Merge pull request #117 from carlopi/main

Bump to DuckDB v1.1.0

Author: hannes

.github/workflows/NodeJS.yml

@@ -243,7 +243,7 @@ jobs:
 
   win-nodejs:
     name: node.js Windows
-    runs-on: windows-latest
+    runs-on: windows-2019
     needs: set-up-npm
     continue-on-error: ${{ matrix.node != '18' && matrix.node != '20' && matrix.node != '21' }}
     env:

binding.gyp

@@ -26,6 +26,7 @@
                 "src/duckdb/ub_src_common_row_operations.cpp", 
                 "src/duckdb/ub_src_common_serializer.cpp", 
                 "src/duckdb/ub_src_common_sort.cpp", 
+                "src/duckdb/ub_src_common_tree_renderer.cpp", 
                 "src/duckdb/ub_src_common_types.cpp", 
                 "src/duckdb/ub_src_common_types_column.cpp", 
                 "src/duckdb/ub_src_common_types_row.cpp", 
@@ -243,6 +244,7 @@
                 "src/duckdb/extension/parquet/parquet_writer.cpp", 
                 "src/duckdb/extension/parquet/serialize_parquet.cpp", 
                 "src/duckdb/extension/parquet/zstd_file_system.cpp", 
+                "src/duckdb/extension/parquet/geo_parquet.cpp", 
                 "src/duckdb/third_party/parquet/parquet_constants.cpp", 
                 "src/duckdb/third_party/parquet/parquet_types.cpp", 
                 "src/duckdb/third_party/thrift/thrift/protocol/TProtocol.cpp", 
@@ -272,6 +274,37 @@
                 "src/duckdb/third_party/zstd/compress/zstd_ldm.cpp", 
                 "src/duckdb/third_party/zstd/compress/zstd_opt.cpp", 
                 "src/duckdb/third_party/lz4/lz4.cpp", 
+                "src/duckdb/third_party/brotli/common/constants.cpp", 
+                "src/duckdb/third_party/brotli/common/context.cpp", 
+                "src/duckdb/third_party/brotli/common/dictionary.cpp", 
+                "src/duckdb/third_party/brotli/common/platform.cpp", 
+                "src/duckdb/third_party/brotli/common/shared_dictionary.cpp", 
+                "src/duckdb/third_party/brotli/common/transform.cpp", 
+                "src/duckdb/third_party/brotli/dec/bit_reader.cpp", 
+                "src/duckdb/third_party/brotli/dec/decode.cpp", 
+                "src/duckdb/third_party/brotli/dec/huffman.cpp", 
+                "src/duckdb/third_party/brotli/dec/state.cpp", 
+                "src/duckdb/third_party/brotli/enc/backward_references.cpp", 
+                "src/duckdb/third_party/brotli/enc/backward_references_hq.cpp", 
+                "src/duckdb/third_party/brotli/enc/bit_cost.cpp", 
+                "src/duckdb/third_party/brotli/enc/block_splitter.cpp", 
+                "src/duckdb/third_party/brotli/enc/brotli_bit_stream.cpp", 
+                "src/duckdb/third_party/brotli/enc/cluster.cpp", 
+                "src/duckdb/third_party/brotli/enc/command.cpp", 
+                "src/duckdb/third_party/brotli/enc/compound_dictionary.cpp", 
+                "src/duckdb/third_party/brotli/enc/compress_fragment.cpp", 
+                "src/duckdb/third_party/brotli/enc/compress_fragment_two_pass.cpp", 
+                "src/duckdb/third_party/brotli/enc/dictionary_hash.cpp", 
+                "src/duckdb/third_party/brotli/enc/encode.cpp", 
+                "src/duckdb/third_party/brotli/enc/encoder_dict.cpp", 
+                "src/duckdb/third_party/brotli/enc/entropy_encode.cpp", 
+                "src/duckdb/third_party/brotli/enc/fast_log.cpp", 
+                "src/duckdb/third_party/brotli/enc/histogram.cpp", 
+                "src/duckdb/third_party/brotli/enc/literal_cost.cpp", 
+                "src/duckdb/third_party/brotli/enc/memory.cpp", 
+                "src/duckdb/third_party/brotli/enc/metablock.cpp", 
+                "src/duckdb/third_party/brotli/enc/static_dict.cpp", 
+                "src/duckdb/third_party/brotli/enc/utf8_util.cpp", 
                 "src/duckdb/extension/icu/./icu-table-range.cpp", 
                 "src/duckdb/extension/icu/./icu-makedate.cpp", 
                 "src/duckdb/extension/icu/./icu-list-range.cpp", 
@@ -313,6 +346,10 @@
                 "src/duckdb/third_party/libpg_query", 
                 "src/duckdb/third_party/libpg_query/include", 
                 "src/duckdb/third_party/lz4", 
+                "src/duckdb/third_party/brotli/include", 
+                "src/duckdb/third_party/brotli/common", 
+                "src/duckdb/third_party/brotli/dec", 
+                "src/duckdb/third_party/brotli/enc", 
                 "src/duckdb/third_party/mbedtls", 
                 "src/duckdb/third_party/mbedtls/include", 
                 "src/duckdb/third_party/mbedtls/library", 
@@ -328,6 +365,10 @@
                 "src/duckdb/third_party/parquet", 
                 "src/duckdb/third_party/thrift", 
                 "src/duckdb/third_party/lz4", 
+                "src/duckdb/third_party/brotli/include", 
+                "src/duckdb/third_party/brotli/common", 
+                "src/duckdb/third_party/brotli/dec", 
+                "src/duckdb/third_party/brotli/enc", 
                 "src/duckdb/third_party/snappy", 
                 "src/duckdb/third_party/zstd/include", 
                 "src/duckdb/third_party/mbedtls", 

src/duckdb/extension/icu/icu-dateadd.cpp

@@ -101,13 +101,15 @@ timestamp_t ICUCalendarAdd::Operation(timestamp_t timestamp, interval_t interval
 		calendar->add(UCAL_MINUTE, interval_m, status);
 		CalendarAddHour(calendar, interval_h, status);
 
-		calendar->add(UCAL_DATE, interval.days, status);
+		// PG Adds months before days
 		calendar->add(UCAL_MONTH, interval.months, status);
+		calendar->add(UCAL_DATE, interval.days, status);
 	} else {
-		// Add interval fields from highest to lowest (ragged to non-ragged)
+		// PG Adds months before days
 		calendar->add(UCAL_MONTH, interval.months, status);
 		calendar->add(UCAL_DATE, interval.days, status);
 
+		// Add interval fields from highest to lowest (ragged to non-ragged)
 		CalendarAddHour(calendar, interval_h, status);
 		calendar->add(UCAL_MINUTE, interval_m, status);
 		calendar->add(UCAL_SECOND, interval_s, status);

src/duckdb/extension/icu/icu-datefunc.cpp

@@ -73,6 +73,10 @@ unique_ptr<FunctionData> ICUDateFunc::Bind(ClientContext &context, ScalarFunctio
 
 void ICUDateFunc::SetTimeZone(icu::Calendar *calendar, const string_t &tz_id) {
 	auto tz = icu_66::TimeZone::createTimeZone(icu::UnicodeString::fromUTF8(icu::StringPiece(tz_id.GetString())));
+	if (*tz == icu::TimeZone::getUnknown()) {
+		delete tz;
+		throw NotImplementedException("Unknown TimeZone '%s'", tz_id.GetString());
+	}
 	calendar->adoptTimeZone(tz);
 }
 
@@ -83,7 +87,7 @@ timestamp_t ICUDateFunc::GetTimeUnsafe(icu::Calendar *calendar, uint64_t micros)
 	if (U_FAILURE(status)) {
 		throw InternalException("Unable to get ICU calendar time.");
 	}
-	return timestamp_t(millis * Interval::MICROS_PER_MSEC + micros);
+	return timestamp_t(millis * Interval::MICROS_PER_MSEC + int64_t(micros));
 }
 
 bool ICUDateFunc::TryGetTime(icu::Calendar *calendar, uint64_t micros, timestamp_t &result) {
@@ -98,7 +102,7 @@ bool ICUDateFunc::TryGetTime(icu::Calendar *calendar, uint64_t micros, timestamp
 	if (!TryMultiplyOperator::Operation<int64_t, int64_t, int64_t>(millis, Interval::MICROS_PER_MSEC, millis)) {
 		return false;
 	}
-	if (!TryAddOperator::Operation<int64_t, int64_t, int64_t>(millis, micros, millis)) {
+	if (!TryAddOperator::Operation<int64_t, int64_t, int64_t>(millis, int64_t(micros), millis)) {
 		return false;
 	}
 

src/duckdb/extension/icu/icu-datesub.cpp

@@ -209,6 +209,17 @@ struct ICUCalendarDiff : public ICUDateFunc {
 		return sub_func(calendar, start_date, end_date);
 	}
 
+	static part_trunc_t DiffTruncationFactory(DatePartSpecifier type) {
+		switch (type) {
+		case DatePartSpecifier::WEEK:
+			//	Weeks are computed without anchors
+			return TruncationFactory(DatePartSpecifier::DAY);
+		default:
+			break;
+		}
+		return TruncationFactory(type);
+	}
+
 	template <typename T>
 	static void ICUDateDiffFunction(DataChunk &args, ExpressionState &state, Vector &result) {
 		D_ASSERT(args.ColumnCount() == 3);
@@ -229,7 +240,7 @@ struct ICUCalendarDiff : public ICUDateFunc {
 			} else {
 				const auto specifier = ConstantVector::GetData<string_t>(part_arg)->GetString();
 				const auto part = GetDatePartSpecifier(specifier);
-				auto trunc_func = TruncationFactory(part);
+				auto trunc_func = DiffTruncationFactory(part);
 				auto sub_func = SubtractFactory(part);
 				BinaryExecutor::ExecuteWithNulls<T, T, int64_t>(
 				    startdate_arg, enddate_arg, result, args.size(),
@@ -248,7 +259,7 @@ struct ICUCalendarDiff : public ICUDateFunc {
 			    [&](string_t specifier, T start_date, T end_date, ValidityMask &mask, idx_t idx) {
 				    if (Timestamp::IsFinite(start_date) && Timestamp::IsFinite(end_date)) {
 					    const auto part = GetDatePartSpecifier(specifier.GetString());
-					    auto trunc_func = TruncationFactory(part);
+					    auto trunc_func = DiffTruncationFactory(part);
 					    auto sub_func = SubtractFactory(part);
 					    return DifferenceFunc<T>(calendar, start_date, end_date, trunc_func, sub_func);
 				    } else {

src/duckdb/extension/icu/icu-strptime.cpp

@@ -68,15 +68,15 @@ struct ICUStrptime : public ICUDateFunc {
 		}
 
 		// Now get the parts in the given time zone
-		uint64_t micros = 0;
+		uint64_t micros = parsed.GetMicros();
 		calendar->set(UCAL_EXTENDED_YEAR, parsed.data[0]); // strptime doesn't understand eras
 		calendar->set(UCAL_MONTH, parsed.data[1] - 1);
 		calendar->set(UCAL_DATE, parsed.data[2]);
 		calendar->set(UCAL_HOUR_OF_DAY, parsed.data[3]);
 		calendar->set(UCAL_MINUTE, parsed.data[4]);
 		calendar->set(UCAL_SECOND, parsed.data[5]);
-		calendar->set(UCAL_MILLISECOND, parsed.data[6] / Interval::MICROS_PER_MSEC);
-		micros = parsed.data[6] % Interval::MICROS_PER_MSEC;
+		calendar->set(UCAL_MILLISECOND, micros / Interval::MICROS_PER_MSEC);
+		micros %= Interval::MICROS_PER_MSEC;
 
 		// This overrides the TZ setting, so only use it if an offset was parsed.
 		// Note that we don't bother/worry about the DST setting because the two just combine.
@@ -158,7 +158,7 @@ struct ICUStrptime : public ICUDateFunc {
 		}
 	}
 
-	static bind_scalar_function_t bind_strptime;
+	static bind_scalar_function_t bind_strptime; // NOLINT
 
 	static duckdb::unique_ptr<FunctionData> StrpTimeBindFunction(ClientContext &context, ScalarFunction &bound_function,
 	                                                             vector<duckdb::unique_ptr<Expression>> &arguments) {
@@ -194,7 +194,7 @@ struct ICUStrptime : public ICUDateFunc {
 				throw InvalidInputException("strptime format list must not be empty");
 			}
 			vector<StrpTimeFormat> formats;
-			bool has_tz = true;
+			bool has_tz = false;
 			for (const auto &child : children) {
 				format_string = child.ToString();
 				format.format_specifier = format_string;
@@ -341,7 +341,7 @@ struct ICUStrptime : public ICUDateFunc {
 	}
 };
 
-bind_scalar_function_t ICUStrptime::bind_strptime = nullptr;
+bind_scalar_function_t ICUStrptime::bind_strptime = nullptr; // NOLINT
 
 struct ICUStrftime : public ICUDateFunc {
 	static void ParseFormatSpecifier(string_t &format_str, StrfTimeFormat &format) {