duckdb 0.9.3-dev2.0 → 0.10.0
Sign up to get free protection for your applications and to get access to all the features.
- package/.github/workflows/NodeJS.yml +1 -1
- package/README.md +6 -6
- package/binding.gyp +32 -7
- package/package.json +1 -1
- package/src/connection.cpp +6 -6
- package/src/database.cpp +12 -10
- package/src/duckdb/extension/icu/icu-datefunc.cpp +22 -10
- package/src/duckdb/extension/icu/icu-datepart.cpp +42 -22
- package/src/duckdb/extension/icu/icu-datetrunc.cpp +40 -7
- package/src/duckdb/extension/icu/icu-strptime.cpp +14 -8
- package/src/duckdb/extension/icu/icu-table-range.cpp +1 -1
- package/src/duckdb/extension/icu/icu-timezone.cpp +43 -16
- package/src/duckdb/extension/icu/icu_extension.cpp +1 -1
- package/src/duckdb/extension/icu/include/icu-datefunc.hpp +3 -0
- package/src/duckdb/extension/icu/third_party/icu/stubdata/stubdata.cpp +1 -1
- package/src/duckdb/extension/json/buffered_json_reader.cpp +78 -62
- package/src/duckdb/extension/json/include/buffered_json_reader.hpp +11 -7
- package/src/duckdb/extension/json/include/json_common.hpp +0 -14
- package/src/duckdb/extension/json/include/json_deserializer.hpp +1 -0
- package/src/duckdb/extension/json/include/json_functions.hpp +1 -0
- package/src/duckdb/extension/json/include/json_scan.hpp +19 -5
- package/src/duckdb/extension/json/include/json_serializer.hpp +2 -1
- package/src/duckdb/extension/json/include/json_structure.hpp +12 -10
- package/src/duckdb/extension/json/json_common.cpp +1 -0
- package/src/duckdb/extension/json/json_deserializer.cpp +13 -0
- package/src/duckdb/extension/json/json_extension.cpp +3 -3
- package/src/duckdb/extension/json/json_functions/copy_json.cpp +8 -4
- package/src/duckdb/extension/json/json_functions/json_array_length.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_contains.cpp +3 -3
- package/src/duckdb/extension/json/json_functions/json_create.cpp +53 -8
- package/src/duckdb/extension/json/json_functions/json_extract.cpp +10 -6
- package/src/duckdb/extension/json/json_functions/json_keys.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_merge_patch.cpp +2 -3
- package/src/duckdb/extension/json/json_functions/json_serialize_plan.cpp +210 -0
- package/src/duckdb/extension/json/json_functions/json_serialize_sql.cpp +22 -19
- package/src/duckdb/extension/json/json_functions/json_structure.cpp +71 -43
- package/src/duckdb/extension/json/json_functions/json_transform.cpp +105 -8
- package/src/duckdb/extension/json/json_functions/json_type.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_valid.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/read_json.cpp +43 -18
- package/src/duckdb/extension/json/json_functions/read_json_objects.cpp +1 -1
- package/src/duckdb/extension/json/json_functions.cpp +9 -5
- package/src/duckdb/extension/json/json_scan.cpp +147 -125
- package/src/duckdb/extension/json/json_serializer.cpp +9 -0
- package/src/duckdb/extension/json/serialize_json.cpp +6 -0
- package/src/duckdb/extension/parquet/column_reader.cpp +53 -18
- package/src/duckdb/extension/parquet/column_writer.cpp +29 -6
- package/src/duckdb/extension/parquet/include/column_reader.hpp +0 -1
- package/src/duckdb/extension/parquet/include/decode_utils.hpp +2 -2
- package/src/duckdb/extension/parquet/include/parquet_crypto.hpp +87 -0
- package/src/duckdb/extension/parquet/include/parquet_dbp_decoder.hpp +4 -3
- package/src/duckdb/extension/parquet/include/parquet_decimal_utils.hpp +16 -3
- package/src/duckdb/extension/parquet/include/parquet_metadata.hpp +10 -0
- package/src/duckdb/extension/parquet/include/parquet_reader.hpp +34 -6
- package/src/duckdb/extension/parquet/include/parquet_statistics.hpp +3 -2
- package/src/duckdb/extension/parquet/include/parquet_timestamp.hpp +2 -0
- package/src/duckdb/extension/parquet/include/parquet_writer.hpp +21 -1
- package/src/duckdb/extension/parquet/parquet_crypto.cpp +370 -0
- package/src/duckdb/extension/parquet/parquet_extension.cpp +254 -24
- package/src/duckdb/extension/parquet/parquet_metadata.cpp +204 -16
- package/src/duckdb/extension/parquet/parquet_reader.cpp +108 -34
- package/src/duckdb/extension/parquet/parquet_statistics.cpp +75 -30
- package/src/duckdb/extension/parquet/parquet_timestamp.cpp +15 -8
- package/src/duckdb/extension/parquet/parquet_writer.cpp +62 -10
- package/src/duckdb/extension/parquet/serialize_parquet.cpp +60 -0
- package/src/duckdb/src/catalog/catalog.cpp +23 -25
- package/src/duckdb/src/catalog/catalog_entry/column_dependency_manager.cpp +1 -0
- package/src/duckdb/src/catalog/catalog_entry/dependency/dependency_dependent_entry.cpp +31 -0
- package/src/duckdb/src/catalog/catalog_entry/dependency/dependency_entry.cpp +44 -0
- package/src/duckdb/src/catalog/catalog_entry/dependency/dependency_subject_entry.cpp +31 -0
- package/src/duckdb/src/catalog/catalog_entry/duck_index_entry.cpp +35 -10
- package/src/duckdb/src/catalog/catalog_entry/duck_schema_entry.cpp +22 -6
- package/src/duckdb/src/catalog/catalog_entry/duck_table_entry.cpp +110 -33
- package/src/duckdb/src/catalog/catalog_entry/index_catalog_entry.cpp +33 -17
- package/src/duckdb/src/catalog/catalog_entry/macro_catalog_entry.cpp +16 -0
- package/src/duckdb/src/catalog/catalog_entry/schema_catalog_entry.cpp +7 -6
- package/src/duckdb/src/catalog/catalog_entry/sequence_catalog_entry.cpp +88 -14
- package/src/duckdb/src/catalog/catalog_entry/table_catalog_entry.cpp +6 -15
- package/src/duckdb/src/catalog/catalog_entry/type_catalog_entry.cpp +20 -20
- package/src/duckdb/src/catalog/catalog_entry/view_catalog_entry.cpp +4 -0
- package/src/duckdb/src/catalog/catalog_entry.cpp +29 -0
- package/src/duckdb/src/catalog/catalog_set.cpp +358 -343
- package/src/duckdb/src/catalog/catalog_transaction.cpp +4 -0
- package/src/duckdb/src/catalog/default/default_functions.cpp +13 -4
- package/src/duckdb/src/catalog/default/default_schemas.cpp +5 -1
- package/src/duckdb/src/catalog/default/default_views.cpp +6 -2
- package/src/duckdb/src/catalog/dependency_catalog_set.cpp +51 -0
- package/src/duckdb/src/catalog/dependency_manager.cpp +510 -114
- package/src/duckdb/src/catalog/duck_catalog.cpp +4 -4
- package/src/duckdb/src/common/adbc/adbc.cpp +73 -53
- package/src/duckdb/src/common/adbc/driver_manager.cpp +1101 -268
- package/src/duckdb/src/common/arrow/arrow_wrapper.cpp +20 -9
- package/src/duckdb/src/common/bind_helpers.cpp +1 -0
- package/src/duckdb/src/common/box_renderer.cpp +52 -1
- package/src/duckdb/src/common/compressed_file_system.cpp +1 -0
- package/src/duckdb/src/common/constants.cpp +0 -1
- package/src/duckdb/src/common/enum_util.cpp +522 -107
- package/src/duckdb/src/common/enums/catalog_type.cpp +64 -1
- package/src/duckdb/src/common/enums/compression_type.cpp +14 -0
- package/src/duckdb/src/common/enums/date_part_specifier.cpp +1 -0
- package/src/duckdb/src/common/enums/expression_type.cpp +4 -0
- package/src/duckdb/src/common/enums/file_compression_type.cpp +1 -0
- package/src/duckdb/src/common/enums/join_type.cpp +33 -0
- package/src/duckdb/src/common/enums/logical_operator_type.cpp +5 -3
- package/src/duckdb/src/common/enums/optimizer_type.cpp +9 -1
- package/src/duckdb/src/common/enums/physical_operator_type.cpp +8 -4
- package/src/duckdb/src/common/enums/statement_type.cpp +2 -2
- package/src/duckdb/src/common/error_data.cpp +113 -0
- package/src/duckdb/src/common/exception/binder_exception.cpp +47 -0
- package/src/duckdb/src/common/exception/catalog_exception.cpp +55 -0
- package/src/duckdb/src/common/exception/parser_exception.cpp +19 -0
- package/src/duckdb/src/common/exception.cpp +110 -121
- package/src/duckdb/src/common/exception_format_value.cpp +9 -1
- package/src/duckdb/src/common/extra_type_info.cpp +48 -0
- package/src/duckdb/src/common/file_system.cpp +12 -7
- package/src/duckdb/src/common/gzip_file_system.cpp +18 -18
- package/src/duckdb/src/common/hive_partitioning.cpp +5 -1
- package/src/duckdb/src/common/http_state.cpp +20 -3
- package/src/duckdb/src/common/local_file_system.cpp +214 -15
- package/src/duckdb/src/common/multi_file_reader.cpp +20 -7
- package/src/duckdb/src/common/operator/cast_operators.cpp +397 -414
- package/src/duckdb/src/common/operator/convert_to_string.cpp +4 -0
- package/src/duckdb/src/common/operator/string_cast.cpp +5 -0
- package/src/duckdb/src/common/progress_bar/progress_bar.cpp +61 -12
- package/src/duckdb/src/common/progress_bar/terminal_progress_bar_display.cpp +13 -4
- package/src/duckdb/src/common/radix_partitioning.cpp +1 -1
- package/src/duckdb/src/common/row_operations/row_aggregate.cpp +2 -1
- package/src/duckdb/src/common/row_operations/row_gather.cpp +7 -1
- package/src/duckdb/src/common/row_operations/row_heap_gather.cpp +78 -12
- package/src/duckdb/src/common/row_operations/row_heap_scatter.cpp +222 -61
- package/src/duckdb/src/common/row_operations/row_matcher.cpp +6 -1
- package/src/duckdb/src/common/row_operations/row_radix_scatter.cpp +51 -0
- package/src/duckdb/src/common/row_operations/row_scatter.cpp +8 -1
- package/src/duckdb/src/common/serializer/binary_deserializer.cpp +6 -0
- package/src/duckdb/src/common/serializer/binary_serializer.cpp +5 -0
- package/src/duckdb/src/common/serializer/serializer.cpp +19 -0
- package/src/duckdb/src/common/sort/comparators.cpp +126 -0
- package/src/duckdb/src/common/sort/partition_state.cpp +17 -17
- package/src/duckdb/src/common/sort/radix_sort.cpp +2 -1
- package/src/duckdb/src/common/sort/sort_state.cpp +10 -5
- package/src/duckdb/src/common/sort/sorted_block.cpp +7 -6
- package/src/duckdb/src/common/string_util.cpp +302 -24
- package/src/duckdb/src/common/tree_renderer.cpp +8 -6
- package/src/duckdb/src/common/types/cast_helpers.cpp +6 -0
- package/src/duckdb/src/common/types/column/column_data_allocator.cpp +1 -1
- package/src/duckdb/src/common/types/column/column_data_collection.cpp +58 -0
- package/src/duckdb/src/common/types/column/column_data_collection_segment.cpp +8 -1
- package/src/duckdb/src/common/types/data_chunk.cpp +9 -0
- package/src/duckdb/src/common/types/date.cpp +2 -2
- package/src/duckdb/src/common/types/hash.cpp +9 -1
- package/src/duckdb/src/common/types/hugeint.cpp +229 -51
- package/src/duckdb/src/common/types/hyperloglog.cpp +10 -3
- package/src/duckdb/src/common/types/interval.cpp +67 -12
- package/src/duckdb/src/common/types/list_segment.cpp +98 -4
- package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +11 -1
- package/src/duckdb/src/common/types/row/row_data_collection.cpp +1 -1
- package/src/duckdb/src/common/types/row/row_data_collection_scanner.cpp +2 -2
- package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +3 -2
- package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +63 -3
- package/src/duckdb/src/common/types/row/tuple_data_scatter_gather.cpp +331 -127
- package/src/duckdb/src/common/types/time.cpp +47 -75
- package/src/duckdb/src/common/types/timestamp.cpp +16 -3
- package/src/duckdb/src/common/types/uhugeint.cpp +746 -0
- package/src/duckdb/src/common/types/validity_mask.cpp +6 -2
- package/src/duckdb/src/common/types/value.cpp +183 -27
- package/src/duckdb/src/common/types/vector.cpp +331 -30
- package/src/duckdb/src/common/types/vector_buffer.cpp +29 -1
- package/src/duckdb/src/common/types/vector_cache.cpp +22 -1
- package/src/duckdb/src/common/types.cpp +606 -90
- package/src/duckdb/src/common/value_operations/comparison_operations.cpp +21 -1
- package/src/duckdb/src/common/vector_operations/comparison_operators.cpp +5 -0
- package/src/duckdb/src/common/vector_operations/generators.cpp +2 -2
- package/src/duckdb/src/common/vector_operations/is_distinct_from.cpp +131 -2
- package/src/duckdb/src/common/vector_operations/vector_copy.cpp +26 -4
- package/src/duckdb/src/common/vector_operations/vector_hash.cpp +41 -0
- package/src/duckdb/src/common/vector_operations/vector_storage.cpp +7 -0
- package/src/duckdb/src/common/virtual_file_system.cpp +0 -1
- package/src/duckdb/src/core_functions/aggregate/distributive/approx_count.cpp +2 -1
- package/src/duckdb/src/core_functions/aggregate/distributive/arg_min_max.cpp +144 -56
- package/src/duckdb/src/core_functions/aggregate/distributive/bitagg.cpp +2 -0
- package/src/duckdb/src/core_functions/aggregate/distributive/bitstring_agg.cpp +27 -0
- package/src/duckdb/src/core_functions/aggregate/distributive/entropy.cpp +4 -3
- package/src/duckdb/src/core_functions/aggregate/distributive/kurtosis.cpp +25 -5
- package/src/duckdb/src/core_functions/aggregate/distributive/minmax.cpp +100 -3
- package/src/duckdb/src/core_functions/aggregate/distributive/string_agg.cpp +2 -1
- package/src/duckdb/src/core_functions/aggregate/holistic/approximate_quantile.cpp +9 -1
- package/src/duckdb/src/core_functions/aggregate/holistic/mode.cpp +83 -52
- package/src/duckdb/src/core_functions/aggregate/holistic/quantile.cpp +485 -289
- package/src/duckdb/src/core_functions/aggregate/holistic/reservoir_quantile.cpp +3 -3
- package/src/duckdb/src/core_functions/aggregate/nested/histogram.cpp +24 -26
- package/src/duckdb/src/core_functions/aggregate/nested/list.cpp +34 -37
- package/src/duckdb/src/core_functions/function_list.cpp +30 -1
- package/src/duckdb/src/core_functions/lambda_functions.cpp +416 -0
- package/src/duckdb/src/core_functions/scalar/array/array_functions.cpp +294 -0
- package/src/duckdb/src/core_functions/scalar/array/array_value.cpp +87 -0
- package/src/duckdb/src/core_functions/scalar/blob/create_sort_key.cpp +686 -0
- package/src/duckdb/src/core_functions/scalar/blob/encode.cpp +1 -0
- package/src/duckdb/src/core_functions/scalar/date/current.cpp +3 -3
- package/src/duckdb/src/core_functions/scalar/date/date_part.cpp +295 -20
- package/src/duckdb/src/core_functions/scalar/date/make_date.cpp +1 -0
- package/src/duckdb/src/core_functions/scalar/date/strftime.cpp +8 -7
- package/src/duckdb/src/core_functions/scalar/date/to_interval.cpp +84 -23
- package/src/duckdb/src/core_functions/scalar/generic/error.cpp +4 -4
- package/src/duckdb/src/core_functions/scalar/generic/least.cpp +7 -8
- package/src/duckdb/src/core_functions/scalar/generic/stats.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/generic/system_functions.cpp +17 -6
- package/src/duckdb/src/core_functions/scalar/list/array_slice.cpp +8 -0
- package/src/duckdb/src/core_functions/scalar/list/list_aggregates.cpp +28 -14
- package/src/duckdb/src/core_functions/scalar/list/list_filter.cpp +49 -0
- package/src/duckdb/src/core_functions/scalar/list/list_reduce.cpp +230 -0
- package/src/duckdb/src/core_functions/scalar/list/list_sort.cpp +85 -16
- package/src/duckdb/src/core_functions/scalar/list/list_transform.cpp +41 -0
- package/src/duckdb/src/core_functions/scalar/list/list_value.cpp +21 -2
- package/src/duckdb/src/core_functions/scalar/map/map.cpp +6 -5
- package/src/duckdb/src/core_functions/scalar/map/map_entries.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/map/map_from_entries.cpp +1 -2
- package/src/duckdb/src/core_functions/scalar/math/numeric.cpp +24 -4
- package/src/duckdb/src/core_functions/scalar/operators/bitwise.cpp +6 -0
- package/src/duckdb/src/core_functions/scalar/random/random.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/random/setseed.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/secret/which_secret.cpp +28 -0
- package/src/duckdb/src/core_functions/scalar/string/bar.cpp +9 -4
- package/src/duckdb/src/core_functions/scalar/string/format_bytes.cpp +7 -2
- package/src/duckdb/src/core_functions/scalar/string/hex.cpp +63 -4
- package/src/duckdb/src/core_functions/scalar/string/pad.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/string/parse_path.cpp +348 -0
- package/src/duckdb/src/core_functions/scalar/string/regexp_escape.cpp +22 -0
- package/src/duckdb/src/core_functions/scalar/string/string_split.cpp +6 -5
- package/src/duckdb/src/core_functions/scalar/struct/struct_insert.cpp +3 -3
- package/src/duckdb/src/core_functions/scalar/struct/struct_pack.cpp +1 -1
- package/src/duckdb/src/execution/aggregate_hashtable.cpp +9 -2
- package/src/duckdb/src/execution/column_binding_resolver.cpp +44 -10
- package/src/duckdb/src/execution/expression_executor/execute_between.cpp +4 -0
- package/src/duckdb/src/execution/expression_executor/execute_case.cpp +4 -0
- package/src/duckdb/src/execution/expression_executor/execute_comparison.cpp +4 -0
- package/src/duckdb/src/execution/expression_executor.cpp +2 -1
- package/src/duckdb/src/execution/index/art/art.cpp +202 -53
- package/src/duckdb/src/execution/index/art/art_key.cpp +20 -27
- package/src/duckdb/src/execution/index/fixed_size_allocator.cpp +52 -17
- package/src/duckdb/src/execution/index/fixed_size_buffer.cpp +14 -8
- package/src/duckdb/src/execution/index/index_type_set.cpp +32 -0
- package/src/duckdb/src/execution/index/unknown_index.cpp +65 -0
- package/src/duckdb/src/execution/join_hashtable.cpp +151 -174
- package/src/duckdb/src/execution/nested_loop_join/nested_loop_join_inner.cpp +4 -0
- package/src/duckdb/src/execution/nested_loop_join/nested_loop_join_mark.cpp +4 -0
- package/src/duckdb/src/execution/operator/aggregate/aggregate_object.cpp +2 -1
- package/src/duckdb/src/execution/operator/aggregate/physical_hash_aggregate.cpp +82 -36
- package/src/duckdb/src/execution/operator/aggregate/physical_ungrouped_aggregate.cpp +58 -32
- package/src/duckdb/src/execution/operator/aggregate/physical_window.cpp +35 -19
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_buffer.cpp +90 -0
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_buffer_manager.cpp +124 -0
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_file_handle.cpp +97 -0
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/base_scanner.cpp +71 -0
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/column_count_scanner.cpp +98 -0
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/scanner_boundary.cpp +105 -0
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/skip_scanner.cpp +63 -0
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/string_value_scanner.cpp +1091 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/csv_sniffer.cpp +124 -26
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp +117 -129
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp +46 -22
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp +83 -199
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_refinement.cpp +21 -122
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_replacement.cpp +18 -17
- package/src/duckdb/src/execution/operator/csv_scanner/state_machine/csv_state_machine.cpp +22 -0
- package/src/duckdb/src/execution/operator/csv_scanner/state_machine/csv_state_machine_cache.cpp +201 -0
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/csv_file_scanner.cpp +221 -0
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/global_csv_state.cpp +204 -0
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_error.cpp +186 -0
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_reader_options.cpp +532 -0
- package/src/duckdb/src/execution/operator/helper/physical_buffered_collector.cpp +85 -0
- package/src/duckdb/src/execution/operator/helper/physical_create_secret.cpp +21 -0
- package/src/duckdb/src/execution/operator/helper/physical_materialized_collector.cpp +1 -1
- package/src/duckdb/src/execution/operator/helper/physical_pragma.cpp +2 -2
- package/src/duckdb/src/execution/operator/helper/physical_reservoir_sample.cpp +34 -9
- package/src/duckdb/src/execution/operator/helper/physical_result_collector.cpp +10 -0
- package/src/duckdb/src/execution/operator/helper/physical_transaction.cpp +1 -0
- package/src/duckdb/src/execution/operator/helper/physical_vacuum.cpp +25 -10
- package/src/duckdb/src/execution/operator/join/perfect_hash_join_executor.cpp +7 -8
- package/src/duckdb/src/execution/operator/join/physical_asof_join.cpp +1 -1
- package/src/duckdb/src/execution/operator/join/physical_blockwise_nl_join.cpp +5 -2
- package/src/duckdb/src/execution/operator/join/physical_comparison_join.cpp +1 -1
- package/src/duckdb/src/execution/operator/join/physical_delim_join.cpp +5 -127
- package/src/duckdb/src/execution/operator/join/physical_hash_join.cpp +221 -61
- package/src/duckdb/src/execution/operator/join/physical_iejoin.cpp +18 -21
- package/src/duckdb/src/execution/operator/join/physical_join.cpp +10 -5
- package/src/duckdb/src/execution/operator/join/physical_left_delim_join.cpp +137 -0
- package/src/duckdb/src/execution/operator/join/physical_nested_loop_join.cpp +11 -4
- package/src/duckdb/src/execution/operator/join/physical_piecewise_merge_join.cpp +2 -2
- package/src/duckdb/src/execution/operator/join/physical_range_join.cpp +19 -4
- package/src/duckdb/src/execution/operator/join/physical_right_delim_join.cpp +121 -0
- package/src/duckdb/src/execution/operator/persistent/physical_batch_insert.cpp +3 -2
- package/src/duckdb/src/execution/operator/persistent/physical_copy_database.cpp +59 -0
- package/src/duckdb/src/execution/operator/persistent/physical_copy_to_file.cpp +132 -92
- package/src/duckdb/src/execution/operator/persistent/physical_export.cpp +54 -54
- package/src/duckdb/src/execution/operator/persistent/physical_insert.cpp +1 -1
- package/src/duckdb/src/execution/operator/projection/physical_unnest.cpp +4 -0
- package/src/duckdb/src/execution/operator/scan/physical_column_data_scan.cpp +21 -3
- package/src/duckdb/src/execution/operator/schema/physical_alter.cpp +1 -0
- package/src/duckdb/src/execution/operator/schema/physical_attach.cpp +61 -43
- package/src/duckdb/src/execution/operator/schema/physical_create_art_index.cpp +15 -13
- package/src/duckdb/src/execution/operator/schema/physical_create_schema.cpp +1 -0
- package/src/duckdb/src/execution/operator/schema/physical_drop.cpp +10 -0
- package/src/duckdb/src/execution/operator/set/physical_cte.cpp +44 -90
- package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +3 -0
- package/src/duckdb/src/execution/operator/set/physical_union.cpp +8 -4
- package/src/duckdb/src/execution/physical_operator.cpp +3 -1
- package/src/duckdb/src/execution/physical_plan/plan_comparison_join.cpp +30 -143
- package/src/duckdb/src/execution/physical_plan/plan_copy_database.cpp +12 -0
- package/src/duckdb/src/execution/physical_plan/plan_copy_to_file.cpp +11 -4
- package/src/duckdb/src/execution/physical_plan/plan_create_index.cpp +8 -8
- package/src/duckdb/src/execution/physical_plan/plan_create_secret.cpp +11 -0
- package/src/duckdb/src/execution/physical_plan/plan_create_table.cpp +9 -8
- package/src/duckdb/src/execution/physical_plan/plan_cte.cpp +5 -3
- package/src/duckdb/src/execution/physical_plan/plan_delim_join.cpp +15 -6
- package/src/duckdb/src/execution/physical_plan/plan_positional_join.cpp +1 -0
- package/src/duckdb/src/execution/physical_plan/plan_pragma.cpp +1 -1
- package/src/duckdb/src/execution/physical_plan/plan_recursive_cte.cpp +3 -1
- package/src/duckdb/src/execution/physical_plan/plan_set_operation.cpp +90 -12
- package/src/duckdb/src/execution/physical_plan/plan_window.cpp +67 -22
- package/src/duckdb/src/execution/physical_plan_generator.cpp +6 -3
- package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +163 -32
- package/src/duckdb/src/execution/reservoir_sample.cpp +112 -32
- package/src/duckdb/src/execution/window_executor.cpp +291 -26
- package/src/duckdb/src/execution/window_segment_tree.cpp +958 -114
- package/src/duckdb/src/function/aggregate/distributive/count.cpp +18 -16
- package/src/duckdb/src/function/aggregate/distributive/first.cpp +11 -4
- package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp +303 -131
- package/src/duckdb/src/function/cast/array_casts.cpp +226 -0
- package/src/duckdb/src/function/cast/bit_cast.cpp +2 -0
- package/src/duckdb/src/function/cast/cast_function_set.cpp +13 -2
- package/src/duckdb/src/function/cast/decimal_cast.cpp +2 -0
- package/src/duckdb/src/function/cast/default_casts.cpp +4 -1
- package/src/duckdb/src/function/cast/list_casts.cpp +151 -6
- package/src/duckdb/src/function/cast/numeric_casts.cpp +4 -0
- package/src/duckdb/src/function/cast/string_cast.cpp +95 -5
- package/src/duckdb/src/function/cast/struct_cast.cpp +53 -19
- package/src/duckdb/src/function/cast/time_casts.cpp +23 -1
- package/src/duckdb/src/function/cast/union/from_struct.cpp +1 -0
- package/src/duckdb/src/function/cast/union_casts.cpp +4 -3
- package/src/duckdb/src/function/cast/vector_cast_helpers.cpp +8 -4
- package/src/duckdb/src/function/cast_rules.cpp +197 -31
- package/src/duckdb/src/function/compression_config.cpp +4 -0
- package/src/duckdb/src/function/function.cpp +15 -9
- package/src/duckdb/src/function/function_binder.cpp +80 -29
- package/src/duckdb/src/function/function_set.cpp +6 -6
- package/src/duckdb/src/function/pragma/pragma_functions.cpp +10 -8
- package/src/duckdb/src/function/pragma/pragma_queries.cpp +34 -38
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_integral.cpp +12 -0
- package/src/duckdb/src/function/scalar/list/contains_or_position.cpp +10 -1
- package/src/duckdb/src/function/scalar/list/list_concat.cpp +11 -1
- package/src/duckdb/src/function/scalar/list/list_extract.cpp +14 -3
- package/src/duckdb/src/function/scalar/list/list_resize.cpp +4 -0
- package/src/duckdb/src/function/scalar/list/list_select.cpp +176 -0
- package/src/duckdb/src/function/scalar/list/list_zip.cpp +165 -0
- package/src/duckdb/src/function/scalar/nested_functions.cpp +33 -0
- package/src/duckdb/src/function/scalar/operators/add.cpp +53 -6
- package/src/duckdb/src/function/scalar/operators/arithmetic.cpp +48 -14
- package/src/duckdb/src/function/scalar/operators/multiply.cpp +9 -1
- package/src/duckdb/src/function/scalar/operators/subtract.cpp +19 -4
- package/src/duckdb/src/function/scalar/sequence/nextval.cpp +28 -55
- package/src/duckdb/src/function/scalar/strftime_format.cpp +242 -19
- package/src/duckdb/src/function/scalar/string/caseconvert.cpp +2 -2
- package/src/duckdb/src/function/scalar/string/concat.cpp +16 -6
- package/src/duckdb/src/function/scalar/string/length.cpp +124 -24
- package/src/duckdb/src/function/scalar/string/regexp.cpp +27 -27
- package/src/duckdb/src/function/scalar/struct/struct_extract.cpp +64 -15
- package/src/duckdb/src/function/scalar/system/aggregate_export.cpp +4 -3
- package/src/duckdb/src/function/scalar_function.cpp +8 -7
- package/src/duckdb/src/function/table/arrow/arrow_duck_schema.cpp +12 -0
- package/src/duckdb/src/function/table/arrow.cpp +20 -27
- package/src/duckdb/src/function/table/arrow_conversion.cpp +433 -150
- package/src/duckdb/src/function/table/copy_csv.cpp +62 -62
- package/src/duckdb/src/function/table/range.cpp +6 -3
- package/src/duckdb/src/function/table/read_csv.cpp +107 -759
- package/src/duckdb/src/function/table/read_file.cpp +242 -0
- package/src/duckdb/src/function/table/sniff_csv.cpp +275 -0
- package/src/duckdb/src/function/table/system/duckdb_columns.cpp +15 -3
- package/src/duckdb/src/function/table/system/duckdb_databases.cpp +5 -0
- package/src/duckdb/src/function/table/system/duckdb_dependencies.cpp +9 -13
- package/src/duckdb/src/function/table/system/duckdb_functions.cpp +67 -14
- package/src/duckdb/src/function/table/system/duckdb_indexes.cpp +12 -15
- package/src/duckdb/src/function/table/system/duckdb_memory.cpp +63 -0
- package/src/duckdb/src/function/table/system/duckdb_optimizers.cpp +57 -0
- package/src/duckdb/src/function/table/system/duckdb_schemas.cpp +5 -0
- package/src/duckdb/src/function/table/system/duckdb_secrets.cpp +128 -0
- package/src/duckdb/src/function/table/system/duckdb_sequences.cpp +12 -6
- package/src/duckdb/src/function/table/system/duckdb_settings.cpp +0 -1
- package/src/duckdb/src/function/table/system/duckdb_tables.cpp +5 -0
- package/src/duckdb/src/function/table/system/duckdb_types.cpp +6 -0
- package/src/duckdb/src/function/table/system/duckdb_views.cpp +5 -0
- package/src/duckdb/src/function/table/system/pragma_table_info.cpp +166 -64
- package/src/duckdb/src/function/table/system/test_all_types.cpp +2 -1
- package/src/duckdb/src/function/table/system_functions.cpp +3 -2
- package/src/duckdb/src/function/table/table_scan.cpp +50 -110
- package/src/duckdb/src/function/table/version/pragma_version.cpp +4 -44
- package/src/duckdb/src/function/table_function.cpp +2 -2
- package/src/duckdb/src/include/duckdb/catalog/catalog.hpp +4 -3
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/dependency/dependency_dependent_entry.hpp +27 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/dependency/dependency_entry.hpp +66 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/dependency/dependency_subject_entry.hpp +27 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/duck_index_entry.hpp +25 -5
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/duck_schema_entry.hpp +3 -1
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/duck_table_entry.hpp +2 -1
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/index_catalog_entry.hpp +19 -5
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/scalar_macro_catalog_entry.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/schema_catalog_entry.hpp +1 -1
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/sequence_catalog_entry.hpp +26 -11
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/table_catalog_entry.hpp +1 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/table_macro_catalog_entry.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/type_catalog_entry.hpp +1 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/view_catalog_entry.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry.hpp +15 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_set.hpp +41 -49
- package/src/duckdb/src/include/duckdb/catalog/catalog_transaction.hpp +1 -0
- package/src/duckdb/src/include/duckdb/catalog/default/builtin_types/types.hpp +3 -1
- package/src/duckdb/src/include/duckdb/catalog/dependency.hpp +120 -8
- package/src/duckdb/src/include/duckdb/catalog/dependency_catalog_set.hpp +32 -0
- package/src/duckdb/src/include/duckdb/catalog/dependency_list.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/dependency_manager.hpp +92 -12
- package/src/duckdb/src/include/duckdb/catalog/standard_entry.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/adbc/adbc-init.hpp +4 -2
- package/src/duckdb/src/include/duckdb/common/adbc/adbc.h +1153 -12
- package/src/duckdb/src/include/duckdb/common/adbc/adbc.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/adbc/driver_manager.h +0 -2
- package/src/duckdb/src/include/duckdb/common/adbc/options.h +64 -0
- package/src/duckdb/src/include/duckdb/common/adbc/single_batch_array_stream.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/arrow/arrow.hpp +25 -6
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_wrapper.hpp +3 -3
- package/src/duckdb/src/include/duckdb/common/arrow/result_arrow_wrapper.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/bit_utils.hpp +30 -0
- package/src/duckdb/src/include/duckdb/common/bitpacking.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/case_insensitive_map.hpp +10 -0
- package/src/duckdb/src/include/duckdb/common/constants.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/enum_util.hpp +75 -19
- package/src/duckdb/src/include/duckdb/common/enums/catalog_type.hpp +11 -1
- package/src/duckdb/src/include/duckdb/common/enums/compression_type.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/enums/expression_type.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/enums/index_constraint_type.hpp +35 -0
- package/src/duckdb/src/include/duckdb/common/enums/join_type.hpp +16 -3
- package/src/duckdb/src/include/duckdb/common/enums/logical_operator_type.hpp +6 -5
- package/src/duckdb/src/include/duckdb/common/enums/memory_tag.hpp +32 -0
- package/src/duckdb/src/include/duckdb/common/enums/on_create_conflict.hpp +26 -0
- package/src/duckdb/src/include/duckdb/common/enums/optimizer_type.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/enums/pending_execution_result.hpp +7 -1
- package/src/duckdb/src/include/duckdb/common/enums/physical_operator_type.hpp +9 -3
- package/src/duckdb/src/include/duckdb/common/enums/statement_type.hpp +6 -5
- package/src/duckdb/src/include/duckdb/common/enums/tableref_type.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/enums/wal_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/error_data.hpp +72 -0
- package/src/duckdb/src/include/duckdb/common/exception/binder_exception.hpp +47 -0
- package/src/duckdb/src/include/duckdb/common/exception/catalog_exception.hpp +39 -0
- package/src/duckdb/src/include/duckdb/common/exception/conversion_exception.hpp +27 -0
- package/src/duckdb/src/include/duckdb/common/exception/http_exception.hpp +62 -0
- package/src/duckdb/src/include/duckdb/common/exception/list.hpp +6 -0
- package/src/duckdb/src/include/duckdb/common/exception/parser_exception.hpp +29 -0
- package/src/duckdb/src/include/duckdb/common/exception/transaction_exception.hpp +25 -0
- package/src/duckdb/src/include/duckdb/common/exception.hpp +52 -166
- package/src/duckdb/src/include/duckdb/common/exception_format_value.hpp +7 -4
- package/src/duckdb/src/include/duckdb/common/extra_type_info.hpp +53 -1
- package/src/duckdb/src/include/duckdb/common/helper.hpp +13 -3
- package/src/duckdb/src/include/duckdb/common/http_state.hpp +18 -4
- package/src/duckdb/src/include/duckdb/common/hugeint.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/limits.hpp +19 -1
- package/src/duckdb/src/include/duckdb/common/local_file_system.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/multi_file_reader.hpp +7 -2
- package/src/duckdb/src/include/duckdb/common/numeric_utils.hpp +16 -3
- package/src/duckdb/src/include/duckdb/common/operator/add.hpp +13 -2
- package/src/duckdb/src/include/duckdb/common/operator/cast_operators.hpp +114 -5
- package/src/duckdb/src/include/duckdb/common/operator/comparison_operators.hpp +0 -4
- package/src/duckdb/src/include/duckdb/common/operator/convert_to_string.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/operator/decimal_cast_operators.hpp +29 -0
- package/src/duckdb/src/include/duckdb/common/operator/double_cast_operator.hpp +52 -0
- package/src/duckdb/src/include/duckdb/common/operator/integer_cast_operator.hpp +459 -0
- package/src/duckdb/src/include/duckdb/common/operator/multiply.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/operator/numeric_cast.hpp +136 -0
- package/src/duckdb/src/include/duckdb/common/operator/string_cast.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/operator/subtract.hpp +7 -1
- package/src/duckdb/src/include/duckdb/common/optional_idx.hpp +7 -5
- package/src/duckdb/src/include/duckdb/common/platform.h +53 -0
- package/src/duckdb/src/include/duckdb/common/progress_bar/display/terminal_progress_bar_display.hpp +5 -5
- package/src/duckdb/src/include/duckdb/common/progress_bar/progress_bar.hpp +22 -6
- package/src/duckdb/src/include/duckdb/common/radix.hpp +6 -0
- package/src/duckdb/src/include/duckdb/common/row_operations/row_operations.hpp +20 -6
- package/src/duckdb/src/include/duckdb/common/serializer/binary_deserializer.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/serializer/binary_serializer.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/serializer/deserializer.hpp +43 -4
- package/src/duckdb/src/include/duckdb/common/serializer/serialization_traits.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/serializer/serializer.hpp +15 -0
- package/src/duckdb/src/include/duckdb/common/sort/comparators.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/sort/partition_state.hpp +12 -2
- package/src/duckdb/src/include/duckdb/common/sort/sort.hpp +81 -0
- package/src/duckdb/src/include/duckdb/common/sort/sorted_block.hpp +0 -78
- package/src/duckdb/src/include/duckdb/common/string_util.hpp +23 -1
- package/src/duckdb/src/include/duckdb/common/type_util.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/types/cast_helpers.hpp +26 -3
- package/src/duckdb/src/include/duckdb/common/types/conflict_manager.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/types/data_chunk.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/types/date.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/types/datetime.hpp +5 -3
- package/src/duckdb/src/include/duckdb/common/types/hash.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/types/hugeint.hpp +81 -15
- package/src/duckdb/src/include/duckdb/common/types/interval.hpp +57 -29
- package/src/duckdb/src/include/duckdb/common/types/list_segment.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +4 -2
- package/src/duckdb/src/include/duckdb/common/types/row/row_data_collection.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_collection.hpp +26 -22
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/string_type.hpp +7 -5
- package/src/duckdb/src/include/duckdb/common/types/time.hpp +6 -2
- package/src/duckdb/src/include/duckdb/common/types/timestamp.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/types/uhugeint.hpp +216 -0
- package/src/duckdb/src/include/duckdb/common/types/validity_mask.hpp +18 -10
- package/src/duckdb/src/include/duckdb/common/types/value.hpp +31 -0
- package/src/duckdb/src/include/duckdb/common/types/vector.hpp +18 -2
- package/src/duckdb/src/include/duckdb/common/types/vector_buffer.hpp +22 -1
- package/src/duckdb/src/include/duckdb/common/types.hpp +151 -49
- package/src/duckdb/src/include/duckdb/common/uhugeint.hpp +81 -0
- package/src/duckdb/src/include/duckdb/common/vector_operations/aggregate_executor.hpp +70 -6
- package/src/duckdb/src/include/duckdb/common/vector_size.hpp +6 -6
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/distributive_functions.hpp +29 -2
- package/src/duckdb/src/include/duckdb/core_functions/lambda_functions.hpp +131 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/array_functions.hpp +69 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/blob_functions.hpp +9 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/date_functions.hpp +40 -4
- package/src/duckdb/src/include/duckdb/core_functions/scalar/list_functions.hpp +42 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/secret_functions.hpp +27 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/string_functions.hpp +56 -2
- package/src/duckdb/src/include/duckdb/core_functions/to_interval.hpp +29 -0
- package/src/duckdb/src/include/duckdb/execution/aggregate_hashtable.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/executor.hpp +11 -13
- package/src/duckdb/src/include/duckdb/execution/index/art/art.hpp +34 -19
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_allocator.hpp +18 -14
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_buffer.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/index/index_type.hpp +57 -0
- package/src/duckdb/src/include/duckdb/execution/index/index_type_set.hpp +29 -0
- package/src/duckdb/src/include/duckdb/execution/index/unknown_index.hpp +65 -0
- package/src/duckdb/src/include/duckdb/execution/join_hashtable.hpp +35 -24
- package/src/duckdb/src/include/duckdb/execution/merge_sort_tree.hpp +630 -0
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_hash_aggregate.hpp +2 -0
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_window.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/buffer_manager/csv_buffer.hpp +103 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/buffer_manager/csv_buffer_manager.hpp +74 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/buffer_manager/csv_file_handle.hpp +60 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/options/csv_option.hpp +155 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/options/csv_reader_options.hpp +163 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/options/state_machine_options.hpp +35 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner/base_scanner.hpp +228 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner/column_count_scanner.hpp +70 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner/scanner_boundary.hpp +93 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner/skip_scanner.hpp +60 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner/string_value_scanner.hpp +197 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/sniffer/csv_sniffer.hpp +189 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/sniffer/quote_rules.hpp +21 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/state_machine/csv_state.hpp +30 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/state_machine/csv_state_machine.hpp +99 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/state_machine/csv_state_machine_cache.hpp +87 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/table_function/csv_file_scanner.hpp +70 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/table_function/global_csv_state.hpp +80 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/util/csv_casting.hpp +137 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/util/csv_error.hpp +104 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_batch_collector.hpp +0 -4
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_buffered_collector.hpp +37 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_create_secret.hpp +38 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_pragma.hpp +4 -7
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_reservoir_sample.hpp +6 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_blockwise_nl_join.hpp +1 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_delim_join.hpp +5 -18
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_hash_join.hpp +14 -5
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_iejoin.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_join.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_left_delim_join.hpp +37 -0
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_nested_loop_join.hpp +1 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_piecewise_merge_join.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_range_join.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_right_delim_join.hpp +37 -0
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_order.hpp +0 -1
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_top_n.hpp +0 -1
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_database.hpp +35 -0
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_to_file.hpp +8 -3
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_export.hpp +14 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_column_data_scan.hpp +1 -4
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_expression_scan.hpp +0 -1
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_cte.hpp +17 -12
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_recursive_cte.hpp +4 -0
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_union.hpp +3 -1
- package/src/duckdb/src/include/duckdb/execution/physical_operator.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/physical_plan_generator.hpp +6 -2
- package/src/duckdb/src/include/duckdb/execution/radix_partitioned_hashtable.hpp +3 -1
- package/src/duckdb/src/include/duckdb/execution/reservoir_sample.hpp +32 -18
- package/src/duckdb/src/include/duckdb/execution/task_error_manager.hpp +57 -0
- package/src/duckdb/src/include/duckdb/execution/window_executor.hpp +2 -0
- package/src/duckdb/src/include/duckdb/execution/window_segment_tree.hpp +101 -19
- package/src/duckdb/src/include/duckdb/function/aggregate_function.hpp +46 -14
- package/src/duckdb/src/include/duckdb/function/aggregate_state.hpp +6 -2
- package/src/duckdb/src/include/duckdb/function/built_in_functions.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/cast/bound_cast_data.hpp +26 -1
- package/src/duckdb/src/include/duckdb/function/cast/cast_function_set.hpp +3 -0
- package/src/duckdb/src/include/duckdb/function/cast/default_casts.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/cast/vector_cast_helpers.hpp +7 -1
- package/src/duckdb/src/include/duckdb/function/compression/compression.hpp +10 -0
- package/src/duckdb/src/include/duckdb/function/copy_function.hpp +16 -4
- package/src/duckdb/src/include/duckdb/function/function.hpp +12 -7
- package/src/duckdb/src/include/duckdb/function/function_binder.hpp +15 -12
- package/src/duckdb/src/include/duckdb/function/function_serialization.hpp +4 -3
- package/src/duckdb/src/include/duckdb/function/macro_function.hpp +3 -3
- package/src/duckdb/src/include/duckdb/function/pragma/pragma_functions.hpp +4 -1
- package/src/duckdb/src/include/duckdb/function/scalar/list/contains_or_position.hpp +3 -0
- package/src/duckdb/src/include/duckdb/function/scalar/nested_functions.hpp +21 -1
- package/src/duckdb/src/include/duckdb/function/scalar/sequence_functions.hpp +22 -0
- package/src/duckdb/src/include/duckdb/function/scalar/strftime_format.hpp +16 -2
- package/src/duckdb/src/include/duckdb/function/scalar_function.hpp +22 -8
- package/src/duckdb/src/include/duckdb/function/table/arrow/arrow_duck_schema.hpp +6 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow.hpp +35 -3
- package/src/duckdb/src/include/duckdb/function/table/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/table/range.hpp +12 -0
- package/src/duckdb/src/include/duckdb/function/table/read_csv.hpp +14 -16
- package/src/duckdb/src/include/duckdb/function/table/system_functions.hpp +12 -8
- package/src/duckdb/src/include/duckdb/function/table/table_scan.hpp +0 -2
- package/src/duckdb/src/include/duckdb/function/table_function.hpp +8 -3
- package/src/duckdb/src/include/duckdb/main/appender.hpp +3 -1
- package/src/duckdb/src/include/duckdb/main/attached_database.hpp +3 -2
- package/src/duckdb/src/include/duckdb/main/buffered_data/buffered_data.hpp +89 -0
- package/src/duckdb/src/include/duckdb/main/buffered_data/simple_buffered_data.hpp +53 -0
- package/src/duckdb/src/include/duckdb/main/capi/capi_internal.hpp +2 -1
- package/src/duckdb/src/include/duckdb/main/capi/cast/generic.hpp +2 -0
- package/src/duckdb/src/include/duckdb/main/chunk_scan_state/query_result.hpp +4 -4
- package/src/duckdb/src/include/duckdb/main/chunk_scan_state.hpp +3 -3
- package/src/duckdb/src/include/duckdb/main/client_config.hpp +8 -10
- package/src/duckdb/src/include/duckdb/main/client_context.hpp +22 -23
- package/src/duckdb/src/include/duckdb/main/client_context_state.hpp +37 -0
- package/src/duckdb/src/include/duckdb/main/client_data.hpp +1 -7
- package/src/duckdb/src/include/duckdb/main/config.hpp +24 -7
- package/src/duckdb/src/include/duckdb/main/connection.hpp +8 -1
- package/src/duckdb/src/include/duckdb/main/connection_manager.hpp +17 -26
- package/src/duckdb/src/include/duckdb/main/database.hpp +4 -2
- package/src/duckdb/src/include/duckdb/main/database_manager.hpp +39 -7
- package/src/duckdb/src/include/duckdb/main/database_path_and_type.hpp +5 -4
- package/src/duckdb/src/include/duckdb/main/error_manager.hpp +4 -1
- package/src/duckdb/src/include/duckdb/main/extension_entries.hpp +203 -197
- package/src/duckdb/src/include/duckdb/main/extension_helper.hpp +42 -16
- package/src/duckdb/src/include/duckdb/main/extension_util.hpp +8 -1
- package/src/duckdb/src/include/duckdb/main/materialized_query_result.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/pending_query_result.hpp +5 -2
- package/src/duckdb/src/include/duckdb/main/prepared_statement.hpp +4 -4
- package/src/duckdb/src/include/duckdb/main/prepared_statement_data.hpp +2 -0
- package/src/duckdb/src/include/duckdb/main/query_profiler.hpp +0 -32
- package/src/duckdb/src/include/duckdb/main/query_result.hpp +13 -12
- package/src/duckdb/src/include/duckdb/main/relation/read_csv_relation.hpp +6 -6
- package/src/duckdb/src/include/duckdb/main/relation/setop_relation.hpp +3 -1
- package/src/duckdb/src/include/duckdb/main/secret/secret.hpp +206 -0
- package/src/duckdb/src/include/duckdb/main/secret/secret_manager.hpp +211 -0
- package/src/duckdb/src/include/duckdb/main/secret/secret_storage.hpp +164 -0
- package/src/duckdb/src/include/duckdb/main/settings.hpp +52 -13
- package/src/duckdb/src/include/duckdb/main/stream_query_result.hpp +9 -1
- package/src/duckdb/src/include/duckdb/optimizer/deliminator.hpp +4 -1
- package/src/duckdb/src/include/duckdb/optimizer/filter_pushdown.hpp +2 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_node.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_relation.hpp +2 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/query_graph_manager.hpp +3 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/relation_statistics_helper.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parallel/event.hpp +2 -2
- package/src/duckdb/src/include/duckdb/parallel/meta_pipeline.hpp +14 -22
- package/src/duckdb/src/include/duckdb/parallel/pipeline.hpp +20 -0
- package/src/duckdb/src/include/duckdb/parallel/pipeline_executor.hpp +3 -5
- package/src/duckdb/src/include/duckdb/parallel/task.hpp +7 -0
- package/src/duckdb/src/include/duckdb/parallel/task_scheduler.hpp +10 -4
- package/src/duckdb/src/include/duckdb/parser/base_expression.hpp +3 -0
- package/src/duckdb/src/include/duckdb/parser/column_definition.hpp +8 -1
- package/src/duckdb/src/include/duckdb/parser/expression/function_expression.hpp +11 -4
- package/src/duckdb/src/include/duckdb/parser/expression/lambda_expression.hpp +16 -9
- package/src/duckdb/src/include/duckdb/parser/expression/lambdaref_expression.hpp +47 -0
- package/src/duckdb/src/include/duckdb/parser/expression/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/expression/window_expression.hpp +29 -2
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_info.hpp +2 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_table_info.hpp +47 -2
- package/src/duckdb/src/include/duckdb/parser/parsed_data/attach_info.hpp +3 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/bound_pragma_info.hpp +29 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/comment_on_info.hpp +45 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_index_info.hpp +21 -22
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_info.hpp +5 -11
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_schema_info.hpp +23 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_secret_info.hpp +47 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_table_info.hpp +3 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_type_info.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_view_info.hpp +4 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/drop_info.hpp +6 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/extra_drop_info.hpp +66 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/parse_info.hpp +3 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/pragma_info.hpp +8 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_expression.hpp +1 -3
- package/src/duckdb/src/include/duckdb/parser/parser_extension.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/qualified_name.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parser/query_error_context.hpp +5 -22
- package/src/duckdb/src/include/duckdb/parser/query_node/set_operation_node.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/statement/copy_database_statement.hpp +40 -0
- package/src/duckdb/src/include/duckdb/parser/statement/list.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parser/statement/set_statement.hpp +4 -3
- package/src/duckdb/src/include/duckdb/parser/tableref/emptytableref.hpp +2 -2
- package/src/duckdb/src/include/duckdb/parser/tableref/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/showref.hpp +47 -0
- package/src/duckdb/src/include/duckdb/parser/tableref.hpp +2 -1
- package/src/duckdb/src/include/duckdb/parser/tokens.hpp +2 -1
- package/src/duckdb/src/include/duckdb/parser/transformer.hpp +20 -3
- package/src/duckdb/src/include/duckdb/planner/bind_context.hpp +5 -1
- package/src/duckdb/src/include/duckdb/planner/binder.hpp +24 -27
- package/src/duckdb/src/include/duckdb/planner/bound_result_modifier.hpp +4 -0
- package/src/duckdb/src/include/duckdb/planner/expression/bound_cast_expression.hpp +4 -0
- package/src/duckdb/src/include/duckdb/planner/expression/bound_comparison_expression.hpp +4 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_function_expression.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_lambda_expression.hpp +4 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_lambdaref_expression.hpp +5 -6
- package/src/duckdb/src/include/duckdb/planner/expression/bound_window_expression.hpp +11 -0
- package/src/duckdb/src/include/duckdb/planner/expression.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/expression_binder/column_alias_binder.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression_binder/index_binder.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/expression_binder/order_binder.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/expression_binder/table_function_binder.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/expression_binder.hpp +65 -22
- package/src/duckdb/src/include/duckdb/planner/filter/struct_filter.hpp +41 -0
- package/src/duckdb/src/include/duckdb/planner/logical_tokens.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/operator/list.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_comparison_join.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_copy_database.hpp +45 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_copy_to_file.hpp +3 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_create_secret.hpp +43 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_cteref.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_pragma.hpp +5 -10
- package/src/duckdb/src/include/duckdb/planner/operator/logical_recursive_cte.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_set_operation.hpp +11 -4
- package/src/duckdb/src/include/duckdb/planner/parsed_data/bound_create_table_info.hpp +3 -3
- package/src/duckdb/src/include/duckdb/planner/pragma_handler.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/query_node/bound_set_operation_node.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/subquery/flatten_dependent_join.hpp +3 -0
- package/src/duckdb/src/include/duckdb/planner/subquery/rewrite_cte_scan.hpp +29 -0
- package/src/duckdb/src/include/duckdb/planner/table_binding.hpp +9 -7
- package/src/duckdb/src/include/duckdb/planner/table_filter.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_dummytableref.hpp +3 -2
- package/src/duckdb/src/include/duckdb/storage/buffer/block_handle.hpp +9 -5
- package/src/duckdb/src/include/duckdb/storage/buffer/buffer_pool.hpp +23 -6
- package/src/duckdb/src/include/duckdb/storage/buffer/temporary_file_information.hpp +7 -0
- package/src/duckdb/src/include/duckdb/storage/buffer_manager.hpp +11 -4
- package/src/duckdb/src/include/duckdb/storage/checkpoint/row_group_writer.hpp +0 -3
- package/src/duckdb/src/include/duckdb/storage/checkpoint/string_checkpoint_state.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/checkpoint/table_data_writer.hpp +7 -7
- package/src/duckdb/src/include/duckdb/storage/checkpoint_manager.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alp/algorithm/alp.hpp +408 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_analyze.hpp +173 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_compress.hpp +283 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_constants.hpp +134 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_fetch.hpp +42 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_scan.hpp +244 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_utils.hpp +103 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/algorithm/alprd.hpp +235 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_analyze.hpp +134 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_compress.hpp +301 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_constants.hpp +35 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_fetch.hpp +41 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_scan.hpp +252 -0
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/chimp_analyze.hpp +7 -103
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/chimp_compress.hpp +5 -234
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/chimp_scan.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/compression/patas/patas_analyze.hpp +7 -107
- package/src/duckdb/src/include/duckdb/storage/compression/patas/patas_compress.hpp +5 -184
- package/src/duckdb/src/include/duckdb/storage/data_table.hpp +12 -17
- package/src/duckdb/src/include/duckdb/storage/database_size.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/index.hpp +40 -42
- package/src/duckdb/src/include/duckdb/storage/index_storage_info.hpp +77 -0
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_manager.hpp +6 -2
- package/src/duckdb/src/include/duckdb/storage/object_cache.hpp +0 -1
- package/src/duckdb/src/include/duckdb/storage/partial_block_manager.hpp +12 -6
- package/src/duckdb/src/include/duckdb/storage/segment/uncompressed.hpp +8 -3
- package/src/duckdb/src/include/duckdb/storage/standard_buffer_manager.hpp +17 -17
- package/src/duckdb/src/include/duckdb/storage/statistics/array_stats.hpp +40 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/base_statistics.hpp +12 -3
- package/src/duckdb/src/include/duckdb/storage/statistics/numeric_stats_union.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/storage_extension.hpp +3 -2
- package/src/duckdb/src/include/duckdb/storage/storage_info.hpp +49 -24
- package/src/duckdb/src/include/duckdb/storage/storage_manager.hpp +8 -4
- package/src/duckdb/src/include/duckdb/storage/table/array_column_data.hpp +67 -0
- package/src/duckdb/src/include/duckdb/storage/table/column_data.hpp +3 -3
- package/src/duckdb/src/include/duckdb/storage/table/column_data_checkpointer.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/table/column_segment.hpp +1 -2
- package/src/duckdb/src/include/duckdb/storage/table/data_table_info.hpp +8 -3
- package/src/duckdb/src/include/duckdb/storage/table/list_column_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/row_group.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/table/row_group_collection.hpp +7 -0
- package/src/duckdb/src/include/duckdb/storage/table/scan_state.hpp +12 -1
- package/src/duckdb/src/include/duckdb/storage/table/standard_column_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/struct_column_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/table_index_list.hpp +16 -12
- package/src/duckdb/src/include/duckdb/storage/table/table_statistics.hpp +4 -0
- package/src/duckdb/src/include/duckdb/storage/table_storage_info.hpp +6 -9
- package/src/duckdb/src/include/duckdb/storage/temporary_memory_manager.hpp +119 -0
- package/src/duckdb/src/include/duckdb/storage/write_ahead_log.hpp +13 -55
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction.hpp +1 -1
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction_manager.hpp +4 -5
- package/src/duckdb/src/include/duckdb/transaction/local_storage.hpp +2 -2
- package/src/duckdb/src/include/duckdb/transaction/meta_transaction.hpp +6 -3
- package/src/duckdb/src/include/duckdb/transaction/transaction_context.hpp +4 -4
- package/src/duckdb/src/include/duckdb/transaction/transaction_manager.hpp +3 -3
- package/src/duckdb/src/include/duckdb/verification/fetch_row_verifier.hpp +25 -0
- package/src/duckdb/src/include/duckdb/verification/statement_verifier.hpp +5 -0
- package/src/duckdb/src/include/duckdb.h +571 -143
- package/src/duckdb/src/main/appender.cpp +17 -2
- package/src/duckdb/src/main/attached_database.cpp +24 -12
- package/src/duckdb/src/main/buffered_data/simple_buffered_data.cpp +96 -0
- package/src/duckdb/src/main/capi/appender-c.cpp +42 -3
- package/src/duckdb/src/main/capi/arrow-c.cpp +32 -9
- package/src/duckdb/src/main/capi/datetime-c.cpp +22 -0
- package/src/duckdb/src/main/capi/duckdb-c.cpp +14 -4
- package/src/duckdb/src/main/capi/duckdb_value-c.cpp +66 -2
- package/src/duckdb/src/main/capi/helper-c.cpp +76 -2
- package/src/duckdb/src/main/capi/hugeint-c.cpp +23 -0
- package/src/duckdb/src/main/capi/logical_types-c.cpp +27 -3
- package/src/duckdb/src/main/capi/pending-c.cpp +43 -9
- package/src/duckdb/src/main/capi/prepared-c.cpp +38 -2
- package/src/duckdb/src/main/capi/result-c.cpp +54 -3
- package/src/duckdb/src/main/capi/table_function-c.cpp +4 -4
- package/src/duckdb/src/main/capi/value-c.cpp +10 -0
- package/src/duckdb/src/main/chunk_scan_state/query_result.cpp +3 -3
- package/src/duckdb/src/main/client_context.cpp +259 -250
- package/src/duckdb/src/main/client_data.cpp +0 -1
- package/src/duckdb/src/main/client_verify.cpp +26 -8
- package/src/duckdb/src/main/config.cpp +34 -13
- package/src/duckdb/src/main/connection.cpp +27 -6
- package/src/duckdb/src/main/connection_manager.cpp +54 -0
- package/src/duckdb/src/main/database.cpp +44 -39
- package/src/duckdb/src/main/database_manager.cpp +106 -8
- package/src/duckdb/src/main/database_path_and_type.cpp +27 -8
- package/src/duckdb/src/main/db_instance_cache.cpp +4 -4
- package/src/duckdb/src/main/error_manager.cpp +12 -3
- package/src/duckdb/src/main/extension/extension_alias.cpp +2 -2
- package/src/duckdb/src/main/extension/extension_helper.cpp +15 -16
- package/src/duckdb/src/main/extension/extension_install.cpp +33 -24
- package/src/duckdb/src/main/extension/extension_load.cpp +22 -21
- package/src/duckdb/src/main/extension/extension_util.cpp +12 -0
- package/src/duckdb/src/main/materialized_query_result.cpp +1 -1
- package/src/duckdb/src/main/pending_query_result.cpp +25 -8
- package/src/duckdb/src/main/prepared_statement.cpp +5 -5
- package/src/duckdb/src/main/prepared_statement_data.cpp +8 -1
- package/src/duckdb/src/main/query_profiler.cpp +11 -11
- package/src/duckdb/src/main/query_result.cpp +32 -6
- package/src/duckdb/src/main/relation/cross_product_relation.cpp +1 -1
- package/src/duckdb/src/main/relation/join_relation.cpp +2 -2
- package/src/duckdb/src/main/relation/read_csv_relation.cpp +38 -32
- package/src/duckdb/src/main/relation/setop_relation.cpp +5 -3
- package/src/duckdb/src/main/relation.cpp +5 -5
- package/src/duckdb/src/main/secret/secret.cpp +135 -0
- package/src/duckdb/src/main/secret/secret_manager.cpp +634 -0
- package/src/duckdb/src/main/secret/secret_storage.cpp +233 -0
- package/src/duckdb/src/main/settings/settings.cpp +133 -38
- package/src/duckdb/src/main/stream_query_result.cpp +53 -14
- package/src/duckdb/src/optimizer/column_lifetime_analyzer.cpp +6 -0
- package/src/duckdb/src/optimizer/cse_optimizer.cpp +1 -1
- package/src/duckdb/src/optimizer/deliminator.cpp +136 -14
- package/src/duckdb/src/optimizer/filter_combiner.cpp +72 -26
- package/src/duckdb/src/optimizer/filter_pushdown.cpp +3 -0
- package/src/duckdb/src/optimizer/join_order/cardinality_estimator.cpp +2 -1
- package/src/duckdb/src/optimizer/join_order/cost_model.cpp +0 -1
- package/src/duckdb/src/optimizer/join_order/join_node.cpp +4 -0
- package/src/duckdb/src/optimizer/join_order/join_order_optimizer.cpp +3 -6
- package/src/duckdb/src/optimizer/join_order/join_relation_set.cpp +20 -0
- package/src/duckdb/src/optimizer/join_order/query_graph_manager.cpp +71 -40
- package/src/duckdb/src/optimizer/join_order/relation_manager.cpp +12 -3
- package/src/duckdb/src/optimizer/join_order/relation_statistics_helper.cpp +77 -3
- package/src/duckdb/src/optimizer/pushdown/pushdown_projection.cpp +7 -7
- package/src/duckdb/src/optimizer/pushdown/pushdown_semi_anti_join.cpp +56 -0
- package/src/duckdb/src/optimizer/remove_unused_columns.cpp +21 -0
- package/src/duckdb/src/optimizer/rule/date_part_simplification.cpp +2 -2
- package/src/duckdb/src/optimizer/rule/move_constants.cpp +15 -10
- package/src/duckdb/src/optimizer/rule/ordered_aggregate_optimizer.cpp +70 -0
- package/src/duckdb/src/optimizer/rule/regex_optimizations.cpp +17 -5
- package/src/duckdb/src/optimizer/statistics/expression/propagate_cast.cpp +1 -0
- package/src/duckdb/src/optimizer/statistics/expression/propagate_comparison.cpp +1 -0
- package/src/duckdb/src/optimizer/statistics/operator/propagate_filter.cpp +1 -2
- package/src/duckdb/src/optimizer/statistics/operator/propagate_join.cpp +22 -9
- package/src/duckdb/src/optimizer/statistics/operator/propagate_window.cpp +28 -4
- package/src/duckdb/src/optimizer/unnest_rewriter.cpp +12 -7
- package/src/duckdb/src/parallel/event.cpp +2 -2
- package/src/duckdb/src/parallel/executor.cpp +114 -81
- package/src/duckdb/src/parallel/executor_task.cpp +2 -4
- package/src/duckdb/src/parallel/meta_pipeline.cpp +28 -29
- package/src/duckdb/src/parallel/pipeline.cpp +41 -41
- package/src/duckdb/src/parallel/pipeline_event.cpp +2 -4
- package/src/duckdb/src/parallel/pipeline_executor.cpp +13 -75
- package/src/duckdb/src/parallel/task_scheduler.cpp +22 -13
- package/src/duckdb/src/parser/column_definition.cpp +22 -4
- package/src/duckdb/src/parser/column_list.cpp +2 -1
- package/src/duckdb/src/parser/expression/function_expression.cpp +1 -1
- package/src/duckdb/src/parser/expression/lambda_expression.cpp +51 -0
- package/src/duckdb/src/parser/expression/lambdaref_expression.cpp +59 -0
- package/src/duckdb/src/parser/expression/window_expression.cpp +9 -1
- package/src/duckdb/src/parser/parsed_data/alter_table_info.cpp +40 -0
- package/src/duckdb/src/parser/parsed_data/attach_info.cpp +1 -0
- package/src/duckdb/src/parser/parsed_data/comment_on_info.cpp +19 -0
- package/src/duckdb/src/parser/parsed_data/create_index_info.cpp +11 -9
- package/src/duckdb/src/parser/parsed_data/create_info.cpp +1 -0
- package/src/duckdb/src/parser/parsed_data/create_secret_info.cpp +22 -0
- package/src/duckdb/src/parser/parsed_data/create_table_info.cpp +17 -0
- package/src/duckdb/src/parser/parsed_data/create_type_info.cpp +19 -0
- package/src/duckdb/src/parser/parsed_data/create_view_info.cpp +13 -9
- package/src/duckdb/src/parser/parsed_data/drop_info.cpp +8 -9
- package/src/duckdb/src/parser/parsed_data/extra_drop_info.cpp +16 -0
- package/src/duckdb/src/parser/parsed_expression_iterator.cpp +3 -1
- package/src/duckdb/src/parser/parser.cpp +14 -8
- package/src/duckdb/src/parser/query_error_context.cpp +12 -13
- package/src/duckdb/src/parser/query_node/select_node.cpp +5 -1
- package/src/duckdb/src/parser/query_node/set_operation_node.cpp +8 -13
- package/src/duckdb/src/parser/statement/copy_database_statement.cpp +41 -0
- package/src/duckdb/src/parser/statement/set_statement.cpp +5 -1
- package/src/duckdb/src/parser/tableref/basetableref.cpp +1 -0
- package/src/duckdb/src/parser/tableref/showref.cpp +47 -0
- package/src/duckdb/src/parser/transform/constraint/transform_constraint.cpp +6 -2
- package/src/duckdb/src/parser/transform/expression/transform_bool_expr.cpp +1 -0
- package/src/duckdb/src/parser/transform/expression/transform_boolean_test.cpp +30 -15
- package/src/duckdb/src/parser/transform/expression/transform_case.cpp +1 -0
- package/src/duckdb/src/parser/transform/expression/transform_columnref.cpp +3 -2
- package/src/duckdb/src/parser/transform/expression/transform_constant.cpp +34 -4
- package/src/duckdb/src/parser/transform/expression/transform_function.cpp +26 -12
- package/src/duckdb/src/parser/transform/expression/transform_grouping_function.cpp +1 -1
- package/src/duckdb/src/parser/transform/expression/transform_interval.cpp +34 -5
- package/src/duckdb/src/parser/transform/expression/transform_is_null.cpp +3 -1
- package/src/duckdb/src/parser/transform/expression/transform_lambda.cpp +3 -1
- package/src/duckdb/src/parser/transform/expression/transform_multi_assign_reference.cpp +3 -3
- package/src/duckdb/src/parser/transform/expression/transform_operator.cpp +3 -3
- package/src/duckdb/src/parser/transform/expression/transform_positional_reference.cpp +1 -1
- package/src/duckdb/src/parser/transform/expression/transform_subquery.cpp +13 -13
- package/src/duckdb/src/parser/transform/helpers/nodetype_to_string.cpp +2 -0
- package/src/duckdb/src/parser/transform/helpers/transform_cte.cpp +1 -1
- package/src/duckdb/src/parser/transform/helpers/transform_typename.cpp +32 -1
- package/src/duckdb/src/parser/transform/statement/transform_alter_table.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_attach.cpp +1 -0
- package/src/duckdb/src/parser/transform/statement/transform_comment_on.cpp +108 -0
- package/src/duckdb/src/parser/transform/statement/transform_copy.cpp +45 -37
- package/src/duckdb/src/parser/transform/statement/transform_copy_database.cpp +29 -0
- package/src/duckdb/src/parser/transform/statement/transform_create_index.cpp +5 -14
- package/src/duckdb/src/parser/transform/statement/transform_create_table.cpp +0 -1
- package/src/duckdb/src/parser/transform/statement/transform_delete.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_drop.cpp +25 -6
- package/src/duckdb/src/parser/transform/statement/transform_import.cpp +2 -1
- package/src/duckdb/src/parser/transform/statement/transform_pragma.cpp +6 -14
- package/src/duckdb/src/parser/transform/statement/transform_secret.cpp +103 -0
- package/src/duckdb/src/parser/transform/statement/transform_select.cpp +8 -1
- package/src/duckdb/src/parser/transform/statement/transform_select_node.cpp +4 -8
- package/src/duckdb/src/parser/transform/statement/transform_set.cpp +18 -5
- package/src/duckdb/src/parser/transform/statement/transform_show.cpp +14 -41
- package/src/duckdb/src/parser/transform/statement/transform_show_select.cpp +13 -6
- package/src/duckdb/src/parser/transform/statement/transform_use.cpp +3 -1
- package/src/duckdb/src/parser/transform/tableref/transform_base_tableref.cpp +1 -1
- package/src/duckdb/src/parser/transform/tableref/transform_join.cpp +1 -2
- package/src/duckdb/src/parser/transform/tableref/transform_pivot.cpp +6 -5
- package/src/duckdb/src/parser/transform/tableref/transform_table_function.cpp +1 -1
- package/src/duckdb/src/parser/transformer.cpp +22 -0
- package/src/duckdb/src/planner/bind_context.cpp +23 -14
- package/src/duckdb/src/planner/binder/expression/bind_aggregate_expression.cpp +15 -14
- package/src/duckdb/src/planner/binder/expression/bind_between_expression.cpp +20 -9
- package/src/duckdb/src/planner/binder/expression/bind_case_expression.cpp +12 -7
- package/src/duckdb/src/planner/binder/expression/bind_cast_expression.cpp +4 -4
- package/src/duckdb/src/planner/binder/expression/bind_collate_expression.cpp +3 -3
- package/src/duckdb/src/planner/binder/expression/bind_columnref_expression.cpp +279 -195
- package/src/duckdb/src/planner/binder/expression/bind_comparison_expression.cpp +103 -17
- package/src/duckdb/src/planner/binder/expression/bind_conjunction_expression.cpp +3 -3
- package/src/duckdb/src/planner/binder/expression/bind_function_expression.cpp +91 -68
- package/src/duckdb/src/planner/binder/expression/bind_lambda.cpp +116 -84
- package/src/duckdb/src/planner/binder/expression/bind_macro_expression.cpp +85 -15
- package/src/duckdb/src/planner/binder/expression/bind_operator_expression.cpp +68 -31
- package/src/duckdb/src/planner/binder/expression/bind_star_expression.cpp +7 -7
- package/src/duckdb/src/planner/binder/expression/bind_subquery_expression.cpp +11 -7
- package/src/duckdb/src/planner/binder/expression/bind_unnest_expression.cpp +42 -19
- package/src/duckdb/src/planner/binder/expression/bind_window_expression.cpp +38 -16
- package/src/duckdb/src/planner/binder/query_node/bind_cte_node.cpp +16 -7
- package/src/duckdb/src/planner/binder/query_node/bind_recursive_cte_node.cpp +3 -0
- package/src/duckdb/src/planner/binder/query_node/bind_select_node.cpp +83 -12
- package/src/duckdb/src/planner/binder/query_node/bind_setop_node.cpp +28 -37
- package/src/duckdb/src/planner/binder/query_node/bind_table_macro_node.cpp +3 -4
- package/src/duckdb/src/planner/binder/query_node/plan_cte_node.cpp +2 -2
- package/src/duckdb/src/planner/binder/query_node/plan_recursive_cte_node.cpp +3 -3
- package/src/duckdb/src/planner/binder/query_node/plan_setop.cpp +7 -5
- package/src/duckdb/src/planner/binder/query_node/plan_subquery.cpp +10 -0
- package/src/duckdb/src/planner/binder/statement/bind_copy.cpp +48 -50
- package/src/duckdb/src/planner/binder/statement/bind_copy_database.cpp +187 -0
- package/src/duckdb/src/planner/binder/statement/bind_create.cpp +38 -22
- package/src/duckdb/src/planner/binder/statement/bind_create_table.cpp +8 -15
- package/src/duckdb/src/planner/binder/statement/bind_drop.cpp +6 -1
- package/src/duckdb/src/planner/binder/statement/bind_export.cpp +2 -2
- package/src/duckdb/src/planner/binder/statement/bind_insert.cpp +12 -10
- package/src/duckdb/src/planner/binder/statement/bind_pragma.cpp +37 -13
- package/src/duckdb/src/planner/binder/statement/bind_set.cpp +8 -2
- package/src/duckdb/src/planner/binder/statement/bind_simple.cpp +2 -0
- package/src/duckdb/src/planner/binder/statement/bind_summarize.cpp +29 -14
- package/src/duckdb/src/planner/binder/statement/bind_vacuum.cpp +1 -1
- package/src/duckdb/src/planner/binder/tableref/bind_basetableref.cpp +16 -6
- package/src/duckdb/src/planner/binder/tableref/bind_expressionlistref.cpp +11 -4
- package/src/duckdb/src/planner/binder/tableref/bind_joinref.cpp +1 -1
- package/src/duckdb/src/planner/binder/tableref/bind_named_parameters.cpp +2 -2
- package/src/duckdb/src/planner/binder/tableref/bind_pivot.cpp +18 -17
- package/src/duckdb/src/planner/binder/tableref/bind_showref.cpp +85 -0
- package/src/duckdb/src/planner/binder/tableref/bind_table_function.cpp +11 -17
- package/src/duckdb/src/planner/binder/tableref/plan_cteref.cpp +1 -9
- package/src/duckdb/src/planner/binder.cpp +31 -26
- package/src/duckdb/src/planner/bound_result_modifier.cpp +24 -0
- package/src/duckdb/src/planner/expression/bound_aggregate_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_cast_expression.cpp +10 -1
- package/src/duckdb/src/planner/expression/bound_function_expression.cpp +20 -4
- package/src/duckdb/src/planner/expression/bound_lambdaref_expression.cpp +9 -10
- package/src/duckdb/src/planner/expression/bound_window_expression.cpp +65 -3
- package/src/duckdb/src/planner/expression.cpp +15 -5
- package/src/duckdb/src/planner/expression_binder/base_select_binder.cpp +5 -6
- package/src/duckdb/src/planner/expression_binder/check_binder.cpp +9 -8
- package/src/duckdb/src/planner/expression_binder/column_alias_binder.cpp +10 -7
- package/src/duckdb/src/planner/expression_binder/having_binder.cpp +9 -4
- package/src/duckdb/src/planner/expression_binder/index_binder.cpp +0 -25
- package/src/duckdb/src/planner/expression_binder/order_binder.cpp +8 -11
- package/src/duckdb/src/planner/expression_binder/qualify_binder.cpp +3 -2
- package/src/duckdb/src/planner/expression_binder/table_function_binder.cpp +15 -8
- package/src/duckdb/src/planner/expression_binder/where_binder.cpp +3 -4
- package/src/duckdb/src/planner/expression_binder.cpp +51 -25
- package/src/duckdb/src/planner/expression_iterator.cpp +2 -1
- package/src/duckdb/src/planner/filter/constant_filter.cpp +1 -0
- package/src/duckdb/src/planner/filter/struct_filter.cpp +33 -0
- package/src/duckdb/src/planner/joinside.cpp +1 -1
- package/src/duckdb/src/planner/logical_operator.cpp +2 -1
- package/src/duckdb/src/planner/operator/logical_copy_database.cpp +32 -0
- package/src/duckdb/src/planner/operator/logical_copy_to_file.cpp +13 -4
- package/src/duckdb/src/planner/operator/logical_create_table.cpp +2 -0
- package/src/duckdb/src/planner/operator/logical_get.cpp +4 -1
- package/src/duckdb/src/planner/operator/logical_join.cpp +8 -0
- package/src/duckdb/src/planner/planner.cpp +24 -23
- package/src/duckdb/src/planner/pragma_handler.cpp +10 -19
- package/src/duckdb/src/planner/subquery/flatten_dependent_join.cpp +99 -6
- package/src/duckdb/src/planner/subquery/rewrite_cte_scan.cpp +36 -0
- package/src/duckdb/src/planner/table_binding.cpp +14 -12
- package/src/duckdb/src/storage/buffer/block_handle.cpp +12 -10
- package/src/duckdb/src/storage/buffer/block_manager.cpp +1 -1
- package/src/duckdb/src/storage/buffer/buffer_pool.cpp +25 -9
- package/src/duckdb/src/storage/buffer/buffer_pool_reservation.cpp +4 -3
- package/src/duckdb/src/storage/buffer_manager.cpp +14 -3
- package/src/duckdb/src/storage/checkpoint/row_group_writer.cpp +0 -8
- package/src/duckdb/src/storage/checkpoint/table_data_writer.cpp +15 -7
- package/src/duckdb/src/storage/checkpoint/write_overflow_strings_to_disk.cpp +1 -1
- package/src/duckdb/src/storage/checkpoint_manager.cpp +94 -41
- package/src/duckdb/src/storage/compression/alp/alp.cpp +57 -0
- package/src/duckdb/src/storage/compression/alp/alp_constants.cpp +13 -0
- package/src/duckdb/src/storage/compression/alprd.cpp +57 -0
- package/src/duckdb/src/storage/compression/bitpacking.cpp +86 -55
- package/src/duckdb/src/storage/compression/bitpacking_hugeint.cpp +41 -41
- package/src/duckdb/src/storage/compression/dictionary_compression.cpp +1 -3
- package/src/duckdb/src/storage/compression/fixed_size_uncompressed.cpp +2 -0
- package/src/duckdb/src/storage/compression/fsst.cpp +4 -4
- package/src/duckdb/src/storage/compression/numeric_constant.cpp +3 -0
- package/src/duckdb/src/storage/compression/rle.cpp +6 -4
- package/src/duckdb/src/storage/compression/string_uncompressed.cpp +7 -7
- package/src/duckdb/src/storage/compression/uncompressed.cpp +1 -0
- package/src/duckdb/src/storage/compression/validity_uncompressed.cpp +6 -6
- package/src/duckdb/src/storage/data_table.cpp +32 -96
- package/src/duckdb/src/storage/index.cpp +23 -11
- package/src/duckdb/src/storage/local_storage.cpp +36 -19
- package/src/duckdb/src/storage/metadata/metadata_manager.cpp +2 -2
- package/src/duckdb/src/storage/partial_block_manager.cpp +1 -1
- package/src/duckdb/src/storage/serialization/serialize_create_info.cpp +9 -4
- package/src/duckdb/src/storage/serialization/serialize_expression.cpp +3 -3
- package/src/duckdb/src/storage/serialization/serialize_extra_drop_info.cpp +42 -0
- package/src/duckdb/src/storage/serialization/serialize_logical_operator.cpp +7 -17
- package/src/duckdb/src/storage/serialization/serialize_macro_function.cpp +2 -2
- package/src/duckdb/src/storage/serialization/serialize_nodes.cpp +84 -77
- package/src/duckdb/src/storage/serialization/serialize_parse_info.cpp +63 -4
- package/src/duckdb/src/storage/serialization/serialize_parsed_expression.cpp +23 -0
- package/src/duckdb/src/storage/serialization/serialize_query_node.cpp +2 -0
- package/src/duckdb/src/storage/serialization/serialize_storage.cpp +35 -0
- package/src/duckdb/src/storage/serialization/serialize_table_filter.cpp +19 -0
- package/src/duckdb/src/storage/serialization/serialize_tableref.cpp +22 -1
- package/src/duckdb/src/storage/serialization/serialize_types.cpp +50 -0
- package/src/duckdb/src/storage/single_file_block_manager.cpp +46 -7
- package/src/duckdb/src/storage/standard_buffer_manager.cpp +57 -28
- package/src/duckdb/src/storage/statistics/array_stats.cpp +131 -0
- package/src/duckdb/src/storage/statistics/base_statistics.cpp +62 -4
- package/src/duckdb/src/storage/statistics/column_statistics.cpp +1 -0
- package/src/duckdb/src/storage/statistics/distinct_statistics.cpp +3 -1
- package/src/duckdb/src/storage/statistics/numeric_stats.cpp +21 -0
- package/src/duckdb/src/storage/statistics/numeric_stats_union.cpp +5 -0
- package/src/duckdb/src/storage/statistics/string_stats.cpp +2 -2
- package/src/duckdb/src/storage/storage_info.cpp +1 -1
- package/src/duckdb/src/storage/storage_manager.cpp +47 -22
- package/src/duckdb/src/storage/table/array_column_data.cpp +241 -0
- package/src/duckdb/src/storage/table/chunk_info.cpp +2 -1
- package/src/duckdb/src/storage/table/column_checkpoint_state.cpp +3 -1
- package/src/duckdb/src/storage/table/column_data.cpp +41 -18
- package/src/duckdb/src/storage/table/column_data_checkpointer.cpp +12 -3
- package/src/duckdb/src/storage/table/column_segment.cpp +40 -6
- package/src/duckdb/src/storage/table/list_column_data.cpp +18 -15
- package/src/duckdb/src/storage/table/row_group.cpp +73 -21
- package/src/duckdb/src/storage/table/row_group_collection.cpp +395 -20
- package/src/duckdb/src/storage/table/row_version_manager.cpp +2 -1
- package/src/duckdb/src/storage/table/scan_state.cpp +4 -0
- package/src/duckdb/src/storage/table/standard_column_data.cpp +11 -5
- package/src/duckdb/src/storage/table/struct_column_data.cpp +30 -10
- package/src/duckdb/src/storage/table/table_statistics.cpp +7 -1
- package/src/duckdb/src/storage/table/update_segment.cpp +18 -2
- package/src/duckdb/src/storage/table_index_list.cpp +73 -7
- package/src/duckdb/src/storage/temporary_memory_manager.cpp +148 -0
- package/src/duckdb/src/storage/wal_replay.cpp +329 -152
- package/src/duckdb/src/storage/write_ahead_log.cpp +157 -137
- package/src/duckdb/src/transaction/cleanup_state.cpp +3 -2
- package/src/duckdb/src/transaction/commit_state.cpp +89 -63
- package/src/duckdb/src/transaction/duck_transaction.cpp +5 -3
- package/src/duckdb/src/transaction/duck_transaction_manager.cpp +26 -54
- package/src/duckdb/src/transaction/meta_transaction.cpp +37 -23
- package/src/duckdb/src/transaction/transaction_context.cpp +23 -4
- package/src/duckdb/src/transaction/undo_buffer.cpp +16 -2
- package/src/duckdb/src/verification/fetch_row_verifier.cpp +13 -0
- package/src/duckdb/src/verification/prepared_statement_verifier.cpp +5 -7
- package/src/duckdb/src/verification/statement_verifier.cpp +6 -5
- package/src/duckdb/third_party/fast_float/fast_float/fast_float.h +100 -29
- package/src/duckdb/third_party/fmt/include/fmt/format-inl.h +1 -1
- package/src/duckdb/third_party/fmt/include/fmt/format.h +4 -2
- package/src/duckdb/third_party/fmt/include/fmt/printf.h +5 -5
- package/src/duckdb/third_party/libpg_query/include/nodes/nodes.hpp +4 -0
- package/src/duckdb/third_party/libpg_query/include/nodes/parsenodes.hpp +82 -21
- package/src/duckdb/third_party/libpg_query/include/parser/gram.hpp +551 -1004
- package/src/duckdb/third_party/libpg_query/include/parser/kwlist.hpp +17 -3
- package/src/duckdb/third_party/libpg_query/src_backend_parser_gram.cpp +24861 -23465
- package/src/duckdb/third_party/libpg_query/src_backend_parser_scan.cpp +420 -389
- package/src/duckdb/third_party/mbedtls/include/mbedtls/aes.h +640 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/aes_alt.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/aria.h +358 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/aria_alt.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/camellia.h +316 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/camellia_alt.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/ccm.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/ccm_alt.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/chacha20.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/chachapoly.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/cipher.h +124 -124
- package/src/duckdb/third_party/mbedtls/include/mbedtls/cmac.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/entropy.h +293 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/gcm.h +383 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/gcm_alt.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/mbedtls_config.h +9 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/nist_kw.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls/timing.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls_wrapper.hpp +35 -6
- package/src/duckdb/third_party/mbedtls/library/aes.cpp +2171 -0
- package/src/duckdb/third_party/mbedtls/library/aesni.h +1 -0
- package/src/duckdb/third_party/mbedtls/library/aria.cpp +1058 -0
- package/src/duckdb/third_party/mbedtls/library/camellia.cpp +1087 -0
- package/src/duckdb/third_party/mbedtls/library/cipher.cpp +1633 -0
- package/src/duckdb/third_party/mbedtls/library/cipher_wrap.cpp +2270 -0
- package/src/duckdb/third_party/mbedtls/library/cipher_wrap.h +146 -0
- package/src/duckdb/third_party/mbedtls/library/entropy.cpp +701 -0
- package/src/duckdb/third_party/mbedtls/library/entropy_poll.cpp +237 -0
- package/src/duckdb/third_party/mbedtls/library/entropy_poll.h +76 -0
- package/src/duckdb/third_party/mbedtls/library/gcm.cpp +1161 -0
- package/src/duckdb/third_party/mbedtls/library/padlock.h +1 -0
- package/src/duckdb/third_party/mbedtls/mbedtls_wrapper.cpp +132 -24
- package/src/duckdb/third_party/pcg/pcg_uint128.hpp +1 -1
- package/src/duckdb/third_party/skiplist/HeadNode.h +934 -0
- package/src/duckdb/third_party/skiplist/IntegrityEnums.h +62 -0
- package/src/duckdb/third_party/skiplist/Node.h +641 -0
- package/src/duckdb/third_party/skiplist/NodeRefs.h +251 -0
- package/src/duckdb/third_party/skiplist/RollingMedian.h +202 -0
- package/src/duckdb/third_party/skiplist/SkipList.cpp +40 -0
- package/src/duckdb/third_party/skiplist/SkipList.h +549 -0
- package/src/duckdb/third_party/thrift/thrift/thrift-config.h +1 -1
- package/src/duckdb/ub_extension_json_json_functions.cpp +2 -0
- package/src/duckdb/ub_src_catalog.cpp +3 -1
- package/src/duckdb/ub_src_catalog_catalog_entry_dependency.cpp +6 -0
- package/src/duckdb/ub_src_common.cpp +1 -1
- package/src/duckdb/ub_src_common_exception.cpp +6 -0
- package/src/duckdb/ub_src_common_types.cpp +2 -2
- package/src/duckdb/ub_src_core_functions.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_array.cpp +4 -0
- package/src/duckdb/ub_src_core_functions_scalar_blob.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_list.cpp +7 -3
- package/src/duckdb/ub_src_core_functions_scalar_secret.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_string.cpp +4 -0
- package/src/duckdb/ub_src_execution_index.cpp +4 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_buffer_manager.cpp +6 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_scanner.cpp +10 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_state_machine.cpp +4 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_table_function.cpp +4 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_util.cpp +4 -0
- package/src/duckdb/ub_src_execution_operator_helper.cpp +4 -0
- package/src/duckdb/ub_src_execution_operator_join.cpp +4 -2
- package/src/duckdb/ub_src_execution_operator_persistent.cpp +2 -0
- package/src/duckdb/ub_src_execution_physical_plan.cpp +4 -2
- package/src/duckdb/ub_src_function_cast.cpp +2 -0
- package/src/duckdb/ub_src_function_scalar_list.cpp +4 -0
- package/src/duckdb/ub_src_function_table.cpp +4 -4
- package/src/duckdb/ub_src_function_table_system.cpp +6 -0
- package/src/duckdb/ub_src_main.cpp +2 -0
- package/src/duckdb/ub_src_main_buffered_data.cpp +2 -0
- package/src/duckdb/ub_src_main_secret.cpp +6 -0
- package/src/duckdb/ub_src_optimizer_pushdown.cpp +2 -0
- package/src/duckdb/ub_src_parser_expression.cpp +2 -0
- package/src/duckdb/ub_src_parser_parsed_data.cpp +6 -0
- package/src/duckdb/ub_src_parser_statement.cpp +2 -2
- package/src/duckdb/ub_src_parser_tableref.cpp +2 -0
- package/src/duckdb/ub_src_parser_transform_statement.cpp +6 -0
- package/src/duckdb/ub_src_planner_binder_statement.cpp +2 -2
- package/src/duckdb/ub_src_planner_binder_tableref.cpp +2 -0
- package/src/duckdb/ub_src_planner_filter.cpp +2 -0
- package/src/duckdb/ub_src_planner_operator.cpp +2 -0
- package/src/duckdb/ub_src_planner_subquery.cpp +2 -0
- package/src/duckdb/ub_src_storage.cpp +2 -0
- package/src/duckdb/ub_src_storage_compression.cpp +2 -0
- package/src/duckdb/ub_src_storage_compression_alp.cpp +4 -0
- package/src/duckdb/ub_src_storage_serialization.cpp +2 -0
- package/src/duckdb/ub_src_storage_statistics.cpp +2 -0
- package/src/duckdb/ub_src_storage_table.cpp +2 -0
- package/src/duckdb_node.hpp +1 -1
- package/src/statement.cpp +18 -8
- package/src/utils.cpp +1 -15
- package/test/affected.test.ts +2 -2
- package/test/columns.test.ts +4 -3
- package/test/config.test.ts +30 -0
- package/test/each.test.ts +2 -2
- package/test/exec.test.ts +2 -2
- package/test/named_columns.test.ts +2 -2
- package/test/null_error.test.ts +2 -2
- package/test/prepare.test.ts +28 -26
- package/test/serialization.test.ts +7 -6
- package/test/test_all_types.test.ts +9 -4
- package/test/typescript_decls.test.ts +6 -6
- package/test/udf.test.ts +23 -23
- package/test/unicode.test.ts +2 -2
@@ -1,5 +1,6 @@
|
|
1
1
|
#include "duckdb/common/types/cast_helpers.hpp"
|
2
|
-
#include "duckdb/execution/operator/
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/sniffer/csv_sniffer.hpp"
|
3
|
+
#include "duckdb/execution/operator/csv_scanner/options/csv_reader_options.hpp"
|
3
4
|
#include "utf8proc.hpp"
|
4
5
|
|
5
6
|
namespace duckdb {
|
@@ -93,18 +94,31 @@ static string NormalizeColumnName(const string &col_name) {
|
|
93
94
|
return col_name_cleaned;
|
94
95
|
}
|
95
96
|
void CSVSniffer::DetectHeader() {
|
97
|
+
auto &sniffer_state_machine = best_candidate->GetStateMachine();
|
98
|
+
|
99
|
+
if (best_header_row.empty()) {
|
100
|
+
sniffer_state_machine.dialect_options.header = false;
|
101
|
+
for (idx_t col = 0; col < sniffer_state_machine.dialect_options.num_cols; col++) {
|
102
|
+
names.push_back(GenerateColumnName(sniffer_state_machine.dialect_options.num_cols, col));
|
103
|
+
}
|
104
|
+
// If the user provided names, we must replace our header with the user provided names
|
105
|
+
for (idx_t i = 0; i < MinValue<idx_t>(names.size(), sniffer_state_machine.options.name_list.size()); i++) {
|
106
|
+
names[i] = sniffer_state_machine.options.name_list[i];
|
107
|
+
}
|
108
|
+
return;
|
109
|
+
}
|
96
110
|
// information for header detection
|
97
111
|
bool first_row_consistent = true;
|
98
112
|
// check if header row is all null and/or consistent with detected column data types
|
99
113
|
bool first_row_nulls = true;
|
100
114
|
// If null-padding is not allowed and there is a mismatch between our header candidate and the number of columns
|
101
115
|
// We can't detect the dialect/type options properly
|
102
|
-
if (!
|
116
|
+
if (!sniffer_state_machine.options.null_padding &&
|
103
117
|
best_sql_types_candidates_per_column_idx.size() != best_header_row.size()) {
|
104
|
-
|
105
|
-
|
106
|
-
options.file_path);
|
118
|
+
auto error = CSVError::SniffingError(options.file_path);
|
119
|
+
error_handler->Error(error);
|
107
120
|
}
|
121
|
+
bool all_varchar = true;
|
108
122
|
for (idx_t col = 0; col < best_header_row.size(); col++) {
|
109
123
|
auto dummy_val = best_header_row[col];
|
110
124
|
if (!dummy_val.IsNull()) {
|
@@ -113,19 +127,29 @@ void CSVSniffer::DetectHeader() {
|
|
113
127
|
|
114
128
|
// try cast to sql_type of column
|
115
129
|
const auto &sql_type = best_sql_types_candidates_per_column_idx[col].back();
|
116
|
-
if (
|
117
|
-
|
130
|
+
if (sql_type != LogicalType::VARCHAR) {
|
131
|
+
all_varchar = false;
|
132
|
+
if (!TryCastValue(sniffer_state_machine, dummy_val, sql_type)) {
|
133
|
+
first_row_consistent = false;
|
134
|
+
}
|
118
135
|
}
|
119
136
|
}
|
120
137
|
bool has_header;
|
121
|
-
if (!
|
122
|
-
has_header = !first_row_consistent || first_row_nulls;
|
138
|
+
if (!sniffer_state_machine.options.dialect_options.header.IsSetByUser()) {
|
139
|
+
has_header = (!first_row_consistent || first_row_nulls) && !all_varchar;
|
123
140
|
} else {
|
124
|
-
has_header =
|
141
|
+
has_header = sniffer_state_machine.options.dialect_options.header.GetValue();
|
125
142
|
}
|
126
143
|
// update parser info, and read, generate & set col_names based on previous findings
|
127
144
|
if (has_header) {
|
128
|
-
|
145
|
+
sniffer_state_machine.dialect_options.header = true;
|
146
|
+
if (sniffer_state_machine.options.null_padding &&
|
147
|
+
!sniffer_state_machine.options.dialect_options.skip_rows.IsSetByUser()) {
|
148
|
+
if (sniffer_state_machine.dialect_options.skip_rows.GetValue() > 0) {
|
149
|
+
sniffer_state_machine.dialect_options.skip_rows =
|
150
|
+
sniffer_state_machine.dialect_options.skip_rows.GetValue() - 1;
|
151
|
+
}
|
152
|
+
}
|
129
153
|
case_insensitive_map_t<idx_t> name_collision_count;
|
130
154
|
|
131
155
|
// get header names from CSV
|
@@ -135,11 +159,11 @@ void CSVSniffer::DetectHeader() {
|
|
135
159
|
|
136
160
|
// generate name if field is empty
|
137
161
|
if (col_name.empty() || val.IsNull()) {
|
138
|
-
col_name = GenerateColumnName(
|
162
|
+
col_name = GenerateColumnName(sniffer_state_machine.dialect_options.num_cols, col);
|
139
163
|
}
|
140
164
|
|
141
165
|
// normalize names or at least trim whitespace
|
142
|
-
if (
|
166
|
+
if (sniffer_state_machine.options.normalize_names) {
|
143
167
|
col_name = NormalizeColumnName(col_name);
|
144
168
|
} else {
|
145
169
|
col_name = TrimWhitespace(col_name);
|
@@ -153,24 +177,24 @@ void CSVSniffer::DetectHeader() {
|
|
153
177
|
names.push_back(col_name);
|
154
178
|
name_collision_count[col_name] = 0;
|
155
179
|
}
|
156
|
-
if (best_header_row.size() <
|
157
|
-
for (idx_t col = best_header_row.size(); col <
|
158
|
-
names.push_back(GenerateColumnName(
|
180
|
+
if (best_header_row.size() < sniffer_state_machine.dialect_options.num_cols && options.null_padding) {
|
181
|
+
for (idx_t col = best_header_row.size(); col < sniffer_state_machine.dialect_options.num_cols; col++) {
|
182
|
+
names.push_back(GenerateColumnName(sniffer_state_machine.dialect_options.num_cols, col));
|
159
183
|
}
|
160
|
-
} else if (best_header_row.size() <
|
184
|
+
} else if (best_header_row.size() < sniffer_state_machine.dialect_options.num_cols) {
|
161
185
|
throw InternalException("Detected header has number of columns inferior to dialect detection");
|
162
186
|
}
|
163
187
|
|
164
188
|
} else {
|
165
|
-
|
166
|
-
for (idx_t col = 0; col <
|
167
|
-
names.push_back(GenerateColumnName(
|
189
|
+
sniffer_state_machine.dialect_options.header = false;
|
190
|
+
for (idx_t col = 0; col < sniffer_state_machine.dialect_options.num_cols; col++) {
|
191
|
+
names.push_back(GenerateColumnName(sniffer_state_machine.dialect_options.num_cols, col));
|
168
192
|
}
|
169
193
|
}
|
170
194
|
|
171
195
|
// If the user provided names, we must replace our header with the user provided names
|
172
|
-
for (idx_t i = 0; i < MinValue<idx_t>(names.size(),
|
173
|
-
names[i] =
|
196
|
+
for (idx_t i = 0; i < MinValue<idx_t>(names.size(), sniffer_state_machine.options.name_list.size()); i++) {
|
197
|
+
names[i] = sniffer_state_machine.options.name_list[i];
|
174
198
|
}
|
175
199
|
}
|
176
200
|
} // namespace duckdb
|
@@ -1,5 +1,5 @@
|
|
1
1
|
#include "duckdb/common/operator/decimal_cast_operators.hpp"
|
2
|
-
#include "duckdb/execution/operator/
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/sniffer/csv_sniffer.hpp"
|
3
3
|
#include "duckdb/common/algorithm.hpp"
|
4
4
|
#include "duckdb/common/string.hpp"
|
5
5
|
|
@@ -13,13 +13,6 @@ struct TryCastFloatingOperator {
|
|
13
13
|
}
|
14
14
|
};
|
15
15
|
|
16
|
-
struct TupleSniffing {
|
17
|
-
idx_t line_number;
|
18
|
-
idx_t position;
|
19
|
-
bool set = false;
|
20
|
-
vector<Value> values;
|
21
|
-
};
|
22
|
-
|
23
16
|
static bool StartsWithNumericDate(string &separator, const string &value) {
|
24
17
|
auto begin = value.c_str();
|
25
18
|
auto end = begin + value.size();
|
@@ -94,19 +87,21 @@ bool CSVSniffer::TryCastValue(CSVStateMachine &candidate, const Value &value, co
|
|
94
87
|
if (value.IsNull()) {
|
95
88
|
return true;
|
96
89
|
}
|
97
|
-
if (candidate.dialect_options.
|
90
|
+
if (!candidate.dialect_options.date_format.find(LogicalTypeId::DATE)->second.GetValue().Empty() &&
|
98
91
|
sql_type.id() == LogicalTypeId::DATE) {
|
99
92
|
date_t result;
|
100
93
|
string error_message;
|
101
94
|
return candidate.dialect_options.date_format.find(LogicalTypeId::DATE)
|
102
|
-
->second.
|
95
|
+
->second.GetValue()
|
96
|
+
.TryParseDate(string_t(StringValue::Get(value)), result, error_message);
|
103
97
|
}
|
104
|
-
if (candidate.dialect_options.
|
98
|
+
if (!candidate.dialect_options.date_format.find(LogicalTypeId::TIMESTAMP)->second.GetValue().Empty() &&
|
105
99
|
sql_type.id() == LogicalTypeId::TIMESTAMP) {
|
106
100
|
timestamp_t result;
|
107
101
|
string error_message;
|
108
102
|
return candidate.dialect_options.date_format.find(LogicalTypeId::TIMESTAMP)
|
109
|
-
->second.
|
103
|
+
->second.GetValue()
|
104
|
+
.TryParseTimestamp(string_t(StringValue::Get(value)), result, error_message);
|
110
105
|
}
|
111
106
|
if (candidate.options.decimal_separator != "." && (sql_type.id() == LogicalTypeId::DOUBLE)) {
|
112
107
|
return TryCastFloatingOperator::Operation<TryCastErrorMessageCommaSeparated, double>(StringValue::Get(value));
|
@@ -118,98 +113,16 @@ bool CSVSniffer::TryCastValue(CSVStateMachine &candidate, const Value &value, co
|
|
118
113
|
|
119
114
|
void CSVSniffer::SetDateFormat(CSVStateMachine &candidate, const string &format_specifier,
|
120
115
|
const LogicalTypeId &sql_type) {
|
121
|
-
|
122
|
-
|
123
|
-
date_format.
|
124
|
-
StrTimeFormat::ParseFormatSpecifier(date_format.format_specifier, date_format);
|
116
|
+
StrpTimeFormat strpformat;
|
117
|
+
StrTimeFormat::ParseFormatSpecifier(format_specifier, strpformat);
|
118
|
+
candidate.dialect_options.date_format[sql_type].Set(strpformat, false);
|
125
119
|
}
|
126
120
|
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
machine.cur_rows = 0;
|
133
|
-
machine.value = "";
|
134
|
-
machine.rows_read = 0;
|
135
|
-
}
|
136
|
-
|
137
|
-
inline static bool Process(CSVStateMachine &machine, vector<TupleSniffing> &sniffed_values, char current_char,
|
138
|
-
idx_t current_pos) {
|
139
|
-
|
140
|
-
if ((machine.dialect_options.new_line == NewLineIdentifier::SINGLE &&
|
141
|
-
(current_char == '\r' || current_char == '\n')) ||
|
142
|
-
(machine.dialect_options.new_line == NewLineIdentifier::CARRY_ON && current_char == '\n')) {
|
143
|
-
machine.rows_read++;
|
144
|
-
}
|
145
|
-
|
146
|
-
if ((machine.previous_state == CSVState::RECORD_SEPARATOR) ||
|
147
|
-
(machine.state != CSVState::RECORD_SEPARATOR && machine.previous_state == CSVState::CARRIAGE_RETURN)) {
|
148
|
-
sniffed_values[machine.cur_rows].position = machine.line_start_pos;
|
149
|
-
sniffed_values[machine.cur_rows].set = true;
|
150
|
-
machine.line_start_pos = current_pos;
|
151
|
-
}
|
152
|
-
|
153
|
-
machine.Transition(current_char);
|
154
|
-
|
155
|
-
bool carriage_return = machine.previous_state == CSVState::CARRIAGE_RETURN;
|
156
|
-
if (machine.previous_state == CSVState::DELIMITER || (machine.previous_state == CSVState::RECORD_SEPARATOR) ||
|
157
|
-
(machine.state != CSVState::RECORD_SEPARATOR && carriage_return)) {
|
158
|
-
// Started a new value
|
159
|
-
// Check if it's UTF-8
|
160
|
-
machine.VerifyUTF8();
|
161
|
-
if (machine.value.empty() || machine.value == machine.options.null_str) {
|
162
|
-
// We set empty == null value
|
163
|
-
sniffed_values[machine.cur_rows].values.push_back(Value(LogicalType::VARCHAR));
|
164
|
-
} else {
|
165
|
-
sniffed_values[machine.cur_rows].values.push_back(Value(machine.value));
|
166
|
-
}
|
167
|
-
sniffed_values[machine.cur_rows].line_number = machine.rows_read;
|
168
|
-
|
169
|
-
machine.value = "";
|
170
|
-
}
|
171
|
-
if (machine.state == CSVState::STANDARD ||
|
172
|
-
(machine.state == CSVState::QUOTED && machine.previous_state == CSVState::QUOTED)) {
|
173
|
-
machine.value += current_char;
|
174
|
-
}
|
175
|
-
machine.cur_rows += machine.previous_state == CSVState::RECORD_SEPARATOR;
|
176
|
-
// It means our carriage return is actually a record separator
|
177
|
-
machine.cur_rows += machine.state != CSVState::RECORD_SEPARATOR && carriage_return;
|
178
|
-
if (machine.cur_rows >= sniffed_values.size()) {
|
179
|
-
// We sniffed enough rows
|
180
|
-
return true;
|
181
|
-
}
|
182
|
-
return false;
|
183
|
-
}
|
184
|
-
|
185
|
-
inline static void Finalize(CSVStateMachine &machine, vector<TupleSniffing> &sniffed_values) {
|
186
|
-
if (machine.cur_rows < sniffed_values.size() && machine.state == CSVState::DELIMITER) {
|
187
|
-
// Started a new empty value
|
188
|
-
sniffed_values[machine.cur_rows].values.push_back(Value(machine.value));
|
189
|
-
}
|
190
|
-
if (machine.cur_rows < sniffed_values.size() && machine.state != CSVState::EMPTY_LINE) {
|
191
|
-
machine.VerifyUTF8();
|
192
|
-
sniffed_values[machine.cur_rows].line_number = machine.rows_read;
|
193
|
-
if (!sniffed_values[machine.cur_rows].set) {
|
194
|
-
sniffed_values[machine.cur_rows].position = machine.line_start_pos;
|
195
|
-
sniffed_values[machine.cur_rows].set = true;
|
196
|
-
}
|
197
|
-
|
198
|
-
sniffed_values[machine.cur_rows++].values.push_back(Value(machine.value));
|
199
|
-
}
|
200
|
-
sniffed_values.erase(sniffed_values.end() - (sniffed_values.size() - machine.cur_rows), sniffed_values.end());
|
201
|
-
}
|
202
|
-
};
|
203
|
-
|
204
|
-
void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate,
|
205
|
-
map<LogicalTypeId, bool> &has_format_candidates,
|
206
|
-
map<LogicalTypeId, vector<string>> &format_candidates,
|
207
|
-
const LogicalType &sql_type, const string &separator, Value &dummy_val) {
|
208
|
-
// generate date format candidates the first time through
|
209
|
-
auto &type_format_candidates = format_candidates[sql_type.id()];
|
210
|
-
const auto had_format_candidates = has_format_candidates[sql_type.id()];
|
211
|
-
if (!has_format_candidates[sql_type.id()]) {
|
212
|
-
has_format_candidates[sql_type.id()] = true;
|
121
|
+
void CSVSniffer::InitializeDateAndTimeStampDetection(CSVStateMachine &candidate, const string &separator,
|
122
|
+
const LogicalType &sql_type) {
|
123
|
+
auto &format_candidate = format_candidates[sql_type.id()];
|
124
|
+
if (!format_candidate.initialized) {
|
125
|
+
format_candidate.initialized = true;
|
213
126
|
// order by preference
|
214
127
|
auto entry = format_template_candidates.find(sql_type.id());
|
215
128
|
if (entry != format_template_candidates.end()) {
|
@@ -218,27 +131,36 @@ void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate,
|
|
218
131
|
const auto format_string = GenerateDateFormat(separator, t);
|
219
132
|
// don't parse ISO 8601
|
220
133
|
if (format_string.find("%Y-%m-%d") == string::npos) {
|
221
|
-
|
134
|
+
format_candidate.format.emplace_back(format_string);
|
222
135
|
}
|
223
136
|
}
|
224
137
|
}
|
225
|
-
// initialise the first candidate
|
226
|
-
candidate.dialect_options.has_format[sql_type.id()] = true;
|
227
|
-
// all formats are constructed to be valid
|
228
|
-
SetDateFormat(candidate, type_format_candidates.back(), sql_type.id());
|
229
138
|
}
|
139
|
+
// initialise the first candidate
|
140
|
+
// all formats are constructed to be valid
|
141
|
+
SetDateFormat(candidate, format_candidate.format.back(), sql_type.id());
|
142
|
+
}
|
143
|
+
|
144
|
+
void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate, const LogicalType &sql_type,
|
145
|
+
const string &separator, Value &dummy_val) {
|
146
|
+
// If it is the first time running date/timestamp detection we must initilize the format variables
|
147
|
+
InitializeDateAndTimeStampDetection(candidate, separator, sql_type);
|
148
|
+
// generate date format candidates the first time through
|
149
|
+
auto &type_format_candidates = format_candidates[sql_type.id()].format;
|
230
150
|
// check all formats and keep the first one that works
|
231
151
|
StrpTimeFormat::ParseResult result;
|
232
152
|
auto save_format_candidates = type_format_candidates;
|
153
|
+
bool had_format_candidates = !save_format_candidates.empty();
|
154
|
+
bool initial_format_candidates =
|
155
|
+
save_format_candidates.size() == format_template_candidates.at(sql_type.id()).size();
|
233
156
|
while (!type_format_candidates.empty()) {
|
234
157
|
// avoid using exceptions for flow control...
|
235
|
-
auto ¤t_format = candidate.dialect_options.date_format[sql_type.id()];
|
158
|
+
auto ¤t_format = candidate.dialect_options.date_format[sql_type.id()].GetValue();
|
236
159
|
if (current_format.Parse(StringValue::Get(dummy_val), result)) {
|
237
160
|
break;
|
238
161
|
}
|
239
162
|
// doesn't work - move to the next one
|
240
163
|
type_format_candidates.pop_back();
|
241
|
-
candidate.dialect_options.has_format[sql_type.id()] = (!type_format_candidates.empty());
|
242
164
|
if (!type_format_candidates.empty()) {
|
243
165
|
SetDateFormat(candidate, type_format_candidates.back(), sql_type.id());
|
244
166
|
}
|
@@ -248,12 +170,14 @@ void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate,
|
|
248
170
|
// so restore the candidates that did work.
|
249
171
|
// or throw them out if they were generated by this value.
|
250
172
|
if (had_format_candidates) {
|
251
|
-
|
252
|
-
|
253
|
-
|
173
|
+
if (initial_format_candidates) {
|
174
|
+
// we reset the whole thing because we tried to sniff the wrong type.
|
175
|
+
format_candidates[sql_type.id()].initialized = false;
|
176
|
+
format_candidates[sql_type.id()].format.clear();
|
177
|
+
return;
|
254
178
|
}
|
255
|
-
|
256
|
-
|
179
|
+
type_format_candidates.swap(save_format_candidates);
|
180
|
+
SetDateFormat(candidate, "", sql_type.id());
|
257
181
|
}
|
258
182
|
}
|
259
183
|
}
|
@@ -262,100 +186,59 @@ void CSVSniffer::DetectTypes() {
|
|
262
186
|
idx_t min_varchar_cols = max_columns_found + 1;
|
263
187
|
vector<LogicalType> return_types;
|
264
188
|
// check which info candidate leads to minimum amount of non-varchar columns...
|
265
|
-
for (auto &
|
189
|
+
for (auto &candidate_cc : candidates) {
|
190
|
+
auto &sniffing_state_machine = candidate_cc->GetStateMachine();
|
266
191
|
unordered_map<idx_t, vector<LogicalType>> info_sql_types_candidates;
|
267
|
-
for (idx_t i = 0; i <
|
268
|
-
info_sql_types_candidates[i] =
|
269
|
-
}
|
270
|
-
map<LogicalTypeId, bool> has_format_candidates;
|
271
|
-
map<LogicalTypeId, vector<string>> format_candidates;
|
272
|
-
for (const auto &t : format_template_candidates) {
|
273
|
-
has_format_candidates[t.first] = false;
|
274
|
-
format_candidates[t.first].clear();
|
192
|
+
for (idx_t i = 0; i < max_columns_found; i++) {
|
193
|
+
info_sql_types_candidates[i] = sniffing_state_machine.options.auto_type_candidates;
|
275
194
|
}
|
276
|
-
D_ASSERT(
|
195
|
+
D_ASSERT(max_columns_found > 0);
|
277
196
|
|
278
|
-
// Set all return_types to VARCHAR so we can do datatype detection based on VARCHAR values
|
197
|
+
// Set all return_types to VARCHAR, so we can do datatype detection based on VARCHAR values
|
279
198
|
return_types.clear();
|
280
|
-
return_types.assign(
|
199
|
+
return_types.assign(max_columns_found, LogicalType::VARCHAR);
|
281
200
|
|
282
201
|
// Reset candidate for parsing
|
283
|
-
candidate->
|
202
|
+
auto candidate = candidate_cc->UpgradeToStringValueScanner();
|
284
203
|
|
285
204
|
// Parse chunk and read csv with info candidate
|
286
|
-
|
287
|
-
candidate->csv_buffer_iterator.Process<SniffValue>(*candidate, tuples);
|
288
|
-
// Potentially Skip empty rows (I find this dirty, but it is what the original code does)
|
289
|
-
// The true line where parsing starts in reference to the csv file
|
290
|
-
idx_t true_line_start = 0;
|
291
|
-
idx_t true_pos = 0;
|
292
|
-
// The start point of the tuples
|
293
|
-
idx_t tuple_true_start = 0;
|
294
|
-
while (tuple_true_start < tuples.size()) {
|
295
|
-
if (tuples[tuple_true_start].values.empty() ||
|
296
|
-
(tuples[tuple_true_start].values.size() == 1 && tuples[tuple_true_start].values[0].IsNull())) {
|
297
|
-
true_line_start = tuples[tuple_true_start].line_number;
|
298
|
-
true_pos = tuples[tuple_true_start].position;
|
299
|
-
tuple_true_start++;
|
300
|
-
} else {
|
301
|
-
break;
|
302
|
-
}
|
303
|
-
}
|
304
|
-
|
305
|
-
// Potentially Skip Notes (I also find this dirty, but it is what the original code does)
|
306
|
-
while (tuple_true_start < tuples.size()) {
|
307
|
-
if (tuples[tuple_true_start].values.size() < max_columns_found && !options.null_padding) {
|
308
|
-
true_line_start = tuples[tuple_true_start].line_number;
|
309
|
-
true_pos = tuples[tuple_true_start].position;
|
310
|
-
tuple_true_start++;
|
311
|
-
} else {
|
312
|
-
break;
|
313
|
-
}
|
314
|
-
}
|
315
|
-
if (tuple_true_start < tuples.size()) {
|
316
|
-
true_pos = tuples[tuple_true_start].position;
|
317
|
-
}
|
318
|
-
if (tuple_true_start > 0) {
|
319
|
-
tuples.erase(tuples.begin(), tuples.begin() + tuple_true_start);
|
320
|
-
}
|
321
|
-
|
205
|
+
auto &tuples = candidate->ParseChunk();
|
322
206
|
idx_t row_idx = 0;
|
323
|
-
if (tuples.
|
207
|
+
if (tuples.number_of_rows > 1 &&
|
208
|
+
(!options.dialect_options.header.IsSetByUser() ||
|
209
|
+
(options.dialect_options.header.IsSetByUser() && options.dialect_options.header.GetValue()))) {
|
324
210
|
// This means we have more than one row, hence we can use the first row to detect if we have a header
|
325
211
|
row_idx = 1;
|
326
212
|
}
|
327
|
-
if (!tuples.empty()) {
|
328
|
-
best_start_without_header = tuples[0].position - true_pos;
|
329
|
-
}
|
330
|
-
|
331
213
|
// First line where we start our type detection
|
332
214
|
const idx_t start_idx_detection = row_idx;
|
333
|
-
for (; row_idx < tuples.
|
334
|
-
for (idx_t
|
335
|
-
auto &col_type_candidates = info_sql_types_candidates[
|
215
|
+
for (; row_idx < tuples.number_of_rows; row_idx++) {
|
216
|
+
for (idx_t col_idx = 0; col_idx < tuples.number_of_columns; col_idx++) {
|
217
|
+
auto &col_type_candidates = info_sql_types_candidates[col_idx];
|
336
218
|
// col_type_candidates can't be empty since anything in a CSV file should at least be a string
|
337
219
|
// and we validate utf-8 compatibility when creating the type
|
338
220
|
D_ASSERT(!col_type_candidates.empty());
|
339
221
|
auto cur_top_candidate = col_type_candidates.back();
|
340
|
-
auto dummy_val = tuples
|
222
|
+
auto dummy_val = tuples.GetValue(row_idx, col_idx);
|
341
223
|
// try cast from string to sql_type
|
342
224
|
while (col_type_candidates.size() > 1) {
|
343
225
|
const auto &sql_type = col_type_candidates.back();
|
344
|
-
// try formatting for date types if the user did not specify one and it starts with numeric
|
226
|
+
// try formatting for date types if the user did not specify one and it starts with numeric
|
227
|
+
// values.
|
345
228
|
string separator;
|
346
|
-
|
347
|
-
|
348
|
-
if (
|
349
|
-
|
350
|
-
|
351
|
-
|
352
|
-
(!has_format_is_set || format_candidates[sql_type.id()].size() > 1) && !dummy_val.IsNull() &&
|
353
|
-
StartsWithNumericDate(separator, StringValue::Get(dummy_val))) {
|
354
|
-
DetectDateAndTimeStampFormats(*candidate, has_format_candidates, format_candidates, sql_type,
|
355
|
-
separator, dummy_val);
|
229
|
+
// If Value is not Null, Has a numeric date format, and the current investigated candidate is
|
230
|
+
// either a timestamp or a date
|
231
|
+
if (!dummy_val.IsNull() && StartsWithNumericDate(separator, StringValue::Get(dummy_val)) &&
|
232
|
+
(col_type_candidates.back().id() == LogicalTypeId::TIMESTAMP ||
|
233
|
+
col_type_candidates.back().id() == LogicalTypeId::DATE)) {
|
234
|
+
DetectDateAndTimeStampFormats(candidate->GetStateMachine(), sql_type, separator, dummy_val);
|
356
235
|
}
|
357
236
|
// try cast from string to sql_type
|
358
|
-
if (
|
237
|
+
if (sql_type == LogicalType::VARCHAR) {
|
238
|
+
// Nothing to convert it to
|
239
|
+
continue;
|
240
|
+
}
|
241
|
+
if (TryCastValue(sniffing_state_machine, dummy_val, sql_type)) {
|
359
242
|
break;
|
360
243
|
} else {
|
361
244
|
if (row_idx != start_idx_detection && cur_top_candidate == LogicalType::BOOLEAN) {
|
@@ -383,29 +266,30 @@ void CSVSniffer::DetectTypes() {
|
|
383
266
|
}
|
384
267
|
}
|
385
268
|
|
386
|
-
// it's good if the dialect creates more non-varchar columns, but only if we sacrifice < 30% of
|
269
|
+
// it's good if the dialect creates more non-varchar columns, but only if we sacrifice < 30% of
|
270
|
+
// best_num_cols.
|
387
271
|
if (varchar_cols < min_varchar_cols && info_sql_types_candidates.size() > (max_columns_found * 0.7)) {
|
272
|
+
best_header_row.clear();
|
388
273
|
// we have a new best_options candidate
|
389
|
-
if (true_line_start > 0) {
|
390
|
-
// Add empty rows to skip_rows
|
391
|
-
candidate->dialect_options.skip_rows += true_line_start;
|
392
|
-
}
|
393
274
|
best_candidate = std::move(candidate);
|
394
275
|
min_varchar_cols = varchar_cols;
|
395
276
|
best_sql_types_candidates_per_column_idx = info_sql_types_candidates;
|
396
|
-
|
397
|
-
|
398
|
-
|
277
|
+
for (auto &format_candidate : format_candidates) {
|
278
|
+
best_format_candidates[format_candidate.first] = format_candidate.second.format;
|
279
|
+
}
|
280
|
+
if (tuples.number_of_rows > 0) {
|
281
|
+
for (idx_t col_idx = 0; col_idx < tuples.number_of_columns; col_idx++) {
|
282
|
+
best_header_row.emplace_back(tuples.GetValue(0, col_idx));
|
283
|
+
}
|
284
|
+
}
|
399
285
|
}
|
400
286
|
}
|
401
|
-
|
402
|
-
|
403
|
-
|
404
|
-
for (const auto &best : best_format_candidates) {
|
405
|
-
if (!best.second.empty()) {
|
406
|
-
SetDateFormat(*best_candidate, best.second.back(), best.first);
|
407
|
-
}
|
287
|
+
if (!best_candidate) {
|
288
|
+
auto error = CSVError::SniffingError(options.file_path);
|
289
|
+
error_handler->Error(error);
|
408
290
|
}
|
291
|
+
// Assert that it's all good at this point.
|
292
|
+
D_ASSERT(best_candidate && !best_format_candidates.empty());
|
409
293
|
}
|
410
294
|
|
411
295
|
} // namespace duckdb
|