duckdb 1.3.2 → 1.3.3-dev4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.github/workflows/NodeJS.yml +8 -20
- package/binding.gyp +9 -1
- package/package.json +1 -1
- package/src/connection.cpp +1 -1
- package/src/duckdb/extension/core_functions/aggregate/algebraic/avg.cpp +4 -0
- package/src/duckdb/extension/core_functions/aggregate/distributive/approx_count.cpp +8 -4
- package/src/duckdb/extension/core_functions/aggregate/distributive/arg_min_max.cpp +16 -12
- package/src/duckdb/extension/core_functions/aggregate/distributive/bitagg.cpp +5 -1
- package/src/duckdb/extension/core_functions/aggregate/distributive/bitstring_agg.cpp +5 -1
- package/src/duckdb/extension/core_functions/aggregate/distributive/bool.cpp +4 -0
- package/src/duckdb/extension/core_functions/aggregate/distributive/kurtosis.cpp +4 -0
- package/src/duckdb/extension/core_functions/aggregate/distributive/product.cpp +4 -0
- package/src/duckdb/extension/core_functions/aggregate/distributive/skew.cpp +4 -0
- package/src/duckdb/extension/core_functions/aggregate/distributive/string_agg.cpp +6 -2
- package/src/duckdb/extension/core_functions/aggregate/distributive/sum.cpp +64 -0
- package/src/duckdb/extension/core_functions/aggregate/holistic/approx_top_k.cpp +7 -3
- package/src/duckdb/extension/core_functions/aggregate/holistic/approximate_quantile.cpp +7 -4
- package/src/duckdb/extension/core_functions/aggregate/holistic/mad.cpp +6 -3
- package/src/duckdb/extension/core_functions/aggregate/holistic/mode.cpp +8 -1
- package/src/duckdb/extension/core_functions/aggregate/holistic/quantile.cpp +7 -46
- package/src/duckdb/extension/core_functions/aggregate/holistic/reservoir_quantile.cpp +9 -15
- package/src/duckdb/extension/core_functions/aggregate/nested/binned_histogram.cpp +12 -8
- package/src/duckdb/extension/core_functions/aggregate/nested/histogram.cpp +7 -5
- package/src/duckdb/extension/core_functions/aggregate/nested/list.cpp +14 -24
- package/src/duckdb/extension/core_functions/aggregate/regression/regr_avg.cpp +5 -0
- package/src/duckdb/extension/core_functions/aggregate/regression/regr_intercept.cpp +3 -0
- package/src/duckdb/extension/core_functions/aggregate/regression/regr_r2.cpp +5 -0
- package/src/duckdb/extension/core_functions/aggregate/regression/regr_sxx_syy.cpp +3 -0
- package/src/duckdb/extension/core_functions/aggregate/regression/regr_sxy.cpp +4 -0
- package/src/duckdb/extension/core_functions/core_functions_extension.cpp +6 -18
- package/src/duckdb/extension/core_functions/function_list.cpp +6 -3
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/algebraic/stddev.hpp +1 -1
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/algebraic_functions.hpp +2 -2
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/distributive_functions.hpp +4 -4
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/holistic_functions.hpp +1 -1
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/quantile_sort_tree.hpp +32 -45
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/quantile_state.hpp +1 -1
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/regression_functions.hpp +8 -8
- package/src/duckdb/extension/core_functions/include/core_functions/aggregate/sum_helpers.hpp +1 -1
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/array_functions.hpp +22 -22
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/blob_functions.hpp +2 -2
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/date_functions.hpp +15 -5
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/generic_functions.hpp +22 -12
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/list_functions.hpp +56 -56
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/map_functions.hpp +2 -2
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/math_functions.hpp +3 -3
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/string_functions.hpp +118 -118
- package/src/duckdb/extension/core_functions/include/core_functions/scalar/struct_functions.hpp +10 -0
- package/src/duckdb/extension/core_functions/include/core_functions_extension.hpp +1 -1
- package/src/duckdb/extension/core_functions/lambda_functions.cpp +4 -4
- package/src/duckdb/extension/core_functions/scalar/array/array_functions.cpp +2 -1
- package/src/duckdb/extension/core_functions/scalar/array/array_value.cpp +7 -3
- package/src/duckdb/extension/core_functions/scalar/bit/bitstring.cpp +7 -0
- package/src/duckdb/extension/core_functions/scalar/blob/base64.cpp +5 -2
- package/src/duckdb/extension/core_functions/scalar/blob/encode.cpp +6 -2
- package/src/duckdb/extension/core_functions/scalar/date/date_diff.cpp +7 -3
- package/src/duckdb/extension/core_functions/scalar/date/date_part.cpp +187 -33
- package/src/duckdb/extension/core_functions/scalar/date/date_sub.cpp +7 -3
- package/src/duckdb/extension/core_functions/scalar/date/date_trunc.cpp +12 -8
- package/src/duckdb/extension/core_functions/scalar/date/epoch.cpp +16 -12
- package/src/duckdb/extension/core_functions/scalar/date/make_date.cpp +11 -7
- package/src/duckdb/extension/core_functions/scalar/date/time_bucket.cpp +7 -3
- package/src/duckdb/extension/core_functions/scalar/date/to_interval.cpp +4 -0
- package/src/duckdb/extension/core_functions/scalar/enum/enum_functions.cpp +6 -6
- package/src/duckdb/extension/core_functions/scalar/generic/binning.cpp +8 -4
- package/src/duckdb/extension/core_functions/scalar/generic/can_implicitly_cast.cpp +6 -2
- package/src/duckdb/extension/core_functions/scalar/generic/cast_to_type.cpp +4 -1
- package/src/duckdb/extension/core_functions/scalar/generic/current_setting.cpp +9 -3
- package/src/duckdb/extension/core_functions/scalar/generic/least.cpp +5 -2
- package/src/duckdb/extension/core_functions/scalar/generic/replace_type.cpp +34 -0
- package/src/duckdb/extension/core_functions/scalar/generic/stats.cpp +5 -2
- package/src/duckdb/extension/core_functions/scalar/generic/system_functions.cpp +13 -9
- package/src/duckdb/extension/core_functions/scalar/generic/typeof.cpp +5 -1
- package/src/duckdb/extension/core_functions/scalar/list/array_slice.cpp +29 -26
- package/src/duckdb/extension/core_functions/scalar/list/flatten.cpp +9 -49
- package/src/duckdb/extension/core_functions/scalar/list/list_aggregates.cpp +17 -34
- package/src/duckdb/extension/core_functions/scalar/list/list_has_any_or_all.cpp +4 -50
- package/src/duckdb/extension/core_functions/scalar/list/list_reduce.cpp +46 -42
- package/src/duckdb/extension/core_functions/scalar/list/list_sort.cpp +48 -51
- package/src/duckdb/extension/core_functions/scalar/list/list_value.cpp +224 -144
- package/src/duckdb/extension/core_functions/scalar/list/range.cpp +5 -1
- package/src/duckdb/extension/core_functions/scalar/map/map.cpp +13 -41
- package/src/duckdb/extension/core_functions/scalar/map/map_concat.cpp +6 -6
- package/src/duckdb/extension/core_functions/scalar/map/map_entries.cpp +6 -42
- package/src/duckdb/extension/core_functions/scalar/map/map_extract.cpp +10 -59
- package/src/duckdb/extension/core_functions/scalar/map/map_from_entries.cpp +7 -32
- package/src/duckdb/extension/core_functions/scalar/map/map_keys_values.cpp +10 -45
- package/src/duckdb/extension/core_functions/scalar/math/numeric.cpp +364 -139
- package/src/duckdb/extension/core_functions/scalar/operators/bitwise.cpp +29 -7
- package/src/duckdb/extension/core_functions/scalar/random/random.cpp +18 -14
- package/src/duckdb/extension/core_functions/scalar/random/setseed.cpp +5 -1
- package/src/duckdb/extension/core_functions/scalar/string/hex.cpp +2 -2
- package/src/duckdb/extension/core_functions/scalar/string/instr.cpp +5 -3
- package/src/duckdb/extension/core_functions/scalar/string/printf.cpp +16 -0
- package/src/duckdb/extension/core_functions/scalar/string/repeat.cpp +2 -17
- package/src/duckdb/extension/core_functions/scalar/struct/struct_insert.cpp +1 -1
- package/src/duckdb/extension/core_functions/scalar/struct/struct_update.cpp +161 -0
- package/src/duckdb/extension/core_functions/scalar/union/union_extract.cpp +7 -3
- package/src/duckdb/extension/core_functions/scalar/union/union_tag.cpp +7 -3
- package/src/duckdb/extension/core_functions/scalar/union/union_value.cpp +7 -3
- package/src/duckdb/extension/icu/icu-current.cpp +5 -5
- package/src/duckdb/extension/icu/icu-dateadd.cpp +11 -11
- package/src/duckdb/extension/icu/icu-datepart.cpp +44 -44
- package/src/duckdb/extension/icu/icu-datesub.cpp +10 -10
- package/src/duckdb/extension/icu/icu-datetrunc.cpp +6 -6
- package/src/duckdb/extension/icu/icu-list-range.cpp +7 -6
- package/src/duckdb/extension/icu/icu-makedate.cpp +8 -11
- package/src/duckdb/extension/icu/icu-strptime.cpp +23 -29
- package/src/duckdb/extension/icu/icu-table-range.cpp +8 -6
- package/src/duckdb/extension/icu/icu-timebucket.cpp +5 -5
- package/src/duckdb/extension/icu/icu-timezone.cpp +24 -30
- package/src/duckdb/extension/icu/icu_extension.cpp +22 -34
- package/src/duckdb/extension/icu/include/icu-casts.hpp +2 -2
- package/src/duckdb/extension/icu/include/icu-current.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-dateadd.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-datepart.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-datesub.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-datetrunc.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-list-range.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-makedate.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-strptime.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-table-range.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-timebucket.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu-timezone.hpp +3 -3
- package/src/duckdb/extension/icu/include/icu_extension.hpp +1 -1
- package/src/duckdb/extension/json/include/json_common.hpp +10 -2
- package/src/duckdb/extension/json/include/json_enums.hpp +3 -1
- package/src/duckdb/extension/json/include/json_extension.hpp +1 -1
- package/src/duckdb/extension/json/include/json_functions.hpp +4 -4
- package/src/duckdb/extension/json/include/json_multi_file_info.hpp +2 -2
- package/src/duckdb/extension/json/include/json_reader.hpp +3 -1
- package/src/duckdb/extension/json/json_enums.cpp +5 -0
- package/src/duckdb/extension/json/json_extension.cpp +27 -38
- package/src/duckdb/extension/json/json_functions/copy_json.cpp +8 -3
- package/src/duckdb/extension/json/json_functions/json_create.cpp +9 -6
- package/src/duckdb/extension/json/json_functions/json_merge_patch.cpp +3 -20
- package/src/duckdb/extension/json/json_functions/json_pretty.cpp +3 -3
- package/src/duckdb/extension/json/json_functions/json_serialize_plan.cpp +6 -4
- package/src/duckdb/extension/json/json_functions/json_serialize_sql.cpp +6 -4
- package/src/duckdb/extension/json/json_functions/json_table_in_out.cpp +6 -2
- package/src/duckdb/extension/json/json_functions/json_transform.cpp +5 -3
- package/src/duckdb/extension/json/json_functions/read_json.cpp +4 -3
- package/src/duckdb/extension/json/json_functions.cpp +135 -8
- package/src/duckdb/extension/json/json_multi_file_info.cpp +5 -2
- package/src/duckdb/extension/json/json_reader.cpp +7 -6
- package/src/duckdb/extension/parquet/column_reader.cpp +46 -21
- package/src/duckdb/extension/parquet/column_writer.cpp +16 -105
- package/src/duckdb/extension/parquet/geo_parquet.cpp +231 -171
- package/src/duckdb/extension/parquet/include/column_reader.hpp +0 -2
- package/src/duckdb/extension/parquet/include/column_writer.hpp +2 -1
- package/src/duckdb/extension/parquet/include/geo_parquet.hpp +160 -66
- package/src/duckdb/extension/parquet/include/parquet_column_schema.hpp +6 -4
- package/src/duckdb/extension/parquet/include/parquet_crypto.hpp +0 -3
- package/src/duckdb/extension/parquet/include/parquet_extension.hpp +1 -1
- package/src/duckdb/extension/parquet/include/parquet_file_metadata_cache.hpp +5 -2
- package/src/duckdb/extension/parquet/include/parquet_multi_file_info.hpp +2 -2
- package/src/duckdb/extension/parquet/include/parquet_reader.hpp +10 -2
- package/src/duckdb/extension/parquet/include/parquet_rle_bp_encoder.hpp +3 -0
- package/src/duckdb/extension/parquet/include/parquet_statistics.hpp +0 -2
- package/src/duckdb/extension/parquet/include/parquet_timestamp.hpp +10 -6
- package/src/duckdb/extension/parquet/include/parquet_writer.hpp +4 -3
- package/src/duckdb/extension/parquet/include/reader/row_number_column_reader.hpp +0 -2
- package/src/duckdb/extension/parquet/include/reader/uuid_column_reader.hpp +3 -13
- package/src/duckdb/extension/parquet/include/reader/variant/variant_binary_decoder.hpp +150 -0
- package/src/duckdb/extension/parquet/include/reader/variant/variant_shredded_conversion.hpp +23 -0
- package/src/duckdb/extension/parquet/include/reader/variant/variant_value.hpp +54 -0
- package/src/duckdb/extension/parquet/include/reader/variant_column_reader.hpp +44 -0
- package/src/duckdb/extension/parquet/include/resizable_buffer.hpp +0 -2
- package/src/duckdb/extension/parquet/include/thrift_tools.hpp +3 -3
- package/src/duckdb/extension/parquet/include/writer/array_column_writer.hpp +2 -1
- package/src/duckdb/extension/parquet/include/writer/list_column_writer.hpp +2 -1
- package/src/duckdb/extension/parquet/include/writer/parquet_write_operators.hpp +47 -10
- package/src/duckdb/extension/parquet/include/writer/parquet_write_stats.hpp +55 -1
- package/src/duckdb/extension/parquet/include/writer/primitive_column_writer.hpp +4 -3
- package/src/duckdb/extension/parquet/include/writer/struct_column_writer.hpp +2 -1
- package/src/duckdb/extension/parquet/include/writer/templated_column_writer.hpp +6 -3
- package/src/duckdb/extension/parquet/include/zstd_file_system.hpp +1 -3
- package/src/duckdb/extension/parquet/parquet_crypto.cpp +11 -11
- package/src/duckdb/extension/parquet/parquet_extension.cpp +84 -68
- package/src/duckdb/extension/parquet/parquet_file_metadata_cache.cpp +4 -4
- package/src/duckdb/extension/parquet/parquet_float16.cpp +0 -3
- package/src/duckdb/extension/parquet/parquet_metadata.cpp +115 -17
- package/src/duckdb/extension/parquet/parquet_multi_file_info.cpp +25 -10
- package/src/duckdb/extension/parquet/parquet_reader.cpp +181 -56
- package/src/duckdb/extension/parquet/parquet_statistics.cpp +26 -8
- package/src/duckdb/extension/parquet/parquet_timestamp.cpp +14 -4
- package/src/duckdb/extension/parquet/parquet_writer.cpp +117 -16
- package/src/duckdb/extension/parquet/reader/decimal_column_reader.cpp +1 -1
- package/src/duckdb/extension/parquet/reader/variant/variant_binary_decoder.cpp +367 -0
- package/src/duckdb/extension/parquet/reader/variant/variant_shredded_conversion.cpp +565 -0
- package/src/duckdb/extension/parquet/reader/variant/variant_value.cpp +85 -0
- package/src/duckdb/extension/parquet/reader/variant_column_reader.cpp +161 -0
- package/src/duckdb/extension/parquet/writer/array_column_writer.cpp +5 -2
- package/src/duckdb/extension/parquet/writer/enum_column_writer.cpp +1 -1
- package/src/duckdb/extension/parquet/writer/list_column_writer.cpp +6 -3
- package/src/duckdb/extension/parquet/writer/primitive_column_writer.cpp +24 -8
- package/src/duckdb/extension/parquet/writer/struct_column_writer.cpp +4 -2
- package/src/duckdb/extension/parquet/zstd_file_system.cpp +7 -6
- package/src/duckdb/src/catalog/catalog.cpp +92 -62
- package/src/duckdb/src/catalog/catalog_entry/duck_table_entry.cpp +8 -8
- package/src/duckdb/src/catalog/catalog_entry/table_catalog_entry.cpp +14 -8
- package/src/duckdb/src/catalog/catalog_set.cpp +1 -0
- package/src/duckdb/src/catalog/default/default_functions.cpp +4 -4
- package/src/duckdb/src/catalog/default/default_table_functions.cpp +5 -4
- package/src/duckdb/src/catalog/default/default_views.cpp +1 -1
- package/src/duckdb/src/catalog/duck_catalog.cpp +28 -0
- package/src/duckdb/src/common/adbc/adbc.cpp +243 -125
- package/src/duckdb/src/common/adbc/driver_manager.cpp +3 -3
- package/src/duckdb/src/common/arrow/appender/append_data.cpp +29 -0
- package/src/duckdb/src/common/arrow/appender/bool_data.cpp +6 -7
- package/src/duckdb/src/common/arrow/appender/fixed_size_list_data.cpp +1 -1
- package/src/duckdb/src/common/arrow/appender/struct_data.cpp +1 -1
- package/src/duckdb/src/common/arrow/appender/union_data.cpp +0 -1
- package/src/duckdb/src/common/arrow/arrow_appender.cpp +13 -17
- package/src/duckdb/src/common/arrow/arrow_converter.cpp +14 -6
- package/src/duckdb/src/common/arrow/arrow_type_extension.cpp +6 -6
- package/src/duckdb/src/common/arrow/physical_arrow_collector.cpp +16 -10
- package/src/duckdb/src/common/arrow/schema_metadata.cpp +2 -2
- package/src/duckdb/src/common/bignum.cpp +362 -0
- package/src/duckdb/src/common/box_renderer.cpp +83 -32
- package/src/duckdb/src/common/complex_json.cpp +20 -5
- package/src/duckdb/src/common/compressed_file_system.cpp +6 -5
- package/src/duckdb/src/common/csv_writer.cpp +381 -0
- package/src/duckdb/src/common/encryption_functions.cpp +228 -0
- package/src/duckdb/src/common/encryption_key_manager.cpp +143 -0
- package/src/duckdb/src/common/encryption_state.cpp +56 -9
- package/src/duckdb/src/common/enum_util.cpp +405 -51
- package/src/duckdb/src/common/enums/expression_type.cpp +2 -0
- package/src/duckdb/src/common/enums/logical_operator_type.cpp +2 -0
- package/src/duckdb/src/common/enums/metric_type.cpp +6 -0
- package/src/duckdb/src/common/enums/optimizer_type.cpp +1 -0
- package/src/duckdb/src/common/enums/physical_operator_type.cpp +2 -0
- package/src/duckdb/src/common/enums/statement_type.cpp +2 -0
- package/src/duckdb/src/common/error_data.cpp +11 -0
- package/src/duckdb/src/common/exception_format_value.cpp +15 -1
- package/src/duckdb/src/common/extra_type_info.cpp +43 -0
- package/src/duckdb/src/common/file_buffer.cpp +11 -8
- package/src/duckdb/src/common/file_system.cpp +82 -12
- package/src/duckdb/src/common/gzip_file_system.cpp +13 -11
- package/src/duckdb/src/common/local_file_system.cpp +25 -16
- package/src/duckdb/src/common/multi_file/base_file_reader.cpp +4 -0
- package/src/duckdb/src/common/multi_file/multi_file_column_mapper.cpp +7 -11
- package/src/duckdb/src/common/multi_file/multi_file_function.cpp +8 -0
- package/src/duckdb/src/common/multi_file/multi_file_list.cpp +8 -4
- package/src/duckdb/src/common/multi_file/multi_file_reader.cpp +9 -5
- package/src/duckdb/src/common/operator/cast_operators.cpp +147 -6
- package/src/duckdb/src/common/operator/string_cast.cpp +41 -12
- package/src/duckdb/src/common/pipe_file_system.cpp +10 -5
- package/src/duckdb/src/common/progress_bar/progress_bar.cpp +2 -2
- package/src/duckdb/src/common/progress_bar/terminal_progress_bar_display.cpp +81 -7
- package/src/duckdb/src/common/progress_bar/unscented_kalman_filter.cpp +288 -0
- package/src/duckdb/src/common/radix_partitioning.cpp +2 -2
- package/src/duckdb/src/common/row_operations/row_aggregate.cpp +8 -11
- package/src/duckdb/src/common/row_operations/row_external.cpp +0 -7
- package/src/duckdb/src/common/row_operations/row_gather.cpp +0 -5
- package/src/duckdb/src/common/row_operations/row_matcher.cpp +55 -37
- package/src/duckdb/src/common/row_operations/row_scatter.cpp +0 -6
- package/src/duckdb/src/common/serializer/buffered_file_reader.cpp +4 -0
- package/src/duckdb/src/common/serializer/buffered_file_writer.cpp +4 -0
- package/src/duckdb/src/common/serializer/memory_stream.cpp +4 -0
- package/src/duckdb/src/common/sort/partition_state.cpp +3 -3
- package/src/duckdb/src/common/sorting/hashed_sort.cpp +724 -0
- package/src/duckdb/src/common/sorting/sort.cpp +513 -0
- package/src/duckdb/src/common/sorting/sorted_run.cpp +341 -0
- package/src/duckdb/src/common/sorting/sorted_run_merger.cpp +969 -0
- package/src/duckdb/src/common/string_util.cpp +64 -44
- package/src/duckdb/src/common/tree_renderer/text_tree_renderer.cpp +40 -3
- package/src/duckdb/src/common/tree_renderer/yaml_tree_renderer.cpp +144 -0
- package/src/duckdb/src/common/tree_renderer.cpp +3 -0
- package/src/duckdb/src/common/types/bignum.cpp +350 -0
- package/src/duckdb/src/common/types/column/column_data_allocator.cpp +27 -29
- package/src/duckdb/src/common/types/column/column_data_collection.cpp +216 -68
- package/src/duckdb/src/common/types/column/column_data_collection_segment.cpp +3 -2
- package/src/duckdb/src/common/types/conflict_info.cpp +1 -2
- package/src/duckdb/src/common/types/conflict_manager.cpp +82 -207
- package/src/duckdb/src/common/types/data_chunk.cpp +10 -3
- package/src/duckdb/src/common/types/date.cpp +8 -10
- package/src/duckdb/src/common/types/hash.cpp +7 -7
- package/src/duckdb/src/common/types/row/block_iterator.cpp +34 -0
- package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +38 -29
- package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +272 -54
- package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +156 -45
- package/src/duckdb/src/common/types/row/tuple_data_iterator.cpp +5 -5
- package/src/duckdb/src/common/types/row/tuple_data_layout.cpp +122 -18
- package/src/duckdb/src/common/types/row/tuple_data_scatter_gather.cpp +466 -83
- package/src/duckdb/src/common/types/row/tuple_data_segment.cpp +8 -28
- package/src/duckdb/src/common/types/time.cpp +2 -2
- package/src/duckdb/src/common/types/timestamp.cpp +26 -14
- package/src/duckdb/src/common/types/uuid.cpp +33 -2
- package/src/duckdb/src/common/types/value.cpp +79 -16
- package/src/duckdb/src/common/types/vector.cpp +190 -22
- package/src/duckdb/src/common/types/vector_buffer.cpp +4 -0
- package/src/duckdb/src/common/types/vector_cache.cpp +4 -0
- package/src/duckdb/src/common/types.cpp +110 -22
- package/src/duckdb/src/common/value_operations/comparison_operations.cpp +24 -27
- package/src/duckdb/src/common/vector_operations/boolean_operators.cpp +12 -9
- package/src/duckdb/src/common/vector_operations/comparison_operators.cpp +5 -4
- package/src/duckdb/src/common/vector_operations/generators.cpp +1 -1
- package/src/duckdb/src/common/vector_operations/is_distinct_from.cpp +70 -135
- package/src/duckdb/src/common/vector_operations/null_operations.cpp +1 -1
- package/src/duckdb/src/common/vector_operations/vector_copy.cpp +5 -2
- package/src/duckdb/src/common/vector_operations/vector_hash.cpp +110 -55
- package/src/duckdb/src/common/vector_operations/vector_storage.cpp +14 -10
- package/src/duckdb/src/common/virtual_file_system.cpp +12 -3
- package/src/duckdb/src/execution/aggregate_hashtable.cpp +88 -50
- package/src/duckdb/src/execution/column_binding_resolver.cpp +7 -6
- package/src/duckdb/src/execution/expression_executor/execute_function.cpp +113 -2
- package/src/duckdb/src/execution/expression_executor.cpp +44 -4
- package/src/duckdb/src/execution/index/art/art.cpp +78 -216
- package/src/duckdb/src/execution/index/art/art_builder.cpp +91 -0
- package/src/duckdb/src/execution/index/art/art_key.cpp +0 -23
- package/src/duckdb/src/execution/index/art/art_merger.cpp +3 -4
- package/src/duckdb/src/execution/index/art/base_leaf.cpp +10 -11
- package/src/duckdb/src/execution/index/art/base_node.cpp +103 -75
- package/src/duckdb/src/execution/index/art/iterator.cpp +3 -3
- package/src/duckdb/src/execution/index/art/leaf.cpp +9 -11
- package/src/duckdb/src/execution/index/art/node.cpp +54 -53
- package/src/duckdb/src/execution/index/art/node256.cpp +30 -56
- package/src/duckdb/src/execution/index/art/node256_leaf.cpp +43 -30
- package/src/duckdb/src/execution/index/art/node48.cpp +69 -101
- package/src/duckdb/src/execution/index/art/plan_art.cpp +2 -1
- package/src/duckdb/src/execution/index/art/prefix.cpp +115 -125
- package/src/duckdb/src/execution/index/bound_index.cpp +39 -10
- package/src/duckdb/src/execution/index/fixed_size_allocator.cpp +23 -8
- package/src/duckdb/src/execution/index/fixed_size_buffer.cpp +35 -23
- package/src/duckdb/src/execution/index/unbound_index.cpp +26 -6
- package/src/duckdb/src/execution/join_hashtable.cpp +52 -55
- package/src/duckdb/src/execution/nested_loop_join/nested_loop_join_inner.cpp +3 -0
- package/src/duckdb/src/execution/operator/aggregate/distinct_aggregate_data.cpp +6 -4
- package/src/duckdb/src/execution/operator/aggregate/physical_hash_aggregate.cpp +27 -18
- package/src/duckdb/src/execution/operator/aggregate/physical_partitioned_aggregate.cpp +4 -2
- package/src/duckdb/src/execution/operator/aggregate/physical_perfecthash_aggregate.cpp +4 -2
- package/src/duckdb/src/execution/operator/aggregate/physical_streaming_window.cpp +8 -2
- package/src/duckdb/src/execution/operator/aggregate/physical_ungrouped_aggregate.cpp +6 -4
- package/src/duckdb/src/execution/operator/aggregate/physical_window.cpp +433 -387
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_buffer.cpp +5 -4
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_file_handle.cpp +12 -4
- package/src/duckdb/src/execution/operator/csv_scanner/encode/csv_encoder.cpp +8 -7
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/string_value_scanner.cpp +7 -5
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp +15 -2
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp +1 -1
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp +4 -4
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/csv_multi_file_info.cpp +12 -3
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_error.cpp +7 -2
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_reader_options.cpp +4 -0
- package/src/duckdb/src/execution/operator/filter/physical_filter.cpp +14 -12
- package/src/duckdb/src/execution/operator/helper/physical_batch_collector.cpp +2 -1
- package/src/duckdb/src/execution/operator/helper/physical_buffered_batch_collector.cpp +2 -2
- package/src/duckdb/src/execution/operator/helper/physical_buffered_collector.cpp +3 -2
- package/src/duckdb/src/execution/operator/helper/physical_execute.cpp +2 -2
- package/src/duckdb/src/execution/operator/helper/physical_limit.cpp +3 -3
- package/src/duckdb/src/execution/operator/helper/physical_limit_percent.cpp +4 -3
- package/src/duckdb/src/execution/operator/helper/physical_materialized_collector.cpp +3 -2
- package/src/duckdb/src/execution/operator/helper/physical_reset.cpp +29 -9
- package/src/duckdb/src/execution/operator/helper/physical_result_collector.cpp +23 -20
- package/src/duckdb/src/execution/operator/helper/physical_set.cpp +28 -11
- package/src/duckdb/src/execution/operator/helper/physical_set_variable.cpp +3 -2
- package/src/duckdb/src/execution/operator/helper/physical_streaming_limit.cpp +4 -3
- package/src/duckdb/src/execution/operator/helper/physical_streaming_sample.cpp +3 -3
- package/src/duckdb/src/execution/operator/helper/physical_transaction.cpp +4 -4
- package/src/duckdb/src/execution/operator/helper/physical_vacuum.cpp +7 -3
- package/src/duckdb/src/execution/operator/helper/physical_verify_vector.cpp +4 -2
- package/src/duckdb/src/execution/operator/join/physical_asof_join.cpp +11 -10
- package/src/duckdb/src/execution/operator/join/physical_blockwise_nl_join.cpp +3 -2
- package/src/duckdb/src/execution/operator/join/physical_comparison_join.cpp +4 -4
- package/src/duckdb/src/execution/operator/join/physical_cross_product.cpp +4 -3
- package/src/duckdb/src/execution/operator/join/physical_delim_join.cpp +2 -2
- package/src/duckdb/src/execution/operator/join/physical_hash_join.cpp +13 -8
- package/src/duckdb/src/execution/operator/join/physical_iejoin.cpp +15 -14
- package/src/duckdb/src/execution/operator/join/physical_join.cpp +3 -3
- package/src/duckdb/src/execution/operator/join/physical_left_delim_join.cpp +5 -4
- package/src/duckdb/src/execution/operator/join/physical_nested_loop_join.cpp +7 -7
- package/src/duckdb/src/execution/operator/join/physical_piecewise_merge_join.cpp +20 -21
- package/src/duckdb/src/execution/operator/join/physical_positional_join.cpp +4 -3
- package/src/duckdb/src/execution/operator/join/physical_range_join.cpp +18 -6
- package/src/duckdb/src/execution/operator/join/physical_right_delim_join.cpp +5 -4
- package/src/duckdb/src/execution/operator/order/physical_order.cpp +62 -203
- package/src/duckdb/src/execution/operator/order/physical_top_n.cpp +5 -4
- package/src/duckdb/src/execution/operator/persistent/physical_batch_copy_to_file.cpp +5 -3
- package/src/duckdb/src/execution/operator/persistent/physical_batch_insert.cpp +9 -7
- package/src/duckdb/src/execution/operator/persistent/physical_copy_database.cpp +7 -5
- package/src/duckdb/src/execution/operator/persistent/physical_copy_to_file.cpp +12 -7
- package/src/duckdb/src/execution/operator/persistent/physical_delete.cpp +34 -5
- package/src/duckdb/src/execution/operator/persistent/physical_export.cpp +6 -20
- package/src/duckdb/src/execution/operator/persistent/physical_insert.cpp +91 -74
- package/src/duckdb/src/execution/operator/persistent/physical_merge_into.cpp +516 -0
- package/src/duckdb/src/execution/operator/persistent/physical_update.cpp +11 -9
- package/src/duckdb/src/execution/operator/projection/physical_pivot.cpp +7 -4
- package/src/duckdb/src/execution/operator/projection/physical_projection.cpp +3 -36
- package/src/duckdb/src/execution/operator/projection/physical_tableinout_function.cpp +26 -4
- package/src/duckdb/src/execution/operator/projection/physical_unnest.cpp +5 -3
- package/src/duckdb/src/execution/operator/scan/physical_column_data_scan.cpp +9 -7
- package/src/duckdb/src/execution/operator/scan/physical_positional_scan.cpp +3 -3
- package/src/duckdb/src/execution/operator/scan/physical_table_scan.cpp +6 -5
- package/src/duckdb/src/execution/operator/schema/physical_attach.cpp +11 -9
- package/src/duckdb/src/execution/operator/schema/physical_create_art_index.cpp +5 -4
- package/src/duckdb/src/execution/operator/schema/physical_create_table.cpp +3 -3
- package/src/duckdb/src/execution/operator/schema/physical_create_type.cpp +3 -2
- package/src/duckdb/src/execution/operator/schema/physical_drop.cpp +3 -2
- package/src/duckdb/src/execution/operator/set/physical_cte.cpp +5 -4
- package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +5 -3
- package/src/duckdb/src/execution/operator/set/physical_union.cpp +3 -3
- package/src/duckdb/src/execution/physical_operator.cpp +42 -32
- package/src/duckdb/src/execution/physical_plan/plan_aggregate.cpp +24 -12
- package/src/duckdb/src/execution/physical_plan/plan_asof_join.cpp +5 -3
- package/src/duckdb/src/execution/physical_plan/plan_comparison_join.cpp +12 -18
- package/src/duckdb/src/execution/physical_plan/plan_get.cpp +3 -1
- package/src/duckdb/src/execution/physical_plan/plan_insert.cpp +11 -10
- package/src/duckdb/src/execution/physical_plan/plan_merge_into.cpp +132 -0
- package/src/duckdb/src/execution/physical_plan/plan_recursive_cte.cpp +16 -18
- package/src/duckdb/src/execution/physical_plan_generator.cpp +8 -5
- package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +16 -27
- package/src/duckdb/src/execution/sample/base_reservoir_sample.cpp +22 -22
- package/src/duckdb/src/function/aggregate/distributive/count.cpp +14 -11
- package/src/duckdb/src/function/aggregate/distributive/first_last_any.cpp +23 -19
- package/src/duckdb/src/function/aggregate/distributive/minmax.cpp +14 -7
- package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp +185 -234
- package/src/duckdb/src/function/cast/bignum_casts.cpp +315 -0
- package/src/duckdb/src/function/cast/blob_cast.cpp +3 -0
- package/src/duckdb/src/function/cast/cast_function_set.cpp +24 -4
- package/src/duckdb/src/function/cast/decimal_cast.cpp +3 -3
- package/src/duckdb/src/function/cast/default_casts.cpp +12 -4
- package/src/duckdb/src/function/cast/enum_casts.cpp +4 -3
- package/src/duckdb/src/function/cast/numeric_casts.cpp +3 -3
- package/src/duckdb/src/function/cast/string_cast.cpp +14 -11
- package/src/duckdb/src/function/cast/struct_cast.cpp +127 -2
- package/src/duckdb/src/function/cast/time_casts.cpp +18 -0
- package/src/duckdb/src/function/cast/union_casts.cpp +7 -6
- package/src/duckdb/src/function/cast/uuid_casts.cpp +3 -0
- package/src/duckdb/src/function/cast/variant/from_variant.cpp +697 -0
- package/src/duckdb/src/function/cast/variant/to_json.cpp +272 -0
- package/src/duckdb/src/function/cast/variant/to_variant.cpp +193 -0
- package/src/duckdb/src/function/cast_rules.cpp +38 -4
- package/src/duckdb/src/function/copy_blob.cpp +157 -0
- package/src/duckdb/src/function/copy_function.cpp +15 -0
- package/src/duckdb/src/function/function.cpp +2 -0
- package/src/duckdb/src/function/function_binder.cpp +239 -13
- package/src/duckdb/src/function/function_list.cpp +8 -0
- package/src/duckdb/src/function/macro_function.cpp +263 -70
- package/src/duckdb/src/function/pragma/pragma_functions.cpp +6 -38
- package/src/duckdb/src/function/pragma/pragma_queries.cpp +37 -22
- package/src/duckdb/src/function/register_function_list.cpp +5 -5
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_integral.cpp +43 -34
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_string.cpp +61 -38
- package/src/duckdb/src/function/scalar/create_sort_key.cpp +374 -154
- package/src/duckdb/src/function/scalar/date/strftime.cpp +31 -28
- package/src/duckdb/src/function/scalar/generic/constant_or_null.cpp +18 -14
- package/src/duckdb/src/function/scalar/generic/error.cpp +18 -7
- package/src/duckdb/src/function/scalar/generic/getvariable.cpp +5 -2
- package/src/duckdb/src/function/scalar/list/contains_or_position.cpp +4 -52
- package/src/duckdb/src/function/scalar/list/list_extract.cpp +5 -12
- package/src/duckdb/src/function/scalar/list/list_resize.cpp +1 -1
- package/src/duckdb/src/function/scalar/list/list_select.cpp +11 -27
- package/src/duckdb/src/function/scalar/map/map_contains.cpp +5 -31
- package/src/duckdb/src/function/scalar/operator/add.cpp +6 -1
- package/src/duckdb/src/function/scalar/operator/arithmetic.cpp +130 -10
- package/src/duckdb/src/function/scalar/operator/multiply.cpp +4 -2
- package/src/duckdb/src/function/scalar/operator/subtract.cpp +3 -1
- package/src/duckdb/src/function/scalar/sequence/nextval.cpp +7 -3
- package/src/duckdb/src/function/scalar/strftime_format.cpp +2 -2
- package/src/duckdb/src/function/scalar/string/caseconvert.cpp +4 -0
- package/src/duckdb/src/function/scalar/string/concat.cpp +18 -19
- package/src/duckdb/src/function/scalar/string/contains.cpp +14 -7
- package/src/duckdb/src/function/scalar/string/length.cpp +13 -9
- package/src/duckdb/src/function/scalar/string/like.cpp +146 -143
- package/src/duckdb/src/function/scalar/string/md5.cpp +6 -2
- package/src/duckdb/src/function/scalar/string/nfc_normalize.cpp +5 -1
- package/src/duckdb/src/function/scalar/string/prefix.cpp +11 -8
- package/src/duckdb/src/function/scalar/string/regexp_escape.cpp +5 -1
- package/src/duckdb/src/function/scalar/string/sha1.cpp +5 -1
- package/src/duckdb/src/function/scalar/string/sha256.cpp +5 -1
- package/src/duckdb/src/function/scalar/string/string_split.cpp +7 -3
- package/src/duckdb/src/function/scalar/string/strip_accents.cpp +5 -1
- package/src/duckdb/src/function/scalar/string/substring.cpp +10 -6
- package/src/duckdb/src/function/scalar/string/suffix.cpp +10 -8
- package/src/duckdb/src/function/scalar/struct/remap_struct.cpp +20 -17
- package/src/duckdb/src/function/scalar/struct/struct_concat.cpp +1 -1
- package/src/duckdb/src/function/scalar/struct/struct_contains.cpp +255 -0
- package/src/duckdb/src/function/scalar/struct/struct_pack.cpp +2 -2
- package/src/duckdb/src/function/scalar/system/aggregate_export.cpp +34 -31
- package/src/duckdb/src/function/scalar/system/current_connection_id.cpp +5 -1
- package/src/duckdb/src/function/scalar/system/current_query_id.cpp +5 -1
- package/src/duckdb/src/function/scalar/system/current_transaction_id.cpp +5 -1
- package/src/duckdb/src/function/scalar/system/parse_log_message.cpp +5 -1
- package/src/duckdb/src/function/scalar/system/write_log.cpp +11 -13
- package/src/duckdb/src/function/scalar/variant/variant_extract.cpp +234 -0
- package/src/duckdb/src/function/scalar/variant/variant_typeof.cpp +70 -0
- package/src/duckdb/src/function/scalar/variant/variant_utils.cpp +412 -0
- package/src/duckdb/src/function/scalar_macro_function.cpp +8 -11
- package/src/duckdb/src/function/table/arrow/arrow_array_scan_state.cpp +2 -3
- package/src/duckdb/src/function/table/arrow/arrow_duck_schema.cpp +27 -2
- package/src/duckdb/src/function/table/arrow.cpp +37 -17
- package/src/duckdb/src/function/table/arrow_conversion.cpp +186 -236
- package/src/duckdb/src/function/table/copy_csv.cpp +76 -245
- package/src/duckdb/src/function/table/direct_file_reader.cpp +172 -0
- package/src/duckdb/src/function/table/read_file.cpp +90 -220
- package/src/duckdb/src/function/table/sniff_csv.cpp +0 -1
- package/src/duckdb/src/function/table/system/duckdb_approx_database_count.cpp +43 -0
- package/src/duckdb/src/function/table/system/duckdb_columns.cpp +2 -2
- package/src/duckdb/src/function/table/system/duckdb_constraints.cpp +3 -7
- package/src/duckdb/src/function/table/system/duckdb_databases.cpp +20 -5
- package/src/duckdb/src/function/table/system/duckdb_extensions.cpp +10 -5
- package/src/duckdb/src/function/table/system/duckdb_functions.cpp +6 -22
- package/src/duckdb/src/function/table/system/duckdb_log.cpp +41 -5
- package/src/duckdb/src/function/table/system/duckdb_log_contexts.cpp +15 -6
- package/src/duckdb/src/function/table/system/duckdb_settings.cpp +29 -6
- package/src/duckdb/src/function/table/system/duckdb_types.cpp +4 -0
- package/src/duckdb/src/function/table/system/logging_utils.cpp +154 -0
- package/src/duckdb/src/function/table/system/pragma_database_size.cpp +2 -2
- package/src/duckdb/src/function/table/system/test_all_types.cpp +30 -6
- package/src/duckdb/src/function/table/system_functions.cpp +2 -0
- package/src/duckdb/src/function/table/table_scan.cpp +82 -48
- package/src/duckdb/src/function/table/version/pragma_version.cpp +7 -4
- package/src/duckdb/src/function/window/window_aggregate_function.cpp +56 -46
- package/src/duckdb/src/function/window/window_aggregator.cpp +33 -19
- package/src/duckdb/src/function/window/window_boundaries_state.cpp +12 -2
- package/src/duckdb/src/function/window/window_collection.cpp +30 -0
- package/src/duckdb/src/function/window/window_constant_aggregator.cpp +32 -24
- package/src/duckdb/src/function/window/window_custom_aggregator.cpp +54 -40
- package/src/duckdb/src/function/window/window_distinct_aggregator.cpp +200 -251
- package/src/duckdb/src/function/window/window_executor.cpp +44 -36
- package/src/duckdb/src/function/window/window_index_tree.cpp +26 -16
- package/src/duckdb/src/function/window/window_merge_sort_tree.cpp +98 -151
- package/src/duckdb/src/function/window/window_naive_aggregator.cpp +94 -72
- package/src/duckdb/src/function/window/window_rank_function.cpp +57 -63
- package/src/duckdb/src/function/window/window_rownumber_function.cpp +45 -47
- package/src/duckdb/src/function/window/window_segment_tree.cpp +28 -22
- package/src/duckdb/src/function/window/window_token_tree.cpp +46 -41
- package/src/duckdb/src/function/window/window_value_function.cpp +632 -93
- package/src/duckdb/src/include/duckdb/catalog/catalog.hpp +24 -5
- package/src/duckdb/src/include/duckdb/catalog/default/builtin_types/types.hpp +5 -2
- package/src/duckdb/src/include/duckdb/catalog/duck_catalog.hpp +16 -0
- package/src/duckdb/src/include/duckdb/common/adbc/adbc.hpp +68 -1
- package/src/duckdb/src/include/duckdb/common/allocator.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/arena_linked_list.hpp +169 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/append_data.hpp +31 -55
- package/src/duckdb/src/include/duckdb/common/arrow/appender/enum_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list_view_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/arrow/appender/map_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/arrow/appender/scalar_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/arrow/appender/varchar_data.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_wrapper.hpp +10 -0
- package/src/duckdb/src/include/duckdb/common/arrow/physical_arrow_batch_collector.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/arrow/physical_arrow_collector.hpp +3 -4
- package/src/duckdb/src/include/duckdb/common/bignum.hpp +85 -0
- package/src/duckdb/src/include/duckdb/common/box_renderer.hpp +4 -4
- package/src/duckdb/src/include/duckdb/common/chrono.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/complex_json.hpp +15 -4
- package/src/duckdb/src/include/duckdb/common/compressed_file_system.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/csv_writer.hpp +153 -0
- package/src/duckdb/src/include/duckdb/common/encryption_functions.hpp +54 -0
- package/src/duckdb/src/include/duckdb/common/encryption_key_manager.hpp +80 -0
- package/src/duckdb/src/include/duckdb/common/encryption_state.hpp +25 -9
- package/src/duckdb/src/include/duckdb/common/enum_util.hpp +120 -0
- package/src/duckdb/src/include/duckdb/common/enums/arrow_format_version.hpp +33 -0
- package/src/duckdb/src/include/duckdb/common/enums/checkpoint_abort.hpp +22 -0
- package/src/duckdb/src/include/duckdb/common/enums/checkpoint_type.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/enums/copy_option_mode.hpp +17 -0
- package/src/duckdb/src/include/duckdb/common/enums/debug_vector_verification.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/explain_format.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/enums/expression_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/enums/file_glob_options.hpp +11 -3
- package/src/duckdb/src/include/duckdb/common/enums/logical_operator_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/enums/merge_action_type.hpp +19 -0
- package/src/duckdb/src/include/duckdb/common/enums/metric_type.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/enums/optimizer_type.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/ordinality_request_type.hpp +16 -0
- package/src/duckdb/src/include/duckdb/common/enums/physical_operator_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/enums/statement_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/enums/tableref_type.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/thread_pin_mode.hpp +17 -0
- package/src/duckdb/src/include/duckdb/common/enums/tuple_data_layout_enums.hpp +25 -0
- package/src/duckdb/src/include/duckdb/common/enums/undo_flags.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/error_data.hpp +4 -2
- package/src/duckdb/src/include/duckdb/common/exception_format_value.hpp +9 -1
- package/src/duckdb/src/include/duckdb/common/extra_type_info.hpp +25 -1
- package/src/duckdb/src/include/duckdb/common/file_buffer.hpp +15 -6
- package/src/duckdb/src/include/duckdb/common/file_open_flags.hpp +14 -0
- package/src/duckdb/src/include/duckdb/common/file_opener.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/file_system.hpp +14 -6
- package/src/duckdb/src/include/duckdb/common/fsst.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/gzip_file_system.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/helper.hpp +21 -3
- package/src/duckdb/src/include/duckdb/common/local_file_system.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/multi_file/base_file_reader.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/multi_file/multi_file_function.hpp +43 -14
- package/src/duckdb/src/include/duckdb/common/multi_file/multi_file_list.hpp +4 -3
- package/src/duckdb/src/include/duckdb/common/multi_file/multi_file_reader.hpp +10 -3
- package/src/duckdb/src/include/duckdb/common/multi_file/multi_file_states.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/numeric_utils.hpp +57 -0
- package/src/duckdb/src/include/duckdb/common/opener_file_system.hpp +7 -3
- package/src/duckdb/src/include/duckdb/common/operator/cast_operators.hpp +84 -0
- package/src/duckdb/src/include/duckdb/common/operator/interpolate.hpp +39 -0
- package/src/duckdb/src/include/duckdb/common/operator/string_cast.hpp +6 -0
- package/src/duckdb/src/include/duckdb/common/optionally_owned_ptr.hpp +18 -2
- package/src/duckdb/src/include/duckdb/common/owning_string_map.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/pipe_file_system.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/progress_bar/display/terminal_progress_bar_display.hpp +44 -5
- package/src/duckdb/src/include/duckdb/common/progress_bar/progress_bar.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/progress_bar/unscented_kalman_filter.hpp +65 -0
- package/src/duckdb/src/include/duckdb/common/row_operations/row_matcher.hpp +8 -14
- package/src/duckdb/src/include/duckdb/common/row_operations/row_operations.hpp +0 -12
- package/src/duckdb/src/include/duckdb/common/serializer/buffered_file_reader.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/serializer/deserializer.hpp +17 -2
- package/src/duckdb/src/include/duckdb/common/serializer/memory_stream.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/serializer/read_stream.hpp +9 -1
- package/src/duckdb/src/include/duckdb/common/serializer/varint.hpp +62 -0
- package/src/duckdb/src/include/duckdb/common/sorting/hashed_sort.hpp +76 -0
- package/src/duckdb/src/include/duckdb/common/sorting/sort.hpp +85 -0
- package/src/duckdb/src/include/duckdb/common/sorting/sort_key.hpp +442 -0
- package/src/duckdb/src/include/duckdb/common/sorting/sort_projection_column.hpp +21 -0
- package/src/duckdb/src/include/duckdb/common/sorting/sorted_run.hpp +55 -0
- package/src/duckdb/src/include/duckdb/common/sorting/sorted_run_merger.hpp +62 -0
- package/src/duckdb/src/include/duckdb/common/tree_renderer/text_tree_renderer.hpp +5 -0
- package/src/duckdb/src/include/duckdb/common/tree_renderer/yaml_tree_renderer.hpp +40 -0
- package/src/duckdb/src/include/duckdb/common/type_util.hpp +34 -4
- package/src/duckdb/src/include/duckdb/common/type_visitor.hpp +36 -6
- package/src/duckdb/src/include/duckdb/common/types/bignum.hpp +159 -0
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_allocator.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_collection_segment.hpp +4 -2
- package/src/duckdb/src/include/duckdb/common/types/conflict_manager.hpp +202 -56
- package/src/duckdb/src/include/duckdb/common/types/constraint_conflict_info.hpp +7 -5
- package/src/duckdb/src/include/duckdb/common/types/data_chunk.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/types/date.hpp +9 -5
- package/src/duckdb/src/include/duckdb/common/types/datetime.hpp +11 -2
- package/src/duckdb/src/include/duckdb/common/types/double_na_equal.hpp +65 -0
- package/src/duckdb/src/include/duckdb/common/types/hash.hpp +22 -10
- package/src/duckdb/src/include/duckdb/common/types/hugeint.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/types/row/block_iterator.hpp +360 -0
- package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/row/row_data_collection.hpp +1 -2
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_allocator.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_collection.hpp +26 -2
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_layout.hpp +43 -5
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_segment.hpp +4 -11
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +10 -1
- package/src/duckdb/src/include/duckdb/common/types/selection_vector.hpp +8 -58
- package/src/duckdb/src/include/duckdb/common/types/string.hpp +338 -0
- package/src/duckdb/src/include/duckdb/common/types/string_type.hpp +7 -1
- package/src/duckdb/src/include/duckdb/common/types/timestamp.hpp +7 -3
- package/src/duckdb/src/include/duckdb/common/types/uhugeint.hpp +4 -4
- package/src/duckdb/src/include/duckdb/common/types/uuid.hpp +5 -0
- package/src/duckdb/src/include/duckdb/common/types/validity_mask.hpp +14 -5
- package/src/duckdb/src/include/duckdb/common/types/value.hpp +15 -2
- package/src/duckdb/src/include/duckdb/common/types/variant.hpp +202 -0
- package/src/duckdb/src/include/duckdb/common/types/vector.hpp +118 -5
- package/src/duckdb/src/include/duckdb/common/types/vector_buffer.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/types.hpp +26 -6
- package/src/duckdb/src/include/duckdb/common/vector_operations/aggregate_executor.hpp +50 -11
- package/src/duckdb/src/include/duckdb/common/virtual_file_system.hpp +2 -3
- package/src/duckdb/src/include/duckdb/common/winapi.hpp +0 -4
- package/src/duckdb/src/include/duckdb/execution/aggregate_hashtable.hpp +8 -6
- package/src/duckdb/src/include/duckdb/execution/executor.hpp +0 -2
- package/src/duckdb/src/include/duckdb/execution/expression_executor.hpp +4 -0
- package/src/duckdb/src/include/duckdb/execution/expression_executor_state.hpp +21 -2
- package/src/duckdb/src/include/duckdb/execution/ht_entry.hpp +4 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/art.hpp +15 -16
- package/src/duckdb/src/include/duckdb/execution/index/art/art_builder.hpp +55 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/art_key.hpp +0 -13
- package/src/duckdb/src/include/duckdb/execution/index/art/art_merger.hpp +1 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/art_operator.hpp +113 -1
- package/src/duckdb/src/include/duckdb/execution/index/art/art_scanner.hpp +5 -2
- package/src/duckdb/src/include/duckdb/execution/index/art/base_leaf.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/index/art/base_node.hpp +18 -15
- package/src/duckdb/src/include/duckdb/execution/index/art/iterator.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/index/art/leaf.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/index/art/node.hpp +30 -3
- package/src/duckdb/src/include/duckdb/execution/index/art/node256.hpp +30 -8
- package/src/duckdb/src/include/duckdb/execution/index/art/node256_leaf.hpp +8 -5
- package/src/duckdb/src/include/duckdb/execution/index/art/node48.hpp +36 -9
- package/src/duckdb/src/include/duckdb/execution/index/art/prefix.hpp +9 -20
- package/src/duckdb/src/include/duckdb/execution/index/bound_index.hpp +8 -6
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_allocator.hpp +21 -4
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_buffer.hpp +95 -11
- package/src/duckdb/src/include/duckdb/execution/index/unbound_index.hpp +22 -11
- package/src/duckdb/src/include/duckdb/execution/join_hashtable.hpp +6 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/distinct_aggregate_data.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_hash_aggregate.hpp +12 -8
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_partitioned_aggregate.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_perfecthash_aggregate.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_streaming_window.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_ungrouped_aggregate.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_window.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_error.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_file_handle.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_multi_file_info.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_reader_options.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state_machine.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/encode/csv_encoder.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/operator/filter/physical_filter.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_batch_collector.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_buffered_batch_collector.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_buffered_collector.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_create_secret.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_execute.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_explain_analyze.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_limit.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_limit_percent.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_load.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_materialized_collector.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_pragma.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_prepare.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_reservoir_sample.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_reset.hpp +5 -4
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_result_collector.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_set.hpp +6 -3
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_set_variable.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_streaming_limit.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_streaming_sample.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_transaction.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_update_extensions.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_vacuum.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_verify_vector.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_asof_join.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_blockwise_nl_join.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_comparison_join.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_cross_product.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_delim_join.hpp +4 -3
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_hash_join.hpp +4 -4
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_iejoin.hpp +5 -4
- 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 +4 -3
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_nested_loop_join.hpp +6 -5
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_piecewise_merge_join.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_positional_join.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_range_join.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_right_delim_join.hpp +4 -3
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_order.hpp +13 -9
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_top_n.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_batch_copy_to_file.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_batch_insert.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_database.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_to_file.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_delete.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_export.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_insert.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_merge_into.hpp +87 -0
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_update.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/projection/physical_pivot.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/projection/physical_projection.hpp +2 -7
- package/src/duckdb/src/include/duckdb/execution/operator/projection/physical_tableinout_function.hpp +6 -1
- package/src/duckdb/src/include/duckdb/execution/operator/projection/physical_unnest.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_column_data_scan.hpp +4 -4
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_dummy_scan.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_empty_result.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_expression_scan.hpp +4 -3
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_positional_scan.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_table_scan.hpp +4 -3
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_alter.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_attach.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_art_index.hpp +4 -4
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_function.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_schema.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_sequence.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_table.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_type.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_view.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_detach.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_drop.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_cte.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_recursive_cte.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_union.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/physical_operator.hpp +23 -22
- package/src/duckdb/src/include/duckdb/execution/physical_plan_generator.hpp +7 -2
- package/src/duckdb/src/include/duckdb/execution/radix_partitioned_hashtable.hpp +4 -1
- package/src/duckdb/src/include/duckdb/execution/reservoir_sample.hpp +0 -1
- package/src/duckdb/src/include/duckdb/function/aggregate/distributive_functions.hpp +3 -3
- package/src/duckdb/src/include/duckdb/function/aggregate_function.hpp +36 -11
- 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 +28 -0
- package/src/duckdb/src/include/duckdb/function/cast/cast_function_set.hpp +6 -1
- package/src/duckdb/src/include/duckdb/function/cast/default_casts.hpp +5 -1
- package/src/duckdb/src/include/duckdb/function/cast/variant/array_to_variant.hpp +66 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/json_to_variant.hpp +283 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/list_to_variant.hpp +70 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/primitive_to_variant.hpp +399 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/struct_to_variant.hpp +111 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/to_variant.hpp +66 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/to_variant_fwd.hpp +179 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/union_to_variant.hpp +59 -0
- package/src/duckdb/src/include/duckdb/function/cast/variant/variant_to_variant.hpp +275 -0
- package/src/duckdb/src/include/duckdb/function/cast/vector_cast_helpers.hpp +2 -3
- package/src/duckdb/src/include/duckdb/function/copy_function.hpp +28 -10
- package/src/duckdb/src/include/duckdb/function/create_sort_key.hpp +13 -0
- package/src/duckdb/src/include/duckdb/function/function_binder.hpp +3 -0
- package/src/duckdb/src/include/duckdb/function/function_list.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/function_serialization.hpp +25 -3
- package/src/duckdb/src/include/duckdb/function/macro_function.hpp +18 -6
- package/src/duckdb/src/include/duckdb/function/pragma/pragma_functions.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/register_function_list_helper.hpp +34 -2
- package/src/duckdb/src/include/duckdb/function/scalar/compressed_materialization_functions.hpp +10 -0
- package/src/duckdb/src/include/duckdb/function/scalar/date_functions.hpp +6 -6
- package/src/duckdb/src/include/duckdb/function/scalar/list/contains_or_position.hpp +5 -5
- package/src/duckdb/src/include/duckdb/function/scalar/list_functions.hpp +19 -19
- package/src/duckdb/src/include/duckdb/function/scalar/string_functions.hpp +103 -103
- package/src/duckdb/src/include/duckdb/function/scalar/struct_functions.hpp +32 -0
- package/src/duckdb/src/include/duckdb/function/scalar/system_functions.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/scalar/variant_functions.hpp +38 -0
- package/src/duckdb/src/include/duckdb/function/scalar/variant_utils.hpp +85 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow/arrow_duck_schema.hpp +8 -2
- package/src/duckdb/src/include/duckdb/function/table/arrow/arrow_type_info.hpp +2 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow.hpp +26 -11
- package/src/duckdb/src/include/duckdb/function/table/direct_file_reader.hpp +39 -0
- package/src/duckdb/src/include/duckdb/function/table/read_csv.hpp +2 -12
- package/src/duckdb/src/include/duckdb/function/table/read_file.hpp +83 -0
- package/src/duckdb/src/include/duckdb/function/table/system_functions.hpp +9 -1
- package/src/duckdb/src/include/duckdb/function/table_function.hpp +8 -5
- package/src/duckdb/src/include/duckdb/function/window/window_aggregate_function.hpp +10 -10
- package/src/duckdb/src/include/duckdb/function/window/window_aggregator.hpp +25 -48
- package/src/duckdb/src/include/duckdb/function/window/window_collection.hpp +142 -0
- package/src/duckdb/src/include/duckdb/function/window/window_constant_aggregator.hpp +11 -12
- package/src/duckdb/src/include/duckdb/function/window/window_custom_aggregator.hpp +8 -8
- package/src/duckdb/src/include/duckdb/function/window/window_distinct_aggregator.hpp +10 -10
- package/src/duckdb/src/include/duckdb/function/window/window_executor.hpp +26 -40
- package/src/duckdb/src/include/duckdb/function/window/window_index_tree.hpp +2 -2
- package/src/duckdb/src/include/duckdb/function/window/window_merge_sort_tree.hpp +32 -30
- package/src/duckdb/src/include/duckdb/function/window/window_naive_aggregator.hpp +5 -3
- package/src/duckdb/src/include/duckdb/function/window/window_rank_function.hpp +17 -16
- package/src/duckdb/src/include/duckdb/function/window/window_rownumber_function.hpp +10 -9
- package/src/duckdb/src/include/duckdb/function/window/window_segment_tree.hpp +8 -8
- package/src/duckdb/src/include/duckdb/function/window/window_token_tree.hpp +6 -6
- package/src/duckdb/src/include/duckdb/function/window/window_value_function.hpp +44 -21
- package/src/duckdb/src/include/duckdb/logging/log_manager.hpp +12 -4
- package/src/duckdb/src/include/duckdb/logging/log_storage.hpp +271 -50
- package/src/duckdb/src/include/duckdb/main/appender.hpp +37 -16
- package/src/duckdb/src/include/duckdb/main/attached_database.hpp +18 -4
- package/src/duckdb/src/include/duckdb/main/capi/capi_internal.hpp +23 -6
- package/src/duckdb/src/include/duckdb/main/capi/extension_api.hpp +92 -8
- package/src/duckdb/src/include/duckdb/main/client_config.hpp +11 -70
- package/src/duckdb/src/include/duckdb/main/client_context.hpp +28 -5
- package/src/duckdb/src/include/duckdb/main/client_data.hpp +21 -23
- package/src/duckdb/src/include/duckdb/main/client_properties.hpp +3 -19
- package/src/duckdb/src/include/duckdb/main/config.hpp +48 -111
- package/src/duckdb/src/include/duckdb/main/database.hpp +23 -27
- package/src/duckdb/src/include/duckdb/main/database_file_opener.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/database_file_path_manager.hpp +39 -0
- package/src/duckdb/src/include/duckdb/main/database_manager.hpp +19 -21
- package/src/duckdb/src/include/duckdb/main/database_path_and_type.hpp +3 -1
- package/src/duckdb/src/include/duckdb/main/db_instance_cache.hpp +8 -4
- package/src/duckdb/src/include/duckdb/main/error_manager.hpp +3 -1
- package/src/duckdb/src/include/duckdb/main/extension/extension_loader.hpp +120 -0
- package/src/duckdb/src/include/duckdb/main/extension.hpp +2 -2
- package/src/duckdb/src/include/duckdb/main/extension_entries.hpp +35 -0
- package/src/duckdb/src/include/duckdb/main/extension_helper.hpp +2 -0
- package/src/duckdb/src/include/duckdb/main/extension_manager.hpp +59 -0
- package/src/duckdb/src/include/duckdb/main/extension_util.hpp +6 -77
- package/src/duckdb/src/include/duckdb/main/query_profiler.hpp +41 -23
- package/src/duckdb/src/include/duckdb/main/relation.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/secret/secret.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/secret/secret_manager.hpp +18 -18
- package/src/duckdb/src/include/duckdb/main/setting_info.hpp +109 -0
- package/src/duckdb/src/include/duckdb/main/settings.hpp +168 -184
- package/src/duckdb/src/include/duckdb/main/valid_checker.hpp +5 -2
- package/src/duckdb/src/include/duckdb/optimizer/build_probe_side_optimizer.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/column_lifetime_analyzer.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/compressed_materialization.hpp +4 -0
- package/src/duckdb/src/include/duckdb/optimizer/cte_inlining.hpp +50 -0
- package/src/duckdb/src/include/duckdb/optimizer/filter_pushdown.hpp +4 -1
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_order_optimizer.hpp +3 -0
- package/src/duckdb/src/include/duckdb/optimizer/late_materialization.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/rule/date_trunc_simplification.hpp +73 -0
- package/src/duckdb/src/include/duckdb/optimizer/rule/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parallel/interrupt.hpp +9 -3
- package/src/duckdb/src/include/duckdb/parallel/task_scheduler.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/common_table_expression_info.hpp +3 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_table_info.hpp +18 -8
- package/src/duckdb/src/include/duckdb/parser/parsed_data/attach_info.hpp +3 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/copy_info.hpp +6 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_info.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_expression_iterator.hpp +14 -0
- package/src/duckdb/src/include/duckdb/parser/parser.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/qualified_name.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/query_node/cte_node.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/statement/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/statement/merge_into_statement.hpp +72 -0
- package/src/duckdb/src/include/duckdb/parser/statement/select_statement.hpp +1 -4
- package/src/duckdb/src/include/duckdb/parser/statement/update_statement.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/bound_ref_wrapper.hpp +38 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/column_data_ref.hpp +4 -9
- package/src/duckdb/src/include/duckdb/parser/tableref/joinref.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/showref.hpp +5 -1
- package/src/duckdb/src/include/duckdb/parser/tableref/table_function_ref.hpp +4 -0
- package/src/duckdb/src/include/duckdb/parser/tokens.hpp +3 -0
- package/src/duckdb/src/include/duckdb/parser/transformer.hpp +9 -2
- package/src/duckdb/src/include/duckdb/planner/bind_context.hpp +5 -0
- package/src/duckdb/src/include/duckdb/planner/binder.hpp +45 -8
- package/src/duckdb/src/include/duckdb/planner/bound_constraint.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/bound_result_modifier.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/bound_tokens.hpp +3 -0
- package/src/duckdb/src/include/duckdb/planner/constraints/bound_check_constraint.hpp +8 -0
- package/src/duckdb/src/include/duckdb/planner/constraints/bound_foreign_key_constraint.hpp +4 -0
- package/src/duckdb/src/include/duckdb/planner/constraints/bound_not_null_constraint.hpp +4 -0
- package/src/duckdb/src/include/duckdb/planner/constraints/bound_unique_constraint.hpp +5 -0
- package/src/duckdb/src/include/duckdb/planner/expression/bound_between_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression_binder/projection_binder.hpp +37 -0
- package/src/duckdb/src/include/duckdb/planner/expression_binder/table_function_binder.hpp +3 -1
- package/src/duckdb/src/include/duckdb/planner/expression_binder.hpp +3 -8
- package/src/duckdb/src/include/duckdb/planner/expression_iterator.hpp +18 -0
- package/src/duckdb/src/include/duckdb/planner/extension_callback.hpp +8 -0
- package/src/duckdb/src/include/duckdb/planner/logical_operator_deep_copy.hpp +67 -0
- package/src/duckdb/src/include/duckdb/planner/logical_tokens.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/operator/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_aggregate.hpp +3 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_cteref.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_get.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_insert.hpp +28 -22
- package/src/duckdb/src/include/duckdb/planner/operator/logical_join.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_materialized_cte.hpp +5 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_merge_into.hpp +75 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_recursive_cte.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_update.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/query_node/bound_cte_node.hpp +2 -0
- package/src/duckdb/src/include/duckdb/storage/arena_allocator.hpp +26 -0
- package/src/duckdb/src/include/duckdb/storage/block.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/block_manager.hpp +24 -8
- package/src/duckdb/src/include/duckdb/storage/buffer/block_handle.hpp +3 -1
- package/src/duckdb/src/include/duckdb/storage/buffer_manager.hpp +55 -36
- package/src/duckdb/src/include/duckdb/storage/caching_file_system.hpp +10 -4
- package/src/duckdb/src/include/duckdb/storage/checkpoint/row_group_writer.hpp +19 -6
- package/src/duckdb/src/include/duckdb/storage/checkpoint/table_data_reader.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/checkpoint/table_data_writer.hpp +15 -8
- package/src/duckdb/src/include/duckdb/storage/checkpoint_manager.hpp +6 -8
- package/src/duckdb/src/include/duckdb/storage/compression/alp/algorithm/alp.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_fetch.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_analyze.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_fetch.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_scan.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/algorithm/packed_data.hpp +3 -1
- package/src/duckdb/src/include/duckdb/storage/compression/dict_fsst/compression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/dict_fsst/decompression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/patas/patas.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/patas/patas_fetch.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/patas/patas_scan.hpp +7 -2
- package/src/duckdb/src/include/duckdb/storage/data_pointer.hpp +5 -0
- package/src/duckdb/src/include/duckdb/storage/data_table.hpp +14 -9
- package/src/duckdb/src/include/duckdb/storage/external_file_cache.hpp +6 -5
- package/src/duckdb/src/include/duckdb/storage/in_memory_block_manager.hpp +7 -2
- package/src/duckdb/src/include/duckdb/storage/magic_bytes.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_manager.hpp +15 -0
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_reader.hpp +7 -0
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_writer.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/optimistic_data_writer.hpp +10 -3
- package/src/duckdb/src/include/duckdb/storage/partial_block_manager.hpp +14 -3
- package/src/duckdb/src/include/duckdb/storage/single_file_block_manager.hpp +65 -20
- package/src/duckdb/src/include/duckdb/storage/standard_buffer_manager.hpp +6 -6
- package/src/duckdb/src/include/duckdb/storage/statistics/base_statistics.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/storage_extension.hpp +4 -4
- package/src/duckdb/src/include/duckdb/storage/storage_info.hpp +80 -20
- package/src/duckdb/src/include/duckdb/storage/storage_manager.hpp +43 -17
- package/src/duckdb/src/include/duckdb/storage/storage_options.hpp +21 -0
- package/src/duckdb/src/include/duckdb/storage/table/array_column_data.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/table/column_checkpoint_state.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/table/column_data.hpp +7 -1
- package/src/duckdb/src/include/duckdb/storage/table/column_data_checkpointer.hpp +5 -2
- package/src/duckdb/src/include/duckdb/storage/table/column_segment.hpp +10 -7
- package/src/duckdb/src/include/duckdb/storage/table/data_table_info.hpp +3 -3
- package/src/duckdb/src/include/duckdb/storage/table/in_memory_checkpoint.hpp +93 -0
- package/src/duckdb/src/include/duckdb/storage/table/list_column_data.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/table/persistent_table_data.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/table/row_group.hpp +17 -2
- package/src/duckdb/src/include/duckdb/storage/table/row_group_collection.hpp +11 -1
- package/src/duckdb/src/include/duckdb/storage/table/row_group_segment_tree.hpp +5 -0
- package/src/duckdb/src/include/duckdb/storage/table/row_id_column_data.hpp +68 -0
- package/src/duckdb/src/include/duckdb/storage/table/segment_lock.hpp +4 -0
- package/src/duckdb/src/include/duckdb/storage/table/segment_tree.hpp +34 -14
- package/src/duckdb/src/include/duckdb/storage/table/standard_column_data.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/table/struct_column_data.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/table/table_index_list.hpp +55 -46
- package/src/duckdb/src/include/duckdb/storage/table/update_segment.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/temporary_file_manager.hpp +17 -6
- package/src/duckdb/src/include/duckdb/storage/write_ahead_log.hpp +2 -1
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction.hpp +3 -0
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction_manager.hpp +1 -0
- package/src/duckdb/src/include/duckdb/transaction/local_storage.hpp +3 -1
- package/src/duckdb/src/include/duckdb/transaction/meta_transaction.hpp +22 -1
- package/src/duckdb/src/include/duckdb/transaction/undo_buffer_allocator.hpp +2 -0
- package/src/duckdb/src/include/duckdb/verification/explain_statement_verifier.hpp +23 -0
- package/src/duckdb/src/include/duckdb/verification/statement_verifier.hpp +14 -7
- package/src/duckdb/src/include/duckdb.h +537 -121
- package/src/duckdb/src/include/duckdb_extension.h +122 -14
- package/src/duckdb/src/logging/log_manager.cpp +59 -15
- package/src/duckdb/src/logging/log_storage.cpp +672 -128
- package/src/duckdb/src/main/appender.cpp +129 -88
- package/src/duckdb/src/main/attached_database.cpp +47 -52
- package/src/duckdb/src/main/capi/aggregate_function-c.cpp +18 -9
- package/src/duckdb/src/main/capi/appender-c.cpp +82 -28
- package/src/duckdb/src/main/capi/arrow-c.cpp +181 -17
- package/src/duckdb/src/main/capi/config-c.cpp +18 -3
- package/src/duckdb/src/main/capi/data_chunk-c.cpp +22 -10
- package/src/duckdb/src/main/capi/duckdb-c.cpp +64 -21
- package/src/duckdb/src/main/capi/duckdb_value-c.cpp +13 -7
- package/src/duckdb/src/main/capi/error_data-c.cpp +46 -0
- package/src/duckdb/src/main/capi/expression-c.cpp +57 -0
- package/src/duckdb/src/main/capi/helper-c.cpp +227 -39
- package/src/duckdb/src/main/capi/logical_types-c.cpp +48 -28
- package/src/duckdb/src/main/capi/prepared-c.cpp +68 -10
- package/src/duckdb/src/main/capi/profiling_info-c.cpp +6 -4
- package/src/duckdb/src/main/capi/result-c.cpp +16 -95
- package/src/duckdb/src/main/capi/scalar_function-c.cpp +43 -1
- package/src/duckdb/src/main/capi/table_function-c.cpp +9 -0
- package/src/duckdb/src/main/client_config.cpp +21 -0
- package/src/duckdb/src/main/client_context.cpp +153 -77
- package/src/duckdb/src/main/client_context_file_opener.cpp +1 -0
- package/src/duckdb/src/main/client_data.cpp +139 -1
- package/src/duckdb/src/main/client_verify.cpp +14 -6
- package/src/duckdb/src/main/config.cpp +214 -121
- package/src/duckdb/src/main/database.cpp +31 -58
- package/src/duckdb/src/main/database_file_path_manager.cpp +42 -0
- package/src/duckdb/src/main/database_manager.cpp +134 -108
- package/src/duckdb/src/main/database_path_and_type.cpp +4 -3
- package/src/duckdb/src/main/db_instance_cache.cpp +64 -35
- package/src/duckdb/src/main/error_manager.cpp +2 -1
- package/src/duckdb/src/main/extension/extension_helper.cpp +3 -22
- package/src/duckdb/src/main/extension/extension_install.cpp +6 -6
- package/src/duckdb/src/main/extension/extension_load.cpp +24 -9
- package/src/duckdb/src/main/extension/extension_loader.cpp +234 -0
- package/src/duckdb/src/main/extension_manager.cpp +115 -0
- package/src/duckdb/src/main/http/http_util.cpp +18 -5
- package/src/duckdb/src/main/profiling_info.cpp +8 -2
- package/src/duckdb/src/main/query_profiler.cpp +65 -30
- package/src/duckdb/src/main/query_result.cpp +1 -1
- package/src/duckdb/src/main/relation/query_relation.cpp +23 -0
- package/src/duckdb/src/main/secret/secret_manager.cpp +8 -7
- package/src/duckdb/src/main/settings/autogenerated_settings.cpp +50 -645
- package/src/duckdb/src/main/settings/custom_settings.cpp +111 -152
- package/src/duckdb/src/main/valid_checker.cpp +10 -4
- package/src/duckdb/src/optimizer/build_probe_side_optimizer.cpp +7 -5
- package/src/duckdb/src/optimizer/column_lifetime_analyzer.cpp +7 -7
- package/src/duckdb/src/optimizer/compressed_materialization/compress_comparison_join.cpp +11 -7
- package/src/duckdb/src/optimizer/compressed_materialization.cpp +56 -39
- package/src/duckdb/src/optimizer/cte_inlining.cpp +225 -0
- package/src/duckdb/src/optimizer/empty_result_pullup.cpp +8 -1
- package/src/duckdb/src/optimizer/filter_combiner.cpp +5 -7
- package/src/duckdb/src/optimizer/filter_pushdown.cpp +3 -0
- package/src/duckdb/src/optimizer/join_order/cardinality_estimator.cpp +18 -2
- package/src/duckdb/src/optimizer/join_order/join_order_optimizer.cpp +1 -0
- package/src/duckdb/src/optimizer/join_order/plan_enumerator.cpp +4 -3
- package/src/duckdb/src/optimizer/join_order/query_graph_manager.cpp +11 -15
- package/src/duckdb/src/optimizer/join_order/relation_manager.cpp +40 -23
- package/src/duckdb/src/optimizer/late_materialization.cpp +16 -23
- package/src/duckdb/src/optimizer/optimizer.cpp +15 -0
- package/src/duckdb/src/optimizer/pushdown/pushdown_aggregate.cpp +15 -20
- package/src/duckdb/src/optimizer/pushdown/pushdown_left_join.cpp +11 -13
- package/src/duckdb/src/optimizer/pushdown/pushdown_outer_join.cpp +201 -0
- package/src/duckdb/src/optimizer/pushdown/pushdown_projection.cpp +20 -26
- package/src/duckdb/src/optimizer/pushdown/pushdown_set_operation.cpp +11 -14
- package/src/duckdb/src/optimizer/remove_unused_columns.cpp +2 -1
- package/src/duckdb/src/optimizer/rule/date_trunc_simplification.cpp +446 -0
- package/src/duckdb/src/optimizer/rule/join_dependent_filter.cpp +3 -9
- package/src/duckdb/src/optimizer/rule/ordered_aggregate_optimizer.cpp +1 -6
- package/src/duckdb/src/optimizer/rule/timestamp_comparison.cpp +3 -6
- package/src/duckdb/src/optimizer/statistics/operator/propagate_aggregate.cpp +33 -1
- package/src/duckdb/src/parallel/event.cpp +1 -3
- package/src/duckdb/src/parallel/executor.cpp +0 -7
- package/src/duckdb/src/parallel/pipeline.cpp +2 -2
- package/src/duckdb/src/parallel/pipeline_executor.cpp +2 -2
- package/src/duckdb/src/parallel/task_scheduler.cpp +146 -34
- package/src/duckdb/src/parallel/thread_context.cpp +2 -9
- package/src/duckdb/src/parser/column_definition.cpp +3 -6
- package/src/duckdb/src/parser/expression/window_expression.cpp +3 -0
- package/src/duckdb/src/parser/parsed_data/attach_info.cpp +8 -35
- package/src/duckdb/src/parser/parsed_data/copy_info.cpp +27 -7
- package/src/duckdb/src/parser/parsed_data/create_index_info.cpp +8 -13
- package/src/duckdb/src/parser/parsed_data/create_info.cpp +16 -0
- package/src/duckdb/src/parser/parsed_data/create_macro_info.cpp +7 -17
- package/src/duckdb/src/parser/parsed_data/create_table_info.cpp +1 -14
- package/src/duckdb/src/parser/parsed_data/create_type_info.cpp +1 -12
- package/src/duckdb/src/parser/parsed_data/create_view_info.cpp +1 -13
- package/src/duckdb/src/parser/parsed_expression_iterator.cpp +22 -0
- package/src/duckdb/src/parser/parser.cpp +5 -0
- package/src/duckdb/src/parser/qualified_name.cpp +26 -0
- package/src/duckdb/src/parser/query_node/cte_node.cpp +1 -0
- package/src/duckdb/src/parser/query_node/select_node.cpp +1 -0
- package/src/duckdb/src/parser/query_node.cpp +1 -0
- package/src/duckdb/src/parser/statement/export_statement.cpp +1 -3
- package/src/duckdb/src/parser/statement/merge_into_statement.cpp +167 -0
- package/src/duckdb/src/parser/statement/update_statement.cpp +19 -16
- package/src/duckdb/src/parser/tableref/bound_ref_wrapper.cpp +29 -0
- package/src/duckdb/src/parser/tableref/column_data_ref.cpp +26 -1
- package/src/duckdb/src/parser/tableref/joinref.cpp +3 -2
- package/src/duckdb/src/parser/tableref/showref.cpp +14 -0
- package/src/duckdb/src/parser/tableref/table_function.cpp +6 -1
- package/src/duckdb/src/parser/transform/expression/transform_expression.cpp +0 -1
- package/src/duckdb/src/parser/transform/expression/transform_function.cpp +6 -1
- package/src/duckdb/src/parser/transform/expression/transform_subquery.cpp +8 -11
- package/src/duckdb/src/parser/transform/helpers/transform_cte.cpp +3 -0
- package/src/duckdb/src/parser/transform/helpers/transform_typename.cpp +7 -5
- package/src/duckdb/src/parser/transform/statement/transform_attach.cpp +4 -4
- package/src/duckdb/src/parser/transform/statement/transform_copy.cpp +16 -80
- package/src/duckdb/src/parser/transform/statement/transform_create_function.cpp +27 -22
- package/src/duckdb/src/parser/transform/statement/transform_create_type.cpp +0 -1
- package/src/duckdb/src/parser/transform/statement/transform_explain.cpp +1 -2
- package/src/duckdb/src/parser/transform/statement/transform_insert.cpp +22 -14
- package/src/duckdb/src/parser/transform/statement/transform_merge_into.cpp +111 -0
- package/src/duckdb/src/parser/transform/statement/transform_pivot_stmt.cpp +2 -0
- package/src/duckdb/src/parser/transform/statement/transform_pragma.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_show.cpp +22 -4
- package/src/duckdb/src/parser/transform/tableref/transform_from.cpp +3 -1
- package/src/duckdb/src/parser/transform/tableref/transform_join.cpp +12 -6
- package/src/duckdb/src/parser/transform/tableref/transform_table_function.cpp +3 -3
- package/src/duckdb/src/parser/transformer.cpp +8 -7
- package/src/duckdb/src/planner/bind_context.cpp +19 -2
- package/src/duckdb/src/planner/binder/expression/bind_aggregate_expression.cpp +13 -6
- package/src/duckdb/src/planner/binder/expression/bind_columnref_expression.cpp +3 -0
- package/src/duckdb/src/planner/binder/expression/bind_function_expression.cpp +18 -4
- package/src/duckdb/src/planner/binder/expression/bind_macro_expression.cpp +8 -25
- package/src/duckdb/src/planner/binder/expression/bind_operator_expression.cpp +31 -4
- package/src/duckdb/src/planner/binder/expression/bind_unnest_expression.cpp +2 -0
- package/src/duckdb/src/planner/binder/expression/bind_window_expression.cpp +48 -11
- package/src/duckdb/src/planner/binder/query_node/bind_cte_node.cpp +9 -1
- package/src/duckdb/src/planner/binder/query_node/bind_recursive_cte_node.cpp +4 -0
- package/src/duckdb/src/planner/binder/query_node/bind_select_node.cpp +6 -6
- package/src/duckdb/src/planner/binder/query_node/bind_table_macro_node.cpp +11 -26
- package/src/duckdb/src/planner/binder/query_node/plan_cte_node.cpp +4 -3
- package/src/duckdb/src/planner/binder/query_node/plan_subquery.cpp +10 -4
- package/src/duckdb/src/planner/binder/statement/bind_attach.cpp +15 -0
- package/src/duckdb/src/planner/binder/statement/bind_copy.cpp +239 -58
- package/src/duckdb/src/planner/binder/statement/bind_create.cpp +157 -55
- package/src/duckdb/src/planner/binder/statement/bind_create_table.cpp +30 -25
- package/src/duckdb/src/planner/binder/statement/bind_delete.cpp +2 -3
- package/src/duckdb/src/planner/binder/statement/bind_drop.cpp +28 -3
- package/src/duckdb/src/planner/binder/statement/bind_export.cpp +36 -0
- package/src/duckdb/src/planner/binder/statement/bind_insert.cpp +282 -322
- package/src/duckdb/src/planner/binder/statement/bind_merge_into.cpp +335 -0
- package/src/duckdb/src/planner/binder/statement/bind_update.cpp +23 -14
- package/src/duckdb/src/planner/binder/tableref/bind_basetableref.cpp +37 -27
- package/src/duckdb/src/planner/binder/tableref/bind_bound_table_ref.cpp +13 -0
- package/src/duckdb/src/planner/binder/tableref/bind_column_data_ref.cpp +4 -1
- package/src/duckdb/src/planner/binder/tableref/bind_pivot.cpp +120 -36
- package/src/duckdb/src/planner/binder/tableref/bind_showref.cpp +30 -0
- package/src/duckdb/src/planner/binder/tableref/bind_table_function.cpp +72 -1
- package/src/duckdb/src/planner/binder/tableref/plan_joinref.cpp +7 -12
- package/src/duckdb/src/planner/binder/tableref/plan_table_function.cpp +15 -1
- package/src/duckdb/src/planner/binder.cpp +42 -175
- package/src/duckdb/src/planner/bound_result_modifier.cpp +8 -0
- package/src/duckdb/src/planner/collation_binding.cpp +2 -1
- package/src/duckdb/src/planner/expression.cpp +1 -1
- package/src/duckdb/src/planner/expression_binder/order_binder.cpp +4 -2
- package/src/duckdb/src/planner/expression_binder/projection_binder.cpp +46 -0
- package/src/duckdb/src/planner/expression_binder/table_function_binder.cpp +8 -6
- package/src/duckdb/src/planner/expression_iterator.cpp +31 -0
- package/src/duckdb/src/planner/logical_operator_deep_copy.cpp +264 -0
- package/src/duckdb/src/planner/logical_operator_visitor.cpp +18 -4
- package/src/duckdb/src/planner/operator/logical_aggregate.cpp +2 -1
- package/src/duckdb/src/planner/operator/logical_comparison_join.cpp +4 -2
- package/src/duckdb/src/planner/operator/logical_copy_to_file.cpp +3 -0
- package/src/duckdb/src/planner/operator/logical_get.cpp +7 -2
- package/src/duckdb/src/planner/operator/logical_insert.cpp +5 -2
- package/src/duckdb/src/planner/operator/logical_join.cpp +6 -7
- package/src/duckdb/src/planner/operator/logical_materialized_cte.cpp +1 -0
- package/src/duckdb/src/planner/operator/logical_merge_into.cpp +43 -0
- package/src/duckdb/src/planner/operator/logical_recursive_cte.cpp +8 -0
- package/src/duckdb/src/planner/planner.cpp +4 -2
- package/src/duckdb/src/planner/pragma_handler.cpp +1 -1
- package/src/duckdb/src/planner/subquery/flatten_dependent_join.cpp +76 -7
- package/src/duckdb/src/planner/table_binding.cpp +6 -12
- package/src/duckdb/src/storage/block.cpp +2 -1
- package/src/duckdb/src/storage/buffer/block_handle.cpp +7 -4
- package/src/duckdb/src/storage/buffer/block_manager.cpp +14 -6
- package/src/duckdb/src/storage/buffer/buffer_pool.cpp +2 -2
- package/src/duckdb/src/storage/buffer_manager.cpp +45 -13
- package/src/duckdb/src/storage/caching_file_system.cpp +20 -12
- package/src/duckdb/src/storage/checkpoint/row_group_writer.cpp +26 -3
- package/src/duckdb/src/storage/checkpoint/table_data_reader.cpp +3 -1
- package/src/duckdb/src/storage/checkpoint/table_data_writer.cpp +56 -35
- package/src/duckdb/src/storage/checkpoint/write_overflow_strings_to_disk.cpp +1 -1
- package/src/duckdb/src/storage/checkpoint_manager.cpp +12 -11
- package/src/duckdb/src/storage/compression/bitpacking.cpp +4 -1
- package/src/duckdb/src/storage/compression/dict_fsst/compression.cpp +48 -25
- package/src/duckdb/src/storage/compression/dict_fsst/decompression.cpp +10 -13
- package/src/duckdb/src/storage/compression/dict_fsst.cpp +2 -2
- package/src/duckdb/src/storage/compression/fixed_size_uncompressed.cpp +10 -5
- package/src/duckdb/src/storage/compression/fsst.cpp +3 -2
- package/src/duckdb/src/storage/compression/rle.cpp +1 -1
- package/src/duckdb/src/storage/compression/zstd.cpp +5 -6
- package/src/duckdb/src/storage/data_table.cpp +167 -144
- package/src/duckdb/src/storage/external_file_cache.cpp +6 -6
- package/src/duckdb/src/storage/local_storage.cpp +132 -68
- package/src/duckdb/src/storage/magic_bytes.cpp +3 -2
- package/src/duckdb/src/storage/metadata/metadata_manager.cpp +88 -17
- package/src/duckdb/src/storage/metadata/metadata_reader.cpp +26 -3
- package/src/duckdb/src/storage/metadata/metadata_writer.cpp +7 -0
- package/src/duckdb/src/storage/open_file_storage_extension.cpp +3 -3
- package/src/duckdb/src/storage/optimistic_data_writer.cpp +5 -3
- package/src/duckdb/src/storage/partial_block_manager.cpp +26 -5
- package/src/duckdb/src/storage/serialization/serialize_logical_operator.cpp +72 -22
- package/src/duckdb/src/storage/serialization/serialize_macro_function.cpp +9 -3
- package/src/duckdb/src/storage/serialization/serialize_query_node.cpp +2 -0
- package/src/duckdb/src/storage/serialization/serialize_tableref.cpp +12 -2
- package/src/duckdb/src/storage/serialization/serialize_types.cpp +14 -0
- package/src/duckdb/src/storage/single_file_block_manager.cpp +381 -86
- package/src/duckdb/src/storage/standard_buffer_manager.cpp +86 -30
- package/src/duckdb/src/storage/statistics/base_statistics.cpp +3 -3
- package/src/duckdb/src/storage/statistics/string_stats.cpp +2 -2
- package/src/duckdb/src/storage/statistics/struct_stats.cpp +1 -1
- package/src/duckdb/src/storage/storage_info.cpp +13 -7
- package/src/duckdb/src/storage/storage_manager.cpp +110 -35
- package/src/duckdb/src/storage/table/array_column_data.cpp +4 -0
- package/src/duckdb/src/storage/table/column_checkpoint_state.cpp +22 -15
- package/src/duckdb/src/storage/table/column_data.cpp +53 -14
- package/src/duckdb/src/storage/table/column_data_checkpointer.cpp +17 -17
- package/src/duckdb/src/storage/table/column_segment.cpp +23 -21
- package/src/duckdb/src/storage/table/in_memory_checkpoint.cpp +136 -0
- package/src/duckdb/src/storage/table/list_column_data.cpp +6 -1
- package/src/duckdb/src/storage/table/row_group.cpp +226 -154
- package/src/duckdb/src/storage/table/row_group_collection.cpp +146 -47
- package/src/duckdb/src/storage/table/row_id_column_data.cpp +173 -0
- package/src/duckdb/src/storage/table/row_version_manager.cpp +1 -1
- package/src/duckdb/src/storage/table/standard_column_data.cpp +14 -2
- package/src/duckdb/src/storage/table/struct_column_data.cpp +15 -0
- package/src/duckdb/src/storage/table/update_segment.cpp +111 -5
- package/src/duckdb/src/storage/table_index_list.cpp +137 -73
- package/src/duckdb/src/storage/temporary_file_manager.cpp +103 -28
- package/src/duckdb/src/storage/wal_replay.cpp +158 -36
- package/src/duckdb/src/storage/write_ahead_log.cpp +102 -17
- package/src/duckdb/src/transaction/commit_state.cpp +2 -0
- package/src/duckdb/src/transaction/duck_transaction.cpp +12 -2
- package/src/duckdb/src/transaction/duck_transaction_manager.cpp +66 -35
- package/src/duckdb/src/transaction/meta_transaction.cpp +85 -23
- package/src/duckdb/src/transaction/rollback_state.cpp +7 -0
- package/src/duckdb/src/transaction/transaction_context.cpp +3 -4
- package/src/duckdb/src/transaction/undo_buffer.cpp +5 -4
- package/src/duckdb/src/transaction/undo_buffer_allocator.cpp +1 -0
- package/src/duckdb/src/transaction/wal_write_state.cpp +2 -0
- package/src/duckdb/src/verification/explain_statement_verifier.cpp +16 -0
- package/src/duckdb/src/verification/prepared_statement_verifier.cpp +1 -1
- package/src/duckdb/src/verification/statement_verifier.cpp +10 -5
- package/src/duckdb/third_party/brotli/common/shared_dictionary.cpp +4 -4
- package/src/duckdb/third_party/fmt/include/fmt/core.h +6 -12
- package/src/duckdb/third_party/fmt/include/fmt/format-inl.h +5 -1
- package/src/duckdb/third_party/fmt/include/fmt/format.h +34 -24
- package/src/duckdb/third_party/fmt/include/fmt/printf.h +49 -21
- package/src/duckdb/third_party/httplib/httplib.hpp +13 -5
- package/src/duckdb/third_party/jaro_winkler/details/jaro_impl.hpp +4 -4
- package/src/duckdb/third_party/libpg_query/include/nodes/nodes.hpp +3 -0
- package/src/duckdb/third_party/libpg_query/include/nodes/parsenodes.hpp +56 -1
- package/src/duckdb/third_party/libpg_query/include/parser/gram.hpp +744 -733
- package/src/duckdb/third_party/libpg_query/include/parser/kwlist.hpp +6 -1
- package/src/duckdb/third_party/libpg_query/src_backend_parser_gram.cpp +19098 -18654
- package/src/duckdb/third_party/mbedtls/include/des_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/aes_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/aria_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/block_cipher.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/build_info.h +4 -4
- package/src/duckdb/third_party/mbedtls/include/mbedtls/camellia_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/ccm_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/chacha20.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/chachapoly.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/cmac.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/config_psa.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/ecdsa.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/gcm_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/mbedtls_config.h +5 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/md5.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/nist_kw.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/pkcs12.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/pkcs5.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/psa_util.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/ripemd160.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/sha3.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/threading.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls/timing.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/mbedtls_wrapper.hpp +16 -7
- package/src/duckdb/third_party/mbedtls/include/platform_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/psa/build_info.h +20 -0
- package/src/duckdb/third_party/mbedtls/include/psa/crypto.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/psa/crypto_config.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/psa/crypto_se_driver.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/rsa_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/sha1_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/sha256_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/sha512_alt.h +1 -1
- package/src/duckdb/third_party/mbedtls/include/ssl_misc.h +1 -1
- package/src/duckdb/third_party/mbedtls/library/aes.cpp +1 -1
- package/src/duckdb/third_party/mbedtls/library/aesce.h +136 -1
- package/src/duckdb/third_party/mbedtls/library/alignment.h +9 -9
- package/src/duckdb/third_party/mbedtls/library/asn1parse.cpp +1 -1
- package/src/duckdb/third_party/mbedtls/library/asn1write.cpp +6 -3
- package/src/duckdb/third_party/mbedtls/library/base64.cpp +48 -24
- package/src/duckdb/third_party/mbedtls/library/base64_internal.h +45 -1
- package/src/duckdb/third_party/mbedtls/library/bignum.cpp +3 -3
- package/src/duckdb/third_party/mbedtls/library/bignum_core.cpp +16 -14
- package/src/duckdb/third_party/mbedtls/library/bignum_core.h +10 -18
- package/src/duckdb/third_party/mbedtls/library/block_cipher_internal.h +99 -1
- package/src/duckdb/third_party/mbedtls/library/check_crypto_config.h +141 -1
- package/src/duckdb/third_party/mbedtls/library/cipher.cpp +18 -12
- package/src/duckdb/third_party/mbedtls/library/cipher_invasive.h +1 -0
- package/src/duckdb/third_party/mbedtls/library/cipher_wrap.cpp +110 -10
- package/src/duckdb/third_party/mbedtls/library/cipher_wrap.h +1 -1
- package/src/duckdb/third_party/mbedtls/library/common.h +20 -4
- package/src/duckdb/third_party/mbedtls/library/constant_time.cpp +1 -1
- package/src/duckdb/third_party/mbedtls/library/constant_time_impl.h +28 -43
- package/src/duckdb/third_party/mbedtls/library/constant_time_internal.h +24 -24
- package/src/duckdb/third_party/mbedtls/library/ctr.h +35 -1
- package/src/duckdb/third_party/mbedtls/library/gcm.cpp +2 -2
- package/src/duckdb/third_party/mbedtls/library/md.cpp +11 -11
- package/src/duckdb/third_party/mbedtls/library/md_psa.h +1 -1
- package/src/duckdb/third_party/mbedtls/library/oid.cpp +2 -2
- package/src/duckdb/third_party/mbedtls/library/pem.cpp +5 -2
- package/src/duckdb/third_party/mbedtls/library/pk.cpp +1 -5
- package/src/duckdb/third_party/mbedtls/library/pk_internal.h +4 -4
- package/src/duckdb/third_party/mbedtls/library/pk_wrap.cpp +16 -18
- package/src/duckdb/third_party/mbedtls/library/pkwrite.h +121 -1
- package/src/duckdb/third_party/mbedtls/library/psa_crypto_core.h +995 -1
- package/src/duckdb/third_party/mbedtls/library/psa_util_internal.h +100 -1
- package/src/duckdb/third_party/mbedtls/library/rsa.cpp +4 -4
- package/src/duckdb/third_party/mbedtls/mbedtls_wrapper.cpp +114 -42
- package/src/duckdb/third_party/parquet/parquet_types.cpp +2340 -769
- package/src/duckdb/third_party/parquet/parquet_types.h +400 -4
- package/src/duckdb/third_party/pdqsort/pdqsort.h +550 -0
- package/src/duckdb/third_party/ska_sort/ska_sort.hpp +1494 -0
- package/src/duckdb/third_party/snappy/snappy-stubs-internal.h +18 -18
- package/src/duckdb/third_party/snappy/snappy.cc +6 -6
- package/src/duckdb/third_party/thrift/thrift/protocol/TCompactProtocol.h +4 -4
- package/src/duckdb/third_party/thrift/thrift/protocol/TCompactProtocol.tcc +36 -36
- package/src/duckdb/third_party/utf8proc/include/utf8proc_wrapper.hpp +1 -1
- package/src/duckdb/third_party/utf8proc/utf8proc_wrapper.cpp +1 -1
- package/src/duckdb/third_party/vergesort/detail/insertion_sort.h +56 -0
- package/src/duckdb/third_party/vergesort/detail/is_sorted_until.h +51 -0
- package/src/duckdb/third_party/vergesort/detail/iter_sort3.h +48 -0
- package/src/duckdb/third_party/vergesort/detail/log2.h +41 -0
- package/src/duckdb/third_party/vergesort/detail/prevnext.h +68 -0
- package/src/duckdb/third_party/vergesort/detail/quicksort.h +138 -0
- package/src/duckdb/third_party/vergesort/vergesort.h +352 -0
- package/src/duckdb/ub_extension_core_functions_scalar_generic.cpp +2 -0
- package/src/duckdb/ub_extension_core_functions_scalar_struct.cpp +2 -0
- package/src/duckdb/ub_extension_parquet_reader.cpp +2 -0
- package/src/duckdb/ub_extension_parquet_reader_variant.cpp +6 -0
- package/src/duckdb/ub_src_common.cpp +8 -0
- package/src/duckdb/ub_src_common_arrow_appender.cpp +2 -0
- package/src/duckdb/ub_src_common_progress_bar.cpp +2 -0
- package/src/duckdb/ub_src_common_sorting.cpp +8 -0
- package/src/duckdb/ub_src_common_tree_renderer.cpp +2 -0
- package/src/duckdb/ub_src_common_types.cpp +1 -1
- package/src/duckdb/ub_src_common_types_row.cpp +2 -0
- package/src/duckdb/ub_src_execution_index_art.cpp +11 -9
- package/src/duckdb/ub_src_execution_operator_persistent.cpp +2 -0
- package/src/duckdb/ub_src_execution_physical_plan.cpp +2 -0
- package/src/duckdb/ub_src_function.cpp +2 -0
- package/src/duckdb/ub_src_function_cast.cpp +1 -1
- package/src/duckdb/ub_src_function_cast_variant.cpp +6 -0
- package/src/duckdb/ub_src_function_scalar_struct.cpp +2 -0
- package/src/duckdb/ub_src_function_scalar_variant.cpp +6 -0
- package/src/duckdb/ub_src_function_table.cpp +2 -0
- package/src/duckdb/ub_src_function_table_system.cpp +4 -0
- package/src/duckdb/ub_src_main.cpp +4 -0
- package/src/duckdb/ub_src_main_capi.cpp +4 -0
- package/src/duckdb/ub_src_optimizer.cpp +2 -0
- package/src/duckdb/ub_src_optimizer_pushdown.cpp +2 -0
- package/src/duckdb/ub_src_optimizer_rule.cpp +2 -0
- package/src/duckdb/ub_src_parser_statement.cpp +2 -0
- package/src/duckdb/ub_src_parser_tableref.cpp +2 -0
- package/src/duckdb/ub_src_parser_transform_statement.cpp +2 -0
- package/src/duckdb/ub_src_planner.cpp +2 -0
- package/src/duckdb/ub_src_planner_binder_statement.cpp +2 -0
- package/src/duckdb/ub_src_planner_binder_tableref.cpp +2 -0
- package/src/duckdb/ub_src_planner_expression_binder.cpp +2 -0
- package/src/duckdb/ub_src_planner_operator.cpp +2 -0
- package/src/duckdb/ub_src_storage_table.cpp +4 -0
- package/test/columns.test.ts +1 -1
- package/test/exec.test.ts +3 -3
- package/test/jsdoc.test.ts +2 -1
- package/test/syntax_error.test.ts +1 -1
- package/test/test_all_types.test.ts +1 -1
@@ -13,22 +13,6 @@
|
|
13
13
|
|
14
14
|
namespace duckdb {
|
15
15
|
|
16
|
-
namespace {
|
17
|
-
|
18
|
-
enum class ArrowArrayPhysicalType : uint8_t { DICTIONARY_ENCODED, RUN_END_ENCODED, DEFAULT };
|
19
|
-
|
20
|
-
ArrowArrayPhysicalType GetArrowArrayPhysicalType(const ArrowType &type) {
|
21
|
-
if (type.HasDictionary()) {
|
22
|
-
return ArrowArrayPhysicalType::DICTIONARY_ENCODED;
|
23
|
-
}
|
24
|
-
if (type.RunEndEncoded()) {
|
25
|
-
return ArrowArrayPhysicalType::RUN_END_ENCODED;
|
26
|
-
}
|
27
|
-
return ArrowArrayPhysicalType::DEFAULT;
|
28
|
-
}
|
29
|
-
|
30
|
-
} // namespace
|
31
|
-
|
32
16
|
#if STANDARD_VECTOR_SIZE > 64
|
33
17
|
static void ShiftRight(unsigned char *ar, int size, int shift) {
|
34
18
|
int carry = 0;
|
@@ -42,7 +26,7 @@ static void ShiftRight(unsigned char *ar, int size, int shift) {
|
|
42
26
|
}
|
43
27
|
#endif
|
44
28
|
|
45
|
-
idx_t GetEffectiveOffset(const ArrowArray &array, int64_t parent_offset,
|
29
|
+
idx_t GetEffectiveOffset(const ArrowArray &array, int64_t parent_offset, idx_t chunk_offset,
|
46
30
|
int64_t nested_offset = -1) {
|
47
31
|
if (nested_offset != -1) {
|
48
32
|
// The parent of this array is a list
|
@@ -52,7 +36,7 @@ idx_t GetEffectiveOffset(const ArrowArray &array, int64_t parent_offset, const A
|
|
52
36
|
// Parent offset is set in the case of a struct, it applies to all child arrays
|
53
37
|
// 'chunk_offset' is how much of the chunk we've already scanned, in case the chunk size exceeds
|
54
38
|
// STANDARD_VECTOR_SIZE
|
55
|
-
return UnsafeNumericCast<idx_t>(array.offset + parent_offset) +
|
39
|
+
return UnsafeNumericCast<idx_t>(array.offset + parent_offset) + chunk_offset;
|
56
40
|
}
|
57
41
|
|
58
42
|
template <class T>
|
@@ -60,7 +44,7 @@ T *ArrowBufferData(ArrowArray &array, idx_t buffer_idx) {
|
|
60
44
|
return (T *)array.buffers[buffer_idx]; // NOLINT
|
61
45
|
}
|
62
46
|
|
63
|
-
static void GetValidityMask(ValidityMask &mask, ArrowArray &array,
|
47
|
+
static void GetValidityMask(ValidityMask &mask, ArrowArray &array, idx_t chunk_offset, idx_t size,
|
64
48
|
int64_t parent_offset, int64_t nested_offset = -1, bool add_null = false) {
|
65
49
|
// In certains we don't need to or cannot copy arrow's validity mask to duckdb.
|
66
50
|
//
|
@@ -69,7 +53,7 @@ static void GetValidityMask(ValidityMask &mask, ArrowArray &array, const ArrowSc
|
|
69
53
|
// 2. n_buffers > 0, meaning the array's arrow type is not `null`
|
70
54
|
// 3. the validity buffer (the first buffer) is not a nullptr
|
71
55
|
if (array.null_count != 0 && array.n_buffers > 0 && array.buffers[0]) {
|
72
|
-
auto bit_offset = GetEffectiveOffset(array, parent_offset,
|
56
|
+
auto bit_offset = GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
73
57
|
mask.EnsureWritable();
|
74
58
|
#if STANDARD_VECTOR_SIZE > 64
|
75
59
|
auto n_bitmask_bytes = (size + 8 - 1) / 8;
|
@@ -107,26 +91,13 @@ static void GetValidityMask(ValidityMask &mask, ArrowArray &array, const ArrowSc
|
|
107
91
|
}
|
108
92
|
}
|
109
93
|
|
110
|
-
|
111
|
-
|
94
|
+
void ArrowToDuckDBConversion::SetValidityMask(Vector &vector, ArrowArray &array, idx_t chunk_offset, idx_t size,
|
95
|
+
int64_t parent_offset, int64_t nested_offset, bool add_null) {
|
112
96
|
D_ASSERT(vector.GetVectorType() == VectorType::FLAT_VECTOR);
|
113
97
|
auto &mask = FlatVector::Validity(vector);
|
114
|
-
GetValidityMask(mask, array,
|
98
|
+
GetValidityMask(mask, array, chunk_offset, size, parent_offset, nested_offset, add_null);
|
115
99
|
}
|
116
100
|
|
117
|
-
static void ColumnArrowToDuckDBRunEndEncoded(Vector &vector, const ArrowArray &array, ArrowArrayScanState &array_state,
|
118
|
-
idx_t size, const ArrowType &arrow_type, int64_t nested_offset = -1,
|
119
|
-
ValidityMask *parent_mask = nullptr, uint64_t parent_offset = 0);
|
120
|
-
|
121
|
-
static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArrayScanState &array_state, idx_t size,
|
122
|
-
const ArrowType &arrow_type, int64_t nested_offset = -1,
|
123
|
-
ValidityMask *parent_mask = nullptr, uint64_t parent_offset = 0,
|
124
|
-
bool ignore_extensions = false);
|
125
|
-
|
126
|
-
static void ColumnArrowToDuckDBDictionary(Vector &vector, ArrowArray &array, ArrowArrayScanState &array_state,
|
127
|
-
idx_t size, const ArrowType &arrow_type, int64_t nested_offset = -1,
|
128
|
-
const ValidityMask *parent_mask = nullptr, uint64_t parent_offset = 0);
|
129
|
-
|
130
101
|
namespace {
|
131
102
|
|
132
103
|
struct ArrowListOffsetData {
|
@@ -223,15 +194,13 @@ static ArrowListOffsetData ConvertArrowListOffsets(Vector &vector, ArrowArray &a
|
|
223
194
|
}
|
224
195
|
}
|
225
196
|
|
226
|
-
static void ArrowToDuckDBList(Vector &vector, ArrowArray &array, ArrowArrayScanState &array_state,
|
227
|
-
const ArrowType &arrow_type, int64_t nested_offset,
|
228
|
-
int64_t parent_offset) {
|
229
|
-
auto &scan_state = array_state.state;
|
230
|
-
|
197
|
+
static void ArrowToDuckDBList(Vector &vector, ArrowArray &array, idx_t chunk_offset, ArrowArrayScanState &array_state,
|
198
|
+
idx_t size, const ArrowType &arrow_type, int64_t nested_offset,
|
199
|
+
const ValidityMask *parent_mask, int64_t parent_offset) {
|
231
200
|
auto &list_info = arrow_type.GetTypeInfo<ArrowListInfo>();
|
232
|
-
SetValidityMask(vector, array,
|
201
|
+
ArrowToDuckDBConversion::SetValidityMask(vector, array, chunk_offset, size, parent_offset, nested_offset);
|
233
202
|
|
234
|
-
auto effective_offset = GetEffectiveOffset(array, parent_offset,
|
203
|
+
auto effective_offset = GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
235
204
|
auto list_data = ConvertArrowListOffsets(vector, array, size, arrow_type, effective_offset);
|
236
205
|
auto &start_offset = list_data.start_offset;
|
237
206
|
auto &list_size = list_data.list_size;
|
@@ -239,8 +208,8 @@ static void ArrowToDuckDBList(Vector &vector, ArrowArray &array, ArrowArrayScanS
|
|
239
208
|
ListVector::Reserve(vector, list_size);
|
240
209
|
ListVector::SetListSize(vector, list_size);
|
241
210
|
auto &child_vector = ListVector::GetEntry(vector);
|
242
|
-
SetValidityMask(child_vector, *array.children[0],
|
243
|
-
|
211
|
+
ArrowToDuckDBConversion::SetValidityMask(child_vector, *array.children[0], chunk_offset, list_size, array.offset,
|
212
|
+
NumericCast<int64_t>(start_offset));
|
244
213
|
auto &list_mask = FlatVector::Validity(vector);
|
245
214
|
if (parent_mask) {
|
246
215
|
//! Since this List is owned by a struct we must guarantee their validity map matches on Null
|
@@ -258,45 +227,47 @@ static void ArrowToDuckDBList(Vector &vector, ArrowArray &array, ArrowArrayScanS
|
|
258
227
|
|
259
228
|
if (list_size == 0 && start_offset == 0) {
|
260
229
|
D_ASSERT(!child_array.dictionary);
|
261
|
-
ColumnArrowToDuckDB(child_vector, child_array, child_state, list_size,
|
230
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(child_vector, child_array, chunk_offset, child_state, list_size,
|
231
|
+
child_type, -1);
|
262
232
|
return;
|
263
233
|
}
|
264
234
|
|
265
|
-
auto array_physical_type =
|
235
|
+
auto array_physical_type = child_type.GetPhysicalType();
|
266
236
|
switch (array_physical_type) {
|
267
237
|
case ArrowArrayPhysicalType::DICTIONARY_ENCODED:
|
268
238
|
// TODO: add support for offsets
|
269
|
-
ColumnArrowToDuckDBDictionary(child_vector, child_array,
|
270
|
-
|
239
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBDictionary(child_vector, child_array, chunk_offset, child_state,
|
240
|
+
list_size, child_type,
|
241
|
+
NumericCast<int64_t>(start_offset));
|
271
242
|
break;
|
272
243
|
case ArrowArrayPhysicalType::RUN_END_ENCODED:
|
273
|
-
ColumnArrowToDuckDBRunEndEncoded(child_vector, child_array,
|
274
|
-
|
244
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBRunEndEncoded(child_vector, child_array, chunk_offset, child_state,
|
245
|
+
list_size, child_type,
|
246
|
+
NumericCast<int64_t>(start_offset));
|
275
247
|
break;
|
276
248
|
case ArrowArrayPhysicalType::DEFAULT:
|
277
|
-
ColumnArrowToDuckDB(child_vector, child_array, child_state, list_size,
|
278
|
-
|
249
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(child_vector, child_array, chunk_offset, child_state, list_size,
|
250
|
+
child_type, NumericCast<int64_t>(start_offset));
|
279
251
|
break;
|
280
252
|
default:
|
281
253
|
throw NotImplementedException("ArrowArrayPhysicalType not recognized");
|
282
254
|
}
|
283
255
|
}
|
284
256
|
|
285
|
-
static void ArrowToDuckDBArray(Vector &vector, ArrowArray &array, ArrowArrayScanState &array_state,
|
286
|
-
const ArrowType &arrow_type, int64_t nested_offset,
|
287
|
-
int64_t parent_offset) {
|
257
|
+
static void ArrowToDuckDBArray(Vector &vector, ArrowArray &array, idx_t chunk_offset, ArrowArrayScanState &array_state,
|
258
|
+
idx_t size, const ArrowType &arrow_type, int64_t nested_offset,
|
259
|
+
const ValidityMask *parent_mask, int64_t parent_offset) {
|
288
260
|
|
289
261
|
auto &array_info = arrow_type.GetTypeInfo<ArrowArrayInfo>();
|
290
|
-
auto &scan_state = array_state.state;
|
291
262
|
auto array_size = array_info.FixedSize();
|
292
263
|
auto child_count = array_size * size;
|
293
|
-
auto child_offset = GetEffectiveOffset(array, parent_offset,
|
264
|
+
auto child_offset = GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset) * array_size;
|
294
265
|
|
295
|
-
SetValidityMask(vector, array,
|
266
|
+
ArrowToDuckDBConversion::SetValidityMask(vector, array, chunk_offset, size, parent_offset, nested_offset);
|
296
267
|
|
297
268
|
auto &child_vector = ArrayVector::GetEntry(vector);
|
298
|
-
SetValidityMask(child_vector, *array.children[0],
|
299
|
-
|
269
|
+
ArrowToDuckDBConversion::SetValidityMask(child_vector, *array.children[0], chunk_offset, child_count, array.offset,
|
270
|
+
NumericCast<int64_t>(child_offset));
|
300
271
|
|
301
272
|
auto &array_mask = FlatVector::Validity(vector);
|
302
273
|
if (parent_mask) {
|
@@ -327,68 +298,16 @@ static void ArrowToDuckDBArray(Vector &vector, ArrowArray &array, ArrowArrayScan
|
|
327
298
|
auto &child_type = array_info.GetChild();
|
328
299
|
if (child_count == 0 && child_offset == 0) {
|
329
300
|
D_ASSERT(!child_array.dictionary);
|
330
|
-
ColumnArrowToDuckDB(child_vector, child_array, child_state, child_count,
|
301
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(child_vector, child_array, chunk_offset, child_state, child_count,
|
302
|
+
child_type, -1);
|
331
303
|
} else {
|
332
304
|
if (child_array.dictionary) {
|
333
|
-
ColumnArrowToDuckDBDictionary(child_vector, child_array,
|
334
|
-
|
305
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBDictionary(child_vector, child_array, chunk_offset, child_state,
|
306
|
+
child_count, child_type,
|
307
|
+
NumericCast<int64_t>(child_offset));
|
335
308
|
} else {
|
336
|
-
ColumnArrowToDuckDB(child_vector, child_array,
|
337
|
-
|
338
|
-
}
|
339
|
-
}
|
340
|
-
}
|
341
|
-
|
342
|
-
static void ArrowToDuckDBBlob(Vector &vector, ArrowArray &array, const ArrowScanLocalState &scan_state, idx_t size,
|
343
|
-
const ArrowType &arrow_type, int64_t nested_offset, int64_t parent_offset) {
|
344
|
-
SetValidityMask(vector, array, scan_state, size, parent_offset, nested_offset);
|
345
|
-
auto &string_info = arrow_type.GetTypeInfo<ArrowStringInfo>();
|
346
|
-
auto size_type = string_info.GetSizeType();
|
347
|
-
if (size_type == ArrowVariableSizeType::FIXED_SIZE) {
|
348
|
-
auto fixed_size = string_info.FixedSize();
|
349
|
-
//! Have to check validity mask before setting this up
|
350
|
-
idx_t offset = GetEffectiveOffset(array, parent_offset, scan_state, nested_offset) * fixed_size;
|
351
|
-
auto cdata = ArrowBufferData<char>(array, 1);
|
352
|
-
auto blob_len = fixed_size;
|
353
|
-
auto result = FlatVector::GetData<string_t>(vector);
|
354
|
-
for (idx_t row_idx = 0; row_idx < size; row_idx++) {
|
355
|
-
if (FlatVector::IsNull(vector, row_idx)) {
|
356
|
-
offset += blob_len;
|
357
|
-
continue;
|
358
|
-
}
|
359
|
-
auto bptr = cdata + offset;
|
360
|
-
result[row_idx] = StringVector::AddStringOrBlob(vector, bptr, blob_len);
|
361
|
-
offset += blob_len;
|
362
|
-
}
|
363
|
-
} else if (size_type == ArrowVariableSizeType::NORMAL) {
|
364
|
-
auto offsets =
|
365
|
-
ArrowBufferData<uint32_t>(array, 1) + GetEffectiveOffset(array, parent_offset, scan_state, nested_offset);
|
366
|
-
auto cdata = ArrowBufferData<char>(array, 2);
|
367
|
-
auto result = FlatVector::GetData<string_t>(vector);
|
368
|
-
for (idx_t row_idx = 0; row_idx < size; row_idx++) {
|
369
|
-
if (FlatVector::IsNull(vector, row_idx)) {
|
370
|
-
continue;
|
371
|
-
}
|
372
|
-
auto bptr = cdata + offsets[row_idx];
|
373
|
-
auto blob_len = offsets[row_idx + 1] - offsets[row_idx];
|
374
|
-
result[row_idx] = StringVector::AddStringOrBlob(vector, bptr, blob_len);
|
375
|
-
}
|
376
|
-
} else {
|
377
|
-
//! Check if last offset is higher than max uint32
|
378
|
-
if (ArrowBufferData<uint64_t>(array, 1)[array.length] > NumericLimits<uint32_t>::Maximum()) { // LCOV_EXCL_START
|
379
|
-
throw ConversionException("DuckDB does not support Blobs over 4GB");
|
380
|
-
} // LCOV_EXCL_STOP
|
381
|
-
auto offsets =
|
382
|
-
ArrowBufferData<uint64_t>(array, 1) + GetEffectiveOffset(array, parent_offset, scan_state, nested_offset);
|
383
|
-
auto cdata = ArrowBufferData<char>(array, 2);
|
384
|
-
auto result = FlatVector::GetData<string_t>(vector);
|
385
|
-
for (idx_t row_idx = 0; row_idx < size; row_idx++) {
|
386
|
-
if (FlatVector::IsNull(vector, row_idx)) {
|
387
|
-
continue;
|
388
|
-
}
|
389
|
-
auto bptr = cdata + offsets[row_idx];
|
390
|
-
auto blob_len = offsets[row_idx + 1] - offsets[row_idx];
|
391
|
-
result[row_idx] = StringVector::AddStringOrBlob(vector, bptr, blob_len);
|
309
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(child_vector, child_array, chunk_offset, child_state,
|
310
|
+
child_count, child_type, NumericCast<int64_t>(child_offset));
|
392
311
|
}
|
393
312
|
}
|
394
313
|
}
|
@@ -455,22 +374,22 @@ static void SetVectorStringView(Vector &vector, idx_t size, ArrowArray &array, i
|
|
455
374
|
}
|
456
375
|
}
|
457
376
|
|
458
|
-
static void DirectConversion(Vector &vector, ArrowArray &array,
|
459
|
-
|
377
|
+
static void DirectConversion(Vector &vector, ArrowArray &array, idx_t chunk_offset, int64_t nested_offset,
|
378
|
+
uint64_t parent_offset) {
|
460
379
|
auto internal_type = GetTypeIdSize(vector.GetType().InternalType());
|
461
380
|
auto data_ptr =
|
462
381
|
ArrowBufferData<data_t>(array, 1) +
|
463
|
-
internal_type * GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
382
|
+
internal_type * GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
464
383
|
FlatVector::SetData(vector, data_ptr);
|
465
384
|
}
|
466
385
|
|
467
386
|
template <class T>
|
468
|
-
static void TimeConversion(Vector &vector, ArrowArray &array,
|
469
|
-
int64_t
|
387
|
+
static void TimeConversion(Vector &vector, ArrowArray &array, idx_t chunk_offset, int64_t nested_offset,
|
388
|
+
int64_t parent_offset, idx_t size, int64_t conversion) {
|
470
389
|
auto tgt_ptr = FlatVector::GetData<dtime_t>(vector);
|
471
390
|
auto &validity_mask = FlatVector::Validity(vector);
|
472
|
-
auto src_ptr =
|
473
|
-
|
391
|
+
auto src_ptr = static_cast<const T *>(array.buffers[1]) +
|
392
|
+
GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
474
393
|
for (idx_t row = 0; row < size; row++) {
|
475
394
|
if (!validity_mask.RowIsValid(row)) {
|
476
395
|
continue;
|
@@ -481,12 +400,12 @@ static void TimeConversion(Vector &vector, ArrowArray &array, const ArrowScanLoc
|
|
481
400
|
}
|
482
401
|
}
|
483
402
|
|
484
|
-
static void UUIDConversion(Vector &vector, const ArrowArray &array,
|
485
|
-
int64_t
|
403
|
+
static void UUIDConversion(Vector &vector, const ArrowArray &array, idx_t chunk_offset, int64_t nested_offset,
|
404
|
+
int64_t parent_offset, idx_t size) {
|
486
405
|
auto tgt_ptr = FlatVector::GetData<hugeint_t>(vector);
|
487
406
|
auto &validity_mask = FlatVector::Validity(vector);
|
488
407
|
auto src_ptr = static_cast<const hugeint_t *>(array.buffers[1]) +
|
489
|
-
GetEffectiveOffset(array, parent_offset,
|
408
|
+
GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
490
409
|
for (idx_t row = 0; row < size; row++) {
|
491
410
|
if (!validity_mask.RowIsValid(row)) {
|
492
411
|
continue;
|
@@ -498,12 +417,12 @@ static void UUIDConversion(Vector &vector, const ArrowArray &array, const ArrowS
|
|
498
417
|
}
|
499
418
|
}
|
500
419
|
|
501
|
-
static void TimestampTZConversion(Vector &vector, ArrowArray &array,
|
502
|
-
int64_t
|
420
|
+
static void TimestampTZConversion(Vector &vector, ArrowArray &array, idx_t chunk_offset, int64_t nested_offset,
|
421
|
+
int64_t parent_offset, idx_t size, int64_t conversion) {
|
503
422
|
auto tgt_ptr = FlatVector::GetData<timestamp_t>(vector);
|
504
423
|
auto &validity_mask = FlatVector::Validity(vector);
|
505
424
|
auto src_ptr =
|
506
|
-
ArrowBufferData<int64_t>(array, 1) + GetEffectiveOffset(array, parent_offset,
|
425
|
+
ArrowBufferData<int64_t>(array, 1) + GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
507
426
|
for (idx_t row = 0; row < size; row++) {
|
508
427
|
if (!validity_mask.RowIsValid(row)) {
|
509
428
|
continue;
|
@@ -514,11 +433,11 @@ static void TimestampTZConversion(Vector &vector, ArrowArray &array, const Arrow
|
|
514
433
|
}
|
515
434
|
}
|
516
435
|
|
517
|
-
static void IntervalConversionUs(Vector &vector, ArrowArray &array,
|
518
|
-
int64_t
|
436
|
+
static void IntervalConversionUs(Vector &vector, ArrowArray &array, idx_t chunk_offset, int64_t nested_offset,
|
437
|
+
int64_t parent_offset, idx_t size, int64_t conversion) {
|
519
438
|
auto tgt_ptr = FlatVector::GetData<interval_t>(vector);
|
520
439
|
auto src_ptr =
|
521
|
-
ArrowBufferData<int64_t>(array, 1) + GetEffectiveOffset(array, parent_offset,
|
440
|
+
ArrowBufferData<int64_t>(array, 1) + GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
522
441
|
for (idx_t row = 0; row < size; row++) {
|
523
442
|
tgt_ptr[row].days = 0;
|
524
443
|
tgt_ptr[row].months = 0;
|
@@ -528,11 +447,11 @@ static void IntervalConversionUs(Vector &vector, ArrowArray &array, const ArrowS
|
|
528
447
|
}
|
529
448
|
}
|
530
449
|
|
531
|
-
static void IntervalConversionMonths(Vector &vector, ArrowArray &array,
|
532
|
-
int64_t
|
450
|
+
static void IntervalConversionMonths(Vector &vector, ArrowArray &array, idx_t chunk_offset, int64_t nested_offset,
|
451
|
+
int64_t parent_offset, idx_t size) {
|
533
452
|
auto tgt_ptr = FlatVector::GetData<interval_t>(vector);
|
534
453
|
auto src_ptr =
|
535
|
-
ArrowBufferData<int32_t>(array, 1) + GetEffectiveOffset(array, parent_offset,
|
454
|
+
ArrowBufferData<int32_t>(array, 1) + GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
536
455
|
for (idx_t row = 0; row < size; row++) {
|
537
456
|
tgt_ptr[row].days = 0;
|
538
457
|
tgt_ptr[row].micros = 0;
|
@@ -540,11 +459,11 @@ static void IntervalConversionMonths(Vector &vector, ArrowArray &array, const Ar
|
|
540
459
|
}
|
541
460
|
}
|
542
461
|
|
543
|
-
static void IntervalConversionMonthDayNanos(Vector &vector, ArrowArray &array,
|
462
|
+
static void IntervalConversionMonthDayNanos(Vector &vector, ArrowArray &array, idx_t chunk_offset,
|
544
463
|
int64_t nested_offset, int64_t parent_offset, idx_t size) {
|
545
464
|
auto tgt_ptr = FlatVector::GetData<interval_t>(vector);
|
546
|
-
auto src_ptr =
|
547
|
-
|
465
|
+
auto src_ptr = ArrowBufferData<ArrowInterval>(array, 1) +
|
466
|
+
GetEffectiveOffset(array, parent_offset, chunk_offset, nested_offset);
|
548
467
|
for (idx_t row = 0; row < size; row++) {
|
549
468
|
tgt_ptr[row].days = src_ptr[row].days;
|
550
469
|
tgt_ptr[row].micros = src_ptr[row].nanoseconds / Interval::NANOS_PER_MICRO;
|
@@ -718,9 +637,11 @@ static void FlattenRunEndsSwitch(Vector &result, ArrowRunEndEncodingState &run_e
|
|
718
637
|
}
|
719
638
|
}
|
720
639
|
|
721
|
-
|
722
|
-
|
723
|
-
|
640
|
+
void ArrowToDuckDBConversion::ColumnArrowToDuckDBRunEndEncoded(Vector &vector, const ArrowArray &array,
|
641
|
+
idx_t chunk_offset, ArrowArrayScanState &array_state,
|
642
|
+
idx_t size, const ArrowType &arrow_type,
|
643
|
+
int64_t nested_offset, ValidityMask *parent_mask,
|
644
|
+
uint64_t parent_offset) {
|
724
645
|
// Scan the 'run_ends' array
|
725
646
|
D_ASSERT(array.n_children == 2);
|
726
647
|
auto &run_ends_array = *array.children[0];
|
@@ -731,7 +652,6 @@ static void ColumnArrowToDuckDBRunEndEncoded(Vector &vector, const ArrowArray &a
|
|
731
652
|
auto &values_type = struct_info.GetChild(1);
|
732
653
|
D_ASSERT(vector.GetType() == values_type.GetDuckType());
|
733
654
|
|
734
|
-
auto &scan_state = array_state.state;
|
735
655
|
if (vector.GetBuffer()) {
|
736
656
|
vector.GetBuffer()->SetAuxiliaryData(make_uniq<ArrowAuxiliaryData>(array_state.owned_data));
|
737
657
|
}
|
@@ -746,14 +666,16 @@ static void ColumnArrowToDuckDBRunEndEncoded(Vector &vector, const ArrowArray &a
|
|
746
666
|
run_end_encoding.run_ends = make_uniq<Vector>(run_ends_type.GetDuckType(), compressed_size);
|
747
667
|
run_end_encoding.values = make_uniq<Vector>(values_type.GetDuckType(), compressed_size);
|
748
668
|
|
749
|
-
ColumnArrowToDuckDB(*run_end_encoding.run_ends, run_ends_array,
|
669
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(*run_end_encoding.run_ends, run_ends_array, chunk_offset,
|
670
|
+
array_state, compressed_size, run_ends_type);
|
750
671
|
auto &values = *run_end_encoding.values;
|
751
|
-
SetValidityMask(values, values_array,
|
752
|
-
|
753
|
-
ColumnArrowToDuckDB(values, values_array, array_state, compressed_size,
|
672
|
+
ArrowToDuckDBConversion::SetValidityMask(values, values_array, chunk_offset, compressed_size,
|
673
|
+
NumericCast<int64_t>(parent_offset), nested_offset);
|
674
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(values, values_array, chunk_offset, array_state, compressed_size,
|
675
|
+
values_type);
|
754
676
|
}
|
755
677
|
|
756
|
-
idx_t scan_offset = GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
678
|
+
idx_t scan_offset = GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
757
679
|
auto physical_type = run_ends_type.GetDuckType().InternalType();
|
758
680
|
switch (physical_type) {
|
759
681
|
case PhysicalType::INT16:
|
@@ -771,7 +693,7 @@ static void ColumnArrowToDuckDBRunEndEncoded(Vector &vector, const ArrowArray &a
|
|
771
693
|
}
|
772
694
|
template <class SRC>
|
773
695
|
void ConvertDecimal(SRC src_ptr, Vector &vector, ArrowArray &array, idx_t size, int64_t nested_offset,
|
774
|
-
uint64_t parent_offset,
|
696
|
+
uint64_t parent_offset, idx_t chunk_offset, ValidityMask &val_mask,
|
775
697
|
DecimalBitWidth arrow_bit_width) {
|
776
698
|
|
777
699
|
switch (vector.GetType().InternalType()) {
|
@@ -791,7 +713,7 @@ void ConvertDecimal(SRC src_ptr, Vector &vector, ArrowArray &array, idx_t size,
|
|
791
713
|
FlatVector::SetData(vector, ArrowBufferData<data_t>(array, 1) +
|
792
714
|
GetTypeIdSize(vector.GetType().InternalType()) *
|
793
715
|
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
794
|
-
|
716
|
+
chunk_offset, nested_offset));
|
795
717
|
} else {
|
796
718
|
auto tgt_ptr = FlatVector::GetData<int32_t>(vector);
|
797
719
|
for (idx_t row = 0; row < size; row++) {
|
@@ -809,7 +731,7 @@ void ConvertDecimal(SRC src_ptr, Vector &vector, ArrowArray &array, idx_t size,
|
|
809
731
|
FlatVector::SetData(vector, ArrowBufferData<data_t>(array, 1) +
|
810
732
|
GetTypeIdSize(vector.GetType().InternalType()) *
|
811
733
|
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
812
|
-
|
734
|
+
chunk_offset, nested_offset));
|
813
735
|
} else {
|
814
736
|
auto tgt_ptr = FlatVector::GetData<int64_t>(vector);
|
815
737
|
for (idx_t row = 0; row < size; row++) {
|
@@ -827,7 +749,7 @@ void ConvertDecimal(SRC src_ptr, Vector &vector, ArrowArray &array, idx_t size,
|
|
827
749
|
FlatVector::SetData(vector, ArrowBufferData<data_t>(array, 1) +
|
828
750
|
GetTypeIdSize(vector.GetType().InternalType()) *
|
829
751
|
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
830
|
-
|
752
|
+
chunk_offset, nested_offset));
|
831
753
|
} else {
|
832
754
|
auto tgt_ptr = FlatVector::GetData<hugeint_t>(vector);
|
833
755
|
for (idx_t row = 0; row < size; row++) {
|
@@ -847,17 +769,18 @@ void ConvertDecimal(SRC src_ptr, Vector &vector, ArrowArray &array, idx_t size,
|
|
847
769
|
}
|
848
770
|
}
|
849
771
|
|
850
|
-
|
851
|
-
|
852
|
-
|
853
|
-
|
772
|
+
void ArrowToDuckDBConversion::ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, idx_t chunk_offset,
|
773
|
+
ArrowArrayScanState &array_state, idx_t size,
|
774
|
+
const ArrowType &arrow_type, int64_t nested_offset,
|
775
|
+
ValidityMask *parent_mask, uint64_t parent_offset,
|
776
|
+
bool ignore_extensions) {
|
854
777
|
D_ASSERT(!array.dictionary);
|
855
778
|
if (!ignore_extensions && arrow_type.HasExtension()) {
|
856
779
|
if (arrow_type.extension_data->arrow_to_duckdb) {
|
857
780
|
// Convert the storage and then call the cast function
|
858
781
|
Vector input_data(arrow_type.extension_data->GetInternalType());
|
859
|
-
ColumnArrowToDuckDB(input_data, array, array_state, size, arrow_type, nested_offset,
|
860
|
-
parent_offset, /*ignore_extensions*/ true);
|
782
|
+
ColumnArrowToDuckDB(input_data, array, chunk_offset, array_state, size, arrow_type, nested_offset,
|
783
|
+
parent_mask, parent_offset, /*ignore_extensions*/ true);
|
861
784
|
arrow_type.extension_data->arrow_to_duckdb(array_state.context, input_data, vector, size);
|
862
785
|
return;
|
863
786
|
}
|
@@ -874,7 +797,7 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
874
797
|
//! Arrow bit-packs boolean values
|
875
798
|
//! Lets first figure out where we are in the source array
|
876
799
|
auto effective_offset =
|
877
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
800
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
878
801
|
auto src_ptr = ArrowBufferData<uint8_t>(array, 1) + effective_offset / 8;
|
879
802
|
auto tgt_ptr = (uint8_t *)FlatVector::GetData(vector);
|
880
803
|
int src_pos = 0;
|
@@ -910,12 +833,15 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
910
833
|
case LogicalTypeId::TIMESTAMP_MS:
|
911
834
|
case LogicalTypeId::TIMESTAMP_NS:
|
912
835
|
case LogicalTypeId::TIME_TZ: {
|
913
|
-
DirectConversion(vector, array,
|
836
|
+
DirectConversion(vector, array, chunk_offset, nested_offset, parent_offset);
|
914
837
|
break;
|
915
838
|
}
|
916
839
|
case LogicalTypeId::UUID:
|
917
|
-
UUIDConversion(vector, array,
|
840
|
+
UUIDConversion(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset), size);
|
918
841
|
break;
|
842
|
+
case LogicalTypeId::BLOB:
|
843
|
+
case LogicalTypeId::BIT:
|
844
|
+
case LogicalTypeId::BIGNUM:
|
919
845
|
case LogicalTypeId::VARCHAR: {
|
920
846
|
auto &string_info = arrow_type.GetTypeInfo<ArrowStringInfo>();
|
921
847
|
auto size_type = string_info.GetSizeType();
|
@@ -923,24 +849,42 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
923
849
|
case ArrowVariableSizeType::SUPER_SIZE: {
|
924
850
|
auto cdata = ArrowBufferData<char>(array, 2);
|
925
851
|
auto offsets = ArrowBufferData<uint64_t>(array, 1) +
|
926
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
852
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
927
853
|
SetVectorString(vector, size, cdata, offsets);
|
928
854
|
break;
|
929
855
|
}
|
930
|
-
case ArrowVariableSizeType::NORMAL:
|
931
|
-
case ArrowVariableSizeType::FIXED_SIZE: {
|
856
|
+
case ArrowVariableSizeType::NORMAL: {
|
932
857
|
auto cdata = ArrowBufferData<char>(array, 2);
|
933
858
|
auto offsets = ArrowBufferData<uint32_t>(array, 1) +
|
934
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
859
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
935
860
|
SetVectorString(vector, size, cdata, offsets);
|
936
861
|
break;
|
937
862
|
}
|
938
863
|
case ArrowVariableSizeType::VIEW: {
|
939
864
|
SetVectorStringView(
|
940
865
|
vector, size, array,
|
941
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
866
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset));
|
942
867
|
break;
|
943
868
|
}
|
869
|
+
case ArrowVariableSizeType::FIXED_SIZE: {
|
870
|
+
SetValidityMask(vector, array, chunk_offset, size, NumericCast<int64_t>(parent_offset), nested_offset);
|
871
|
+
auto fixed_size = string_info.FixedSize();
|
872
|
+
// Have to check validity mask before setting this up
|
873
|
+
idx_t offset = GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset) *
|
874
|
+
fixed_size;
|
875
|
+
auto cdata = ArrowBufferData<char>(array, 1);
|
876
|
+
auto blob_len = fixed_size;
|
877
|
+
auto result = FlatVector::GetData<string_t>(vector);
|
878
|
+
for (idx_t row_idx = 0; row_idx < size; row_idx++) {
|
879
|
+
if (FlatVector::IsNull(vector, row_idx)) {
|
880
|
+
offset += blob_len;
|
881
|
+
continue;
|
882
|
+
}
|
883
|
+
auto bptr = cdata + offset;
|
884
|
+
result[row_idx] = StringVector::AddStringOrBlob(vector, bptr, blob_len);
|
885
|
+
offset += blob_len;
|
886
|
+
}
|
887
|
+
}
|
944
888
|
}
|
945
889
|
break;
|
946
890
|
}
|
@@ -949,13 +893,13 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
949
893
|
auto precision = datetime_info.GetDateTimeType();
|
950
894
|
switch (precision) {
|
951
895
|
case ArrowDateTimeType::DAYS: {
|
952
|
-
DirectConversion(vector, array,
|
896
|
+
DirectConversion(vector, array, chunk_offset, nested_offset, parent_offset);
|
953
897
|
break;
|
954
898
|
}
|
955
899
|
case ArrowDateTimeType::MILLISECONDS: {
|
956
900
|
//! convert date from nanoseconds to days
|
957
901
|
auto src_ptr = ArrowBufferData<uint64_t>(array, 1) +
|
958
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
902
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
959
903
|
auto tgt_ptr = FlatVector::GetData<date_t>(vector);
|
960
904
|
for (idx_t row = 0; row < size; row++) {
|
961
905
|
tgt_ptr[row] = date_t(UnsafeNumericCast<int32_t>(static_cast<int64_t>(src_ptr[row]) /
|
@@ -973,24 +917,24 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
973
917
|
auto precision = datetime_info.GetDateTimeType();
|
974
918
|
switch (precision) {
|
975
919
|
case ArrowDateTimeType::SECONDS: {
|
976
|
-
TimeConversion<int32_t>(vector, array,
|
977
|
-
1000000);
|
920
|
+
TimeConversion<int32_t>(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset),
|
921
|
+
size, 1000000);
|
978
922
|
break;
|
979
923
|
}
|
980
924
|
case ArrowDateTimeType::MILLISECONDS: {
|
981
|
-
TimeConversion<int32_t>(vector, array,
|
982
|
-
1000);
|
925
|
+
TimeConversion<int32_t>(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset),
|
926
|
+
size, 1000);
|
983
927
|
break;
|
984
928
|
}
|
985
929
|
case ArrowDateTimeType::MICROSECONDS: {
|
986
|
-
TimeConversion<int64_t>(vector, array,
|
987
|
-
1);
|
930
|
+
TimeConversion<int64_t>(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset),
|
931
|
+
size, 1);
|
988
932
|
break;
|
989
933
|
}
|
990
934
|
case ArrowDateTimeType::NANOSECONDS: {
|
991
935
|
auto tgt_ptr = FlatVector::GetData<dtime_t>(vector);
|
992
936
|
auto src_ptr = ArrowBufferData<int64_t>(array, 1) +
|
993
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
937
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
994
938
|
for (idx_t row = 0; row < size; row++) {
|
995
939
|
tgt_ptr[row].micros = src_ptr[row] / 1000;
|
996
940
|
}
|
@@ -1006,23 +950,23 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1006
950
|
auto precision = datetime_info.GetDateTimeType();
|
1007
951
|
switch (precision) {
|
1008
952
|
case ArrowDateTimeType::SECONDS: {
|
1009
|
-
TimestampTZConversion(vector, array,
|
953
|
+
TimestampTZConversion(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset), size,
|
1010
954
|
1000000);
|
1011
955
|
break;
|
1012
956
|
}
|
1013
957
|
case ArrowDateTimeType::MILLISECONDS: {
|
1014
|
-
TimestampTZConversion(vector, array,
|
958
|
+
TimestampTZConversion(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset), size,
|
1015
959
|
1000);
|
1016
960
|
break;
|
1017
961
|
}
|
1018
962
|
case ArrowDateTimeType::MICROSECONDS: {
|
1019
|
-
DirectConversion(vector, array,
|
963
|
+
DirectConversion(vector, array, chunk_offset, nested_offset, parent_offset);
|
1020
964
|
break;
|
1021
965
|
}
|
1022
966
|
case ArrowDateTimeType::NANOSECONDS: {
|
1023
967
|
auto tgt_ptr = FlatVector::GetData<timestamp_t>(vector);
|
1024
968
|
auto src_ptr = ArrowBufferData<int64_t>(array, 1) +
|
1025
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
969
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
1026
970
|
for (idx_t row = 0; row < size; row++) {
|
1027
971
|
tgt_ptr[row].value = src_ptr[row] / 1000;
|
1028
972
|
}
|
@@ -1038,25 +982,25 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1038
982
|
auto precision = datetime_info.GetDateTimeType();
|
1039
983
|
switch (precision) {
|
1040
984
|
case ArrowDateTimeType::SECONDS: {
|
1041
|
-
IntervalConversionUs(vector, array,
|
985
|
+
IntervalConversionUs(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset), size,
|
1042
986
|
1000000);
|
1043
987
|
break;
|
1044
988
|
}
|
1045
989
|
case ArrowDateTimeType::DAYS:
|
1046
990
|
case ArrowDateTimeType::MILLISECONDS: {
|
1047
|
-
IntervalConversionUs(vector, array,
|
991
|
+
IntervalConversionUs(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset), size,
|
1048
992
|
1000);
|
1049
993
|
break;
|
1050
994
|
}
|
1051
995
|
case ArrowDateTimeType::MICROSECONDS: {
|
1052
|
-
IntervalConversionUs(vector, array,
|
996
|
+
IntervalConversionUs(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset), size,
|
1053
997
|
1);
|
1054
998
|
break;
|
1055
999
|
}
|
1056
1000
|
case ArrowDateTimeType::NANOSECONDS: {
|
1057
1001
|
auto tgt_ptr = FlatVector::GetData<interval_t>(vector);
|
1058
1002
|
auto src_ptr = ArrowBufferData<int64_t>(array, 1) +
|
1059
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
1003
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
1060
1004
|
for (idx_t row = 0; row < size; row++) {
|
1061
1005
|
tgt_ptr[row].micros = src_ptr[row] / 1000;
|
1062
1006
|
tgt_ptr[row].days = 0;
|
@@ -1065,12 +1009,12 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1065
1009
|
break;
|
1066
1010
|
}
|
1067
1011
|
case ArrowDateTimeType::MONTHS: {
|
1068
|
-
IntervalConversionMonths(vector, array,
|
1012
|
+
IntervalConversionMonths(vector, array, chunk_offset, nested_offset, NumericCast<int64_t>(parent_offset),
|
1069
1013
|
size);
|
1070
1014
|
break;
|
1071
1015
|
}
|
1072
1016
|
case ArrowDateTimeType::MONTH_DAY_NANO: {
|
1073
|
-
IntervalConversionMonthDayNanos(vector, array,
|
1017
|
+
IntervalConversionMonthDayNanos(vector, array, chunk_offset, nested_offset,
|
1074
1018
|
NumericCast<int64_t>(parent_offset), size);
|
1075
1019
|
break;
|
1076
1020
|
}
|
@@ -1087,22 +1031,25 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1087
1031
|
switch (bit_width) {
|
1088
1032
|
case DecimalBitWidth::DECIMAL_32: {
|
1089
1033
|
auto src_ptr = ArrowBufferData<int32_t>(array, 1) +
|
1090
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
1091
|
-
ConvertDecimal(src_ptr, vector, array, size, nested_offset, parent_offset,
|
1034
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
1035
|
+
ConvertDecimal(src_ptr, vector, array, size, nested_offset, parent_offset, chunk_offset, val_mask,
|
1036
|
+
bit_width);
|
1092
1037
|
break;
|
1093
1038
|
}
|
1094
1039
|
|
1095
1040
|
case DecimalBitWidth::DECIMAL_64: {
|
1096
1041
|
auto src_ptr = ArrowBufferData<int64_t>(array, 1) +
|
1097
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
1098
|
-
ConvertDecimal(src_ptr, vector, array, size, nested_offset, parent_offset,
|
1042
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
1043
|
+
ConvertDecimal(src_ptr, vector, array, size, nested_offset, parent_offset, chunk_offset, val_mask,
|
1044
|
+
bit_width);
|
1099
1045
|
break;
|
1100
1046
|
}
|
1101
1047
|
|
1102
1048
|
case DecimalBitWidth::DECIMAL_128: {
|
1103
1049
|
auto src_ptr = ArrowBufferData<hugeint_t>(array, 1) +
|
1104
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
1105
|
-
ConvertDecimal(src_ptr, vector, array, size, nested_offset, parent_offset,
|
1050
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
1051
|
+
ConvertDecimal(src_ptr, vector, array, size, nested_offset, parent_offset, chunk_offset, val_mask,
|
1052
|
+
bit_width);
|
1106
1053
|
break;
|
1107
1054
|
}
|
1108
1055
|
default:
|
@@ -1110,25 +1057,18 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1110
1057
|
}
|
1111
1058
|
break;
|
1112
1059
|
}
|
1113
|
-
case LogicalTypeId::BLOB:
|
1114
|
-
case LogicalTypeId::BIT:
|
1115
|
-
case LogicalTypeId::VARINT: {
|
1116
|
-
ArrowToDuckDBBlob(vector, array, scan_state, size, arrow_type, nested_offset,
|
1117
|
-
NumericCast<int64_t>(parent_offset));
|
1118
|
-
break;
|
1119
|
-
}
|
1120
1060
|
case LogicalTypeId::LIST: {
|
1121
|
-
ArrowToDuckDBList(vector, array, array_state, size, arrow_type, nested_offset, parent_mask,
|
1061
|
+
ArrowToDuckDBList(vector, array, chunk_offset, array_state, size, arrow_type, nested_offset, parent_mask,
|
1122
1062
|
NumericCast<int64_t>(parent_offset));
|
1123
1063
|
break;
|
1124
1064
|
}
|
1125
1065
|
case LogicalTypeId::ARRAY: {
|
1126
|
-
ArrowToDuckDBArray(vector, array, array_state, size, arrow_type, nested_offset, parent_mask,
|
1066
|
+
ArrowToDuckDBArray(vector, array, chunk_offset, array_state, size, arrow_type, nested_offset, parent_mask,
|
1127
1067
|
NumericCast<int64_t>(parent_offset));
|
1128
1068
|
break;
|
1129
1069
|
}
|
1130
1070
|
case LogicalTypeId::MAP: {
|
1131
|
-
ArrowToDuckDBList(vector, array, array_state, size, arrow_type, nested_offset, parent_mask,
|
1071
|
+
ArrowToDuckDBList(vector, array, chunk_offset, array_state, size, arrow_type, nested_offset, parent_mask,
|
1132
1072
|
NumericCast<int64_t>(parent_offset));
|
1133
1073
|
ArrowToDuckDBMapVerify(vector, size);
|
1134
1074
|
break;
|
@@ -1144,7 +1084,8 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1144
1084
|
auto &child_type = struct_info.GetChild(child_idx);
|
1145
1085
|
auto &child_state = array_state.GetChild(child_idx);
|
1146
1086
|
|
1147
|
-
SetValidityMask(child_entry, child_array,
|
1087
|
+
ArrowToDuckDBConversion::SetValidityMask(child_entry, child_array, chunk_offset, size, array.offset,
|
1088
|
+
nested_offset);
|
1148
1089
|
if (!struct_validity_mask.AllValid()) {
|
1149
1090
|
auto &child_validity_mark = FlatVector::Validity(child_entry);
|
1150
1091
|
for (idx_t i = 0; i < size; i++) {
|
@@ -1154,19 +1095,21 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1154
1095
|
}
|
1155
1096
|
}
|
1156
1097
|
|
1157
|
-
auto array_physical_type =
|
1098
|
+
auto array_physical_type = child_type.GetPhysicalType();
|
1158
1099
|
switch (array_physical_type) {
|
1159
1100
|
case ArrowArrayPhysicalType::DICTIONARY_ENCODED:
|
1160
|
-
ColumnArrowToDuckDBDictionary(
|
1161
|
-
|
1101
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBDictionary(
|
1102
|
+
child_entry, child_array, chunk_offset, child_state, size, child_type, nested_offset,
|
1103
|
+
&struct_validity_mask, NumericCast<uint64_t>(array.offset));
|
1162
1104
|
break;
|
1163
1105
|
case ArrowArrayPhysicalType::RUN_END_ENCODED:
|
1164
|
-
ColumnArrowToDuckDBRunEndEncoded(child_entry, child_array, child_state, size, child_type,
|
1165
|
-
&struct_validity_mask,
|
1106
|
+
ColumnArrowToDuckDBRunEndEncoded(child_entry, child_array, chunk_offset, child_state, size, child_type,
|
1107
|
+
nested_offset, &struct_validity_mask,
|
1108
|
+
NumericCast<uint64_t>(array.offset));
|
1166
1109
|
break;
|
1167
1110
|
case ArrowArrayPhysicalType::DEFAULT:
|
1168
|
-
ColumnArrowToDuckDB(child_entry, child_array, child_state, size, child_type,
|
1169
|
-
&struct_validity_mask, NumericCast<uint64_t>(array.offset), false);
|
1111
|
+
ColumnArrowToDuckDB(child_entry, child_array, chunk_offset, child_state, size, child_type,
|
1112
|
+
nested_offset, &struct_validity_mask, NumericCast<uint64_t>(array.offset), false);
|
1170
1113
|
break;
|
1171
1114
|
default:
|
1172
1115
|
throw NotImplementedException("ArrowArrayPhysicalType not recognized");
|
@@ -1188,19 +1131,22 @@ static void ColumnArrowToDuckDB(Vector &vector, ArrowArray &array, ArrowArraySca
|
|
1188
1131
|
auto &child_state = array_state.GetChild(child_idx);
|
1189
1132
|
auto &child_type = union_info.GetChild(child_idx);
|
1190
1133
|
|
1191
|
-
SetValidityMask(child, child_array,
|
1192
|
-
|
1134
|
+
ArrowToDuckDBConversion::SetValidityMask(child, child_array, chunk_offset, size,
|
1135
|
+
NumericCast<int64_t>(parent_offset), nested_offset);
|
1136
|
+
auto array_physical_type = child_type.GetPhysicalType();
|
1193
1137
|
|
1194
1138
|
switch (array_physical_type) {
|
1195
1139
|
case ArrowArrayPhysicalType::DICTIONARY_ENCODED:
|
1196
|
-
ColumnArrowToDuckDBDictionary(child, child_array,
|
1140
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBDictionary(child, child_array, chunk_offset, child_state,
|
1141
|
+
size, child_type);
|
1197
1142
|
break;
|
1198
1143
|
case ArrowArrayPhysicalType::RUN_END_ENCODED:
|
1199
|
-
ColumnArrowToDuckDBRunEndEncoded(child, child_array,
|
1144
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBRunEndEncoded(child, child_array, chunk_offset, child_state,
|
1145
|
+
size, child_type);
|
1200
1146
|
break;
|
1201
1147
|
case ArrowArrayPhysicalType::DEFAULT:
|
1202
|
-
ColumnArrowToDuckDB(child, child_array, child_state, size,
|
1203
|
-
|
1148
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(child, child_array, chunk_offset, child_state, size,
|
1149
|
+
child_type, nested_offset, &validity_mask, false);
|
1204
1150
|
break;
|
1205
1151
|
default:
|
1206
1152
|
throw NotImplementedException("ArrowArrayPhysicalType not recognized");
|
@@ -1361,33 +1307,34 @@ static bool CanContainNull(const ArrowArray &array, const ValidityMask *parent_m
|
|
1361
1307
|
return !parent_mask->AllValid();
|
1362
1308
|
}
|
1363
1309
|
|
1364
|
-
|
1365
|
-
|
1366
|
-
|
1310
|
+
void ArrowToDuckDBConversion::ColumnArrowToDuckDBDictionary(Vector &vector, ArrowArray &array, idx_t chunk_offset,
|
1311
|
+
ArrowArrayScanState &array_state, idx_t size,
|
1312
|
+
const ArrowType &arrow_type, int64_t nested_offset,
|
1313
|
+
const ValidityMask *parent_mask, uint64_t parent_offset) {
|
1367
1314
|
if (vector.GetBuffer()) {
|
1368
1315
|
vector.GetBuffer()->SetAuxiliaryData(make_uniq<ArrowAuxiliaryData>(array_state.owned_data));
|
1369
1316
|
}
|
1370
1317
|
D_ASSERT(arrow_type.HasDictionary());
|
1371
|
-
auto &scan_state = array_state.state;
|
1372
1318
|
const bool has_nulls = CanContainNull(array, parent_mask);
|
1373
1319
|
if (array_state.CacheOutdated(array.dictionary)) {
|
1374
1320
|
//! We need to set the dictionary data for this column
|
1375
1321
|
auto base_vector = make_uniq<Vector>(vector.GetType(), NumericCast<idx_t>(array.dictionary->length));
|
1376
|
-
SetValidityMask(*base_vector, *array.dictionary,
|
1377
|
-
|
1322
|
+
ArrowToDuckDBConversion::SetValidityMask(*base_vector, *array.dictionary, chunk_offset,
|
1323
|
+
NumericCast<idx_t>(array.dictionary->length), 0, 0, has_nulls);
|
1378
1324
|
auto &dictionary_type = arrow_type.GetDictionary();
|
1379
|
-
auto arrow_physical_type =
|
1325
|
+
auto arrow_physical_type = dictionary_type.GetPhysicalType();
|
1326
|
+
;
|
1380
1327
|
switch (arrow_physical_type) {
|
1381
1328
|
case ArrowArrayPhysicalType::DICTIONARY_ENCODED:
|
1382
|
-
ColumnArrowToDuckDBDictionary(*base_vector, *array.dictionary, array_state,
|
1329
|
+
ColumnArrowToDuckDBDictionary(*base_vector, *array.dictionary, chunk_offset, array_state,
|
1383
1330
|
NumericCast<idx_t>(array.dictionary->length), dictionary_type);
|
1384
1331
|
break;
|
1385
1332
|
case ArrowArrayPhysicalType::RUN_END_ENCODED:
|
1386
|
-
ColumnArrowToDuckDBRunEndEncoded(*base_vector, *array.dictionary, array_state,
|
1333
|
+
ColumnArrowToDuckDBRunEndEncoded(*base_vector, *array.dictionary, chunk_offset, array_state,
|
1387
1334
|
NumericCast<idx_t>(array.dictionary->length), dictionary_type);
|
1388
1335
|
break;
|
1389
1336
|
case ArrowArrayPhysicalType::DEFAULT:
|
1390
|
-
ColumnArrowToDuckDB(*base_vector, *array.dictionary, array_state,
|
1337
|
+
ColumnArrowToDuckDB(*base_vector, *array.dictionary, chunk_offset, array_state,
|
1391
1338
|
NumericCast<idx_t>(array.dictionary->length), dictionary_type);
|
1392
1339
|
break;
|
1393
1340
|
default:
|
@@ -1399,12 +1346,12 @@ static void ColumnArrowToDuckDBDictionary(Vector &vector, ArrowArray &array, Arr
|
|
1399
1346
|
//! Get Pointer to Indices of Dictionary
|
1400
1347
|
auto indices = ArrowBufferData<data_t>(array, 1) +
|
1401
1348
|
GetTypeIdSize(offset_type.InternalType()) *
|
1402
|
-
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset),
|
1349
|
+
GetEffectiveOffset(array, NumericCast<int64_t>(parent_offset), chunk_offset, nested_offset);
|
1403
1350
|
|
1404
1351
|
SelectionVector sel;
|
1405
1352
|
if (has_nulls) {
|
1406
1353
|
ValidityMask indices_validity;
|
1407
|
-
GetValidityMask(indices_validity, array,
|
1354
|
+
GetValidityMask(indices_validity, array, chunk_offset, size, NumericCast<int64_t>(parent_offset));
|
1408
1355
|
if (parent_mask && !parent_mask->AllValid()) {
|
1409
1356
|
auto &struct_validity_mask = *parent_mask;
|
1410
1357
|
for (idx_t i = 0; i < size; i++) {
|
@@ -1467,19 +1414,22 @@ void ArrowTableFunction::ArrowToDuckDB(ArrowScanLocalState &scan_state, const ar
|
|
1467
1414
|
if (!array_state.owned_data) {
|
1468
1415
|
array_state.owned_data = scan_state.chunk;
|
1469
1416
|
}
|
1470
|
-
|
1471
|
-
auto array_physical_type = GetArrowArrayPhysicalType(arrow_type);
|
1417
|
+
auto array_physical_type = arrow_type.GetPhysicalType();
|
1472
1418
|
|
1473
1419
|
switch (array_physical_type) {
|
1474
1420
|
case ArrowArrayPhysicalType::DICTIONARY_ENCODED:
|
1475
|
-
ColumnArrowToDuckDBDictionary(output.data[idx], array,
|
1421
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBDictionary(output.data[idx], array, scan_state.chunk_offset,
|
1422
|
+
array_state, output.size(), arrow_type);
|
1476
1423
|
break;
|
1477
1424
|
case ArrowArrayPhysicalType::RUN_END_ENCODED:
|
1478
|
-
ColumnArrowToDuckDBRunEndEncoded(output.data[idx], array,
|
1425
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDBRunEndEncoded(output.data[idx], array, scan_state.chunk_offset,
|
1426
|
+
array_state, output.size(), arrow_type);
|
1479
1427
|
break;
|
1480
1428
|
case ArrowArrayPhysicalType::DEFAULT:
|
1481
|
-
SetValidityMask(output.data[idx], array, scan_state, output.size(),
|
1482
|
-
|
1429
|
+
ArrowToDuckDBConversion::SetValidityMask(output.data[idx], array, scan_state.chunk_offset, output.size(),
|
1430
|
+
parent_array.offset, -1);
|
1431
|
+
ArrowToDuckDBConversion::ColumnArrowToDuckDB(output.data[idx], array, scan_state.chunk_offset, array_state,
|
1432
|
+
output.size(), arrow_type);
|
1483
1433
|
break;
|
1484
1434
|
default:
|
1485
1435
|
throw NotImplementedException("ArrowArrayPhysicalType not recognized");
|