duckdb 0.8.2-dev87.0 → 0.9.0
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/README.md +7 -0
- package/binding.gyp +30 -15
- package/binding.gyp.in +1 -2
- package/configure.py +11 -3
- package/duckdb_extension_config.cmake +10 -0
- package/lib/duckdb.js +14 -4
- package/package.json +3 -1
- package/src/connection.cpp +67 -38
- package/src/data_chunk.cpp +1 -3
- package/src/database.cpp +9 -17
- package/src/duckdb/extension/icu/icu-dateadd.cpp +13 -21
- package/src/duckdb/extension/icu/icu-datefunc.cpp +10 -1
- package/src/duckdb/extension/icu/icu-datepart.cpp +216 -100
- package/src/duckdb/extension/icu/icu-datesub.cpp +13 -17
- package/src/duckdb/extension/icu/icu-datetrunc.cpp +8 -9
- package/src/duckdb/extension/icu/icu-list-range.cpp +7 -9
- package/src/duckdb/extension/icu/icu-makedate.cpp +27 -16
- package/src/duckdb/extension/icu/icu-strptime.cpp +36 -65
- package/src/duckdb/extension/icu/icu-table-range.cpp +11 -14
- package/src/duckdb/extension/icu/icu-timebucket.cpp +21 -23
- package/src/duckdb/extension/icu/icu-timezone.cpp +26 -37
- package/src/duckdb/extension/icu/icu_extension.cpp +29 -36
- package/src/duckdb/extension/icu/include/icu-dateadd.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-datepart.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-datesub.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-datetrunc.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-list-range.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-makedate.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-strptime.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-table-range.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-timebucket.hpp +1 -1
- package/src/duckdb/extension/icu/include/icu-timezone.hpp +1 -1
- package/src/duckdb/extension/icu/third_party/icu/i18n/unicode/gregocal.h +1 -1
- package/src/duckdb/extension/json/buffered_json_reader.cpp +82 -92
- package/src/duckdb/extension/json/include/buffered_json_reader.hpp +38 -52
- package/src/duckdb/extension/json/include/json_common.hpp +47 -231
- package/src/duckdb/extension/json/include/json_deserializer.hpp +9 -18
- package/src/duckdb/extension/json/include/json_enums.hpp +60 -0
- package/src/duckdb/extension/json/include/json_executors.hpp +49 -13
- package/src/duckdb/extension/json/include/json_functions.hpp +2 -1
- package/src/duckdb/extension/json/include/json_scan.hpp +21 -21
- package/src/duckdb/extension/json/include/json_serializer.hpp +12 -18
- package/src/duckdb/extension/json/include/json_transform.hpp +2 -2
- package/src/duckdb/extension/json/json_common.cpp +272 -40
- package/src/duckdb/extension/json/json_deserializer.cpp +37 -73
- package/src/duckdb/extension/json/json_enums.cpp +105 -0
- package/src/duckdb/extension/json/json_functions/copy_json.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_create.cpp +21 -2
- package/src/duckdb/extension/json/json_functions/json_serialize_sql.cpp +4 -1
- package/src/duckdb/extension/json/json_functions/json_structure.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_transform.cpp +98 -57
- package/src/duckdb/extension/json/json_functions/json_type.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/read_json.cpp +21 -2
- package/src/duckdb/extension/json/json_functions.cpp +30 -31
- package/src/duckdb/extension/json/json_scan.cpp +148 -175
- package/src/duckdb/extension/json/json_serializer.cpp +29 -72
- package/src/duckdb/extension/json/serialize_json.cpp +92 -0
- package/src/duckdb/extension/parquet/column_reader.cpp +37 -25
- package/src/duckdb/extension/parquet/column_writer.cpp +121 -104
- package/src/duckdb/extension/parquet/include/cast_column_reader.hpp +2 -2
- package/src/duckdb/extension/parquet/include/column_reader.hpp +14 -16
- package/src/duckdb/extension/parquet/include/column_writer.hpp +11 -9
- package/src/duckdb/extension/parquet/include/list_column_reader.hpp +2 -2
- package/src/duckdb/extension/parquet/include/parquet_dbp_decoder.hpp +3 -3
- package/src/duckdb/extension/parquet/include/parquet_decimal_utils.hpp +3 -3
- package/src/duckdb/extension/parquet/include/parquet_file_metadata_cache.hpp +2 -2
- package/src/duckdb/extension/parquet/include/parquet_reader.hpp +3 -2
- package/src/duckdb/extension/parquet/include/parquet_rle_bp_encoder.hpp +4 -4
- package/src/duckdb/extension/parquet/include/parquet_statistics.hpp +2 -2
- package/src/duckdb/extension/parquet/include/parquet_support.hpp +9 -11
- package/src/duckdb/extension/parquet/include/parquet_timestamp.hpp +1 -0
- package/src/duckdb/extension/parquet/include/parquet_writer.hpp +29 -5
- package/src/duckdb/extension/parquet/include/string_column_reader.hpp +1 -1
- package/src/duckdb/extension/parquet/include/struct_column_reader.hpp +2 -3
- package/src/duckdb/extension/parquet/include/zstd_file_system.hpp +2 -2
- package/src/duckdb/extension/parquet/parquet_extension.cpp +340 -93
- package/src/duckdb/extension/parquet/parquet_reader.cpp +10 -10
- package/src/duckdb/extension/parquet/parquet_statistics.cpp +25 -8
- package/src/duckdb/extension/parquet/parquet_timestamp.cpp +6 -0
- package/src/duckdb/extension/parquet/parquet_writer.cpp +170 -33
- package/src/duckdb/extension/parquet/serialize_parquet.cpp +26 -0
- package/src/duckdb/extension/parquet/zstd_file_system.cpp +2 -2
- package/src/duckdb/src/catalog/catalog.cpp +177 -70
- package/src/duckdb/src/catalog/catalog_entry/duck_index_entry.cpp +5 -0
- package/src/duckdb/src/catalog/catalog_entry/duck_table_entry.cpp +8 -11
- package/src/duckdb/src/catalog/catalog_entry/index_catalog_entry.cpp +17 -42
- package/src/duckdb/src/catalog/catalog_entry/macro_catalog_entry.cpp +2 -11
- package/src/duckdb/src/catalog/catalog_entry/schema_catalog_entry.cpp +4 -15
- package/src/duckdb/src/catalog/catalog_entry/sequence_catalog_entry.cpp +11 -29
- package/src/duckdb/src/catalog/catalog_entry/table_catalog_entry.cpp +11 -44
- package/src/duckdb/src/catalog/catalog_entry/type_catalog_entry.cpp +8 -29
- package/src/duckdb/src/catalog/catalog_entry/view_catalog_entry.cpp +11 -28
- package/src/duckdb/src/catalog/catalog_entry.cpp +16 -1
- package/src/duckdb/src/catalog/catalog_search_path.cpp +5 -4
- package/src/duckdb/src/catalog/catalog_set.cpp +16 -77
- package/src/duckdb/src/catalog/default/default_functions.cpp +23 -2
- package/src/duckdb/src/catalog/dependency_manager.cpp +0 -36
- package/src/duckdb/src/catalog/duck_catalog.cpp +4 -0
- package/src/duckdb/src/common/adbc/adbc.cpp +541 -171
- package/src/duckdb/src/common/adbc/driver_manager.cpp +92 -39
- package/src/duckdb/src/common/adbc/nanoarrow/allocator.cpp +57 -0
- package/src/duckdb/src/common/adbc/nanoarrow/metadata.cpp +121 -0
- package/src/duckdb/src/common/adbc/nanoarrow/schema.cpp +474 -0
- package/src/duckdb/src/common/adbc/nanoarrow/single_batch_array_stream.cpp +84 -0
- package/src/duckdb/src/common/allocator.cpp +14 -2
- package/src/duckdb/src/common/arrow/appender/bool_data.cpp +44 -0
- package/src/duckdb/src/common/arrow/appender/list_data.cpp +78 -0
- package/src/duckdb/src/common/arrow/appender/map_data.cpp +86 -0
- package/src/duckdb/src/common/arrow/appender/struct_data.cpp +45 -0
- package/src/duckdb/src/common/arrow/appender/union_data.cpp +70 -0
- package/src/duckdb/src/common/arrow/arrow_appender.cpp +95 -666
- package/src/duckdb/src/common/arrow/arrow_converter.cpp +68 -38
- package/src/duckdb/src/common/arrow/arrow_wrapper.cpp +37 -42
- package/src/duckdb/src/common/assert.cpp +3 -0
- package/src/duckdb/src/common/constants.cpp +2 -2
- package/src/duckdb/src/common/crypto/md5.cpp +2 -12
- package/src/duckdb/src/common/enum_util.cpp +4967 -4412
- package/src/duckdb/src/common/enums/date_part_specifier.cpp +2 -0
- package/src/duckdb/src/common/enums/logical_operator_type.cpp +4 -0
- package/src/duckdb/src/common/enums/optimizer_type.cpp +2 -0
- package/src/duckdb/src/common/enums/physical_operator_type.cpp +4 -0
- package/src/duckdb/src/common/exception.cpp +15 -2
- package/src/duckdb/src/common/extra_type_info.cpp +315 -0
- package/src/duckdb/src/common/file_buffer.cpp +2 -2
- package/src/duckdb/src/common/file_system.cpp +46 -12
- package/src/duckdb/src/common/filename_pattern.cpp +1 -1
- package/src/duckdb/src/common/gzip_file_system.cpp +7 -12
- package/src/duckdb/src/common/hive_partitioning.cpp +10 -6
- package/src/duckdb/src/common/http_state.cpp +78 -0
- package/src/duckdb/src/common/local_file_system.cpp +36 -28
- package/src/duckdb/src/common/multi_file_reader.cpp +175 -70
- package/src/duckdb/src/common/operator/cast_operators.cpp +110 -1
- package/src/duckdb/src/common/operator/string_cast.cpp +45 -8
- package/src/duckdb/src/common/radix_partitioning.cpp +34 -39
- package/src/duckdb/src/common/re2_regex.cpp +1 -1
- package/src/duckdb/src/common/row_operations/row_aggregate.cpp +18 -3
- package/src/duckdb/src/common/row_operations/row_external.cpp +1 -1
- package/src/duckdb/src/common/row_operations/row_matcher.cpp +375 -0
- package/src/duckdb/src/common/serializer/binary_deserializer.cpp +63 -73
- package/src/duckdb/src/common/serializer/binary_serializer.cpp +88 -78
- package/src/duckdb/src/common/serializer/buffered_file_reader.cpp +3 -20
- package/src/duckdb/src/common/serializer/buffered_file_writer.cpp +1 -1
- package/src/duckdb/src/common/serializer/memory_stream.cpp +61 -0
- package/src/duckdb/src/common/serializer/serializer.cpp +15 -0
- package/src/duckdb/src/common/sort/merge_sorter.cpp +9 -16
- package/src/duckdb/src/common/sort/partition_state.cpp +210 -100
- package/src/duckdb/src/common/sort/sort_state.cpp +1 -1
- package/src/duckdb/src/common/sort/sorted_block.cpp +1 -1
- package/src/duckdb/src/common/types/batched_data_collection.cpp +7 -2
- package/src/duckdb/src/common/types/bit.cpp +51 -0
- package/src/duckdb/src/common/types/column/column_data_allocator.cpp +9 -6
- package/src/duckdb/src/common/types/column/column_data_collection.cpp +68 -2
- package/src/duckdb/src/common/types/column/column_data_collection_segment.cpp +20 -6
- package/src/duckdb/src/common/types/column/partitioned_column_data.cpp +2 -2
- package/src/duckdb/src/common/types/data_chunk.cpp +77 -36
- package/src/duckdb/src/common/types/date.cpp +15 -0
- package/src/duckdb/src/common/types/hugeint.cpp +40 -0
- package/src/duckdb/src/common/types/hyperloglog.cpp +9 -7
- package/src/duckdb/src/common/types/interval.cpp +6 -0
- package/src/duckdb/src/common/types/list_segment.cpp +56 -198
- package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +251 -131
- package/src/duckdb/src/common/types/row/row_data_collection_scanner.cpp +35 -5
- package/src/duckdb/src/common/types/row/row_layout.cpp +3 -31
- package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +43 -35
- package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +74 -41
- package/src/duckdb/src/common/types/row/tuple_data_layout.cpp +11 -1
- package/src/duckdb/src/common/types/row/tuple_data_scatter_gather.cpp +46 -45
- package/src/duckdb/src/common/types/row/tuple_data_segment.cpp +21 -16
- package/src/duckdb/src/common/types/string_heap.cpp +4 -0
- package/src/duckdb/src/common/types/time.cpp +105 -0
- package/src/duckdb/src/common/types/timestamp.cpp +7 -0
- package/src/duckdb/src/common/types/uuid.cpp +2 -2
- package/src/duckdb/src/common/types/validity_mask.cpp +89 -0
- package/src/duckdb/src/common/types/value.cpp +103 -189
- package/src/duckdb/src/common/types/vector.cpp +79 -216
- package/src/duckdb/src/common/types.cpp +50 -745
- package/src/duckdb/src/common/vector_operations/vector_hash.cpp +1 -0
- package/src/duckdb/src/common/virtual_file_system.cpp +142 -1
- package/src/duckdb/src/core_functions/aggregate/algebraic/avg.cpp +0 -1
- package/src/duckdb/src/core_functions/aggregate/distributive/string_agg.cpp +6 -7
- package/src/duckdb/src/core_functions/aggregate/holistic/approximate_quantile.cpp +11 -8
- package/src/duckdb/src/core_functions/aggregate/holistic/mode.cpp +6 -8
- package/src/duckdb/src/core_functions/aggregate/holistic/quantile.cpp +137 -92
- package/src/duckdb/src/core_functions/aggregate/holistic/reservoir_quantile.cpp +15 -10
- package/src/duckdb/src/core_functions/aggregate/nested/histogram.cpp +1 -0
- package/src/duckdb/src/core_functions/aggregate/nested/list.cpp +83 -59
- package/src/duckdb/src/core_functions/aggregate/regression/regr_avg.cpp +4 -4
- package/src/duckdb/src/core_functions/aggregate/regression/regr_intercept.cpp +4 -4
- package/src/duckdb/src/core_functions/aggregate/regression/regr_r2.cpp +5 -4
- package/src/duckdb/src/core_functions/aggregate/regression/regr_sxx_syy.cpp +8 -8
- package/src/duckdb/src/core_functions/aggregate/regression/regr_sxy.cpp +4 -3
- package/src/duckdb/src/core_functions/function_list.cpp +20 -6
- package/src/duckdb/src/core_functions/scalar/date/date_diff.cpp +2 -0
- package/src/duckdb/src/core_functions/scalar/date/date_part.cpp +450 -126
- package/src/duckdb/src/core_functions/scalar/date/date_sub.cpp +2 -0
- package/src/duckdb/src/core_functions/scalar/date/date_trunc.cpp +4 -0
- package/src/duckdb/src/core_functions/scalar/date/epoch.cpp +10 -24
- package/src/duckdb/src/core_functions/scalar/date/make_date.cpp +19 -4
- package/src/duckdb/src/core_functions/scalar/date/strftime.cpp +12 -2
- package/src/duckdb/src/core_functions/scalar/debug/vector_type.cpp +23 -0
- package/src/duckdb/src/core_functions/scalar/enum/enum_functions.cpp +16 -12
- package/src/duckdb/src/core_functions/scalar/generic/current_setting.cpp +3 -1
- package/src/duckdb/src/core_functions/scalar/generic/hash.cpp +3 -0
- package/src/duckdb/src/core_functions/scalar/list/array_slice.cpp +324 -82
- package/src/duckdb/src/core_functions/scalar/list/list_aggregates.cpp +25 -18
- package/src/duckdb/src/core_functions/scalar/list/list_cosine_similarity.cpp +78 -0
- package/src/duckdb/src/core_functions/scalar/list/list_distance.cpp +72 -0
- package/src/duckdb/src/core_functions/scalar/list/list_inner_product.cpp +70 -0
- package/src/duckdb/src/core_functions/scalar/list/list_lambdas.cpp +18 -6
- package/src/duckdb/src/core_functions/scalar/list/list_sort.cpp +10 -1
- package/src/duckdb/src/core_functions/scalar/map/map_concat.cpp +0 -2
- package/src/duckdb/src/core_functions/scalar/map/map_entries.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/string/repeat.cpp +8 -5
- package/src/duckdb/src/core_functions/scalar/string/sha256.cpp +32 -0
- package/src/duckdb/src/core_functions/scalar/string/to_base.cpp +66 -0
- package/src/duckdb/src/core_functions/scalar/struct/struct_pack.cpp +24 -14
- package/src/duckdb/src/core_functions/scalar/union/union_tag.cpp +1 -1
- package/src/duckdb/src/execution/aggregate_hashtable.cpp +229 -348
- package/src/duckdb/src/execution/column_binding_resolver.cpp +11 -7
- package/src/duckdb/src/execution/expression_executor/execute_parameter.cpp +2 -2
- package/src/duckdb/src/execution/expression_executor.cpp +1 -1
- package/src/duckdb/src/execution/index/art/art.cpp +279 -296
- package/src/duckdb/src/execution/index/art/art_key.cpp +0 -11
- package/src/duckdb/src/execution/index/art/iterator.cpp +127 -217
- package/src/duckdb/src/execution/index/art/leaf.cpp +228 -272
- package/src/duckdb/src/execution/index/art/node.cpp +225 -313
- package/src/duckdb/src/execution/index/art/node16.cpp +34 -75
- package/src/duckdb/src/execution/index/art/node256.cpp +40 -63
- package/src/duckdb/src/execution/index/art/node4.cpp +44 -77
- package/src/duckdb/src/execution/index/art/node48.cpp +45 -79
- package/src/duckdb/src/execution/index/art/prefix.cpp +246 -347
- package/src/duckdb/src/execution/index/fixed_size_allocator.cpp +323 -0
- package/src/duckdb/src/execution/index/fixed_size_buffer.cpp +285 -0
- package/src/duckdb/src/execution/join_hashtable.cpp +80 -69
- package/src/duckdb/src/execution/nested_loop_join/nested_loop_join_inner.cpp +20 -27
- package/src/duckdb/src/execution/nested_loop_join/nested_loop_join_mark.cpp +21 -9
- package/src/duckdb/src/execution/operator/aggregate/aggregate_object.cpp +1 -0
- package/src/duckdb/src/execution/operator/aggregate/physical_hash_aggregate.cpp +257 -324
- package/src/duckdb/src/execution/operator/aggregate/physical_perfecthash_aggregate.cpp +6 -4
- package/src/duckdb/src/execution/operator/aggregate/physical_streaming_window.cpp +8 -3
- package/src/duckdb/src/execution/operator/aggregate/physical_ungrouped_aggregate.cpp +231 -190
- package/src/duckdb/src/execution/operator/aggregate/physical_window.cpp +368 -1070
- package/src/duckdb/src/execution/operator/{persistent → csv_scanner}/base_csv_reader.cpp +162 -175
- package/src/duckdb/src/execution/operator/csv_scanner/buffered_csv_reader.cpp +434 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_buffer.cpp +89 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_buffer_manager.cpp +90 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_file_handle.cpp +95 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_reader_options.cpp +494 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_state_machine.cpp +35 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_state_machine_cache.cpp +106 -0
- package/src/duckdb/src/execution/operator/{persistent → csv_scanner}/parallel_csv_reader.cpp +69 -51
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/csv_sniffer.cpp +61 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp +339 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp +171 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp +415 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_refinement.cpp +196 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_replacement.cpp +39 -0
- package/src/duckdb/src/execution/operator/filter/physical_filter.cpp +1 -1
- package/src/duckdb/src/execution/operator/helper/physical_batch_collector.cpp +12 -9
- package/src/duckdb/src/execution/operator/helper/physical_explain_analyze.cpp +2 -2
- package/src/duckdb/src/execution/operator/helper/physical_limit.cpp +10 -8
- package/src/duckdb/src/execution/operator/helper/physical_load.cpp +2 -1
- package/src/duckdb/src/execution/operator/helper/physical_materialized_collector.cpp +7 -5
- package/src/duckdb/src/execution/operator/helper/physical_reset.cpp +3 -1
- package/src/duckdb/src/execution/operator/helper/physical_set.cpp +3 -1
- package/src/duckdb/src/execution/operator/helper/physical_vacuum.cpp +7 -5
- package/src/duckdb/src/execution/operator/join/physical_asof_join.cpp +465 -289
- package/src/duckdb/src/execution/operator/join/physical_blockwise_nl_join.cpp +2 -2
- package/src/duckdb/src/execution/operator/join/physical_comparison_join.cpp +1 -2
- package/src/duckdb/src/execution/operator/join/physical_delim_join.cpp +13 -6
- package/src/duckdb/src/execution/operator/join/physical_hash_join.cpp +37 -19
- package/src/duckdb/src/execution/operator/join/physical_iejoin.cpp +35 -17
- package/src/duckdb/src/execution/operator/join/physical_join.cpp +1 -1
- package/src/duckdb/src/execution/operator/join/physical_nested_loop_join.cpp +7 -4
- package/src/duckdb/src/execution/operator/join/physical_piecewise_merge_join.cpp +31 -10
- package/src/duckdb/src/execution/operator/join/physical_range_join.cpp +41 -5
- package/src/duckdb/src/execution/operator/order/physical_order.cpp +7 -5
- package/src/duckdb/src/execution/operator/order/physical_top_n.cpp +7 -5
- package/src/duckdb/src/execution/operator/persistent/csv_rejects_table.cpp +48 -0
- package/src/duckdb/src/execution/operator/persistent/physical_batch_copy_to_file.cpp +14 -10
- package/src/duckdb/src/execution/operator/persistent/physical_batch_insert.cpp +69 -47
- package/src/duckdb/src/execution/operator/persistent/physical_copy_to_file.cpp +9 -7
- package/src/duckdb/src/execution/operator/persistent/physical_export.cpp +1 -1
- package/src/duckdb/src/execution/operator/persistent/physical_fixed_batch_copy.cpp +14 -12
- package/src/duckdb/src/execution/operator/persistent/physical_insert.cpp +12 -12
- package/src/duckdb/src/execution/operator/persistent/physical_update.cpp +4 -2
- package/src/duckdb/src/execution/operator/projection/physical_pivot.cpp +2 -1
- package/src/duckdb/src/execution/operator/projection/physical_unnest.cpp +24 -27
- package/src/duckdb/src/execution/operator/scan/physical_column_data_scan.cpp +19 -0
- package/src/duckdb/src/execution/operator/scan/physical_table_scan.cpp +7 -12
- package/src/duckdb/src/execution/operator/schema/physical_attach.cpp +6 -2
- package/src/duckdb/src/execution/operator/schema/physical_create_art_index.cpp +198 -0
- package/src/duckdb/src/execution/operator/schema/physical_create_type.cpp +2 -6
- package/src/duckdb/src/execution/operator/set/physical_cte.cpp +160 -0
- package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +16 -7
- package/src/duckdb/src/execution/perfect_aggregate_hashtable.cpp +37 -6
- package/src/duckdb/src/execution/physical_operator.cpp +3 -2
- package/src/duckdb/src/execution/physical_plan/plan_aggregate.cpp +43 -10
- package/src/duckdb/src/execution/physical_plan/plan_asof_join.cpp +57 -35
- package/src/duckdb/src/execution/physical_plan/plan_comparison_join.cpp +45 -25
- package/src/duckdb/src/execution/physical_plan/plan_create_index.cpp +45 -34
- package/src/duckdb/src/execution/physical_plan/plan_cte.cpp +33 -0
- package/src/duckdb/src/execution/physical_plan/plan_delim_join.cpp +2 -5
- package/src/duckdb/src/execution/physical_plan/plan_get.cpp +2 -2
- package/src/duckdb/src/execution/physical_plan/plan_recursive_cte.cpp +25 -4
- package/src/duckdb/src/execution/physical_plan_generator.cpp +6 -11
- package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +658 -363
- package/src/duckdb/src/execution/reservoir_sample.cpp +3 -9
- package/src/duckdb/src/execution/window_executor.cpp +1285 -0
- package/src/duckdb/src/execution/window_segment_tree.cpp +408 -144
- package/src/duckdb/src/function/aggregate/distributive/count.cpp +2 -13
- package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp +6 -12
- package/src/duckdb/src/function/cast/bit_cast.cpp +34 -2
- package/src/duckdb/src/function/cast/blob_cast.cpp +3 -0
- package/src/duckdb/src/function/cast/cast_function_set.cpp +1 -0
- package/src/duckdb/src/function/cast/numeric_casts.cpp +2 -0
- package/src/duckdb/src/function/cast/string_cast.cpp +2 -2
- package/src/duckdb/src/function/cast/struct_cast.cpp +8 -0
- package/src/duckdb/src/function/cast/time_casts.cpp +19 -6
- package/src/duckdb/src/function/cast/union/from_struct.cpp +114 -0
- package/src/duckdb/src/function/cast/union_casts.cpp +25 -36
- package/src/duckdb/src/function/cast/vector_cast_helpers.cpp +15 -4
- package/src/duckdb/src/function/function.cpp +3 -1
- package/src/duckdb/src/function/function_binder.cpp +18 -8
- package/src/duckdb/src/function/macro_function.cpp +0 -42
- package/src/duckdb/src/function/pragma/pragma_functions.cpp +5 -0
- package/src/duckdb/src/function/pragma/pragma_queries.cpp +15 -1
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_integral.cpp +214 -0
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_string.cpp +250 -0
- package/src/duckdb/src/function/scalar/compressed_materialization_functions.cpp +29 -0
- package/src/duckdb/src/function/scalar/list/list_resize.cpp +162 -0
- package/src/duckdb/src/function/scalar/nested_functions.cpp +1 -0
- package/src/duckdb/src/function/scalar/operators/add.cpp +9 -0
- package/src/duckdb/src/function/scalar/operators/arithmetic.cpp +15 -14
- package/src/duckdb/src/function/scalar/strftime_format.cpp +33 -12
- package/src/duckdb/src/function/scalar/string/like.cpp +12 -7
- package/src/duckdb/src/function/scalar/string/suffix.cpp +1 -1
- package/src/duckdb/src/function/scalar/system/aggregate_export.cpp +19 -11
- package/src/duckdb/src/function/scalar_function.cpp +3 -19
- package/src/duckdb/src/function/scalar_macro_function.cpp +0 -10
- package/src/duckdb/src/function/table/arrow/arrow_duck_schema.cpp +57 -0
- package/src/duckdb/src/function/table/arrow.cpp +131 -100
- package/src/duckdb/src/function/table/arrow_conversion.cpp +95 -74
- package/src/duckdb/src/function/table/copy_csv.cpp +133 -127
- package/src/duckdb/src/function/table/read_csv.cpp +198 -381
- package/src/duckdb/src/function/table/system/duckdb_columns.cpp +3 -1
- package/src/duckdb/src/function/table/system/pragma_metadata_info.cpp +83 -0
- package/src/duckdb/src/function/table/system/pragma_storage_info.cpp +5 -0
- package/src/duckdb/src/function/table/system/test_all_types.cpp +48 -21
- package/src/duckdb/src/function/table/system_functions.cpp +2 -0
- package/src/duckdb/src/function/table/table_scan.cpp +29 -24
- package/src/duckdb/src/function/table/version/pragma_version.cpp +49 -2
- package/src/duckdb/src/function/table_macro_function.cpp +0 -10
- package/src/duckdb/src/include/duckdb/catalog/catalog.hpp +23 -5
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/duck_index_entry.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/index_catalog_entry.hpp +3 -3
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/macro_catalog_entry.hpp +1 -4
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/schema_catalog_entry.hpp +2 -7
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/sequence_catalog_entry.hpp +1 -8
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/table_catalog_entry.hpp +2 -13
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/type_catalog_entry.hpp +1 -6
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/view_catalog_entry.hpp +2 -5
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry.hpp +9 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_set.hpp +0 -6
- package/src/duckdb/src/include/duckdb/catalog/duck_catalog.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/adbc/adbc.h +1 -0
- package/src/duckdb/src/include/duckdb/common/adbc/adbc.hpp +4 -1
- package/src/duckdb/src/include/duckdb/common/adbc/single_batch_array_stream.hpp +16 -0
- package/src/duckdb/src/include/duckdb/common/allocator.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/append_data.hpp +109 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/bool_data.hpp +15 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/enum_data.hpp +69 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list_data.hpp +18 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/map_data.hpp +18 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/scalar_data.hpp +88 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/struct_data.hpp +18 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/union_data.hpp +21 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/varchar_data.hpp +105 -0
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_appender.hpp +9 -4
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_converter.hpp +3 -5
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_wrapper.hpp +5 -3
- package/src/duckdb/src/include/duckdb/common/arrow/nanoarrow/nanoarrow.h +462 -0
- package/src/duckdb/src/include/duckdb/common/arrow/nanoarrow/nanoarrow.hpp +14 -0
- package/src/duckdb/src/include/duckdb/common/arrow/result_arrow_wrapper.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/assert.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/bitpacking.hpp +70 -55
- package/src/duckdb/src/include/duckdb/common/box_renderer.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/bswap.hpp +42 -0
- package/src/duckdb/src/include/duckdb/common/case_insensitive_map.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/constants.hpp +6 -15
- package/src/duckdb/src/include/duckdb/common/dl.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/enum_util.hpp +689 -577
- package/src/duckdb/src/include/duckdb/common/enums/cte_materialize.hpp +21 -0
- package/src/duckdb/src/include/duckdb/common/enums/date_part_specifier.hpp +18 -2
- package/src/duckdb/src/include/duckdb/common/enums/index_type.hpp +4 -3
- package/src/duckdb/src/include/duckdb/common/enums/joinref_type.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/logical_operator_type.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/enums/operator_result_type.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/enums/optimizer_type.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/enums/pending_execution_result.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/enums/physical_operator_type.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/exception.hpp +15 -1
- package/src/duckdb/src/include/duckdb/common/extra_operator_info.hpp +27 -0
- package/src/duckdb/src/include/duckdb/common/extra_type_info.hpp +185 -0
- package/src/duckdb/src/include/duckdb/common/file_opener.hpp +9 -0
- package/src/duckdb/src/include/duckdb/common/file_system.hpp +10 -8
- package/src/duckdb/src/include/duckdb/common/filename_pattern.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/fixed_size_map.hpp +208 -0
- package/src/duckdb/src/include/duckdb/common/helper.hpp +8 -3
- package/src/duckdb/src/include/duckdb/common/hive_partitioning.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/http_state.hpp +61 -28
- package/src/duckdb/src/include/duckdb/common/hugeint.hpp +15 -0
- package/src/duckdb/src/include/duckdb/common/index_vector.hpp +12 -0
- package/src/duckdb/src/include/duckdb/common/limits.hpp +52 -149
- package/src/duckdb/src/include/duckdb/common/multi_file_reader.hpp +14 -7
- package/src/duckdb/src/include/duckdb/common/multi_file_reader_options.hpp +10 -44
- package/src/duckdb/src/include/duckdb/common/mutex.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/numeric_utils.hpp +48 -0
- package/src/duckdb/src/include/duckdb/common/opener_file_system.hpp +6 -2
- package/src/duckdb/src/include/duckdb/common/operator/add.hpp +5 -2
- package/src/duckdb/src/include/duckdb/common/operator/cast_operators.hpp +92 -4
- package/src/duckdb/src/include/duckdb/common/operator/comparison_operators.hpp +38 -2
- package/src/duckdb/src/include/duckdb/common/operator/multiply.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/operator/numeric_cast.hpp +10 -0
- package/src/duckdb/src/include/duckdb/common/operator/string_cast.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/operator/subtract.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/optional_idx.hpp +4 -1
- package/src/duckdb/src/include/duckdb/common/perfect_map_set.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/printer.hpp +11 -0
- package/src/duckdb/src/include/duckdb/common/radix.hpp +9 -20
- package/src/duckdb/src/include/duckdb/common/radix_partitioning.hpp +6 -21
- package/src/duckdb/src/include/duckdb/common/row_operations/row_matcher.hpp +63 -0
- package/src/duckdb/src/include/duckdb/common/row_operations/row_operations.hpp +3 -3
- package/src/duckdb/src/include/duckdb/common/serializer/binary_deserializer.hpp +103 -41
- package/src/duckdb/src/include/duckdb/common/serializer/binary_serializer.hpp +59 -42
- package/src/duckdb/src/include/duckdb/common/serializer/buffered_file_reader.hpp +4 -10
- package/src/duckdb/src/include/duckdb/common/serializer/buffered_file_writer.hpp +3 -3
- package/src/duckdb/src/include/duckdb/common/serializer/deserialization_data.hpp +181 -0
- package/src/duckdb/src/include/duckdb/common/serializer/{format_deserializer.hpp → deserializer.hpp} +222 -134
- package/src/duckdb/src/include/duckdb/common/serializer/encoding_util.hpp +132 -0
- package/src/duckdb/src/include/duckdb/common/serializer/memory_stream.hpp +62 -0
- package/src/duckdb/src/include/duckdb/common/serializer/read_stream.hpp +38 -0
- package/src/duckdb/src/include/duckdb/common/serializer/serialization_traits.hpp +172 -19
- package/src/duckdb/src/include/duckdb/common/serializer/serializer.hpp +307 -0
- package/src/duckdb/src/include/duckdb/common/serializer/write_stream.hpp +36 -0
- package/src/duckdb/src/include/duckdb/common/shared_ptr.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/sort/partition_state.hpp +48 -17
- package/src/duckdb/src/include/duckdb/common/stack_checker.hpp +34 -0
- package/src/duckdb/src/include/duckdb/common/string_util.hpp +11 -0
- package/src/duckdb/src/include/duckdb/common/type_util.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/typedefs.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/types/batched_data_collection.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/types/bit.hpp +81 -0
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_allocator.hpp +11 -1
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_collection.hpp +12 -1
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_collection_segment.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_scan_states.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/types/data_chunk.hpp +4 -6
- package/src/duckdb/src/include/duckdb/common/types/date.hpp +9 -5
- package/src/duckdb/src/include/duckdb/common/types/datetime.hpp +46 -3
- package/src/duckdb/src/include/duckdb/common/types/hyperloglog.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/types/interval.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/list_segment.hpp +11 -15
- package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +46 -11
- package/src/duckdb/src/include/duckdb/common/types/row/row_data_collection_scanner.hpp +10 -1
- package/src/duckdb/src/include/duckdb/common/types/row/row_layout.hpp +1 -23
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_allocator.hpp +14 -8
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_collection.hpp +15 -5
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_layout.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_segment.hpp +13 -8
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +8 -4
- package/src/duckdb/src/include/duckdb/common/types/string_heap.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/types/string_type.hpp +9 -0
- package/src/duckdb/src/include/duckdb/common/types/time.hpp +5 -0
- package/src/duckdb/src/include/duckdb/common/types/timestamp.hpp +16 -10
- package/src/duckdb/src/include/duckdb/common/types/validity_mask.hpp +7 -1
- package/src/duckdb/src/include/duckdb/common/types/value.hpp +8 -7
- package/src/duckdb/src/include/duckdb/common/types/vector.hpp +13 -11
- package/src/duckdb/src/include/duckdb/common/types.hpp +8 -35
- package/src/duckdb/src/include/duckdb/common/vector.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/vector_operations/aggregate_executor.hpp +7 -2
- package/src/duckdb/src/include/duckdb/common/virtual_file_system.hpp +40 -97
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/algebraic/corr.hpp +4 -4
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/algebraic/covar.hpp +3 -1
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/algebraic_functions.hpp +3 -1
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/distributive_functions.hpp +4 -2
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/holistic_functions.hpp +3 -1
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/nested_functions.hpp +3 -1
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/regression/regr_count.hpp +1 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/regression/regr_slope.hpp +3 -3
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/regression_functions.hpp +3 -1
- package/src/duckdb/src/include/duckdb/core_functions/scalar/bit_functions.hpp +7 -5
- package/src/duckdb/src/include/duckdb/core_functions/scalar/blob_functions.hpp +7 -5
- package/src/duckdb/src/include/duckdb/core_functions/scalar/date_functions.hpp +44 -15
- package/src/duckdb/src/include/duckdb/core_functions/scalar/debug_functions.hpp +27 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/enum_functions.hpp +10 -8
- package/src/duckdb/src/include/duckdb/core_functions/scalar/generic_functions.hpp +15 -13
- package/src/duckdb/src/include/duckdb/core_functions/scalar/list_functions.hpp +66 -13
- package/src/duckdb/src/include/duckdb/core_functions/scalar/map_functions.hpp +6 -4
- package/src/duckdb/src/include/duckdb/core_functions/scalar/math_functions.hpp +38 -36
- package/src/duckdb/src/include/duckdb/core_functions/scalar/operators_functions.hpp +6 -4
- package/src/duckdb/src/include/duckdb/core_functions/scalar/random_functions.hpp +6 -4
- package/src/duckdb/src/include/duckdb/core_functions/scalar/string_functions.hpp +34 -14
- package/src/duckdb/src/include/duckdb/core_functions/scalar/struct_functions.hpp +10 -5
- package/src/duckdb/src/include/duckdb/core_functions/scalar/union_functions.hpp +5 -3
- package/src/duckdb/src/include/duckdb/execution/aggregate_hashtable.hpp +132 -131
- package/src/duckdb/src/include/duckdb/execution/executor.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/art.hpp +27 -16
- package/src/duckdb/src/include/duckdb/execution/index/art/art_key.hpp +0 -1
- package/src/duckdb/src/include/duckdb/execution/index/art/iterator.hpp +36 -32
- package/src/duckdb/src/include/duckdb/execution/index/art/leaf.hpp +47 -56
- package/src/duckdb/src/include/duckdb/execution/index/art/node.hpp +67 -64
- package/src/duckdb/src/include/duckdb/execution/index/art/node16.hpp +17 -20
- package/src/duckdb/src/include/duckdb/execution/index/art/node256.hpp +17 -25
- package/src/duckdb/src/include/duckdb/execution/index/art/node4.hpp +19 -22
- package/src/duckdb/src/include/duckdb/execution/index/art/node48.hpp +17 -26
- package/src/duckdb/src/include/duckdb/execution/index/art/prefix.hpp +60 -55
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_allocator.hpp +120 -0
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_buffer.hpp +109 -0
- package/src/duckdb/src/include/duckdb/execution/index/index_pointer.hpp +96 -0
- package/src/duckdb/src/include/duckdb/execution/join_hashtable.hpp +14 -8
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_hash_aggregate.hpp +8 -7
- 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_ungrouped_aggregate.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_window.hpp +6 -5
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_batch_collector.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_explain_analyze.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_limit.hpp +1 -1
- 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_vacuum.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_asof_join.hpp +5 -12
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_blockwise_nl_join.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_delim_join.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_hash_join.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_iejoin.hpp +3 -3
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_nested_loop_join.hpp +2 -2
- 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_range_join.hpp +12 -1
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_order.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_top_n.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/csv_rejects_table.hpp +36 -0
- 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 +2 -2
- 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_fixed_batch_copy.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_insert.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_update.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/base_csv_reader.hpp +23 -19
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/buffered_csv_reader.hpp +72 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_buffer.hpp +110 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_buffer_manager.hpp +103 -0
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/csv_file_handle.hpp +8 -15
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/csv_line_info.hpp +9 -4
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/csv_reader_options.hpp +79 -33
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_sniffer.hpp +129 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_state_machine.hpp +75 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_state_machine_cache.hpp +51 -0
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/parallel_csv_reader.hpp +23 -28
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/quote_rules.hpp +21 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_column_data_scan.hpp +10 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_table_scan.hpp +5 -5
- package/src/duckdb/src/include/duckdb/execution/operator/schema/{physical_create_index.hpp → physical_create_art_index.hpp} +14 -7
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_cte.hpp +62 -0
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_recursive_cte.hpp +8 -2
- package/src/duckdb/src/include/duckdb/execution/perfect_aggregate_hashtable.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/physical_operator.hpp +3 -5
- package/src/duckdb/src/include/duckdb/execution/physical_operator_states.hpp +11 -0
- package/src/duckdb/src/include/duckdb/execution/physical_plan_generator.hpp +6 -2
- package/src/duckdb/src/include/duckdb/execution/radix_partitioned_hashtable.hpp +18 -21
- package/src/duckdb/src/include/duckdb/execution/window_executor.hpp +313 -0
- package/src/duckdb/src/include/duckdb/execution/window_segment_tree.hpp +79 -63
- package/src/duckdb/src/include/duckdb/function/aggregate_function.hpp +3 -5
- package/src/duckdb/src/include/duckdb/function/aggregate_state.hpp +2 -2
- package/src/duckdb/src/include/duckdb/function/built_in_functions.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/cast/bound_cast_data.hpp +32 -0
- package/src/duckdb/src/include/duckdb/function/compression_function.hpp +36 -4
- package/src/duckdb/src/include/duckdb/function/copy_function.hpp +11 -4
- package/src/duckdb/src/include/duckdb/function/function_serialization.hpp +58 -61
- package/src/duckdb/src/include/duckdb/function/macro_function.hpp +1 -4
- package/src/duckdb/src/include/duckdb/function/scalar/compressed_materialization_functions.hpp +49 -0
- package/src/duckdb/src/include/duckdb/function/scalar/list/contains_or_position.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/scalar/nested_functions.hpp +14 -10
- package/src/duckdb/src/include/duckdb/function/scalar/strftime_format.hpp +14 -5
- package/src/duckdb/src/include/duckdb/function/scalar/string_functions.hpp +2 -0
- package/src/duckdb/src/include/duckdb/function/scalar_function.hpp +2 -7
- package/src/duckdb/src/include/duckdb/function/scalar_macro_function.hpp +2 -4
- package/src/duckdb/src/include/duckdb/function/table/arrow/arrow_duck_schema.hpp +99 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow.hpp +11 -36
- package/src/duckdb/src/include/duckdb/function/table/read_csv.hpp +22 -22
- package/src/duckdb/src/include/duckdb/function/table/system_functions.hpp +9 -1
- package/src/duckdb/src/include/duckdb/function/table_function.hpp +2 -3
- package/src/duckdb/src/include/duckdb/function/table_macro_function.hpp +2 -4
- package/src/duckdb/src/include/duckdb/function/udf_function.hpp +2 -1
- package/src/duckdb/src/include/duckdb/main/attached_database.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/capi/capi_internal.hpp +4 -3
- package/src/duckdb/src/include/duckdb/main/chunk_scan_state/query_result.hpp +29 -0
- package/src/duckdb/src/include/duckdb/main/chunk_scan_state.hpp +43 -0
- package/src/duckdb/src/include/duckdb/main/client_config.hpp +9 -2
- package/src/duckdb/src/include/duckdb/main/client_context.hpp +16 -14
- package/src/duckdb/src/include/duckdb/main/client_context_file_opener.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/client_data.hpp +2 -1
- package/src/duckdb/src/include/duckdb/main/client_properties.hpp +25 -0
- package/src/duckdb/src/include/duckdb/main/config.hpp +19 -1
- package/src/duckdb/src/include/duckdb/main/connection.hpp +3 -4
- package/src/duckdb/src/include/duckdb/main/extension/generated_extension_loader.hpp +27 -0
- package/src/duckdb/src/include/duckdb/main/extension_entries.hpp +258 -144
- package/src/duckdb/src/include/duckdb/main/extension_helper.hpp +42 -6
- package/src/duckdb/src/include/duckdb/main/extension_util.hpp +18 -0
- package/src/duckdb/src/include/duckdb/main/pending_query_result.hpp +5 -0
- package/src/duckdb/src/include/duckdb/main/prepared_statement.hpp +73 -5
- package/src/duckdb/src/include/duckdb/main/prepared_statement_data.hpp +7 -6
- package/src/duckdb/src/include/duckdb/main/query_result.hpp +3 -28
- package/src/duckdb/src/include/duckdb/main/relation/aggregate_relation.hpp +4 -1
- package/src/duckdb/src/include/duckdb/main/relation/cross_product_relation.hpp +4 -1
- package/src/duckdb/src/include/duckdb/main/relation/join_relation.hpp +5 -2
- package/src/duckdb/src/include/duckdb/main/relation/read_csv_relation.hpp +7 -7
- package/src/duckdb/src/include/duckdb/main/relation/table_function_relation.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/relation.hpp +17 -4
- package/src/duckdb/src/include/duckdb/main/settings.hpp +72 -12
- package/src/duckdb/src/include/duckdb/optimizer/column_binding_replacer.hpp +47 -0
- package/src/duckdb/src/include/duckdb/optimizer/compressed_materialization.hpp +132 -0
- package/src/duckdb/src/include/duckdb/optimizer/deliminator.hpp +13 -16
- package/src/duckdb/src/include/duckdb/optimizer/filter_pushdown.hpp +7 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/cardinality_estimator.hpp +38 -64
- package/src/duckdb/src/include/duckdb/optimizer/join_order/cost_model.hpp +37 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/estimated_properties.hpp +10 -1
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_node.hpp +14 -29
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_order_optimizer.hpp +8 -22
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_relation.hpp +1 -12
- package/src/duckdb/src/include/duckdb/optimizer/join_order/plan_enumerator.hpp +89 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/query_graph.hpp +19 -30
- package/src/duckdb/src/include/duckdb/optimizer/join_order/query_graph_manager.hpp +113 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/relation_manager.hpp +73 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/relation_statistics_helper.hpp +73 -0
- package/src/duckdb/src/include/duckdb/optimizer/matcher/set_matcher.hpp +13 -0
- package/src/duckdb/src/include/duckdb/optimizer/optimizer.hpp +3 -0
- package/src/duckdb/src/include/duckdb/optimizer/remove_duplicate_groups.hpp +40 -0
- package/src/duckdb/src/include/duckdb/optimizer/rule/empty_needle_removal.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/statistics_propagator.hpp +11 -3
- package/src/duckdb/src/include/duckdb/optimizer/topn_optimizer.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parallel/event.hpp +12 -1
- package/src/duckdb/src/include/duckdb/parallel/pipeline.hpp +2 -3
- package/src/duckdb/src/include/duckdb/parallel/pipeline_executor.hpp +3 -2
- package/src/duckdb/src/include/duckdb/parallel/task_scheduler.hpp +9 -1
- package/src/duckdb/src/include/duckdb/parser/column_definition.hpp +4 -6
- package/src/duckdb/src/include/duckdb/parser/column_list.hpp +3 -3
- package/src/duckdb/src/include/duckdb/parser/common_table_expression_info.hpp +4 -2
- package/src/duckdb/src/include/duckdb/parser/constraint.hpp +3 -8
- package/src/duckdb/src/include/duckdb/parser/constraints/check_constraint.hpp +2 -2
- package/src/duckdb/src/include/duckdb/parser/constraints/foreign_key_constraint.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/constraints/not_null_constraint.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/constraints/unique_constraint.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/between_expression.hpp +5 -5
- package/src/duckdb/src/include/duckdb/parser/expression/bound_expression.hpp +1 -4
- package/src/duckdb/src/include/duckdb/parser/expression/case_expression.hpp +4 -6
- package/src/duckdb/src/include/duckdb/parser/expression/cast_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/collate_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/columnref_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/comparison_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/conjunction_expression.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/expression/constant_expression.hpp +4 -4
- package/src/duckdb/src/include/duckdb/parser/expression/default_expression.hpp +2 -3
- package/src/duckdb/src/include/duckdb/parser/expression/function_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/lambda_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/operator_expression.hpp +22 -7
- package/src/duckdb/src/include/duckdb/parser/expression/parameter_expression.hpp +19 -5
- package/src/duckdb/src/include/duckdb/parser/expression/positional_reference_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/expression/star_expression.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/expression/subquery_expression.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/expression/window_expression.hpp +5 -4
- package/src/duckdb/src/include/duckdb/parser/group_by_node.hpp +11 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_info.hpp +12 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_scalar_function_info.hpp +0 -2
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_table_function_info.hpp +0 -2
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_table_info.hpp +66 -29
- package/src/duckdb/src/include/duckdb/parser/parsed_data/attach_info.hpp +6 -2
- package/src/duckdb/src/include/duckdb/parser/parsed_data/copy_info.hpp +8 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_collation_info.hpp +0 -3
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_copy_function_info.hpp +0 -3
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_function_info.hpp +0 -5
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_index_info.hpp +7 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_info.hpp +7 -12
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_macro_info.hpp +2 -5
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_schema_info.hpp +2 -9
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_sequence_info.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_table_info.hpp +3 -5
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_type_info.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_view_info.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/detach_info.hpp +6 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/drop_info.hpp +6 -2
- package/src/duckdb/src/include/duckdb/parser/parsed_data/exported_table_data.hpp +7 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/load_info.hpp +14 -19
- package/src/duckdb/src/include/duckdb/parser/parsed_data/parse_info.hpp +22 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/pragma_info.hpp +10 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/sample_options.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/parsed_data/show_select_info.hpp +7 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/transaction_info.hpp +8 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/vacuum_info.hpp +9 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_expression.hpp +3 -16
- package/src/duckdb/src/include/duckdb/parser/parser.hpp +4 -0
- package/src/duckdb/src/include/duckdb/parser/query_node/cte_node.hpp +52 -0
- package/src/duckdb/src/include/duckdb/parser/query_node/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/query_node/recursive_cte_node.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/query_node/select_node.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/query_node/set_operation_node.hpp +2 -4
- package/src/duckdb/src/include/duckdb/parser/query_node.hpp +9 -15
- package/src/duckdb/src/include/duckdb/parser/result_modifier.hpp +14 -32
- package/src/duckdb/src/include/duckdb/parser/statement/execute_statement.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parser/statement/select_statement.hpp +4 -9
- package/src/duckdb/src/include/duckdb/parser/tableref/basetableref.hpp +2 -6
- package/src/duckdb/src/include/duckdb/parser/tableref/emptytableref.hpp +2 -5
- package/src/duckdb/src/include/duckdb/parser/tableref/expressionlistref.hpp +2 -6
- package/src/duckdb/src/include/duckdb/parser/tableref/joinref.hpp +3 -7
- package/src/duckdb/src/include/duckdb/parser/tableref/pivotref.hpp +6 -14
- package/src/duckdb/src/include/duckdb/parser/tableref/subqueryref.hpp +5 -6
- package/src/duckdb/src/include/duckdb/parser/tableref/table_function_ref.hpp +2 -6
- package/src/duckdb/src/include/duckdb/parser/tableref.hpp +2 -10
- package/src/duckdb/src/include/duckdb/parser/tokens.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parser/transformer.hpp +24 -26
- package/src/duckdb/src/include/duckdb/planner/binder.hpp +16 -5
- package/src/duckdb/src/include/duckdb/planner/bound_constraint.hpp +0 -9
- package/src/duckdb/src/include/duckdb/planner/bound_parameter_map.hpp +30 -2
- package/src/duckdb/src/include/duckdb/planner/bound_result_modifier.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/bound_tokens.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/column_binding.hpp +9 -0
- package/src/duckdb/src/include/duckdb/planner/constraints/bound_unique_constraint.hpp +3 -3
- package/src/duckdb/src/include/duckdb/planner/expression/bound_aggregate_expression.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_between_expression.hpp +6 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_case_expression.hpp +3 -3
- package/src/duckdb/src/include/duckdb/planner/expression/bound_cast_expression.hpp +5 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_columnref_expression.hpp +2 -5
- package/src/duckdb/src/include/duckdb/planner/expression/bound_comparison_expression.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_conjunction_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_constant_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_default_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_function_expression.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_lambda_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_lambdaref_expression.hpp +2 -5
- package/src/duckdb/src/include/duckdb/planner/expression/bound_operator_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_parameter_data.hpp +12 -29
- package/src/duckdb/src/include/duckdb/planner/expression/bound_parameter_expression.hpp +9 -5
- package/src/duckdb/src/include/duckdb/planner/expression/bound_reference_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_subquery_expression.hpp +0 -3
- package/src/duckdb/src/include/duckdb/planner/expression/bound_unnest_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_window_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/expression.hpp +2 -11
- package/src/duckdb/src/include/duckdb/planner/expression_binder/base_select_binder.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/expression_binder/lateral_binder.hpp +0 -2
- package/src/duckdb/src/include/duckdb/planner/expression_binder.hpp +13 -1
- package/src/duckdb/src/include/duckdb/planner/extension_callback.hpp +26 -0
- package/src/duckdb/src/include/duckdb/planner/filter/conjunction_filter.hpp +4 -4
- package/src/duckdb/src/include/duckdb/planner/filter/constant_filter.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/filter/null_filter.hpp +4 -4
- package/src/duckdb/src/include/duckdb/planner/joinside.hpp +1 -3
- package/src/duckdb/src/include/duckdb/planner/logical_operator.hpp +2 -16
- package/src/duckdb/src/include/duckdb/planner/logical_tokens.hpp +1 -2
- package/src/duckdb/src/include/duckdb/planner/operator/list.hpp +3 -3
- package/src/duckdb/src/include/duckdb/planner/operator/logical_aggregate.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_any_join.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_column_data_get.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_comparison_join.hpp +12 -11
- package/src/duckdb/src/include/duckdb/planner/operator/logical_copy_to_file.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_create.hpp +8 -8
- package/src/duckdb/src/include/duckdb/planner/operator/logical_create_index.hpp +11 -25
- package/src/duckdb/src/include/duckdb/planner/operator/logical_create_table.hpp +8 -8
- package/src/duckdb/src/include/duckdb/planner/operator/logical_cross_product.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_cteref.hpp +9 -4
- package/src/duckdb/src/include/duckdb/planner/operator/logical_delete.hpp +6 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_delim_get.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_dependent_join.hpp +42 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_distinct.hpp +6 -12
- package/src/duckdb/src/include/duckdb/planner/operator/logical_dummy_scan.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_empty_result.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_execute.hpp +0 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_explain.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_export.hpp +0 -3
- package/src/duckdb/src/include/duckdb/planner/operator/logical_expression_get.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_extension_operator.hpp +7 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_filter.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_get.hpp +11 -3
- package/src/duckdb/src/include/duckdb/planner/operator/logical_insert.hpp +5 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_join.hpp +1 -3
- package/src/duckdb/src/include/duckdb/planner/operator/logical_limit.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_limit_percent.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_materialized_cte.hpp +50 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_order.hpp +6 -37
- package/src/duckdb/src/include/duckdb/planner/operator/logical_pivot.hpp +6 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_positional_join.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_pragma.hpp +0 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_prepare.hpp +0 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_projection.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_recursive_cte.hpp +10 -9
- package/src/duckdb/src/include/duckdb/planner/operator/logical_reset.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_sample.hpp +5 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_set.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_set_operation.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_show.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_simple.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_top_n.hpp +4 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_unnest.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_update.hpp +6 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_window.hpp +3 -2
- package/src/duckdb/src/include/duckdb/planner/operator_extension.hpp +1 -2
- package/src/duckdb/src/include/duckdb/planner/parsed_data/bound_create_table_info.hpp +0 -5
- package/src/duckdb/src/include/duckdb/planner/planner.hpp +5 -4
- package/src/duckdb/src/include/duckdb/planner/query_node/bound_cte_node.hpp +44 -0
- package/src/duckdb/src/include/duckdb/planner/query_node/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/subquery/flatten_dependent_join.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/subquery/has_correlated_expressions.hpp +4 -1
- package/src/duckdb/src/include/duckdb/planner/subquery/recursive_dependent_join_planner.hpp +31 -0
- package/src/duckdb/src/include/duckdb/planner/subquery/rewrite_correlated_expressions.hpp +8 -2
- package/src/duckdb/src/include/duckdb/planner/table_filter.hpp +4 -7
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_cteref.hpp +5 -2
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_pivotref.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/arena_allocator.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/block.hpp +36 -4
- package/src/duckdb/src/include/duckdb/storage/block_manager.hpp +11 -11
- package/src/duckdb/src/include/duckdb/storage/buffer/block_handle.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/checkpoint/row_group_writer.hpp +8 -7
- package/src/duckdb/src/include/duckdb/storage/checkpoint/string_checkpoint_state.hpp +27 -4
- package/src/duckdb/src/include/duckdb/storage/checkpoint/table_data_reader.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/checkpoint/table_data_writer.hpp +7 -7
- package/src/duckdb/src/include/duckdb/storage/checkpoint/write_overflow_strings_to_disk.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/checkpoint_manager.hpp +29 -24
- package/src/duckdb/src/include/duckdb/storage/compression/bitpacking.hpp +1 -8
- package/src/duckdb/src/include/duckdb/storage/data_pointer.hpp +31 -4
- package/src/duckdb/src/include/duckdb/storage/data_table.hpp +4 -4
- package/src/duckdb/src/include/duckdb/storage/database_size.hpp +6 -0
- package/src/duckdb/src/include/duckdb/storage/in_memory_block_manager.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/index.hpp +12 -10
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_manager.hpp +91 -0
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_reader.hpp +57 -0
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_writer.hpp +52 -0
- package/src/duckdb/src/include/duckdb/storage/object_cache.hpp +22 -0
- package/src/duckdb/src/include/duckdb/storage/partial_block_manager.hpp +37 -21
- package/src/duckdb/src/include/duckdb/storage/single_file_block_manager.hpp +8 -5
- package/src/duckdb/src/include/duckdb/storage/statistics/base_statistics.hpp +3 -8
- package/src/duckdb/src/include/duckdb/storage/statistics/column_statistics.hpp +3 -1
- package/src/duckdb/src/include/duckdb/storage/statistics/distinct_statistics.hpp +4 -7
- package/src/duckdb/src/include/duckdb/storage/statistics/list_stats.hpp +2 -4
- package/src/duckdb/src/include/duckdb/storage/statistics/node_statistics.hpp +0 -26
- package/src/duckdb/src/include/duckdb/storage/statistics/numeric_stats.hpp +2 -4
- package/src/duckdb/src/include/duckdb/storage/statistics/string_stats.hpp +6 -4
- package/src/duckdb/src/include/duckdb/storage/statistics/struct_stats.hpp +2 -4
- package/src/duckdb/src/include/duckdb/storage/storage_info.hpp +25 -8
- package/src/duckdb/src/include/duckdb/storage/storage_manager.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/string_uncompressed.hpp +6 -1
- package/src/duckdb/src/include/duckdb/storage/table/chunk_info.hpp +28 -16
- package/src/duckdb/src/include/duckdb/storage/table/column_checkpoint_state.hpp +5 -20
- package/src/duckdb/src/include/duckdb/storage/table/column_data.hpp +3 -3
- package/src/duckdb/src/include/duckdb/storage/table/column_segment.hpp +7 -3
- package/src/duckdb/src/include/duckdb/storage/table/list_column_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/persistent_table_data.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/table/row_group.hpp +21 -21
- package/src/duckdb/src/include/duckdb/storage/table/row_group_collection.hpp +4 -4
- package/src/duckdb/src/include/duckdb/storage/table/row_group_segment_tree.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/table/row_version_manager.hpp +59 -0
- package/src/duckdb/src/include/duckdb/storage/table/standard_column_data.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/table/table_index_list.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/table_statistics.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/table/update_segment.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table_io_manager.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/table_storage_info.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/write_ahead_log.hpp +29 -32
- package/src/duckdb/src/include/duckdb/transaction/commit_state.hpp +1 -6
- package/src/duckdb/src/include/duckdb/transaction/delete_info.hpp +3 -2
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction.hpp +4 -2
- package/src/duckdb/src/include/duckdb/transaction/local_storage.hpp +3 -4
- package/src/duckdb/src/include/duckdb/transaction/undo_buffer.hpp +0 -1
- package/src/duckdb/src/include/duckdb/verification/prepared_statement_verifier.hpp +1 -1
- package/src/duckdb/src/include/duckdb/verification/statement_verifier.hpp +0 -1
- package/src/duckdb/src/include/duckdb.h +101 -4
- package/src/duckdb/src/main/appender.cpp +3 -1
- package/src/duckdb/src/main/attached_database.cpp +2 -2
- package/src/duckdb/src/main/capi/arrow-c.cpp +196 -8
- package/src/duckdb/src/main/capi/duckdb-c.cpp +16 -0
- package/src/duckdb/src/main/capi/duckdb_value-c.cpp +1 -1
- package/src/duckdb/src/main/capi/logical_types-c.cpp +22 -0
- package/src/duckdb/src/main/capi/pending-c.cpp +23 -0
- package/src/duckdb/src/main/capi/prepared-c.cpp +114 -30
- package/src/duckdb/src/main/capi/result-c.cpp +3 -1
- package/src/duckdb/src/main/chunk_scan_state/query_result.cpp +53 -0
- package/src/duckdb/src/main/chunk_scan_state.cpp +48 -0
- package/src/duckdb/src/main/client_context.cpp +42 -25
- package/src/duckdb/src/main/client_context_file_opener.cpp +17 -0
- package/src/duckdb/src/main/client_verify.cpp +17 -1
- package/src/duckdb/src/main/config.cpp +10 -4
- package/src/duckdb/src/main/connection.cpp +5 -7
- package/src/duckdb/src/main/database.cpp +9 -12
- package/src/duckdb/src/main/db_instance_cache.cpp +14 -6
- package/src/duckdb/src/main/extension/extension_helper.cpp +195 -87
- package/src/duckdb/src/main/extension/extension_install.cpp +79 -15
- package/src/duckdb/src/main/extension/extension_load.cpp +63 -14
- package/src/duckdb/src/main/extension/extension_util.cpp +72 -0
- package/src/duckdb/src/main/pending_query_result.cpp +9 -1
- package/src/duckdb/src/main/prepared_statement.cpp +38 -11
- package/src/duckdb/src/main/prepared_statement_data.cpp +23 -18
- package/src/duckdb/src/main/query_result.cpp +16 -31
- package/src/duckdb/src/main/relation/aggregate_relation.cpp +20 -10
- package/src/duckdb/src/main/relation/cross_product_relation.cpp +4 -3
- package/src/duckdb/src/main/relation/join_relation.cpp +6 -6
- package/src/duckdb/src/main/relation/read_csv_relation.cpp +38 -13
- package/src/duckdb/src/main/relation/table_function_relation.cpp +8 -2
- package/src/duckdb/src/main/relation.cpp +35 -11
- package/src/duckdb/src/main/settings/settings.cpp +134 -43
- package/src/duckdb/src/optimizer/column_binding_replacer.cpp +43 -0
- package/src/duckdb/src/optimizer/column_lifetime_analyzer.cpp +11 -7
- package/src/duckdb/src/optimizer/compressed_materialization/compress_aggregate.cpp +140 -0
- package/src/duckdb/src/optimizer/compressed_materialization/compress_distinct.cpp +42 -0
- package/src/duckdb/src/optimizer/compressed_materialization/compress_order.cpp +65 -0
- package/src/duckdb/src/optimizer/compressed_materialization.cpp +477 -0
- package/src/duckdb/src/optimizer/deliminator.cpp +180 -323
- package/src/duckdb/src/optimizer/filter_pushdown.cpp +23 -6
- package/src/duckdb/src/optimizer/join_order/cardinality_estimator.cpp +79 -325
- package/src/duckdb/src/optimizer/join_order/cost_model.cpp +19 -0
- package/src/duckdb/src/optimizer/join_order/estimated_properties.cpp +7 -0
- package/src/duckdb/src/optimizer/join_order/join_node.cpp +5 -37
- package/src/duckdb/src/optimizer/join_order/join_order_optimizer.cpp +48 -1047
- package/src/duckdb/src/optimizer/join_order/join_relation_set.cpp +2 -6
- package/src/duckdb/src/optimizer/join_order/plan_enumerator.cpp +552 -0
- package/src/duckdb/src/optimizer/join_order/query_graph.cpp +52 -41
- package/src/duckdb/src/optimizer/join_order/query_graph_manager.cpp +409 -0
- package/src/duckdb/src/optimizer/join_order/relation_manager.cpp +356 -0
- package/src/duckdb/src/optimizer/join_order/relation_statistics_helper.cpp +351 -0
- package/src/duckdb/src/optimizer/optimizer.cpp +49 -14
- package/src/duckdb/src/optimizer/pushdown/pushdown_cross_product.cpp +5 -5
- package/src/duckdb/src/optimizer/pushdown/pushdown_get.cpp +0 -1
- package/src/duckdb/src/optimizer/pushdown/pushdown_projection.cpp +34 -7
- package/src/duckdb/src/optimizer/remove_duplicate_groups.cpp +127 -0
- package/src/duckdb/src/optimizer/remove_unused_columns.cpp +4 -0
- package/src/duckdb/src/optimizer/rule/date_part_simplification.cpp +0 -3
- package/src/duckdb/src/optimizer/rule/regex_optimizations.cpp +154 -15
- package/src/duckdb/src/optimizer/statistics/expression/propagate_cast.cpp +14 -0
- package/src/duckdb/src/optimizer/statistics/operator/propagate_join.cpp +65 -8
- package/src/duckdb/src/optimizer/statistics/operator/propagate_order.cpp +1 -1
- package/src/duckdb/src/optimizer/statistics/operator/propagate_projection.cpp +0 -1
- package/src/duckdb/src/optimizer/statistics_propagator.cpp +7 -5
- package/src/duckdb/src/optimizer/topn_optimizer.cpp +27 -10
- package/src/duckdb/src/optimizer/unnest_rewriter.cpp +3 -5
- package/src/duckdb/src/parallel/executor.cpp +25 -1
- package/src/duckdb/src/parallel/pipeline.cpp +0 -17
- package/src/duckdb/src/parallel/pipeline_executor.cpp +26 -7
- package/src/duckdb/src/parallel/pipeline_finish_event.cpp +55 -1
- package/src/duckdb/src/parallel/task_scheduler.cpp +18 -2
- package/src/duckdb/src/parser/column_definition.cpp +18 -55
- package/src/duckdb/src/parser/column_list.cpp +8 -13
- package/src/duckdb/src/parser/constraint.cpp +0 -33
- package/src/duckdb/src/parser/constraints/check_constraint.cpp +0 -11
- package/src/duckdb/src/parser/constraints/foreign_key_constraint.cpp +3 -27
- package/src/duckdb/src/parser/constraints/not_null_constraint.cpp +0 -11
- package/src/duckdb/src/parser/constraints/unique_constraint.cpp +3 -24
- package/src/duckdb/src/parser/expression/between_expression.cpp +5 -31
- package/src/duckdb/src/parser/expression/case_expression.cpp +2 -54
- package/src/duckdb/src/parser/expression/cast_expression.cpp +5 -30
- package/src/duckdb/src/parser/expression/collate_expression.cpp +5 -27
- package/src/duckdb/src/parser/expression/columnref_expression.cpp +5 -25
- package/src/duckdb/src/parser/expression/comparison_expression.cpp +5 -27
- package/src/duckdb/src/parser/expression/conjunction_expression.cpp +2 -25
- package/src/duckdb/src/parser/expression/constant_expression.cpp +5 -23
- package/src/duckdb/src/parser/expression/default_expression.cpp +2 -13
- package/src/duckdb/src/parser/expression/function_expression.cpp +5 -64
- package/src/duckdb/src/parser/expression/lambda_expression.cpp +6 -28
- package/src/duckdb/src/parser/expression/operator_expression.cpp +2 -25
- package/src/duckdb/src/parser/expression/parameter_expression.cpp +7 -30
- package/src/duckdb/src/parser/expression/positional_reference_expression.cpp +6 -23
- package/src/duckdb/src/parser/expression/star_expression.cpp +2 -62
- package/src/duckdb/src/parser/expression/subquery_expression.cpp +2 -46
- package/src/duckdb/src/parser/expression/window_expression.cpp +5 -92
- package/src/duckdb/src/parser/keyword_helper.cpp +1 -1
- package/src/duckdb/src/parser/parsed_data/alter_info.cpp +4 -36
- package/src/duckdb/src/parser/parsed_data/alter_scalar_function_info.cpp +0 -18
- package/src/duckdb/src/parser/parsed_data/alter_table_function_info.cpp +0 -13
- package/src/duckdb/src/parser/parsed_data/alter_table_info.cpp +38 -188
- package/src/duckdb/src/parser/parsed_data/attach_info.cpp +0 -29
- package/src/duckdb/src/parser/parsed_data/create_collation_info.cpp +0 -4
- package/src/duckdb/src/parser/parsed_data/create_copy_function_info.cpp +0 -4
- package/src/duckdb/src/parser/parsed_data/create_index_info.cpp +2 -34
- package/src/duckdb/src/parser/parsed_data/create_info.cpp +0 -47
- package/src/duckdb/src/parser/parsed_data/create_macro_info.cpp +1 -28
- package/src/duckdb/src/parser/parsed_data/create_sequence_info.cpp +0 -29
- package/src/duckdb/src/parser/parsed_data/create_table_info.cpp +0 -23
- package/src/duckdb/src/parser/parsed_data/create_type_info.cpp +0 -22
- package/src/duckdb/src/parser/parsed_data/create_view_info.cpp +0 -23
- package/src/duckdb/src/parser/parsed_data/detach_info.cpp +1 -20
- package/src/duckdb/src/parser/parsed_data/drop_info.cpp +1 -27
- package/src/duckdb/src/parser/parsed_data/sample_options.cpp +2 -43
- package/src/duckdb/src/parser/parsed_data/transaction_info.cpp +2 -15
- package/src/duckdb/src/parser/parsed_data/vacuum_info.cpp +1 -21
- package/src/duckdb/src/parser/parsed_expression.cpp +2 -149
- package/src/duckdb/src/parser/parsed_expression_iterator.cpp +7 -0
- package/src/duckdb/src/parser/parser.cpp +62 -36
- package/src/duckdb/src/parser/query_node/cte_node.cpp +41 -0
- package/src/duckdb/src/parser/query_node/recursive_cte_node.cpp +2 -40
- package/src/duckdb/src/parser/query_node/select_node.cpp +2 -76
- package/src/duckdb/src/parser/query_node/set_operation_node.cpp +2 -32
- package/src/duckdb/src/parser/query_node.cpp +12 -104
- package/src/duckdb/src/parser/result_modifier.cpp +2 -183
- package/src/duckdb/src/parser/statement/execute_statement.cpp +2 -2
- package/src/duckdb/src/parser/statement/select_statement.cpp +2 -23
- package/src/duckdb/src/parser/tableref/basetableref.cpp +2 -40
- package/src/duckdb/src/parser/tableref/emptytableref.cpp +0 -13
- package/src/duckdb/src/parser/tableref/expressionlistref.cpp +2 -43
- package/src/duckdb/src/parser/tableref/joinref.cpp +5 -46
- package/src/duckdb/src/parser/tableref/pivotref.cpp +0 -116
- package/src/duckdb/src/parser/tableref/subqueryref.cpp +5 -28
- package/src/duckdb/src/parser/tableref/table_function.cpp +2 -32
- package/src/duckdb/src/parser/tableref.cpp +2 -96
- package/src/duckdb/src/parser/transform/constraint/transform_constraint.cpp +55 -38
- package/src/duckdb/src/parser/transform/expression/transform_array_access.cpp +13 -4
- package/src/duckdb/src/parser/transform/expression/transform_constant.cpp +55 -3
- package/src/duckdb/src/parser/transform/expression/transform_expression.cpp +2 -0
- package/src/duckdb/src/parser/transform/expression/transform_function.cpp +3 -0
- package/src/duckdb/src/parser/transform/expression/transform_multi_assign_reference.cpp +44 -0
- package/src/duckdb/src/parser/transform/expression/transform_param_ref.cpp +45 -26
- package/src/duckdb/src/parser/transform/helpers/transform_cte.cpp +19 -1
- package/src/duckdb/src/parser/transform/helpers/transform_typename.cpp +16 -1
- package/src/duckdb/src/parser/transform/statement/transform_copy.cpp +13 -0
- package/src/duckdb/src/parser/transform/statement/transform_create_index.cpp +32 -17
- package/src/duckdb/src/parser/transform/statement/transform_create_type.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_delete.cpp +6 -1
- package/src/duckdb/src/parser/transform/statement/transform_insert.cpp +6 -1
- package/src/duckdb/src/parser/transform/statement/transform_load.cpp +1 -0
- package/src/duckdb/src/parser/transform/statement/transform_pivot_stmt.cpp +7 -2
- package/src/duckdb/src/parser/transform/statement/transform_pragma.cpp +14 -11
- package/src/duckdb/src/parser/transform/statement/transform_prepare.cpp +28 -6
- package/src/duckdb/src/parser/transform/statement/transform_select_node.cpp +11 -2
- package/src/duckdb/src/parser/transform/statement/transform_update.cpp +6 -1
- package/src/duckdb/src/parser/transformer.cpp +44 -25
- package/src/duckdb/src/planner/binder/expression/bind_aggregate_expression.cpp +1 -4
- package/src/duckdb/src/planner/binder/expression/bind_comparison_expression.cpp +1 -0
- package/src/duckdb/src/planner/binder/expression/bind_function_expression.cpp +14 -5
- package/src/duckdb/src/planner/binder/expression/bind_macro_expression.cpp +5 -3
- package/src/duckdb/src/planner/binder/expression/bind_parameter_expression.cpp +12 -22
- package/src/duckdb/src/planner/binder/expression/bind_subquery_expression.cpp +1 -4
- package/src/duckdb/src/planner/binder/query_node/bind_cte_node.cpp +64 -0
- package/src/duckdb/src/planner/binder/query_node/bind_select_node.cpp +28 -6
- package/src/duckdb/src/planner/binder/query_node/plan_cte_node.cpp +26 -0
- package/src/duckdb/src/planner/binder/query_node/plan_recursive_cte_node.cpp +5 -5
- package/src/duckdb/src/planner/binder/query_node/plan_setop.cpp +4 -4
- package/src/duckdb/src/planner/binder/query_node/plan_subquery.cpp +36 -33
- package/src/duckdb/src/planner/binder/statement/bind_copy.cpp +1 -1
- package/src/duckdb/src/planner/binder/statement/bind_create.cpp +14 -52
- package/src/duckdb/src/planner/binder/statement/bind_create_table.cpp +0 -23
- package/src/duckdb/src/planner/binder/statement/bind_drop.cpp +3 -0
- package/src/duckdb/src/planner/binder/statement/bind_execute.cpp +13 -7
- package/src/duckdb/src/planner/binder/statement/bind_export.cpp +168 -30
- package/src/duckdb/src/planner/binder/tableref/bind_basetableref.cpp +93 -28
- package/src/duckdb/src/planner/binder/tableref/bind_joinref.cpp +32 -5
- package/src/duckdb/src/planner/binder/tableref/bind_pivot.cpp +116 -49
- package/src/duckdb/src/planner/binder/tableref/plan_cteref.cpp +1 -1
- package/src/duckdb/src/planner/binder/tableref/plan_joinref.cpp +79 -35
- package/src/duckdb/src/planner/binder/tableref/plan_subqueryref.cpp +3 -3
- package/src/duckdb/src/planner/binder.cpp +49 -32
- package/src/duckdb/src/planner/bound_parameter_map.cpp +67 -0
- package/src/duckdb/src/planner/bound_result_modifier.cpp +0 -33
- package/src/duckdb/src/planner/expression/bound_aggregate_expression.cpp +20 -21
- package/src/duckdb/src/planner/expression/bound_between_expression.cpp +4 -19
- package/src/duckdb/src/planner/expression/bound_case_expression.cpp +0 -36
- package/src/duckdb/src/planner/expression/bound_cast_expression.cpp +13 -23
- package/src/duckdb/src/planner/expression/bound_columnref_expression.cpp +0 -20
- package/src/duckdb/src/planner/expression/bound_comparison_expression.cpp +0 -13
- package/src/duckdb/src/planner/expression/bound_conjunction_expression.cpp +0 -13
- package/src/duckdb/src/planner/expression/bound_constant_expression.cpp +0 -11
- package/src/duckdb/src/planner/expression/bound_expression.cpp +1 -5
- package/src/duckdb/src/planner/expression/bound_function_expression.cpp +18 -16
- package/src/duckdb/src/planner/expression/bound_lambda_expression.cpp +0 -4
- package/src/duckdb/src/planner/expression/bound_lambdaref_expression.cpp +0 -23
- package/src/duckdb/src/planner/expression/bound_operator_expression.cpp +0 -16
- package/src/duckdb/src/planner/expression/bound_parameter_expression.cpp +23 -33
- package/src/duckdb/src/planner/expression/bound_reference_expression.cpp +0 -16
- package/src/duckdb/src/planner/expression/bound_subquery_expression.cpp +0 -4
- package/src/duckdb/src/planner/expression/bound_unnest_expression.cpp +0 -15
- package/src/duckdb/src/planner/expression/bound_window_expression.cpp +41 -50
- package/src/duckdb/src/planner/expression.cpp +0 -74
- package/src/duckdb/src/planner/expression_binder/base_select_binder.cpp +14 -6
- package/src/duckdb/src/planner/expression_binder/lateral_binder.cpp +4 -31
- package/src/duckdb/src/planner/expression_binder/order_binder.cpp +5 -4
- package/src/duckdb/src/planner/expression_binder.cpp +23 -0
- package/src/duckdb/src/planner/expression_iterator.cpp +6 -0
- package/src/duckdb/src/planner/filter/conjunction_filter.cpp +0 -21
- package/src/duckdb/src/planner/filter/constant_filter.cpp +0 -12
- package/src/duckdb/src/planner/filter/null_filter.cpp +0 -14
- package/src/duckdb/src/planner/joinside.cpp +0 -24
- package/src/duckdb/src/planner/logical_operator.cpp +18 -206
- package/src/duckdb/src/planner/logical_operator_visitor.cpp +5 -6
- package/src/duckdb/src/planner/operator/logical_aggregate.cpp +0 -46
- package/src/duckdb/src/planner/operator/logical_any_join.cpp +0 -14
- package/src/duckdb/src/planner/operator/logical_column_data_get.cpp +0 -23
- package/src/duckdb/src/planner/operator/logical_comparison_join.cpp +0 -21
- package/src/duckdb/src/planner/operator/logical_copy_to_file.cpp +4 -50
- package/src/duckdb/src/planner/operator/logical_create.cpp +10 -8
- package/src/duckdb/src/planner/operator/logical_create_index.cpp +30 -26
- package/src/duckdb/src/planner/operator/logical_create_table.cpp +12 -6
- package/src/duckdb/src/planner/operator/logical_cross_product.cpp +0 -9
- package/src/duckdb/src/planner/operator/logical_cteref.cpp +0 -16
- package/src/duckdb/src/planner/operator/logical_delete.cpp +4 -18
- package/src/duckdb/src/planner/operator/logical_delim_get.cpp +0 -12
- package/src/duckdb/src/planner/operator/logical_dependent_join.cpp +22 -0
- package/src/duckdb/src/planner/operator/logical_distinct.cpp +10 -13
- package/src/duckdb/src/planner/operator/logical_dummy_scan.cpp +0 -10
- package/src/duckdb/src/planner/operator/logical_empty_result.cpp +0 -15
- package/src/duckdb/src/planner/operator/logical_expression_get.cpp +0 -24
- package/src/duckdb/src/planner/operator/logical_extension_operator.cpp +32 -6
- package/src/duckdb/src/planner/operator/logical_filter.cpp +0 -15
- package/src/duckdb/src/planner/operator/logical_get.cpp +63 -70
- package/src/duckdb/src/planner/operator/logical_insert.cpp +4 -74
- package/src/duckdb/src/planner/operator/logical_join.cpp +0 -17
- package/src/duckdb/src/planner/operator/logical_limit.cpp +0 -16
- package/src/duckdb/src/planner/operator/logical_limit_percent.cpp +0 -16
- package/src/duckdb/src/planner/operator/logical_materialized_cte.cpp +9 -0
- package/src/duckdb/src/planner/operator/logical_order.cpp +35 -11
- package/src/duckdb/src/planner/operator/logical_pivot.cpp +3 -20
- package/src/duckdb/src/planner/operator/logical_positional_join.cpp +0 -10
- package/src/duckdb/src/planner/operator/logical_pragma.cpp +0 -8
- package/src/duckdb/src/planner/operator/logical_prepare.cpp +0 -8
- package/src/duckdb/src/planner/operator/logical_projection.cpp +0 -12
- package/src/duckdb/src/planner/operator/logical_recursive_cte.cpp +0 -15
- package/src/duckdb/src/planner/operator/logical_reset.cpp +0 -12
- package/src/duckdb/src/planner/operator/logical_sample.cpp +3 -11
- package/src/duckdb/src/planner/operator/logical_set.cpp +0 -14
- package/src/duckdb/src/planner/operator/logical_set_operation.cpp +0 -13
- package/src/duckdb/src/planner/operator/logical_simple.cpp +0 -60
- package/src/duckdb/src/planner/operator/logical_top_n.cpp +0 -14
- package/src/duckdb/src/planner/operator/logical_unnest.cpp +0 -14
- package/src/duckdb/src/planner/operator/logical_update.cpp +4 -25
- package/src/duckdb/src/planner/operator/logical_window.cpp +0 -13
- package/src/duckdb/src/planner/planner.cpp +26 -24
- package/src/duckdb/src/planner/subquery/flatten_dependent_join.cpp +90 -38
- package/src/duckdb/src/planner/subquery/has_correlated_expressions.cpp +22 -7
- package/src/duckdb/src/planner/subquery/rewrite_correlated_expressions.cpp +65 -7
- package/src/duckdb/src/planner/table_filter.cpp +0 -59
- package/src/duckdb/src/storage/arena_allocator.cpp +13 -2
- package/src/duckdb/src/storage/buffer/block_manager.cpp +13 -9
- package/src/duckdb/src/storage/checkpoint/row_group_writer.cpp +5 -18
- package/src/duckdb/src/storage/checkpoint/table_data_reader.cpp +10 -8
- package/src/duckdb/src/storage/checkpoint/table_data_writer.cpp +25 -25
- package/src/duckdb/src/storage/checkpoint/write_overflow_strings_to_disk.cpp +53 -26
- package/src/duckdb/src/storage/checkpoint_manager.cpp +314 -267
- package/src/duckdb/src/storage/compression/bitpacking.cpp +138 -107
- package/src/duckdb/src/storage/compression/bitpacking_hugeint.cpp +295 -0
- package/src/duckdb/src/storage/compression/fixed_size_uncompressed.cpp +6 -1
- package/src/duckdb/src/storage/compression/fsst.cpp +1 -1
- package/src/duckdb/src/storage/compression/rle.cpp +66 -16
- package/src/duckdb/src/storage/compression/string_uncompressed.cpp +84 -51
- package/src/duckdb/src/storage/compression/validity_uncompressed.cpp +4 -4
- package/src/duckdb/src/storage/data_pointer.cpp +20 -0
- package/src/duckdb/src/storage/data_table.cpp +60 -39
- package/src/duckdb/src/storage/index.cpp +11 -27
- package/src/duckdb/src/storage/local_storage.cpp +17 -16
- package/src/duckdb/src/storage/metadata/metadata_manager.cpp +322 -0
- package/src/duckdb/src/storage/metadata/metadata_reader.cpp +89 -0
- package/src/duckdb/src/storage/metadata/metadata_writer.cpp +92 -0
- package/src/duckdb/src/storage/partial_block_manager.cpp +42 -15
- package/src/duckdb/src/storage/serialization/serialize_constraint.cpp +98 -0
- package/src/duckdb/src/storage/serialization/serialize_create_info.cpp +198 -0
- package/src/duckdb/src/storage/serialization/serialize_expression.cpp +283 -0
- package/src/duckdb/src/storage/serialization/serialize_logical_operator.cpp +748 -0
- package/src/duckdb/src/storage/serialization/serialize_macro_function.cpp +62 -0
- package/src/duckdb/src/storage/serialization/serialize_nodes.cpp +459 -0
- package/src/duckdb/src/storage/serialization/serialize_parse_info.cpp +421 -0
- package/src/duckdb/src/storage/serialization/serialize_parsed_expression.cpp +342 -0
- package/src/duckdb/src/storage/serialization/serialize_query_node.cpp +122 -0
- package/src/duckdb/src/storage/serialization/serialize_result_modifier.cpp +97 -0
- package/src/duckdb/src/storage/serialization/serialize_statement.cpp +22 -0
- package/src/duckdb/src/storage/serialization/serialize_storage.cpp +78 -0
- package/src/duckdb/src/storage/serialization/serialize_table_filter.cpp +97 -0
- package/src/duckdb/src/storage/serialization/serialize_tableref.cpp +164 -0
- package/src/duckdb/src/storage/serialization/serialize_types.cpp +127 -0
- package/src/duckdb/src/storage/single_file_block_manager.cpp +93 -64
- package/src/duckdb/src/storage/standard_buffer_manager.cpp +10 -16
- package/src/duckdb/src/storage/statistics/base_statistics.cpp +62 -53
- package/src/duckdb/src/storage/statistics/column_statistics.cpp +10 -7
- package/src/duckdb/src/storage/statistics/distinct_statistics.cpp +0 -26
- package/src/duckdb/src/storage/statistics/list_stats.cpp +12 -7
- package/src/duckdb/src/storage/statistics/numeric_stats.cpp +53 -43
- package/src/duckdb/src/storage/statistics/string_stats.cpp +37 -18
- package/src/duckdb/src/storage/statistics/struct_stats.cpp +17 -12
- package/src/duckdb/src/storage/storage_info.cpp +3 -2
- package/src/duckdb/src/storage/storage_manager.cpp +22 -7
- package/src/duckdb/src/storage/table/chunk_info.cpp +59 -36
- package/src/duckdb/src/storage/table/column_checkpoint_state.cpp +31 -34
- package/src/duckdb/src/storage/table/column_data.cpp +44 -41
- package/src/duckdb/src/storage/table/column_data_checkpointer.cpp +7 -11
- package/src/duckdb/src/storage/table/column_segment.cpp +21 -12
- package/src/duckdb/src/storage/table/list_column_data.cpp +24 -14
- package/src/duckdb/src/storage/table/persistent_table_data.cpp +1 -2
- package/src/duckdb/src/storage/table/row_group.cpp +131 -209
- package/src/duckdb/src/storage/table/row_group_collection.cpp +34 -25
- package/src/duckdb/src/storage/table/row_version_manager.cpp +228 -0
- package/src/duckdb/src/storage/table/standard_column_data.cpp +10 -7
- package/src/duckdb/src/storage/table/struct_column_data.cpp +22 -11
- package/src/duckdb/src/storage/table/table_statistics.cpp +19 -9
- package/src/duckdb/src/storage/table/update_segment.cpp +3 -3
- package/src/duckdb/src/storage/table_index_list.cpp +2 -2
- package/src/duckdb/src/storage/wal_replay.cpp +135 -127
- package/src/duckdb/src/storage/write_ahead_log.cpp +136 -64
- package/src/duckdb/src/transaction/cleanup_state.cpp +2 -1
- package/src/duckdb/src/transaction/commit_state.cpp +32 -13
- package/src/duckdb/src/transaction/duck_transaction.cpp +5 -2
- package/src/duckdb/src/transaction/rollback_state.cpp +2 -1
- package/src/duckdb/src/transaction/undo_buffer.cpp +3 -5
- package/src/duckdb/src/verification/deserialized_statement_verifier.cpp +11 -6
- package/src/duckdb/src/verification/prepared_statement_verifier.cpp +16 -11
- package/src/duckdb/src/verification/statement_verifier.cpp +0 -3
- package/src/duckdb/third_party/concurrentqueue/concurrentqueue.h +2 -2
- package/src/duckdb/third_party/concurrentqueue/lightweightsemaphore.h +5 -2
- package/src/duckdb/third_party/fast_float/fast_float/fast_float.h +2 -0
- package/src/duckdb/third_party/httplib/httplib.hpp +10 -1
- package/src/duckdb/third_party/libpg_query/include/nodes/parsenodes.hpp +11 -0
- package/src/duckdb/third_party/libpg_query/include/parser/gram.hpp +2 -1
- package/src/duckdb/third_party/libpg_query/pg_functions.cpp +13 -0
- package/src/duckdb/third_party/libpg_query/src_backend_parser_gram.cpp +11019 -10364
- package/src/duckdb/third_party/libpg_query/src_backend_parser_scansup.cpp +9 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls_wrapper.hpp +14 -1
- package/src/duckdb/third_party/mbedtls/mbedtls_wrapper.cpp +54 -2
- package/src/duckdb/third_party/parquet/parquet_types.h +1 -1
- package/src/duckdb/third_party/utf8proc/include/utf8proc_wrapper.hpp +8 -0
- package/src/duckdb/ub_extension_icu_third_party_icu_i18n.cpp +6 -6
- package/src/duckdb/ub_src_common.cpp +3 -3
- package/src/duckdb/ub_src_common_adbc_nanoarrow.cpp +8 -0
- package/src/duckdb/ub_src_common_arrow_appender.cpp +10 -0
- package/src/duckdb/ub_src_common_row_operations.cpp +1 -1
- package/src/duckdb/ub_src_common_serializer.cpp +3 -3
- package/src/duckdb/ub_src_core_functions_scalar_debug.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_list.cpp +6 -0
- package/src/duckdb/ub_src_core_functions_scalar_string.cpp +4 -0
- package/src/duckdb/ub_src_execution.cpp +2 -2
- package/src/duckdb/ub_src_execution_index.cpp +4 -0
- package/src/duckdb/ub_src_execution_index_art.cpp +0 -8
- package/src/duckdb/ub_src_execution_operator_csv_scanner.cpp +18 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_sniffer.cpp +12 -0
- package/src/duckdb/ub_src_execution_operator_persistent.cpp +1 -11
- package/src/duckdb/ub_src_execution_operator_schema.cpp +1 -1
- package/src/duckdb/ub_src_execution_operator_set.cpp +2 -0
- package/src/duckdb/ub_src_execution_physical_plan.cpp +2 -0
- package/src/duckdb/ub_src_function_cast_union.cpp +2 -0
- package/src/duckdb/ub_src_function_scalar.cpp +2 -0
- package/src/duckdb/ub_src_function_scalar_compressed_materialization.cpp +4 -0
- package/src/duckdb/ub_src_function_scalar_list.cpp +2 -0
- package/src/duckdb/ub_src_function_table_arrow.cpp +2 -0
- package/src/duckdb/ub_src_function_table_system.cpp +2 -0
- package/src/duckdb/ub_src_main.cpp +2 -0
- package/src/duckdb/ub_src_main_chunk_scan_state.cpp +2 -0
- package/src/duckdb/ub_src_optimizer.cpp +6 -0
- package/src/duckdb/ub_src_optimizer_compressed_materialization.cpp +6 -0
- package/src/duckdb/ub_src_optimizer_join_order.cpp +10 -0
- package/src/duckdb/ub_src_optimizer_statistics_expression.cpp +0 -2
- package/src/duckdb/ub_src_parser.cpp +0 -2
- package/src/duckdb/ub_src_parser_query_node.cpp +2 -0
- package/src/duckdb/ub_src_parser_transform_expression.cpp +2 -0
- package/src/duckdb/ub_src_planner.cpp +2 -2
- package/src/duckdb/ub_src_planner_binder_query_node.cpp +4 -0
- package/src/duckdb/ub_src_planner_expression.cpp +0 -2
- package/src/duckdb/ub_src_planner_operator.cpp +3 -11
- package/src/duckdb/ub_src_storage.cpp +2 -4
- package/src/duckdb/ub_src_storage_compression.cpp +2 -0
- package/src/duckdb/ub_src_storage_metadata.cpp +6 -0
- package/src/duckdb/ub_src_storage_serialization.cpp +30 -0
- package/src/duckdb/ub_src_storage_table.cpp +2 -0
- package/src/duckdb_node.cpp +6 -12
- package/src/duckdb_node.hpp +25 -13
- package/src/statement.cpp +27 -25
- package/test/close_hang.test.ts +39 -0
- package/test/columns.test.ts +25 -3
- package/test/database_fail.test.ts +26 -0
- package/test/extension.test.ts +1 -1
- package/test/prepare.test.ts +10 -1
- package/test/test_all_types.test.ts +234 -0
- package/test/worker.js +7 -0
- package/tsconfig.json +1 -0
- package/src/duckdb/src/common/field_writer.cpp +0 -97
- package/src/duckdb/src/common/row_operations/row_match.cpp +0 -359
- package/src/duckdb/src/common/serializer/buffered_deserializer.cpp +0 -27
- package/src/duckdb/src/common/serializer/buffered_serializer.cpp +0 -36
- package/src/duckdb/src/common/serializer.cpp +0 -24
- package/src/duckdb/src/execution/index/art/fixed_size_allocator.cpp +0 -242
- package/src/duckdb/src/execution/index/art/leaf_segment.cpp +0 -52
- package/src/duckdb/src/execution/index/art/prefix_segment.cpp +0 -42
- package/src/duckdb/src/execution/index/art/swizzleable_pointer.cpp +0 -22
- package/src/duckdb/src/execution/operator/persistent/buffered_csv_reader.cpp +0 -1487
- package/src/duckdb/src/execution/operator/persistent/csv_buffer.cpp +0 -72
- package/src/duckdb/src/execution/operator/persistent/csv_file_handle.cpp +0 -158
- package/src/duckdb/src/execution/operator/persistent/csv_reader_options.cpp +0 -260
- package/src/duckdb/src/execution/operator/schema/physical_create_index.cpp +0 -193
- package/src/duckdb/src/execution/partitionable_hashtable.cpp +0 -172
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_options.hpp +0 -25
- package/src/duckdb/src/include/duckdb/common/field_writer.hpp +0 -383
- package/src/duckdb/src/include/duckdb/common/serializer/buffered_deserializer.hpp +0 -41
- package/src/duckdb/src/include/duckdb/common/serializer/buffered_serializer.hpp +0 -50
- package/src/duckdb/src/include/duckdb/common/serializer/format_serializer.hpp +0 -248
- package/src/duckdb/src/include/duckdb/common/serializer.hpp +0 -158
- package/src/duckdb/src/include/duckdb/execution/index/art/fixed_size_allocator.hpp +0 -117
- package/src/duckdb/src/include/duckdb/execution/index/art/leaf_segment.hpp +0 -38
- package/src/duckdb/src/include/duckdb/execution/index/art/prefix_segment.hpp +0 -40
- package/src/duckdb/src/include/duckdb/execution/index/art/swizzleable_pointer.hpp +0 -58
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/buffered_csv_reader.hpp +0 -133
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/csv_buffer.hpp +0 -74
- package/src/duckdb/src/include/duckdb/execution/partitionable_hashtable.hpp +0 -69
- package/src/duckdb/src/include/duckdb/planner/operator/logical_asof_join.hpp +0 -27
- package/src/duckdb/src/include/duckdb/planner/operator/logical_delim_join.hpp +0 -32
- package/src/duckdb/src/include/duckdb/planner/plan_serialization.hpp +0 -44
- package/src/duckdb/src/include/duckdb/storage/meta_block_reader.hpp +0 -49
- package/src/duckdb/src/include/duckdb/storage/meta_block_writer.hpp +0 -50
- package/src/duckdb/src/include/duckdb/verification/deserialized_statement_verifier_v2.hpp +0 -26
- package/src/duckdb/src/optimizer/statistics/expression/propagate_and_compress.cpp +0 -118
- package/src/duckdb/src/parser/common_table_expression_info.cpp +0 -19
- package/src/duckdb/src/planner/expression/bound_default_expression.cpp +0 -16
- package/src/duckdb/src/planner/operator/logical_asof_join.cpp +0 -14
- package/src/duckdb/src/planner/operator/logical_delim_join.cpp +0 -27
- package/src/duckdb/src/planner/operator/logical_execute.cpp +0 -12
- package/src/duckdb/src/planner/operator/logical_explain.cpp +0 -22
- package/src/duckdb/src/planner/operator/logical_export.cpp +0 -13
- package/src/duckdb/src/planner/operator/logical_show.cpp +0 -21
- package/src/duckdb/src/planner/parsed_data/bound_create_table_info.cpp +0 -20
- package/src/duckdb/src/planner/plan_serialization.cpp +0 -20
- package/src/duckdb/src/storage/meta_block_reader.cpp +0 -78
- package/src/duckdb/src/storage/meta_block_writer.cpp +0 -80
- package/src/duckdb/src/verification/deserialized_statement_verifier_v2.cpp +0 -20
- package/src/duckdb/ub_src_planner_parsed_data.cpp +0 -2
@@ -5,53 +5,19 @@
|
|
5
5
|
#include "duckdb/common/types/interval.hpp"
|
6
6
|
#include "duckdb/common/types/uuid.hpp"
|
7
7
|
#include "duckdb/function/table/arrow.hpp"
|
8
|
+
#include "duckdb/common/arrow/appender/append_data.hpp"
|
9
|
+
#include "duckdb/common/arrow/appender/list.hpp"
|
8
10
|
|
9
11
|
namespace duckdb {
|
10
12
|
|
11
|
-
//===--------------------------------------------------------------------===//
|
12
|
-
// Arrow append data
|
13
|
-
//===--------------------------------------------------------------------===//
|
14
|
-
typedef void (*initialize_t)(ArrowAppendData &result, const LogicalType &type, idx_t capacity);
|
15
|
-
typedef void (*append_vector_t)(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size);
|
16
|
-
typedef void (*finalize_t)(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result);
|
17
|
-
|
18
|
-
struct ArrowAppendData {
|
19
|
-
explicit ArrowAppendData(ArrowOptions &options_p) : options(options_p) {
|
20
|
-
}
|
21
|
-
// the buffers of the arrow vector
|
22
|
-
ArrowBuffer validity;
|
23
|
-
ArrowBuffer main_buffer;
|
24
|
-
ArrowBuffer aux_buffer;
|
25
|
-
|
26
|
-
idx_t row_count = 0;
|
27
|
-
idx_t null_count = 0;
|
28
|
-
|
29
|
-
// function pointers for construction
|
30
|
-
initialize_t initialize = nullptr;
|
31
|
-
append_vector_t append_vector = nullptr;
|
32
|
-
finalize_t finalize = nullptr;
|
33
|
-
|
34
|
-
// child data (if any)
|
35
|
-
vector<unique_ptr<ArrowAppendData>> child_data;
|
36
|
-
|
37
|
-
// the arrow array C API data, only set after Finalize
|
38
|
-
unique_ptr<ArrowArray> array;
|
39
|
-
duckdb::array<const void *, 3> buffers = {{nullptr, nullptr, nullptr}};
|
40
|
-
vector<ArrowArray *> child_pointers;
|
41
|
-
|
42
|
-
ArrowOptions options;
|
43
|
-
};
|
44
|
-
|
45
13
|
//===--------------------------------------------------------------------===//
|
46
14
|
// ArrowAppender
|
47
15
|
//===--------------------------------------------------------------------===//
|
48
|
-
static unique_ptr<ArrowAppendData> InitializeArrowChild(const LogicalType &type, idx_t capacity, ArrowOptions &options);
|
49
|
-
static ArrowArray *FinalizeArrowChild(const LogicalType &type, ArrowAppendData &append_data);
|
50
16
|
|
51
|
-
ArrowAppender::ArrowAppender(vector<LogicalType> types_p, idx_t initial_capacity,
|
17
|
+
ArrowAppender::ArrowAppender(vector<LogicalType> types_p, idx_t initial_capacity, ClientProperties options)
|
52
18
|
: types(std::move(types_p)) {
|
53
19
|
for (auto &type : types) {
|
54
|
-
auto entry =
|
20
|
+
auto entry = ArrowAppender::InitializeChild(type, initial_capacity, options);
|
55
21
|
root_data.push_back(std::move(entry));
|
56
22
|
}
|
57
23
|
}
|
@@ -59,564 +25,87 @@ ArrowAppender::ArrowAppender(vector<LogicalType> types_p, idx_t initial_capacity
|
|
59
25
|
ArrowAppender::~ArrowAppender() {
|
60
26
|
}
|
61
27
|
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
}
|
69
|
-
|
70
|
-
static void UnsetBit(uint8_t *data, idx_t current_byte, uint8_t current_bit) {
|
71
|
-
data[current_byte] &= ~((uint64_t)1 << current_bit);
|
72
|
-
}
|
73
|
-
|
74
|
-
static void NextBit(idx_t ¤t_byte, uint8_t ¤t_bit) {
|
75
|
-
current_bit++;
|
76
|
-
if (current_bit == 8) {
|
77
|
-
current_byte++;
|
78
|
-
current_bit = 0;
|
28
|
+
//! Append a data chunk to the underlying arrow array
|
29
|
+
void ArrowAppender::Append(DataChunk &input, idx_t from, idx_t to, idx_t input_size) {
|
30
|
+
D_ASSERT(types == input.GetTypes());
|
31
|
+
D_ASSERT(to >= from);
|
32
|
+
for (idx_t i = 0; i < input.ColumnCount(); i++) {
|
33
|
+
root_data[i]->append_vector(*root_data[i], input.data[i], from, to, input_size);
|
79
34
|
}
|
35
|
+
row_count += to - from;
|
80
36
|
}
|
81
37
|
|
82
|
-
|
83
|
-
|
84
|
-
buffer.resize(byte_count, 0xFF);
|
85
|
-
}
|
86
|
-
|
87
|
-
static void SetNull(ArrowAppendData &append_data, uint8_t *validity_data, idx_t current_byte, uint8_t current_bit) {
|
88
|
-
UnsetBit(validity_data, current_byte, current_bit);
|
89
|
-
append_data.null_count++;
|
90
|
-
}
|
91
|
-
|
92
|
-
static void AppendValidity(ArrowAppendData &append_data, UnifiedVectorFormat &format, idx_t from, idx_t to) {
|
93
|
-
// resize the buffer, filling the validity buffer with all valid values
|
94
|
-
idx_t size = to - from;
|
95
|
-
ResizeValidity(append_data.validity, append_data.row_count + size);
|
96
|
-
if (format.validity.AllValid()) {
|
97
|
-
// if all values are valid we don't need to do anything else
|
38
|
+
void ArrowAppender::ReleaseArray(ArrowArray *array) {
|
39
|
+
if (!array || !array->release) {
|
98
40
|
return;
|
99
41
|
}
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
uint8_t current_bit;
|
104
|
-
idx_t current_byte;
|
105
|
-
GetBitPosition(append_data.row_count, current_byte, current_bit);
|
106
|
-
for (idx_t i = from; i < to; i++) {
|
107
|
-
auto source_idx = format.sel->get_index(i);
|
108
|
-
// append the validity mask
|
109
|
-
if (!format.validity.RowIsValid(source_idx)) {
|
110
|
-
SetNull(append_data, validity_data, current_byte, current_bit);
|
111
|
-
}
|
112
|
-
NextBit(current_byte, current_bit);
|
113
|
-
}
|
42
|
+
array->release = nullptr;
|
43
|
+
auto holder = static_cast<ArrowAppendData *>(array->private_data);
|
44
|
+
delete holder;
|
114
45
|
}
|
115
46
|
|
116
47
|
//===--------------------------------------------------------------------===//
|
117
|
-
//
|
118
|
-
//===--------------------------------------------------------------------===//
|
119
|
-
struct ArrowScalarConverter {
|
120
|
-
template <class TGT, class SRC>
|
121
|
-
static TGT Operation(SRC input) {
|
122
|
-
return input;
|
123
|
-
}
|
124
|
-
|
125
|
-
static bool SkipNulls() {
|
126
|
-
return false;
|
127
|
-
}
|
128
|
-
|
129
|
-
template <class TGT>
|
130
|
-
static void SetNull(TGT &value) {
|
131
|
-
}
|
132
|
-
};
|
133
|
-
|
134
|
-
struct ArrowIntervalConverter {
|
135
|
-
template <class TGT, class SRC>
|
136
|
-
static TGT Operation(SRC input) {
|
137
|
-
ArrowInterval result;
|
138
|
-
result.months = input.months;
|
139
|
-
result.days = input.days;
|
140
|
-
result.nanoseconds = input.micros * Interval::NANOS_PER_MICRO;
|
141
|
-
return result;
|
142
|
-
}
|
143
|
-
|
144
|
-
static bool SkipNulls() {
|
145
|
-
return true;
|
146
|
-
}
|
147
|
-
|
148
|
-
template <class TGT>
|
149
|
-
static void SetNull(TGT &value) {
|
150
|
-
}
|
151
|
-
};
|
152
|
-
|
153
|
-
template <class TGT, class SRC = TGT, class OP = ArrowScalarConverter>
|
154
|
-
struct ArrowScalarBaseData {
|
155
|
-
static void Append(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size) {
|
156
|
-
idx_t size = to - from;
|
157
|
-
UnifiedVectorFormat format;
|
158
|
-
input.ToUnifiedFormat(input_size, format);
|
159
|
-
|
160
|
-
// append the validity mask
|
161
|
-
AppendValidity(append_data, format, from, to);
|
162
|
-
|
163
|
-
// append the main data
|
164
|
-
append_data.main_buffer.resize(append_data.main_buffer.size() + sizeof(TGT) * size);
|
165
|
-
auto data = UnifiedVectorFormat::GetData<SRC>(format);
|
166
|
-
auto result_data = append_data.main_buffer.GetData<TGT>();
|
167
|
-
|
168
|
-
for (idx_t i = from; i < to; i++) {
|
169
|
-
auto source_idx = format.sel->get_index(i);
|
170
|
-
auto result_idx = append_data.row_count + i - from;
|
171
|
-
|
172
|
-
if (OP::SkipNulls() && !format.validity.RowIsValid(source_idx)) {
|
173
|
-
OP::template SetNull<TGT>(result_data[result_idx]);
|
174
|
-
continue;
|
175
|
-
}
|
176
|
-
result_data[result_idx] = OP::template Operation<TGT, SRC>(data[source_idx]);
|
177
|
-
}
|
178
|
-
append_data.row_count += size;
|
179
|
-
}
|
180
|
-
};
|
181
|
-
|
182
|
-
template <class TGT, class SRC = TGT, class OP = ArrowScalarConverter>
|
183
|
-
struct ArrowScalarData : public ArrowScalarBaseData<TGT, SRC, OP> {
|
184
|
-
static void Initialize(ArrowAppendData &result, const LogicalType &type, idx_t capacity) {
|
185
|
-
result.main_buffer.reserve(capacity * sizeof(TGT));
|
186
|
-
}
|
187
|
-
|
188
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
189
|
-
result->n_buffers = 2;
|
190
|
-
result->buffers[1] = append_data.main_buffer.data();
|
191
|
-
}
|
192
|
-
};
|
193
|
-
|
194
|
-
//===--------------------------------------------------------------------===//
|
195
|
-
// Enums
|
196
|
-
//===--------------------------------------------------------------------===//
|
197
|
-
template <class TGT>
|
198
|
-
struct ArrowEnumData : public ArrowScalarBaseData<TGT> {
|
199
|
-
static idx_t GetLength(string_t input) {
|
200
|
-
return input.GetSize();
|
201
|
-
}
|
202
|
-
static void WriteData(data_ptr_t target, string_t input) {
|
203
|
-
memcpy(target, input.GetData(), input.GetSize());
|
204
|
-
}
|
205
|
-
static void EnumAppendVector(ArrowAppendData &append_data, const Vector &input, idx_t size) {
|
206
|
-
D_ASSERT(input.GetVectorType() == VectorType::FLAT_VECTOR);
|
207
|
-
|
208
|
-
// resize the validity mask and set up the validity buffer for iteration
|
209
|
-
ResizeValidity(append_data.validity, append_data.row_count + size);
|
210
|
-
|
211
|
-
// resize the offset buffer - the offset buffer holds the offsets into the child array
|
212
|
-
append_data.main_buffer.resize(append_data.main_buffer.size() + sizeof(uint32_t) * (size + 1));
|
213
|
-
auto data = FlatVector::GetData<string_t>(input);
|
214
|
-
auto offset_data = append_data.main_buffer.GetData<uint32_t>();
|
215
|
-
if (append_data.row_count == 0) {
|
216
|
-
// first entry
|
217
|
-
offset_data[0] = 0;
|
218
|
-
}
|
219
|
-
// now append the string data to the auxiliary buffer
|
220
|
-
// the auxiliary buffer's length depends on the string lengths, so we resize as required
|
221
|
-
auto last_offset = offset_data[append_data.row_count];
|
222
|
-
for (idx_t i = 0; i < size; i++) {
|
223
|
-
auto offset_idx = append_data.row_count + i + 1;
|
224
|
-
|
225
|
-
auto string_length = GetLength(data[i]);
|
226
|
-
|
227
|
-
// append the offset data
|
228
|
-
auto current_offset = last_offset + string_length;
|
229
|
-
offset_data[offset_idx] = current_offset;
|
230
|
-
|
231
|
-
// resize the string buffer if required, and write the string data
|
232
|
-
append_data.aux_buffer.resize(current_offset);
|
233
|
-
WriteData(append_data.aux_buffer.data() + last_offset, data[i]);
|
234
|
-
|
235
|
-
last_offset = current_offset;
|
236
|
-
}
|
237
|
-
append_data.row_count += size;
|
238
|
-
}
|
239
|
-
static void Initialize(ArrowAppendData &result, const LogicalType &type, idx_t capacity) {
|
240
|
-
result.main_buffer.reserve(capacity * sizeof(TGT));
|
241
|
-
// construct the enum child data
|
242
|
-
auto enum_data = InitializeArrowChild(LogicalType::VARCHAR, EnumType::GetSize(type), result.options);
|
243
|
-
EnumAppendVector(*enum_data, EnumType::GetValuesInsertOrder(type), EnumType::GetSize(type));
|
244
|
-
result.child_data.push_back(std::move(enum_data));
|
245
|
-
}
|
246
|
-
|
247
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
248
|
-
result->n_buffers = 2;
|
249
|
-
result->buffers[1] = append_data.main_buffer.data();
|
250
|
-
// finalize the enum child data, and assign it to the dictionary
|
251
|
-
result->dictionary = FinalizeArrowChild(LogicalType::VARCHAR, *append_data.child_data[0]);
|
252
|
-
}
|
253
|
-
};
|
254
|
-
|
255
|
-
//===--------------------------------------------------------------------===//
|
256
|
-
// Boolean
|
257
|
-
//===--------------------------------------------------------------------===//
|
258
|
-
struct ArrowBoolData {
|
259
|
-
static void Initialize(ArrowAppendData &result, const LogicalType &type, idx_t capacity) {
|
260
|
-
auto byte_count = (capacity + 7) / 8;
|
261
|
-
result.main_buffer.reserve(byte_count);
|
262
|
-
}
|
263
|
-
|
264
|
-
static void Append(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size) {
|
265
|
-
idx_t size = to - from;
|
266
|
-
UnifiedVectorFormat format;
|
267
|
-
input.ToUnifiedFormat(input_size, format);
|
268
|
-
|
269
|
-
// we initialize both the validity and the bit set to 1's
|
270
|
-
ResizeValidity(append_data.validity, append_data.row_count + size);
|
271
|
-
ResizeValidity(append_data.main_buffer, append_data.row_count + size);
|
272
|
-
auto data = UnifiedVectorFormat::GetData<bool>(format);
|
273
|
-
|
274
|
-
auto result_data = append_data.main_buffer.GetData<uint8_t>();
|
275
|
-
auto validity_data = append_data.validity.GetData<uint8_t>();
|
276
|
-
uint8_t current_bit;
|
277
|
-
idx_t current_byte;
|
278
|
-
GetBitPosition(append_data.row_count, current_byte, current_bit);
|
279
|
-
for (idx_t i = from; i < to; i++) {
|
280
|
-
auto source_idx = format.sel->get_index(i);
|
281
|
-
// append the validity mask
|
282
|
-
if (!format.validity.RowIsValid(source_idx)) {
|
283
|
-
SetNull(append_data, validity_data, current_byte, current_bit);
|
284
|
-
} else if (!data[source_idx]) {
|
285
|
-
UnsetBit(result_data, current_byte, current_bit);
|
286
|
-
}
|
287
|
-
NextBit(current_byte, current_bit);
|
288
|
-
}
|
289
|
-
append_data.row_count += size;
|
290
|
-
}
|
291
|
-
|
292
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
293
|
-
result->n_buffers = 2;
|
294
|
-
result->buffers[1] = append_data.main_buffer.data();
|
295
|
-
}
|
296
|
-
};
|
297
|
-
|
298
|
-
//===--------------------------------------------------------------------===//
|
299
|
-
// Varchar
|
300
|
-
//===--------------------------------------------------------------------===//
|
301
|
-
struct ArrowVarcharConverter {
|
302
|
-
template <class SRC>
|
303
|
-
static idx_t GetLength(SRC input) {
|
304
|
-
return input.GetSize();
|
305
|
-
}
|
306
|
-
|
307
|
-
template <class SRC>
|
308
|
-
static void WriteData(data_ptr_t target, SRC input) {
|
309
|
-
memcpy(target, input.GetData(), input.GetSize());
|
310
|
-
}
|
311
|
-
};
|
312
|
-
|
313
|
-
struct ArrowUUIDConverter {
|
314
|
-
template <class SRC>
|
315
|
-
static idx_t GetLength(SRC input) {
|
316
|
-
return UUID::STRING_SIZE;
|
317
|
-
}
|
318
|
-
|
319
|
-
template <class SRC>
|
320
|
-
static void WriteData(data_ptr_t target, SRC input) {
|
321
|
-
UUID::ToString(input, char_ptr_cast(target));
|
322
|
-
}
|
323
|
-
};
|
324
|
-
|
325
|
-
template <class SRC = string_t, class OP = ArrowVarcharConverter, class BUFTYPE = uint64_t>
|
326
|
-
struct ArrowVarcharData {
|
327
|
-
static void Initialize(ArrowAppendData &result, const LogicalType &type, idx_t capacity) {
|
328
|
-
result.main_buffer.reserve((capacity + 1) * sizeof(BUFTYPE));
|
329
|
-
|
330
|
-
result.aux_buffer.reserve(capacity);
|
331
|
-
}
|
332
|
-
|
333
|
-
static void Append(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size) {
|
334
|
-
idx_t size = to - from;
|
335
|
-
UnifiedVectorFormat format;
|
336
|
-
input.ToUnifiedFormat(input_size, format);
|
337
|
-
|
338
|
-
// resize the validity mask and set up the validity buffer for iteration
|
339
|
-
ResizeValidity(append_data.validity, append_data.row_count + size);
|
340
|
-
auto validity_data = (uint8_t *)append_data.validity.data();
|
341
|
-
|
342
|
-
// resize the offset buffer - the offset buffer holds the offsets into the child array
|
343
|
-
append_data.main_buffer.resize(append_data.main_buffer.size() + sizeof(BUFTYPE) * (size + 1));
|
344
|
-
auto data = UnifiedVectorFormat::GetData<SRC>(format);
|
345
|
-
auto offset_data = append_data.main_buffer.GetData<BUFTYPE>();
|
346
|
-
if (append_data.row_count == 0) {
|
347
|
-
// first entry
|
348
|
-
offset_data[0] = 0;
|
349
|
-
}
|
350
|
-
// now append the string data to the auxiliary buffer
|
351
|
-
// the auxiliary buffer's length depends on the string lengths, so we resize as required
|
352
|
-
auto last_offset = offset_data[append_data.row_count];
|
353
|
-
idx_t max_offset = append_data.row_count + to - from;
|
354
|
-
if (max_offset > NumericLimits<uint32_t>::Maximum() &&
|
355
|
-
append_data.options.offset_size == ArrowOffsetSize::REGULAR) {
|
356
|
-
throw InvalidInputException("Arrow Appender: The maximum total string size for regular string buffers is "
|
357
|
-
"%u but the offset of %lu exceeds this.",
|
358
|
-
NumericLimits<uint32_t>::Maximum(), max_offset);
|
359
|
-
}
|
360
|
-
for (idx_t i = from; i < to; i++) {
|
361
|
-
auto source_idx = format.sel->get_index(i);
|
362
|
-
auto offset_idx = append_data.row_count + i + 1 - from;
|
363
|
-
|
364
|
-
if (!format.validity.RowIsValid(source_idx)) {
|
365
|
-
uint8_t current_bit;
|
366
|
-
idx_t current_byte;
|
367
|
-
GetBitPosition(append_data.row_count + i - from, current_byte, current_bit);
|
368
|
-
SetNull(append_data, validity_data, current_byte, current_bit);
|
369
|
-
offset_data[offset_idx] = last_offset;
|
370
|
-
continue;
|
371
|
-
}
|
372
|
-
|
373
|
-
auto string_length = OP::GetLength(data[source_idx]);
|
374
|
-
|
375
|
-
// append the offset data
|
376
|
-
auto current_offset = last_offset + string_length;
|
377
|
-
offset_data[offset_idx] = current_offset;
|
378
|
-
|
379
|
-
// resize the string buffer if required, and write the string data
|
380
|
-
append_data.aux_buffer.resize(current_offset);
|
381
|
-
OP::WriteData(append_data.aux_buffer.data() + last_offset, data[source_idx]);
|
382
|
-
|
383
|
-
last_offset = current_offset;
|
384
|
-
}
|
385
|
-
append_data.row_count += size;
|
386
|
-
}
|
387
|
-
|
388
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
389
|
-
result->n_buffers = 3;
|
390
|
-
result->buffers[1] = append_data.main_buffer.data();
|
391
|
-
result->buffers[2] = append_data.aux_buffer.data();
|
392
|
-
}
|
393
|
-
};
|
394
|
-
|
395
|
-
//===--------------------------------------------------------------------===//
|
396
|
-
// Structs
|
48
|
+
// Finalize Arrow Child
|
397
49
|
//===--------------------------------------------------------------------===//
|
398
|
-
|
399
|
-
|
400
|
-
auto &children = StructType::GetChildTypes(type);
|
401
|
-
for (auto &child : children) {
|
402
|
-
auto child_buffer = InitializeArrowChild(child.second, capacity, result.options);
|
403
|
-
result.child_data.push_back(std::move(child_buffer));
|
404
|
-
}
|
405
|
-
}
|
406
|
-
|
407
|
-
static void Append(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size) {
|
408
|
-
UnifiedVectorFormat format;
|
409
|
-
input.ToUnifiedFormat(input_size, format);
|
410
|
-
idx_t size = to - from;
|
411
|
-
AppendValidity(append_data, format, from, to);
|
412
|
-
// append the children of the struct
|
413
|
-
auto &children = StructVector::GetEntries(input);
|
414
|
-
for (idx_t child_idx = 0; child_idx < children.size(); child_idx++) {
|
415
|
-
auto &child = children[child_idx];
|
416
|
-
auto &child_data = *append_data.child_data[child_idx];
|
417
|
-
child_data.append_vector(child_data, *child, from, to, size);
|
418
|
-
}
|
419
|
-
append_data.row_count += size;
|
420
|
-
}
|
421
|
-
|
422
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
423
|
-
result->n_buffers = 1;
|
50
|
+
ArrowArray *ArrowAppender::FinalizeChild(const LogicalType &type, ArrowAppendData &append_data) {
|
51
|
+
auto result = make_uniq<ArrowArray>();
|
424
52
|
|
425
|
-
|
426
|
-
|
427
|
-
|
428
|
-
|
429
|
-
|
430
|
-
|
431
|
-
|
432
|
-
|
433
|
-
|
434
|
-
|
53
|
+
result->private_data = nullptr;
|
54
|
+
result->release = ArrowAppender::ReleaseArray;
|
55
|
+
result->n_children = 0;
|
56
|
+
result->null_count = 0;
|
57
|
+
result->offset = 0;
|
58
|
+
result->dictionary = nullptr;
|
59
|
+
result->buffers = append_data.buffers.data();
|
60
|
+
result->null_count = append_data.null_count;
|
61
|
+
result->length = append_data.row_count;
|
62
|
+
result->buffers[0] = append_data.validity.data();
|
435
63
|
|
436
|
-
|
437
|
-
|
438
|
-
//===--------------------------------------------------------------------===//
|
439
|
-
void AppendListOffsets(ArrowAppendData &append_data, UnifiedVectorFormat &format, idx_t from, idx_t to,
|
440
|
-
vector<sel_t> &child_sel) {
|
441
|
-
// resize the offset buffer - the offset buffer holds the offsets into the child array
|
442
|
-
idx_t size = to - from;
|
443
|
-
append_data.main_buffer.resize(append_data.main_buffer.size() + sizeof(uint32_t) * (size + 1));
|
444
|
-
auto data = UnifiedVectorFormat::GetData<list_entry_t>(format);
|
445
|
-
auto offset_data = append_data.main_buffer.GetData<uint32_t>();
|
446
|
-
if (append_data.row_count == 0) {
|
447
|
-
// first entry
|
448
|
-
offset_data[0] = 0;
|
64
|
+
if (append_data.finalize) {
|
65
|
+
append_data.finalize(append_data, type, result.get());
|
449
66
|
}
|
450
|
-
// set up the offsets using the list entries
|
451
|
-
auto last_offset = offset_data[append_data.row_count];
|
452
|
-
for (idx_t i = from; i < to; i++) {
|
453
|
-
auto source_idx = format.sel->get_index(i);
|
454
|
-
auto offset_idx = append_data.row_count + i + 1 - from;
|
455
|
-
|
456
|
-
if (!format.validity.RowIsValid(source_idx)) {
|
457
|
-
offset_data[offset_idx] = last_offset;
|
458
|
-
continue;
|
459
|
-
}
|
460
|
-
|
461
|
-
// append the offset data
|
462
|
-
auto list_length = data[source_idx].length;
|
463
|
-
last_offset += list_length;
|
464
|
-
offset_data[offset_idx] = last_offset;
|
465
67
|
|
466
|
-
|
467
|
-
|
468
|
-
}
|
469
|
-
}
|
68
|
+
append_data.array = std::move(result);
|
69
|
+
return append_data.array.get();
|
470
70
|
}
|
471
71
|
|
472
|
-
|
473
|
-
|
474
|
-
|
475
|
-
|
476
|
-
auto child_buffer = InitializeArrowChild(child_type, capacity, result.options);
|
477
|
-
result.child_data.push_back(std::move(child_buffer));
|
478
|
-
}
|
479
|
-
|
480
|
-
static void Append(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size) {
|
481
|
-
UnifiedVectorFormat format;
|
482
|
-
input.ToUnifiedFormat(input_size, format);
|
483
|
-
idx_t size = to - from;
|
484
|
-
vector<sel_t> child_indices;
|
485
|
-
AppendValidity(append_data, format, from, to);
|
486
|
-
AppendListOffsets(append_data, format, from, to, child_indices);
|
487
|
-
|
488
|
-
// append the child vector of the list
|
489
|
-
SelectionVector child_sel(child_indices.data());
|
490
|
-
auto &child = ListVector::GetEntry(input);
|
491
|
-
auto child_size = child_indices.size();
|
492
|
-
if (size != input_size) {
|
493
|
-
// Let's avoid doing this
|
494
|
-
Vector child_copy(child.GetType());
|
495
|
-
child_copy.Slice(child, child_sel, child_size);
|
496
|
-
append_data.child_data[0]->append_vector(*append_data.child_data[0], child_copy, 0, child_size, child_size);
|
497
|
-
} else {
|
498
|
-
// We don't care about the vector, slice it
|
499
|
-
child.Slice(child_sel, child_size);
|
500
|
-
append_data.child_data[0]->append_vector(*append_data.child_data[0], child, 0, child_size, child_size);
|
501
|
-
}
|
502
|
-
append_data.row_count += size;
|
503
|
-
}
|
504
|
-
|
505
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
506
|
-
result->n_buffers = 2;
|
507
|
-
result->buffers[1] = append_data.main_buffer.data();
|
508
|
-
|
509
|
-
auto &child_type = ListType::GetChildType(type);
|
510
|
-
append_data.child_pointers.resize(1);
|
511
|
-
result->children = append_data.child_pointers.data();
|
512
|
-
result->n_children = 1;
|
513
|
-
append_data.child_pointers[0] = FinalizeArrowChild(child_type, *append_data.child_data[0]);
|
514
|
-
}
|
515
|
-
};
|
516
|
-
|
517
|
-
//===--------------------------------------------------------------------===//
|
518
|
-
// Maps
|
519
|
-
//===--------------------------------------------------------------------===//
|
520
|
-
struct ArrowMapData {
|
521
|
-
static void Initialize(ArrowAppendData &result, const LogicalType &type, idx_t capacity) {
|
522
|
-
// map types are stored in a (too) clever way
|
523
|
-
// the main buffer holds the null values and the offsets
|
524
|
-
// then we have a single child, which is a struct of the map_type, and the key_type
|
525
|
-
result.main_buffer.reserve((capacity + 1) * sizeof(uint32_t));
|
526
|
-
|
527
|
-
auto &key_type = MapType::KeyType(type);
|
528
|
-
auto &value_type = MapType::ValueType(type);
|
529
|
-
auto internal_struct = make_uniq<ArrowAppendData>(result.options);
|
530
|
-
internal_struct->child_data.push_back(InitializeArrowChild(key_type, capacity, result.options));
|
531
|
-
internal_struct->child_data.push_back(InitializeArrowChild(value_type, capacity, result.options));
|
532
|
-
|
533
|
-
result.child_data.push_back(std::move(internal_struct));
|
534
|
-
}
|
535
|
-
|
536
|
-
static void Append(ArrowAppendData &append_data, Vector &input, idx_t from, idx_t to, idx_t input_size) {
|
537
|
-
UnifiedVectorFormat format;
|
538
|
-
input.ToUnifiedFormat(input_size, format);
|
539
|
-
idx_t size = to - from;
|
540
|
-
AppendValidity(append_data, format, from, to);
|
541
|
-
vector<sel_t> child_indices;
|
542
|
-
AppendListOffsets(append_data, format, from, to, child_indices);
|
543
|
-
|
544
|
-
SelectionVector child_sel(child_indices.data());
|
545
|
-
auto &key_vector = MapVector::GetKeys(input);
|
546
|
-
auto &value_vector = MapVector::GetValues(input);
|
547
|
-
auto list_size = child_indices.size();
|
548
|
-
|
549
|
-
auto &struct_data = *append_data.child_data[0];
|
550
|
-
auto &key_data = *struct_data.child_data[0];
|
551
|
-
auto &value_data = *struct_data.child_data[1];
|
552
|
-
|
553
|
-
if (size != input_size) {
|
554
|
-
// Let's avoid doing this
|
555
|
-
Vector key_vector_copy(key_vector.GetType());
|
556
|
-
key_vector_copy.Slice(key_vector, child_sel, list_size);
|
557
|
-
Vector value_vector_copy(value_vector.GetType());
|
558
|
-
value_vector_copy.Slice(value_vector, child_sel, list_size);
|
559
|
-
key_data.append_vector(key_data, key_vector_copy, 0, list_size, list_size);
|
560
|
-
value_data.append_vector(value_data, value_vector_copy, 0, list_size, list_size);
|
561
|
-
} else {
|
562
|
-
// We don't care about the vector, slice it
|
563
|
-
key_vector.Slice(child_sel, list_size);
|
564
|
-
value_vector.Slice(child_sel, list_size);
|
565
|
-
key_data.append_vector(key_data, key_vector, 0, list_size, list_size);
|
566
|
-
value_data.append_vector(value_data, value_vector, 0, list_size, list_size);
|
567
|
-
}
|
568
|
-
|
569
|
-
append_data.row_count += size;
|
570
|
-
struct_data.row_count += size;
|
571
|
-
}
|
572
|
-
|
573
|
-
static void Finalize(ArrowAppendData &append_data, const LogicalType &type, ArrowArray *result) {
|
574
|
-
// set up the main map buffer
|
575
|
-
result->n_buffers = 2;
|
576
|
-
result->buffers[1] = append_data.main_buffer.data();
|
577
|
-
|
578
|
-
// the main map buffer has a single child: a struct
|
579
|
-
append_data.child_pointers.resize(1);
|
580
|
-
result->children = append_data.child_pointers.data();
|
581
|
-
result->n_children = 1;
|
582
|
-
append_data.child_pointers[0] = FinalizeArrowChild(type, *append_data.child_data[0]);
|
583
|
-
|
584
|
-
// now that struct has two children: the key and the value type
|
585
|
-
auto &struct_data = *append_data.child_data[0];
|
586
|
-
auto &struct_result = append_data.child_pointers[0];
|
587
|
-
struct_data.child_pointers.resize(2);
|
588
|
-
struct_result->n_buffers = 1;
|
589
|
-
struct_result->n_children = 2;
|
590
|
-
struct_result->length = struct_data.child_data[0]->row_count;
|
591
|
-
struct_result->children = struct_data.child_pointers.data();
|
72
|
+
//! Returns the underlying arrow array
|
73
|
+
ArrowArray ArrowAppender::Finalize() {
|
74
|
+
D_ASSERT(root_data.size() == types.size());
|
75
|
+
auto root_holder = make_uniq<ArrowAppendData>(options);
|
592
76
|
|
593
|
-
|
77
|
+
ArrowArray result;
|
78
|
+
root_holder->child_pointers.resize(types.size());
|
79
|
+
result.children = root_holder->child_pointers.data();
|
80
|
+
result.n_children = types.size();
|
594
81
|
|
595
|
-
|
596
|
-
|
597
|
-
|
598
|
-
|
82
|
+
// Configure root array
|
83
|
+
result.length = row_count;
|
84
|
+
result.n_buffers = 1;
|
85
|
+
result.buffers = root_holder->buffers.data(); // there is no actual buffer there since we don't have NULLs
|
86
|
+
result.offset = 0;
|
87
|
+
result.null_count = 0; // needs to be 0
|
88
|
+
result.dictionary = nullptr;
|
89
|
+
root_holder->child_data = std::move(root_data);
|
599
90
|
|
600
|
-
|
601
|
-
|
602
|
-
|
603
|
-
|
91
|
+
// FIXME: this violates a property of the arrow format, if root owns all the child memory then consumers can't move
|
92
|
+
// child arrays https://arrow.apache.org/docs/format/CDataInterface.html#moving-child-arrays
|
93
|
+
for (idx_t i = 0; i < root_holder->child_data.size(); i++) {
|
94
|
+
root_holder->child_pointers[i] = ArrowAppender::FinalizeChild(types[i], *root_holder->child_data[i]);
|
604
95
|
}
|
605
|
-
};
|
606
96
|
|
607
|
-
|
608
|
-
|
609
|
-
|
610
|
-
|
611
|
-
root_data[i]->append_vector(*root_data[i], input.data[i], from, to, input_size);
|
612
|
-
}
|
613
|
-
row_count += to - from;
|
97
|
+
// Release ownership to caller
|
98
|
+
result.private_data = root_holder.release();
|
99
|
+
result.release = ArrowAppender::ReleaseArray;
|
100
|
+
return result;
|
614
101
|
}
|
102
|
+
|
615
103
|
//===--------------------------------------------------------------------===//
|
616
104
|
// Initialize Arrow Child
|
617
105
|
//===--------------------------------------------------------------------===//
|
106
|
+
|
618
107
|
template <class OP>
|
619
|
-
static void
|
108
|
+
static void InitializeAppenderForType(ArrowAppendData &append_data) {
|
620
109
|
append_data.initialize = OP::Initialize;
|
621
110
|
append_data.append_vector = OP::Append;
|
622
111
|
append_data.finalize = OP::Finalize;
|
@@ -626,17 +115,17 @@ static void InitializeFunctionPointers(ArrowAppendData &append_data, const Logic
|
|
626
115
|
// handle special logical types
|
627
116
|
switch (type.id()) {
|
628
117
|
case LogicalTypeId::BOOLEAN:
|
629
|
-
|
118
|
+
InitializeAppenderForType<ArrowBoolData>(append_data);
|
630
119
|
break;
|
631
120
|
case LogicalTypeId::TINYINT:
|
632
|
-
|
121
|
+
InitializeAppenderForType<ArrowScalarData<int8_t>>(append_data);
|
633
122
|
break;
|
634
123
|
case LogicalTypeId::SMALLINT:
|
635
|
-
|
124
|
+
InitializeAppenderForType<ArrowScalarData<int16_t>>(append_data);
|
636
125
|
break;
|
637
126
|
case LogicalTypeId::DATE:
|
638
127
|
case LogicalTypeId::INTEGER:
|
639
|
-
|
128
|
+
InitializeAppenderForType<ArrowScalarData<int32_t>>(append_data);
|
640
129
|
break;
|
641
130
|
case LogicalTypeId::TIME:
|
642
131
|
case LogicalTypeId::TIMESTAMP_SEC:
|
@@ -646,42 +135,42 @@ static void InitializeFunctionPointers(ArrowAppendData &append_data, const Logic
|
|
646
135
|
case LogicalTypeId::TIMESTAMP_TZ:
|
647
136
|
case LogicalTypeId::TIME_TZ:
|
648
137
|
case LogicalTypeId::BIGINT:
|
649
|
-
|
138
|
+
InitializeAppenderForType<ArrowScalarData<int64_t>>(append_data);
|
650
139
|
break;
|
651
140
|
case LogicalTypeId::HUGEINT:
|
652
|
-
|
141
|
+
InitializeAppenderForType<ArrowScalarData<hugeint_t>>(append_data);
|
653
142
|
break;
|
654
143
|
case LogicalTypeId::UTINYINT:
|
655
|
-
|
144
|
+
InitializeAppenderForType<ArrowScalarData<uint8_t>>(append_data);
|
656
145
|
break;
|
657
146
|
case LogicalTypeId::USMALLINT:
|
658
|
-
|
147
|
+
InitializeAppenderForType<ArrowScalarData<uint16_t>>(append_data);
|
659
148
|
break;
|
660
149
|
case LogicalTypeId::UINTEGER:
|
661
|
-
|
150
|
+
InitializeAppenderForType<ArrowScalarData<uint32_t>>(append_data);
|
662
151
|
break;
|
663
152
|
case LogicalTypeId::UBIGINT:
|
664
|
-
|
153
|
+
InitializeAppenderForType<ArrowScalarData<uint64_t>>(append_data);
|
665
154
|
break;
|
666
155
|
case LogicalTypeId::FLOAT:
|
667
|
-
|
156
|
+
InitializeAppenderForType<ArrowScalarData<float>>(append_data);
|
668
157
|
break;
|
669
158
|
case LogicalTypeId::DOUBLE:
|
670
|
-
|
159
|
+
InitializeAppenderForType<ArrowScalarData<double>>(append_data);
|
671
160
|
break;
|
672
161
|
case LogicalTypeId::DECIMAL:
|
673
162
|
switch (type.InternalType()) {
|
674
163
|
case PhysicalType::INT16:
|
675
|
-
|
164
|
+
InitializeAppenderForType<ArrowScalarData<hugeint_t, int16_t>>(append_data);
|
676
165
|
break;
|
677
166
|
case PhysicalType::INT32:
|
678
|
-
|
167
|
+
InitializeAppenderForType<ArrowScalarData<hugeint_t, int32_t>>(append_data);
|
679
168
|
break;
|
680
169
|
case PhysicalType::INT64:
|
681
|
-
|
170
|
+
InitializeAppenderForType<ArrowScalarData<hugeint_t, int64_t>>(append_data);
|
682
171
|
break;
|
683
172
|
case PhysicalType::INT128:
|
684
|
-
|
173
|
+
InitializeAppenderForType<ArrowScalarData<hugeint_t>>(append_data);
|
685
174
|
break;
|
686
175
|
default:
|
687
176
|
throw InternalException("Unsupported internal decimal type");
|
@@ -690,52 +179,56 @@ static void InitializeFunctionPointers(ArrowAppendData &append_data, const Logic
|
|
690
179
|
case LogicalTypeId::VARCHAR:
|
691
180
|
case LogicalTypeId::BLOB:
|
692
181
|
case LogicalTypeId::BIT:
|
693
|
-
if (append_data.options.
|
694
|
-
|
182
|
+
if (append_data.options.arrow_offset_size == ArrowOffsetSize::LARGE) {
|
183
|
+
InitializeAppenderForType<ArrowVarcharData<string_t>>(append_data);
|
695
184
|
} else {
|
696
|
-
|
185
|
+
InitializeAppenderForType<ArrowVarcharData<string_t, ArrowVarcharConverter, uint32_t>>(append_data);
|
697
186
|
}
|
698
187
|
break;
|
699
188
|
case LogicalTypeId::UUID:
|
700
|
-
if (append_data.options.
|
701
|
-
|
189
|
+
if (append_data.options.arrow_offset_size == ArrowOffsetSize::LARGE) {
|
190
|
+
InitializeAppenderForType<ArrowVarcharData<hugeint_t, ArrowUUIDConverter>>(append_data);
|
702
191
|
} else {
|
703
|
-
|
192
|
+
InitializeAppenderForType<ArrowVarcharData<hugeint_t, ArrowUUIDConverter, uint32_t>>(append_data);
|
704
193
|
}
|
705
194
|
break;
|
706
195
|
case LogicalTypeId::ENUM:
|
707
196
|
switch (type.InternalType()) {
|
708
197
|
case PhysicalType::UINT8:
|
709
|
-
|
198
|
+
InitializeAppenderForType<ArrowEnumData<uint8_t>>(append_data);
|
710
199
|
break;
|
711
200
|
case PhysicalType::UINT16:
|
712
|
-
|
201
|
+
InitializeAppenderForType<ArrowEnumData<uint16_t>>(append_data);
|
713
202
|
break;
|
714
203
|
case PhysicalType::UINT32:
|
715
|
-
|
204
|
+
InitializeAppenderForType<ArrowEnumData<uint32_t>>(append_data);
|
716
205
|
break;
|
717
206
|
default:
|
718
207
|
throw InternalException("Unsupported internal enum type");
|
719
208
|
}
|
720
209
|
break;
|
721
210
|
case LogicalTypeId::INTERVAL:
|
722
|
-
|
211
|
+
InitializeAppenderForType<ArrowScalarData<ArrowInterval, interval_t, ArrowIntervalConverter>>(append_data);
|
212
|
+
break;
|
213
|
+
case LogicalTypeId::UNION:
|
214
|
+
InitializeAppenderForType<ArrowUnionData>(append_data);
|
723
215
|
break;
|
724
216
|
case LogicalTypeId::STRUCT:
|
725
|
-
|
217
|
+
InitializeAppenderForType<ArrowStructData>(append_data);
|
726
218
|
break;
|
727
219
|
case LogicalTypeId::LIST:
|
728
|
-
|
220
|
+
InitializeAppenderForType<ArrowListData>(append_data);
|
729
221
|
break;
|
730
222
|
case LogicalTypeId::MAP:
|
731
|
-
|
223
|
+
InitializeAppenderForType<ArrowMapData>(append_data);
|
732
224
|
break;
|
733
225
|
default:
|
734
|
-
throw
|
226
|
+
throw NotImplementedException("Unsupported type in DuckDB -> Arrow Conversion: %s\n", type.ToString());
|
735
227
|
}
|
736
228
|
}
|
737
229
|
|
738
|
-
unique_ptr<ArrowAppendData>
|
230
|
+
unique_ptr<ArrowAppendData> ArrowAppender::InitializeChild(const LogicalType &type, idx_t capacity,
|
231
|
+
ClientProperties &options) {
|
739
232
|
auto result = make_uniq<ArrowAppendData>(options);
|
740
233
|
InitializeFunctionPointers(*result, type);
|
741
234
|
|
@@ -745,68 +238,4 @@ unique_ptr<ArrowAppendData> InitializeArrowChild(const LogicalType &type, idx_t
|
|
745
238
|
return result;
|
746
239
|
}
|
747
240
|
|
748
|
-
static void ReleaseDuckDBArrowAppendArray(ArrowArray *array) {
|
749
|
-
if (!array || !array->release) {
|
750
|
-
return;
|
751
|
-
}
|
752
|
-
array->release = nullptr;
|
753
|
-
auto holder = static_cast<ArrowAppendData *>(array->private_data);
|
754
|
-
delete holder;
|
755
|
-
}
|
756
|
-
|
757
|
-
//===--------------------------------------------------------------------===//
|
758
|
-
// Finalize Arrow Child
|
759
|
-
//===--------------------------------------------------------------------===//
|
760
|
-
ArrowArray *FinalizeArrowChild(const LogicalType &type, ArrowAppendData &append_data) {
|
761
|
-
auto result = make_uniq<ArrowArray>();
|
762
|
-
|
763
|
-
result->private_data = nullptr;
|
764
|
-
result->release = ReleaseDuckDBArrowAppendArray;
|
765
|
-
result->n_children = 0;
|
766
|
-
result->null_count = 0;
|
767
|
-
result->offset = 0;
|
768
|
-
result->dictionary = nullptr;
|
769
|
-
result->buffers = append_data.buffers.data();
|
770
|
-
result->null_count = append_data.null_count;
|
771
|
-
result->length = append_data.row_count;
|
772
|
-
result->buffers[0] = append_data.validity.data();
|
773
|
-
|
774
|
-
if (append_data.finalize) {
|
775
|
-
append_data.finalize(append_data, type, result.get());
|
776
|
-
}
|
777
|
-
|
778
|
-
append_data.array = std::move(result);
|
779
|
-
return append_data.array.get();
|
780
|
-
}
|
781
|
-
|
782
|
-
//! Returns the underlying arrow array
|
783
|
-
ArrowArray ArrowAppender::Finalize() {
|
784
|
-
D_ASSERT(root_data.size() == types.size());
|
785
|
-
auto root_holder = make_uniq<ArrowAppendData>(options);
|
786
|
-
|
787
|
-
ArrowArray result;
|
788
|
-
root_holder->child_pointers.resize(types.size());
|
789
|
-
result.children = root_holder->child_pointers.data();
|
790
|
-
result.n_children = types.size();
|
791
|
-
|
792
|
-
// Configure root array
|
793
|
-
result.length = row_count;
|
794
|
-
result.n_children = types.size();
|
795
|
-
result.n_buffers = 1;
|
796
|
-
result.buffers = root_holder->buffers.data(); // there is no actual buffer there since we don't have NULLs
|
797
|
-
result.offset = 0;
|
798
|
-
result.null_count = 0; // needs to be 0
|
799
|
-
result.dictionary = nullptr;
|
800
|
-
root_holder->child_data = std::move(root_data);
|
801
|
-
|
802
|
-
for (idx_t i = 0; i < root_holder->child_data.size(); i++) {
|
803
|
-
root_holder->child_pointers[i] = FinalizeArrowChild(types[i], *root_holder->child_data[i]);
|
804
|
-
}
|
805
|
-
|
806
|
-
// Release ownership to caller
|
807
|
-
result.private_data = root_holder.release();
|
808
|
-
result.release = ReleaseDuckDBArrowAppendArray;
|
809
|
-
return result;
|
810
|
-
}
|
811
|
-
|
812
241
|
} // namespace duckdb
|