duckdb · Mytherin · Jul 9, 2025 · Jul 1, 2025 · Jul 1, 2025 · Jul 1, 2025
diff --git a/.github/actions/build_extensions/action.yml b/.github/actions/build_extensions/action.yml
@@ -114,7 +114,7 @@ runs:
       run: |
         echo "VCPKG_TOOLCHAIN_PATH=$VCPKG_ROOT/scripts/buildsystems/vcpkg.cmake" >> $GITHUB_ENV
         echo "VCPKG_TARGET_TRIPLET=${{ inputs.vcpkg_target_triplet }}" >> $GITHUB_ENV
-        echo "BUILD_COMPLETE_EXTENSION_SET=${{ inputs.build_complete_extensions_set }}" >> docker_env.txt
+        echo "BUILD_COMPLETE_EXTENSION_SET=${{ inputs.build_complete_extensions_set }}" >> $GITHUB_ENV
 
     - name: workaround for https://github.com/duckdb/duckdb/issues/8360
       if: inputs.vcpkg_target_triplet == 'x64-windows-static-md'

diff --git a/.github/config/out_of_tree_extensions.cmake b/.github/config/out_of_tree_extensions.cmake
@@ -24,7 +24,7 @@ duckdb_extension_load(httpfs
     INCLUDE_DIR extension/httpfs/include
     )
 
-################# AVRO
+################## AVRO
 if (NOT MINGW)
     duckdb_extension_load(avro
             APPLY_PATCHES
@@ -74,7 +74,7 @@ duckdb_extension_load(excel
     APPLY_PATCHES
     LOAD_TESTS
     GIT_URL https://github.com/duckdb/duckdb-excel
-    GIT_TAG 7e97933214d0c7de2315668ec68589ae85651afb
+    GIT_TAG cf00672f2d16685d9aefcca48c6a04d8c37d7015
     INCLUDE_DIR src/excel/include
     )
 

diff --git a/.github/workflows/Python.yml b/.github/workflows/Python.yml
@@ -391,10 +391,10 @@ jobs:
         ./scripts/upload-assets-to-staging.sh twine_upload tools/pythonpkg/wheelhouse/*.whl
 
   linux-release-cleanup:
+     if: github.ref == 'refs/heads/v1.3-ossivalis' || github.ref == 'refs/heads/main'
      name: PyPi Release Cleanup
      needs: 
       - twine-upload
-     if: ${{ github.ref == 'refs/heads/v1.2-histrionicus' || github.ref == 'refs/heads/main' }}
      runs-on: ubuntu-22.04
      env:
        PYPI_CLEANUP_USERNAME: 'mytherin'

diff --git a/data/csv/afl/5194/crashes/case_0.csv b/data/csv/afl/5194/crashes/case_0.csv
@@ -0,0 +1,25 @@
+a,b,c
+1,1,1
+1,1,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,\n,1
+1,1000;"aa ""
+;a ""
+10"\n,1
+1,\n,1
+1,1,1
+1,1,1
diff --git a/data/csv/afl/5194/crashes/case_4.csv b/data/csv/afl/5194/crashes/case_4.csv
diff --git a/extension/parquet/column_reader.cpp b/extension/parquet/column_reader.cpp
@@ -763,6 +763,8 @@ unique_ptr<ColumnReader> CreateDecimalReader(ParquetReader &reader, const Parque
 		return make_uniq<TemplatedColumnReader<int32_t, TemplatedParquetValueConversion<T>>>(reader, schema);
 	case PhysicalType::INT64:
 		return make_uniq<TemplatedColumnReader<int64_t, TemplatedParquetValueConversion<T>>>(reader, schema);
+	case PhysicalType::INT128:
+		return make_uniq<TemplatedColumnReader<hugeint_t, TemplatedParquetValueConversion<T>>>(reader, schema);
 	default:
 		throw NotImplementedException("Unimplemented internal type for CreateDecimalReader");
 	}

diff --git a/scripts/merge_vcpkg_deps.py b/scripts/merge_vcpkg_deps.py
@@ -68,7 +68,7 @@ def prefix_overlay_port(overlay_port):
 else:
     data['vcpkg-configuration'] = {}
 
-REGISTRY_BASELINE = '9989b8b4707261ce77425ae5364b7de7139a2030'
+REGISTRY_BASELINE = '02558971ebafdbaa697a0704a3ed7ba365cd5495'
 # NOTE: use 'scripts/list_vcpkg_registry_packages.py --baseline <baseline>' to generate the list of packages
 data['vcpkg-configuration']['registries'] = [
     {

diff --git a/src/common/arrow/arrow_type_extension.cpp b/src/common/arrow/arrow_type_extension.cpp
@@ -382,7 +382,7 @@ void ArrowTypeExtensionSet::Initialize(const DBConfig &config) {
 
 	// Types that are 1:n
 	config.RegisterArrowExtension({"arrow.json", &ArrowJson::PopulateSchema, &ArrowJson::GetType,
-	                               make_shared_ptr<ArrowTypeExtensionData>(LogicalType::VARCHAR)});
+	                               make_shared_ptr<ArrowTypeExtensionData>(LogicalType::JSON())});
 
 	config.RegisterArrowExtension({"DuckDB", "bit", &ArrowBit::PopulateSchema, &ArrowBit::GetType,
 	                               make_shared_ptr<ArrowTypeExtensionData>(LogicalType::BIT), nullptr, nullptr});

diff --git a/src/common/settings.json b/src/common/settings.json
@@ -374,10 +374,11 @@
     },
     {
         "name": "enable_http_logging",
-        "description": "Enables HTTP logging",
+        "description": "(deprecated) Enables HTTP logging",
         "type": "BOOLEAN",
         "scope": "local",
-        "struct": "EnableHTTPLoggingSetting"
+        "struct": "EnableHTTPLoggingSetting",
+        "custom_implementation": true
     },
     {
         "name": "enable_http_metadata_cache",
@@ -510,10 +511,11 @@
     },
     {
         "name": "http_logging_output",
-        "description": "The file to which HTTP logging output should be saved, or empty to print to the terminal",
+        "description": "(deprecated) The file to which HTTP logging output should be saved, or empty to print to the terminal",
         "type": "VARCHAR",
         "scope": "local",
-        "struct": "HTTPLoggingOutputSetting"
+        "struct": "HTTPLoggingOutputSetting",
+        "custom_implementation": true
     },
     {
         "name": "http_proxy",

diff --git a/src/execution/operator/csv_scanner/scanner/scanner_boundary.cpp b/src/execution/operator/csv_scanner/scanner/scanner_boundary.cpp
@@ -41,6 +41,11 @@ idx_t CSVIterator::BytesPerThread(const CSVReaderOptions &reader_options) {
 		// If we are setting up the buffer size directly, we must make sure each thread will read the full buffer.
 		return max_row_size;
 	}
+	if (bytes_per_thread == 0) {
+		// Bytes per thread can never be zero, but it might happen if max_row_size = 0
+		// Not sure why a human being would do that...
+		return 1;
+	}
 	return bytes_per_thread;
 }
 

diff --git a/src/execution/operator/csv_scanner/scanner/string_value_scanner.cpp b/src/execution/operator/csv_scanner/scanner/string_value_scanner.cpp
@@ -1373,7 +1373,7 @@ void StringValueScanner::ProcessOverBufferValue() {
 			result.escaped = true;
 		}
 		if (states.IsComment()) {
-			result.comment = true;
+			result.SetComment(result, j);
 		}
 		if (states.IsInvalid()) {
 			result.InvalidState(result);
@@ -1435,7 +1435,7 @@ void StringValueScanner::ProcessOverBufferValue() {
 			result.SetQuoted(result, j);
 		}
 		if (states.IsComment()) {
-			result.comment = true;
+			result.SetComment(result, j);
 		}
 		if (states.IsEscaped() && result.state_machine.dialect_options.state_machine_options.escape != '\0') {
 			result.escaped = true;

diff --git a/src/execution/physical_plan/plan_asof_join.cpp b/src/execution/physical_plan/plan_asof_join.cpp
@@ -95,8 +95,13 @@ PhysicalPlanGenerator::PlanAsOfLoopJoin(LogicalComparisonJoin &op, PhysicalOpera
 			asof_idx = i;
 			arg_min_max = "arg_min";
 			break;
-		default:
+		case ExpressionType::COMPARE_EQUAL:
+		case ExpressionType::COMPARE_NOTEQUAL:
+		case ExpressionType::COMPARE_DISTINCT_FROM:
 			break;
+		default:
+			//	Unsupported NLJ comparison
+			return nullptr;
 		}
 	}
 

diff --git a/src/function/function_list.cpp b/src/function/function_list.cpp
@@ -53,8 +53,8 @@ static const StaticFunctionDefinition function[] = {
 	DUCKDB_SCALAR_FUNCTION_SET(InternalCompressIntegralUintegerFun),
 	DUCKDB_SCALAR_FUNCTION_SET(InternalCompressIntegralUsmallintFun),
 	DUCKDB_SCALAR_FUNCTION_SET(InternalCompressIntegralUtinyintFun),
-	DUCKDB_SCALAR_FUNCTION(InternalCompressStringHugeintFun),
 	DUCKDB_SCALAR_FUNCTION(InternalCompressStringUbigintFun),
+	DUCKDB_SCALAR_FUNCTION(InternalCompressStringUhugeintFun),
 	DUCKDB_SCALAR_FUNCTION(InternalCompressStringUintegerFun),
 	DUCKDB_SCALAR_FUNCTION(InternalCompressStringUsmallintFun),
 	DUCKDB_SCALAR_FUNCTION(InternalCompressStringUtinyintFun),

diff --git a/src/function/scalar/compressed_materialization/compress_string.cpp b/src/function/scalar/compressed_materialization/compress_string.cpp
@@ -93,8 +93,8 @@ static scalar_function_t GetStringCompressFunctionSwitch(const LogicalType &resu
 		return GetStringCompressFunction<uint32_t>(result_type);
 	case LogicalTypeId::UBIGINT:
 		return GetStringCompressFunction<uint64_t>(result_type);
-	case LogicalTypeId::HUGEINT:
-		return GetStringCompressFunction<hugeint_t>(result_type);
+	case LogicalTypeId::UHUGEINT:
+		return GetStringCompressFunction<uhugeint_t>(result_type);
 	default:
 		throw InternalException("Unexpected type in GetStringCompressFunctionSwitch");
 	}
@@ -189,8 +189,8 @@ static scalar_function_t GetStringDecompressFunctionSwitch(const LogicalType &in
 		return GetStringDecompressFunction<uint32_t>(input_type);
 	case LogicalTypeId::UBIGINT:
 		return GetStringDecompressFunction<uint64_t>(input_type);
-	case LogicalTypeId::HUGEINT:
-		return GetStringDecompressFunction<hugeint_t>(input_type);
+	case LogicalTypeId::UHUGEINT:
+		return GetStringDecompressFunction<uhugeint_t>(input_type);
 	default:
 		throw InternalException("Unexpected type in GetStringDecompressFunctionSwitch");
 	}
@@ -262,8 +262,8 @@ ScalarFunction InternalCompressStringUbigintFun::GetFunction() {
 	return CMStringCompressFun::GetFunction(LogicalType(LogicalTypeId::UBIGINT));
 }
 
-ScalarFunction InternalCompressStringHugeintFun::GetFunction() {
-	return CMStringCompressFun::GetFunction(LogicalType(LogicalTypeId::HUGEINT));
+ScalarFunction InternalCompressStringUhugeintFun::GetFunction() {
+	return CMStringCompressFun::GetFunction(LogicalType(LogicalTypeId::UHUGEINT));
 }
 
 ScalarFunctionSet InternalDecompressStringFun::GetFunctions() {

diff --git a/src/function/scalar/compressed_materialization/functions.json b/src/function/scalar/compressed_materialization/functions.json
@@ -56,7 +56,7 @@
         "type": "scalar_function"
     },
     {
-        "name": "__internal_compress_string_hugeint",
+        "name": "__internal_compress_string_uhugeint",
         "parameters": "",
         "description": "",
         "example": "",

diff --git a/src/function/scalar/compressed_materialization_utils.cpp b/src/function/scalar/compressed_materialization_utils.cpp
@@ -8,7 +8,7 @@ const vector<LogicalType> CMUtils::IntegralTypes() {
 
 const vector<LogicalType> CMUtils::StringTypes() {
 	return {LogicalType::UTINYINT, LogicalType::USMALLINT, LogicalType::UINTEGER, LogicalType::UBIGINT,
-	        LogicalType::HUGEINT};
+	        LogicalType::UHUGEINT};
 }
 
 // LCOV_EXCL_START