chore: Update vendored sources to duckdb/duckdb@be47ec4

Merge pull request duckdb/duckdb#9164 from Mause/feature/jdbc-uuid-param
Merge pull request duckdb/duckdb#9185 from pdet/adbc_07
Merge pull request duckdb/duckdb#9126 from Maxxen/parquet-kv-metadata
Merge pull request duckdb/duckdb#9123 from lnkuiper/parquet_schema
Merge pull request duckdb/duckdb#9086 from lnkuiper/json_inconsistent_structure
Merge pull request duckdb/duckdb#8977 from Tishj/python_readcsv_multi_v2
Merge pull request duckdb/duckdb#9279 from hawkfish/nsdate-cast
Merge pull request duckdb/duckdb#8851 from taniabogatsch/binary_lambdas
Merge pull request duckdb/duckdb#8983 from Maxxen/types/fixedsizelist
Merge pull request duckdb/duckdb#9318 from Maxxen/fix-unused
Merge pull request duckdb/duckdb#9220 from hawkfish/exclude
Merge pull request duckdb/duckdb#9230 from Maxxen/json-plan-serialization
Merge pull request duckdb/duckdb#9011 from Tmonster/add_create_statement_support_to_fuzzer
Merge pull request duckdb/duckdb#9400 from Maxxen/array-fixes
Merge pull request duckdb/duckdb#8741 from Tishj/python_import_cache_upgrade
Merge fixes
Merge pull request duckdb/duckdb#9395 from taniabogatsch/lambda-performance
Merge pull request duckdb/duckdb#9427 from Tishj/python_table_support_replacement_scan
Merge pull request duckdb/duckdb#9516 from carlopi/fixformat
Merge pull request duckdb/duckdb#9485 from Maxxen/fix-parquet-serialization
Merge pull request duckdb/duckdb#9388 from chrisiou/issue217
Merge pull request duckdb/duckdb#9565 from Maxxen/fix-array-vector-sizes
Merge pull request duckdb/duckdb#9583 from carlopi/feature
Merge pull request duckdb/duckdb#8907 from cryoEncryp/new-list-functions
Merge pull request duckdb/duckdb#8642 from Virgiel/capi-streaming-arrow
Merge pull request duckdb/duckdb#8658 from Tishj/pytype_optional
Merge pull request duckdb/duckdb#9040 from Light-City/feature/set_mg

src/duckdb/extension/parquet/column_reader.cpp

@@ -182,7 +182,7 @@ idx_t ColumnReader::GroupRowsAvailable() {
 
 unique_ptr<BaseStatistics> ColumnReader::Stats(idx_t row_group_idx_p, const vector<ColumnChunk> &columns) {
 	if (Type().id() == LogicalTypeId::LIST || Type().id() == LogicalTypeId::STRUCT ||
-	    Type().id() == LogicalTypeId::MAP) {
+	    Type().id() == LogicalTypeId::MAP || Type().id() == LogicalTypeId::ARRAY) {
 		return nullptr;
 	}
 	return ParquetStatisticsUtils::TransformColumnStatistics(Schema(), Type(), columns[file_idx]);

src/duckdb/extension/parquet/include/parquet_metadata.hpp

@@ -23,4 +23,9 @@ class ParquetSchemaFunction : public TableFunction {
 	ParquetSchemaFunction();
 };
 
+class ParquetKeyValueMetadataFunction : public TableFunction {
+public:
+	ParquetKeyValueMetadataFunction();
+};
+
 } // namespace duckdb

src/duckdb/extension/parquet/include/parquet_reader.hpp

@@ -10,16 +10,16 @@
 
 #include "duckdb.hpp"
 #ifndef DUCKDB_AMALGAMATION
-#include "duckdb/planner/table_filter.hpp"
-#include "duckdb/planner/filter/constant_filter.hpp"
-#include "duckdb/planner/filter/null_filter.hpp"
-#include "duckdb/planner/filter/conjunction_filter.hpp"
 #include "duckdb/common/common.hpp"
 #include "duckdb/common/exception.hpp"
+#include "duckdb/common/multi_file_reader.hpp"
+#include "duckdb/common/multi_file_reader_options.hpp"
 #include "duckdb/common/string_util.hpp"
 #include "duckdb/common/types/data_chunk.hpp"
-#include "duckdb/common/multi_file_reader_options.hpp"
-#include "duckdb/common/multi_file_reader.hpp"
+#include "duckdb/planner/filter/conjunction_filter.hpp"
+#include "duckdb/planner/filter/constant_filter.hpp"
+#include "duckdb/planner/filter/null_filter.hpp"
+#include "duckdb/planner/table_filter.hpp"
 #endif
 #include "column_reader.hpp"
 #include "parquet_file_metadata_cache.hpp"
@@ -64,6 +64,21 @@ struct ParquetReaderScanState {
 	bool current_group_prefetched = false;
 };
 
+struct ParquetColumnDefinition {
+public:
+	static ParquetColumnDefinition FromSchemaValue(ClientContext &context, const Value &column_value);
+
+public:
+	int32_t field_id;
+	string name;
+	LogicalType type;
+	Value default_value;
+
+public:
+	void Serialize(Serializer &serializer) const;
+	static ParquetColumnDefinition Deserialize(Deserializer &deserializer);
+};
+
 struct ParquetOptions {
 	explicit ParquetOptions() {
 	}
@@ -72,6 +87,7 @@ struct ParquetOptions {
 	bool binary_as_string = false;
 	bool file_row_number = false;
 	MultiFileReaderOptions file_options;
+	vector<ParquetColumnDefinition> schema;
 
 public:
 	void Serialize(Serializer &serializer) const;
@@ -95,6 +111,11 @@ class ParquetReader {
 	MultiFileReaderData reader_data;
 	unique_ptr<ColumnReader> root_reader;
 
+	//! Index of the file_row_number column
+	idx_t file_row_number_idx = DConstants::INVALID_INDEX;
+	//! Parquet schema for the generated columns
+	vector<duckdb_parquet::format::SchemaElement> generated_column_schema;
+
 public:
 	void InitializeScan(ParquetReaderScanState &state, vector<idx_t> groups_to_read);
 	void Scan(ParquetReaderScanState &state, DataChunk &output);

src/duckdb/extension/parquet/include/parquet_writer.hpp

@@ -26,6 +26,9 @@ namespace duckdb {
 class FileSystem;
 class FileOpener;
 
+class Serializer;
+class Deserializer;
+
 struct PreparedRowGroup {
 	duckdb_parquet::format::RowGroup row_group;
 	vector<unique_ptr<ColumnWriterState>> states;
@@ -37,6 +40,9 @@ struct ChildFieldIDs {
 	ChildFieldIDs();
 	ChildFieldIDs Copy() const;
 	unique_ptr<case_insensitive_map_t<FieldID>> ids;
+
+	void Serialize(Serializer &serializer) const;
+	static ChildFieldIDs Deserialize(Deserializer &source);
 };
 
 struct FieldID {
@@ -47,12 +53,16 @@ struct FieldID {
 	bool set;
 	int32_t field_id;
 	ChildFieldIDs child_field_ids;
+
+	void Serialize(Serializer &serializer) const;
+	static FieldID Deserialize(Deserializer &source);
 };
 
 class ParquetWriter {
 public:
 	ParquetWriter(FileSystem &fs, string file_name, vector<LogicalType> types, vector<string> names,
-	              duckdb_parquet::format::CompressionCodec::type codec, ChildFieldIDs field_ids);
+	              duckdb_parquet::format::CompressionCodec::type codec, ChildFieldIDs field_ids,
+	              const vector<pair<string, string>> &kv_metadata);
 
 public:
 	void PrepareRowGroup(ColumnDataCollection &buffer, PreparedRowGroup &result);