>(append_data);
+		} else {
+			if (append_data.options.arrow_offset_size == ArrowOffsetSize::LARGE) {
+				InitializeAppenderForType<ArrowVarcharData<hugeint_t, ArrowUUIDConverter>>(append_data);
+			} else {
+				InitializeAppenderForType<ArrowVarcharData<hugeint_t, ArrowUUIDConverter, int32_t>>(append_data);
+			}
+		}
+		break;
 	case LogicalTypeId::HUGEINT:
 		InitializeAppenderForType<ArrowScalarData<hugeint_t>>(append_data);
 		break;

diff --git a/src/common/arrow/arrow_converter.cpp b/src/common/arrow/arrow_converter.cpp
@@ -146,11 +146,23 @@ void SetArrowFormat(DuckDBArrowSchemaHolder &root_holder, ArrowSchema &child, co
 		child.format = "g";
 		break;
 	case LogicalTypeId::UUID: {
-		// This is a canonical extension, hence needs the "arrow." prefix
-		child.format = "w:16";
-		auto schema_metadata = ArrowSchemaMetadata::MetadataFromName("arrow.uuid");
-		root_holder.metadata_info.emplace_back(schema_metadata.SerializeMetadata());
-		child.metadata = root_holder.metadata_info.back().get();
+		if (options.arrow_lossless_conversion) {
+			// This is a canonical extension, hence needs the "arrow." prefix
+			child.format = "w:16";
+			auto schema_metadata = ArrowSchemaMetadata::MetadataFromName("arrow.uuid");
+			root_holder.metadata_info.emplace_back(schema_metadata.SerializeMetadata());
+			child.metadata = root_holder.metadata_info.back().get();
+		} else {
+			if (options.produce_arrow_string_view) {
+				child.format = "vu";
+			} else {
+				if (options.arrow_offset_size == ArrowOffsetSize::LARGE) {
+					child.format = "U";
+				} else {
+					child.format = "u";
+				}
+			}
+		}
 		break;
 	}
 	case LogicalTypeId::VARCHAR:

diff --git a/src/core_functions/function_list.cpp b/src/core_functions/function_list.cpp
@@ -52,10 +52,10 @@ static const StaticFunctionDefinition internal_functions[] = {
 	DUCKDB_SCALAR_FUNCTION_SET(BitwiseAndFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ListHasAnyFunAlias),
 	DUCKDB_SCALAR_FUNCTION(PowOperatorFun),
-	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ListInnerProductFunAlias),
+	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ListNegativeInnerProductFunAlias),
 	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ListDistanceFunAlias),
 	DUCKDB_SCALAR_FUNCTION_SET(LeftShiftFun),
-	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ListCosineSimilarityFunAlias),
+	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ListCosineDistanceFunAlias),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ListHasAllFunAlias2),
 	DUCKDB_SCALAR_FUNCTION_SET(RightShiftFun),
 	DUCKDB_SCALAR_FUNCTION_SET(AbsOperatorFun),
@@ -82,6 +82,7 @@ static const StaticFunctionDefinition internal_functions[] = {
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ArrayAggrFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ArrayAggregateFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ArrayApplyFun),
+	DUCKDB_SCALAR_FUNCTION_SET(ArrayCosineDistanceFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ArrayCosineSimilarityFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ArrayCrossProductFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ArrayDistanceFun),
@@ -92,6 +93,8 @@ static const StaticFunctionDefinition internal_functions[] = {
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ArrayHasAllFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ArrayHasAnyFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ArrayInnerProductFun),
+	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ArrayNegativeDotProductFun),
+	DUCKDB_SCALAR_FUNCTION_SET(ArrayNegativeInnerProductFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ArrayReduceFun),
 	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ArrayReverseSortFun),
 	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ArraySliceFun),
@@ -230,6 +233,7 @@ static const StaticFunctionDefinition internal_functions[] = {
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ListAggrFun),
 	DUCKDB_SCALAR_FUNCTION(ListAggregateFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ListApplyFun),
+	DUCKDB_SCALAR_FUNCTION_SET(ListCosineDistanceFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ListCosineSimilarityFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ListDistanceFun),
 	DUCKDB_SCALAR_FUNCTION(ListDistinctFun),
@@ -239,6 +243,8 @@ static const StaticFunctionDefinition internal_functions[] = {
 	DUCKDB_SCALAR_FUNCTION(ListHasAllFun),
 	DUCKDB_SCALAR_FUNCTION(ListHasAnyFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ListInnerProductFun),
+	DUCKDB_SCALAR_FUNCTION_SET_ALIAS(ListNegativeDotProductFun),
+	DUCKDB_SCALAR_FUNCTION_SET(ListNegativeInnerProductFun),
 	DUCKDB_SCALAR_FUNCTION_ALIAS(ListPackFun),
 	DUCKDB_SCALAR_FUNCTION(ListReduceFun),
 	DUCKDB_SCALAR_FUNCTION_SET(ListReverseSortFun),