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
@@ -13,12 +13,15 @@
|
|
13
13
|
#include "duckdb/parallel/event.hpp"
|
14
14
|
#include "duckdb/parallel/thread_context.hpp"
|
15
15
|
|
16
|
+
#include <thread>
|
17
|
+
|
16
18
|
namespace duckdb {
|
17
19
|
|
18
20
|
PhysicalAsOfJoin::PhysicalAsOfJoin(LogicalComparisonJoin &op, unique_ptr<PhysicalOperator> left,
|
19
21
|
unique_ptr<PhysicalOperator> right)
|
20
22
|
: PhysicalComparisonJoin(op, PhysicalOperatorType::ASOF_JOIN, std::move(op.conditions), op.join_type,
|
21
|
-
op.estimated_cardinality)
|
23
|
+
op.estimated_cardinality),
|
24
|
+
comparison_type(ExpressionType::INVALID) {
|
22
25
|
|
23
26
|
// Convert the conditions partitions and sorts
|
24
27
|
for (auto &cond : conditions) {
|
@@ -29,9 +32,19 @@ PhysicalAsOfJoin::PhysicalAsOfJoin(LogicalComparisonJoin &op, unique_ptr<Physica
|
|
29
32
|
auto right = cond.right->Copy();
|
30
33
|
switch (cond.comparison) {
|
31
34
|
case ExpressionType::COMPARE_GREATERTHANOREQUALTO:
|
35
|
+
case ExpressionType::COMPARE_GREATERTHAN:
|
32
36
|
null_sensitive.emplace_back(lhs_orders.size());
|
33
37
|
lhs_orders.emplace_back(OrderType::ASCENDING, OrderByNullType::NULLS_LAST, std::move(left));
|
34
38
|
rhs_orders.emplace_back(OrderType::ASCENDING, OrderByNullType::NULLS_LAST, std::move(right));
|
39
|
+
comparison_type = cond.comparison;
|
40
|
+
break;
|
41
|
+
case ExpressionType::COMPARE_LESSTHANOREQUALTO:
|
42
|
+
case ExpressionType::COMPARE_LESSTHAN:
|
43
|
+
// Always put NULLS LAST so they can be ignored.
|
44
|
+
null_sensitive.emplace_back(lhs_orders.size());
|
45
|
+
lhs_orders.emplace_back(OrderType::DESCENDING, OrderByNullType::NULLS_LAST, std::move(left));
|
46
|
+
rhs_orders.emplace_back(OrderType::DESCENDING, OrderByNullType::NULLS_LAST, std::move(right));
|
47
|
+
comparison_type = cond.comparison;
|
35
48
|
break;
|
36
49
|
case ExpressionType::COMPARE_EQUAL:
|
37
50
|
null_sensitive.emplace_back(lhs_orders.size());
|
@@ -67,21 +80,32 @@ PhysicalAsOfJoin::PhysicalAsOfJoin(LogicalComparisonJoin &op, unique_ptr<Physica
|
|
67
80
|
class AsOfGlobalSinkState : public GlobalSinkState {
|
68
81
|
public:
|
69
82
|
AsOfGlobalSinkState(ClientContext &context, const PhysicalAsOfJoin &op)
|
70
|
-
:
|
71
|
-
op.estimated_cardinality),
|
83
|
+
: rhs_sink(context, op.rhs_partitions, op.rhs_orders, op.children[1]->types, {}, op.estimated_cardinality),
|
72
84
|
is_outer(IsRightOuterJoin(op.join_type)), has_null(false) {
|
73
85
|
}
|
74
86
|
|
75
87
|
idx_t Count() const {
|
76
|
-
return
|
88
|
+
return rhs_sink.count;
|
77
89
|
}
|
78
90
|
|
79
|
-
|
91
|
+
PartitionLocalSinkState *RegisterBuffer(ClientContext &context) {
|
92
|
+
lock_guard<mutex> guard(lock);
|
93
|
+
lhs_buffers.emplace_back(make_uniq<PartitionLocalSinkState>(context, *lhs_sink));
|
94
|
+
return lhs_buffers.back().get();
|
95
|
+
}
|
96
|
+
|
97
|
+
PartitionGlobalSinkState rhs_sink;
|
80
98
|
|
81
99
|
// One per partition
|
82
100
|
const bool is_outer;
|
83
101
|
vector<OuterJoinMarker> right_outers;
|
84
102
|
bool has_null;
|
103
|
+
|
104
|
+
// Left side buffering
|
105
|
+
unique_ptr<PartitionGlobalSinkState> lhs_sink;
|
106
|
+
|
107
|
+
mutex lock;
|
108
|
+
vector<unique_ptr<PartitionLocalSinkState>> lhs_buffers;
|
85
109
|
};
|
86
110
|
|
87
111
|
class AsOfLocalSinkState : public LocalSinkState {
|
@@ -108,7 +132,7 @@ unique_ptr<GlobalSinkState> PhysicalAsOfJoin::GetGlobalSinkState(ClientContext &
|
|
108
132
|
unique_ptr<LocalSinkState> PhysicalAsOfJoin::GetLocalSinkState(ExecutionContext &context) const {
|
109
133
|
// We only sink the RHS
|
110
134
|
auto &gsink = sink_state->Cast<AsOfGlobalSinkState>();
|
111
|
-
return make_uniq<AsOfLocalSinkState>(context.client, gsink.
|
135
|
+
return make_uniq<AsOfLocalSinkState>(context.client, gsink.rhs_sink);
|
112
136
|
}
|
113
137
|
|
114
138
|
SinkResultType PhysicalAsOfJoin::Sink(ExecutionContext &context, DataChunk &chunk, OperatorSinkInput &input) const {
|
@@ -119,27 +143,33 @@ SinkResultType PhysicalAsOfJoin::Sink(ExecutionContext &context, DataChunk &chun
|
|
119
143
|
return SinkResultType::NEED_MORE_INPUT;
|
120
144
|
}
|
121
145
|
|
122
|
-
|
123
|
-
auto &lstate =
|
146
|
+
SinkCombineResultType PhysicalAsOfJoin::Combine(ExecutionContext &context, OperatorSinkCombineInput &input) const {
|
147
|
+
auto &lstate = input.local_state.Cast<AsOfLocalSinkState>();
|
124
148
|
lstate.Combine();
|
149
|
+
return SinkCombineResultType::FINISHED;
|
125
150
|
}
|
126
151
|
|
127
152
|
//===--------------------------------------------------------------------===//
|
128
153
|
// Finalize
|
129
154
|
//===--------------------------------------------------------------------===//
|
130
155
|
SinkFinalizeType PhysicalAsOfJoin::Finalize(Pipeline &pipeline, Event &event, ClientContext &context,
|
131
|
-
|
132
|
-
auto &gstate =
|
156
|
+
OperatorSinkFinalizeInput &input) const {
|
157
|
+
auto &gstate = input.global_state.Cast<AsOfGlobalSinkState>();
|
158
|
+
|
159
|
+
// The data is all in so we can initialise the left partitioning.
|
160
|
+
const vector<unique_ptr<BaseStatistics>> partitions_stats;
|
161
|
+
gstate.lhs_sink = make_uniq<PartitionGlobalSinkState>(context, lhs_partitions, lhs_orders, children[0]->types,
|
162
|
+
partitions_stats, 0);
|
163
|
+
gstate.lhs_sink->SyncPartitioning(gstate.rhs_sink);
|
133
164
|
|
134
165
|
// Find the first group to sort
|
135
|
-
|
136
|
-
if (groups.empty() && EmptyResultIfRHSIsEmpty()) {
|
166
|
+
if (!gstate.rhs_sink.HasMergeTasks() && EmptyResultIfRHSIsEmpty()) {
|
137
167
|
// Empty input!
|
138
168
|
return SinkFinalizeType::NO_OUTPUT_POSSIBLE;
|
139
169
|
}
|
140
170
|
|
141
171
|
// Schedule all the sorts for maximum thread utilisation
|
142
|
-
auto new_event = make_shared<PartitionMergeEvent>(gstate.
|
172
|
+
auto new_event = make_shared<PartitionMergeEvent>(gstate.rhs_sink, pipeline);
|
143
173
|
event.InsertEvent(std::move(new_event));
|
144
174
|
|
145
175
|
return SinkFinalizeType::READY;
|
@@ -152,10 +182,10 @@ class AsOfGlobalState : public GlobalOperatorState {
|
|
152
182
|
public:
|
153
183
|
explicit AsOfGlobalState(AsOfGlobalSinkState &gsink) {
|
154
184
|
// for FULL/RIGHT OUTER JOIN, initialize right_outers to false for every tuple
|
155
|
-
auto &
|
185
|
+
auto &rhs_partition = gsink.rhs_sink;
|
156
186
|
auto &right_outers = gsink.right_outers;
|
157
|
-
right_outers.reserve(
|
158
|
-
for (const auto &hash_group :
|
187
|
+
right_outers.reserve(rhs_partition.hash_groups.size());
|
188
|
+
for (const auto &hash_group : rhs_partition.hash_groups) {
|
159
189
|
right_outers.emplace_back(OuterJoinMarker(gsink.is_outer));
|
160
190
|
right_outers.back().Initialize(hash_group->count);
|
161
191
|
}
|
@@ -169,79 +199,47 @@ unique_ptr<GlobalOperatorState> PhysicalAsOfJoin::GetGlobalOperatorState(ClientC
|
|
169
199
|
|
170
200
|
class AsOfLocalState : public CachingOperatorState {
|
171
201
|
public:
|
172
|
-
|
173
|
-
|
202
|
+
AsOfLocalState(ClientContext &context, const PhysicalAsOfJoin &op)
|
203
|
+
: context(context), allocator(Allocator::Get(context)), op(op), lhs_executor(context),
|
204
|
+
left_outer(IsLeftOuterJoin(op.join_type)), fetch_next_left(true) {
|
205
|
+
lhs_keys.Initialize(allocator, op.join_key_types);
|
206
|
+
for (const auto &cond : op.conditions) {
|
207
|
+
lhs_executor.AddExpression(*cond.left);
|
208
|
+
}
|
174
209
|
|
175
|
-
|
210
|
+
lhs_payload.Initialize(allocator, op.children[0]->types);
|
211
|
+
lhs_sel.Initialize();
|
212
|
+
left_outer.Initialize(STANDARD_VECTOR_SIZE);
|
176
213
|
|
177
|
-
|
178
|
-
|
214
|
+
auto &gsink = op.sink_state->Cast<AsOfGlobalSinkState>();
|
215
|
+
lhs_partition_sink = gsink.RegisterBuffer(context);
|
216
|
+
}
|
179
217
|
|
180
|
-
|
218
|
+
bool Sink(DataChunk &input);
|
219
|
+
OperatorResultType ExecuteInternal(ExecutionContext &context, DataChunk &input, DataChunk &chunk);
|
181
220
|
|
182
221
|
ClientContext &context;
|
183
222
|
Allocator &allocator;
|
184
223
|
const PhysicalAsOfJoin &op;
|
185
|
-
BufferManager &buffer_manager;
|
186
|
-
const bool force_external;
|
187
|
-
Orders lhs_orders;
|
188
224
|
|
189
|
-
// LHS sorting
|
190
225
|
ExpressionExecutor lhs_executor;
|
191
226
|
DataChunk lhs_keys;
|
192
227
|
ValidityMask lhs_valid_mask;
|
193
228
|
SelectionVector lhs_sel;
|
194
|
-
|
195
|
-
RowLayout lhs_layout;
|
196
|
-
unique_ptr<GlobalSortState> lhs_global_state;
|
197
|
-
DataChunk lhs_sorted;
|
198
|
-
|
199
|
-
// LHS binning
|
200
|
-
Vector hash_vector;
|
201
|
-
Vector bin_vector;
|
229
|
+
DataChunk lhs_payload;
|
202
230
|
|
203
|
-
// Output
|
204
|
-
idx_t lhs_match_count;
|
205
|
-
SelectionVector lhs_matched;
|
206
231
|
OuterJoinMarker left_outer;
|
207
232
|
bool fetch_next_left;
|
208
|
-
DataChunk group_payload;
|
209
|
-
DataChunk rhs_payload;
|
210
|
-
};
|
211
233
|
|
212
|
-
|
213
|
-
|
214
|
-
buffer_manager(BufferManager::GetBufferManager(context)), force_external(force_external), lhs_executor(context),
|
215
|
-
hash_vector(LogicalType::HASH), bin_vector(LogicalType::HASH), left_outer(IsLeftOuterJoin(op.join_type)),
|
216
|
-
fetch_next_left(true) {
|
217
|
-
vector<unique_ptr<BaseStatistics>> partition_stats;
|
218
|
-
Orders partitions; // Not used.
|
219
|
-
PartitionGlobalSinkState::GenerateOrderings(partitions, lhs_orders, op.lhs_partitions, op.lhs_orders,
|
220
|
-
partition_stats);
|
221
|
-
|
222
|
-
// We sort the row numbers of the incoming block, not the rows
|
223
|
-
lhs_layout.Initialize({LogicalType::UINTEGER});
|
224
|
-
lhs_sorted.Initialize(allocator, lhs_layout.GetTypes());
|
225
|
-
|
226
|
-
lhs_keys.Initialize(allocator, op.join_key_types);
|
227
|
-
for (const auto &cond : op.conditions) {
|
228
|
-
lhs_executor.AddExpression(*cond.left);
|
229
|
-
}
|
230
|
-
|
231
|
-
group_payload.Initialize(allocator, op.children[1]->types);
|
232
|
-
rhs_payload.Initialize(allocator, op.children[1]->types);
|
233
|
-
|
234
|
-
lhs_matched.Initialize();
|
235
|
-
lhs_sel.Initialize();
|
236
|
-
left_outer.Initialize(STANDARD_VECTOR_SIZE);
|
237
|
-
}
|
234
|
+
optional_ptr<PartitionLocalSinkState> lhs_partition_sink;
|
235
|
+
};
|
238
236
|
|
239
|
-
|
237
|
+
bool AsOfLocalState::Sink(DataChunk &input) {
|
240
238
|
// Compute the join keys
|
241
239
|
lhs_keys.Reset();
|
242
240
|
lhs_executor.Execute(input, lhs_keys);
|
243
241
|
|
244
|
-
//
|
242
|
+
// Combine the NULLs
|
245
243
|
const auto count = input.size();
|
246
244
|
lhs_valid_mask.Reset();
|
247
245
|
for (auto col_idx : op.null_sensitive) {
|
@@ -251,17 +249,19 @@ void AsOfLocalState::ResolveJoinKeys(DataChunk &input) {
|
|
251
249
|
lhs_valid_mask.Combine(unified.validity, count);
|
252
250
|
}
|
253
251
|
|
254
|
-
// Convert the mask to a selection vector
|
255
|
-
//
|
256
|
-
lhs_valid = 0;
|
252
|
+
// Convert the mask to a selection vector
|
253
|
+
// and mark all the rows that cannot match for early return.
|
254
|
+
idx_t lhs_valid = 0;
|
257
255
|
const auto entry_count = lhs_valid_mask.EntryCount(count);
|
258
256
|
idx_t base_idx = 0;
|
257
|
+
left_outer.Reset();
|
259
258
|
for (idx_t entry_idx = 0; entry_idx < entry_count;) {
|
260
259
|
const auto validity_entry = lhs_valid_mask.GetValidityEntry(entry_idx++);
|
261
260
|
const auto next = MinValue<idx_t>(base_idx + ValidityMask::BITS_PER_VALUE, count);
|
262
261
|
if (ValidityMask::AllValid(validity_entry)) {
|
263
262
|
for (; base_idx < next; ++base_idx) {
|
264
263
|
lhs_sel.set_index(lhs_valid++, base_idx);
|
264
|
+
left_outer.SetMatch(base_idx);
|
265
265
|
}
|
266
266
|
} else if (ValidityMask::NoneValid(validity_entry)) {
|
267
267
|
base_idx = next;
|
@@ -270,120 +270,240 @@ void AsOfLocalState::ResolveJoinKeys(DataChunk &input) {
|
|
270
270
|
for (; base_idx < next; ++base_idx) {
|
271
271
|
if (ValidityMask::RowIsValid(validity_entry, base_idx - start)) {
|
272
272
|
lhs_sel.set_index(lhs_valid++, base_idx);
|
273
|
+
left_outer.SetMatch(base_idx);
|
273
274
|
}
|
274
275
|
}
|
275
276
|
}
|
276
277
|
}
|
277
278
|
|
278
279
|
// Slice the keys to the ones we can match
|
279
|
-
|
280
|
-
|
280
|
+
lhs_payload.Reset();
|
281
|
+
if (lhs_valid == count) {
|
282
|
+
lhs_payload.Reference(input);
|
283
|
+
lhs_payload.SetCardinality(input);
|
284
|
+
} else {
|
285
|
+
lhs_payload.Slice(input, lhs_sel, lhs_valid);
|
286
|
+
lhs_payload.SetCardinality(lhs_valid);
|
287
|
+
|
288
|
+
// Flush the ones that can't match
|
289
|
+
fetch_next_left = false;
|
281
290
|
}
|
282
291
|
|
283
|
-
|
284
|
-
|
285
|
-
|
286
|
-
|
287
|
-
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
|
292
|
+
lhs_partition_sink->Sink(lhs_payload);
|
293
|
+
|
294
|
+
return false;
|
295
|
+
}
|
296
|
+
|
297
|
+
OperatorResultType AsOfLocalState::ExecuteInternal(ExecutionContext &context, DataChunk &input, DataChunk &chunk) {
|
298
|
+
input.Verify();
|
299
|
+
Sink(input);
|
300
|
+
|
301
|
+
// If there were any unmatchable rows, return them now so we can forget about them.
|
302
|
+
if (!fetch_next_left) {
|
303
|
+
fetch_next_left = true;
|
304
|
+
left_outer.ConstructLeftJoinResult(input, chunk);
|
305
|
+
left_outer.Reset();
|
306
|
+
}
|
307
|
+
|
308
|
+
// Just keep asking for data and buffering it
|
309
|
+
return OperatorResultType::NEED_MORE_INPUT;
|
310
|
+
}
|
311
|
+
|
312
|
+
OperatorResultType PhysicalAsOfJoin::ExecuteInternal(ExecutionContext &context, DataChunk &input, DataChunk &chunk,
|
313
|
+
GlobalOperatorState &gstate, OperatorState &lstate_p) const {
|
314
|
+
auto &gsink = sink_state->Cast<AsOfGlobalSinkState>();
|
315
|
+
auto &lstate = lstate_p.Cast<AsOfLocalState>();
|
316
|
+
|
317
|
+
if (gsink.rhs_sink.count == 0) {
|
318
|
+
// empty RHS
|
319
|
+
if (!EmptyResultIfRHSIsEmpty()) {
|
320
|
+
ConstructEmptyJoinResult(join_type, gsink.has_null, input, chunk);
|
321
|
+
return OperatorResultType::NEED_MORE_INPUT;
|
322
|
+
} else {
|
323
|
+
return OperatorResultType::FINISHED;
|
293
324
|
}
|
325
|
+
}
|
326
|
+
|
327
|
+
return lstate.ExecuteInternal(context, input, chunk);
|
328
|
+
}
|
329
|
+
|
330
|
+
//===--------------------------------------------------------------------===//
|
331
|
+
// Source
|
332
|
+
//===--------------------------------------------------------------------===//
|
333
|
+
class AsOfProbeBuffer {
|
334
|
+
public:
|
335
|
+
using Orders = vector<BoundOrderByNode>;
|
336
|
+
|
337
|
+
static bool IsExternal(ClientContext &context) {
|
338
|
+
return ClientConfig::GetConfig(context).force_external;
|
339
|
+
}
|
340
|
+
|
341
|
+
AsOfProbeBuffer(ClientContext &context, const PhysicalAsOfJoin &op);
|
342
|
+
|
343
|
+
public:
|
344
|
+
void ResolveJoin(bool *found_matches, idx_t *matches = nullptr);
|
345
|
+
bool Scanning() const {
|
346
|
+
return lhs_scanner.get();
|
347
|
+
}
|
348
|
+
void BeginLeftScan(hash_t scan_bin);
|
349
|
+
bool NextLeft();
|
350
|
+
void EndScan();
|
351
|
+
|
352
|
+
// resolve joins that output max N elements (SEMI, ANTI, MARK)
|
353
|
+
void ResolveSimpleJoin(ExecutionContext &context, DataChunk &chunk);
|
354
|
+
// resolve joins that can potentially output N*M elements (INNER, LEFT, FULL)
|
355
|
+
void ResolveComplexJoin(ExecutionContext &context, DataChunk &chunk);
|
356
|
+
// Chunk may be empty
|
357
|
+
void GetData(ExecutionContext &context, DataChunk &chunk);
|
358
|
+
bool HasMoreData() const {
|
359
|
+
return !fetch_next_left || (lhs_scanner && lhs_scanner->Remaining());
|
360
|
+
}
|
361
|
+
|
362
|
+
ClientContext &context;
|
363
|
+
Allocator &allocator;
|
364
|
+
const PhysicalAsOfJoin &op;
|
365
|
+
BufferManager &buffer_manager;
|
366
|
+
const bool force_external;
|
367
|
+
const idx_t memory_per_thread;
|
368
|
+
Orders lhs_orders;
|
369
|
+
|
370
|
+
// LHS scanning
|
371
|
+
SelectionVector lhs_sel;
|
372
|
+
optional_ptr<PartitionGlobalHashGroup> left_hash;
|
373
|
+
OuterJoinMarker left_outer;
|
374
|
+
unique_ptr<SBIterator> left_itr;
|
375
|
+
unique_ptr<PayloadScanner> lhs_scanner;
|
376
|
+
DataChunk lhs_payload;
|
377
|
+
|
378
|
+
// RHS scanning
|
379
|
+
optional_ptr<PartitionGlobalHashGroup> right_hash;
|
380
|
+
optional_ptr<OuterJoinMarker> right_outer;
|
381
|
+
unique_ptr<SBIterator> right_itr;
|
382
|
+
unique_ptr<PayloadScanner> rhs_scanner;
|
383
|
+
DataChunk rhs_payload;
|
384
|
+
|
385
|
+
idx_t lhs_match_count;
|
386
|
+
bool fetch_next_left;
|
387
|
+
};
|
388
|
+
|
389
|
+
AsOfProbeBuffer::AsOfProbeBuffer(ClientContext &context, const PhysicalAsOfJoin &op)
|
390
|
+
: context(context), allocator(Allocator::Get(context)), op(op),
|
391
|
+
buffer_manager(BufferManager::GetBufferManager(context)), force_external(IsExternal(context)),
|
392
|
+
memory_per_thread(op.GetMaxThreadMemory(context)), left_outer(IsLeftOuterJoin(op.join_type)),
|
393
|
+
fetch_next_left(true) {
|
394
|
+
vector<unique_ptr<BaseStatistics>> partition_stats;
|
395
|
+
Orders partitions; // Not used.
|
396
|
+
PartitionGlobalSinkState::GenerateOrderings(partitions, lhs_orders, op.lhs_partitions, op.lhs_orders,
|
397
|
+
partition_stats);
|
398
|
+
|
399
|
+
// We sort the row numbers of the incoming block, not the rows
|
400
|
+
lhs_payload.Initialize(allocator, op.children[0]->types);
|
401
|
+
rhs_payload.Initialize(allocator, op.children[1]->types);
|
294
402
|
|
295
|
-
|
296
|
-
|
297
|
-
|
403
|
+
lhs_sel.Initialize();
|
404
|
+
left_outer.Initialize(STANDARD_VECTOR_SIZE);
|
405
|
+
}
|
406
|
+
|
407
|
+
void AsOfProbeBuffer::BeginLeftScan(hash_t scan_bin) {
|
408
|
+
auto &gsink = op.sink_state->Cast<AsOfGlobalSinkState>();
|
409
|
+
auto &lhs_sink = *gsink.lhs_sink;
|
410
|
+
const auto left_group = lhs_sink.bin_groups[scan_bin];
|
411
|
+
if (left_group >= lhs_sink.bin_groups.size()) {
|
412
|
+
return;
|
298
413
|
}
|
299
414
|
|
300
|
-
|
301
|
-
|
302
|
-
|
303
|
-
|
304
|
-
|
415
|
+
auto iterator_comp = ExpressionType::INVALID;
|
416
|
+
switch (op.comparison_type) {
|
417
|
+
case ExpressionType::COMPARE_GREATERTHANOREQUALTO:
|
418
|
+
iterator_comp = ExpressionType::COMPARE_LESSTHANOREQUALTO;
|
419
|
+
break;
|
420
|
+
case ExpressionType::COMPARE_GREATERTHAN:
|
421
|
+
iterator_comp = ExpressionType::COMPARE_LESSTHAN;
|
422
|
+
break;
|
423
|
+
case ExpressionType::COMPARE_LESSTHANOREQUALTO:
|
424
|
+
iterator_comp = ExpressionType::COMPARE_GREATERTHANOREQUALTO;
|
425
|
+
break;
|
426
|
+
case ExpressionType::COMPARE_LESSTHAN:
|
427
|
+
iterator_comp = ExpressionType::COMPARE_GREATERTHAN;
|
428
|
+
break;
|
429
|
+
default:
|
430
|
+
throw NotImplementedException("Unsupported comparison type for ASOF join");
|
431
|
+
}
|
305
432
|
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
433
|
+
left_hash = lhs_sink.hash_groups[left_group].get();
|
434
|
+
auto &left_sort = *(left_hash->global_sort);
|
435
|
+
if (left_sort.sorted_blocks.empty()) {
|
436
|
+
return;
|
437
|
+
}
|
438
|
+
lhs_scanner = make_uniq<PayloadScanner>(left_sort, false);
|
439
|
+
left_itr = make_uniq<SBIterator>(left_sort, iterator_comp);
|
440
|
+
|
441
|
+
// We are only probing the corresponding right side bin, which may be empty
|
442
|
+
// If they are empty, we leave the iterator as null so we can emit left matches
|
443
|
+
auto &rhs_sink = gsink.rhs_sink;
|
444
|
+
const auto right_group = rhs_sink.bin_groups[scan_bin];
|
445
|
+
if (right_group < rhs_sink.bin_groups.size()) {
|
446
|
+
right_hash = rhs_sink.hash_groups[right_group].get();
|
447
|
+
right_outer = gsink.right_outers.data() + right_group;
|
448
|
+
auto &right_sort = *(right_hash->global_sort);
|
449
|
+
right_itr = make_uniq<SBIterator>(right_sort, iterator_comp);
|
450
|
+
rhs_scanner = make_uniq<PayloadScanner>(right_sort, false);
|
451
|
+
}
|
452
|
+
}
|
311
453
|
|
312
|
-
|
313
|
-
|
314
|
-
|
315
|
-
global_state.PrepareMergePhase();
|
316
|
-
while (global_state.sorted_blocks.size() > 1) {
|
317
|
-
MergeSorter merge_sorter(*lhs_global_state, buffer_manager);
|
318
|
-
merge_sorter.PerformInMergeRound();
|
319
|
-
global_state.CompleteMergeRound();
|
454
|
+
bool AsOfProbeBuffer::NextLeft() {
|
455
|
+
if (!HasMoreData()) {
|
456
|
+
return false;
|
320
457
|
}
|
321
458
|
|
322
|
-
//
|
323
|
-
|
459
|
+
// Scan the next sorted chunk
|
460
|
+
lhs_payload.Reset();
|
461
|
+
left_itr->SetIndex(lhs_scanner->Scanned());
|
462
|
+
lhs_scanner->Scan(lhs_payload);
|
324
463
|
|
325
|
-
|
326
|
-
lhs_sorted.Reset();
|
327
|
-
scanner->Scan(lhs_sorted);
|
464
|
+
return true;
|
328
465
|
}
|
329
466
|
|
330
|
-
void
|
331
|
-
|
332
|
-
|
467
|
+
void AsOfProbeBuffer::EndScan() {
|
468
|
+
right_hash = nullptr;
|
469
|
+
right_itr.reset();
|
470
|
+
rhs_scanner.reset();
|
471
|
+
right_outer = nullptr;
|
333
472
|
|
334
|
-
|
335
|
-
|
473
|
+
left_hash = nullptr;
|
474
|
+
left_itr.reset();
|
475
|
+
lhs_scanner.reset();
|
476
|
+
}
|
336
477
|
|
337
|
-
|
338
|
-
//
|
339
|
-
|
340
|
-
|
341
|
-
|
478
|
+
void AsOfProbeBuffer::ResolveJoin(bool *found_match, idx_t *matches) {
|
479
|
+
// If there was no right partition, there are no matches
|
480
|
+
lhs_match_count = 0;
|
481
|
+
left_outer.Reset();
|
482
|
+
if (!right_itr) {
|
483
|
+
return;
|
484
|
+
}
|
342
485
|
|
343
|
-
|
344
|
-
|
345
|
-
optional_ptr<OuterJoinMarker> right_outer;
|
486
|
+
const auto count = lhs_payload.size();
|
487
|
+
const auto left_base = left_itr->GetIndex();
|
346
488
|
// Searching for right <= left
|
347
|
-
|
348
|
-
|
349
|
-
lhs_match_count = 0;
|
350
|
-
const auto sorted_sel = FlatVector::GetData<sel_t>(lhs_sorted.data[0]);
|
351
|
-
for (idx_t i = 0; i < lhs_valid; ++i) {
|
352
|
-
// idx is the index in the input; i is the index in the sorted keys
|
353
|
-
const auto idx = sorted_sel[i];
|
354
|
-
const auto curr_bin = bins[bin_unified.sel->get_index(idx)];
|
355
|
-
if (!hash_group || curr_bin != prev_bin) {
|
356
|
-
// Grab the next group
|
357
|
-
prev_bin = curr_bin;
|
358
|
-
const auto group_idx = global_partition.bin_groups[curr_bin];
|
359
|
-
if (group_idx >= global_partition.hash_groups.size()) {
|
360
|
-
// No matching partition
|
361
|
-
hash_group = nullptr;
|
362
|
-
right_outer = nullptr;
|
363
|
-
right.reset();
|
364
|
-
continue;
|
365
|
-
}
|
366
|
-
hash_group = global_partition.hash_groups[group_idx].get();
|
367
|
-
right_outer = gsink.right_outers.data() + group_idx;
|
368
|
-
right = make_uniq<SBIterator>(*(hash_group->global_sort), ExpressionType::COMPARE_LESSTHANOREQUALTO);
|
369
|
-
}
|
370
|
-
left.SetIndex(i);
|
489
|
+
for (idx_t i = 0; i < count; ++i) {
|
490
|
+
left_itr->SetIndex(left_base + i);
|
371
491
|
|
372
492
|
// If right > left, then there is no match
|
373
|
-
if (!
|
493
|
+
if (!right_itr->Compare(*left_itr)) {
|
374
494
|
continue;
|
375
495
|
}
|
376
496
|
|
377
497
|
// Exponential search forward for a non-matching value using radix iterators
|
378
498
|
// (We use exponential search to avoid thrashing the block manager on large probes)
|
379
499
|
idx_t bound = 1;
|
380
|
-
idx_t begin =
|
381
|
-
|
382
|
-
while (
|
383
|
-
if (
|
500
|
+
idx_t begin = right_itr->GetIndex();
|
501
|
+
right_itr->SetIndex(begin + bound);
|
502
|
+
while (right_itr->GetIndex() < right_hash->count) {
|
503
|
+
if (right_itr->Compare(*left_itr)) {
|
384
504
|
// If right <= left, jump ahead
|
385
505
|
bound *= 2;
|
386
|
-
|
506
|
+
right_itr->SetIndex(begin + bound);
|
387
507
|
} else {
|
388
508
|
break;
|
389
509
|
}
|
@@ -392,255 +512,311 @@ void AsOfLocalState::ResolveJoin(DataChunk &input, bool *found_match, std::pair<
|
|
392
512
|
// Binary search for the first non-matching value using radix iterators
|
393
513
|
// The previous value (which we know exists) is the match
|
394
514
|
auto first = begin + bound / 2;
|
395
|
-
auto last = MinValue<idx_t>(begin + bound,
|
515
|
+
auto last = MinValue<idx_t>(begin + bound, right_hash->count);
|
396
516
|
while (first < last) {
|
397
517
|
const auto mid = first + (last - first) / 2;
|
398
|
-
|
399
|
-
if (
|
518
|
+
right_itr->SetIndex(mid);
|
519
|
+
if (right_itr->Compare(*left_itr)) {
|
400
520
|
// If right <= left, new lower bound
|
401
521
|
first = mid + 1;
|
402
522
|
} else {
|
403
523
|
last = mid;
|
404
524
|
}
|
405
525
|
}
|
406
|
-
|
526
|
+
right_itr->SetIndex(--first);
|
407
527
|
|
408
528
|
// Check partitions for strict equality
|
409
|
-
if (
|
529
|
+
if (right_hash->ComparePartitions(*left_itr, *right_itr)) {
|
410
530
|
continue;
|
411
531
|
}
|
412
532
|
|
413
533
|
// Emit match data
|
414
534
|
right_outer->SetMatch(first);
|
415
|
-
left_outer.SetMatch(
|
535
|
+
left_outer.SetMatch(i);
|
416
536
|
if (found_match) {
|
417
|
-
found_match[
|
537
|
+
found_match[i] = true;
|
418
538
|
}
|
419
539
|
if (matches) {
|
420
|
-
matches[
|
540
|
+
matches[i] = first;
|
421
541
|
}
|
422
|
-
|
542
|
+
lhs_sel.set_index(lhs_match_count++, i);
|
423
543
|
}
|
424
544
|
}
|
425
545
|
|
426
546
|
unique_ptr<OperatorState> PhysicalAsOfJoin::GetOperatorState(ExecutionContext &context) const {
|
427
|
-
|
428
|
-
return make_uniq<AsOfLocalState>(context.client, *this, config.force_external);
|
547
|
+
return make_uniq<AsOfLocalState>(context.client, *this);
|
429
548
|
}
|
430
549
|
|
431
|
-
void
|
432
|
-
OperatorState &lstate_p) const {
|
433
|
-
auto &lstate = lstate_p.Cast<AsOfLocalState>();
|
434
|
-
auto &gsink = sink_state->Cast<AsOfGlobalSinkState>();
|
435
|
-
|
550
|
+
void AsOfProbeBuffer::ResolveSimpleJoin(ExecutionContext &context, DataChunk &chunk) {
|
436
551
|
// perform the actual join
|
437
552
|
bool found_match[STANDARD_VECTOR_SIZE] = {false};
|
438
|
-
|
553
|
+
ResolveJoin(found_match);
|
439
554
|
|
440
555
|
// now construct the result based on the join result
|
441
|
-
switch (join_type) {
|
442
|
-
case JoinType::MARK: {
|
443
|
-
PhysicalJoin::ConstructMarkJoinResult(lstate.lhs_keys, input, chunk, found_match, gsink.has_null);
|
444
|
-
break;
|
445
|
-
}
|
556
|
+
switch (op.join_type) {
|
446
557
|
case JoinType::SEMI:
|
447
|
-
PhysicalJoin::ConstructSemiJoinResult(
|
558
|
+
PhysicalJoin::ConstructSemiJoinResult(lhs_payload, chunk, found_match);
|
448
559
|
break;
|
449
560
|
case JoinType::ANTI:
|
450
|
-
PhysicalJoin::ConstructAntiJoinResult(
|
561
|
+
PhysicalJoin::ConstructAntiJoinResult(lhs_payload, chunk, found_match);
|
451
562
|
break;
|
452
563
|
default:
|
453
564
|
throw NotImplementedException("Unimplemented join type for AsOf join");
|
454
565
|
}
|
455
566
|
}
|
456
567
|
|
457
|
-
|
458
|
-
OperatorState &lstate_p) const {
|
459
|
-
auto &lstate = lstate_p.Cast<AsOfLocalState>();
|
460
|
-
auto &gsink = sink_state->Cast<AsOfGlobalSinkState>();
|
461
|
-
|
462
|
-
if (!lstate.fetch_next_left) {
|
463
|
-
lstate.fetch_next_left = true;
|
464
|
-
if (lstate.left_outer.Enabled()) {
|
465
|
-
// left join: before we move to the next chunk, see if we need to output any vectors that didn't
|
466
|
-
// have a match found
|
467
|
-
lstate.left_outer.ConstructLeftJoinResult(input, chunk);
|
468
|
-
lstate.left_outer.Reset();
|
469
|
-
}
|
470
|
-
return OperatorResultType::NEED_MORE_INPUT;
|
471
|
-
}
|
472
|
-
|
568
|
+
void AsOfProbeBuffer::ResolveComplexJoin(ExecutionContext &context, DataChunk &chunk) {
|
473
569
|
// perform the actual join
|
474
|
-
|
475
|
-
|
476
|
-
|
477
|
-
|
478
|
-
|
479
|
-
|
480
|
-
hash_t scan_bin = global_partition.bin_groups.size();
|
481
|
-
optional_ptr<PartitionGlobalHashGroup> hash_group;
|
482
|
-
unique_ptr<PayloadScanner> scanner;
|
483
|
-
for (idx_t i = 0; i < lstate.lhs_match_count; ++i) {
|
484
|
-
const auto idx = lstate.lhs_matched[i];
|
485
|
-
const auto match_bin = matches[idx].first;
|
486
|
-
const auto match_pos = matches[idx].second;
|
487
|
-
if (match_bin != scan_bin) {
|
488
|
-
// Grab the next group
|
489
|
-
const auto group_idx = global_partition.bin_groups[match_bin];
|
490
|
-
hash_group = global_partition.hash_groups[group_idx].get();
|
491
|
-
scan_bin = match_bin;
|
492
|
-
scanner = make_uniq<PayloadScanner>(*hash_group->global_sort, false);
|
493
|
-
lstate.group_payload.Reset();
|
494
|
-
}
|
570
|
+
idx_t matches[STANDARD_VECTOR_SIZE];
|
571
|
+
ResolveJoin(nullptr, matches);
|
572
|
+
|
573
|
+
for (idx_t i = 0; i < lhs_match_count; ++i) {
|
574
|
+
const auto idx = lhs_sel[i];
|
575
|
+
const auto match_pos = matches[idx];
|
495
576
|
// Skip to the range containing the match
|
496
|
-
while (match_pos >=
|
497
|
-
|
498
|
-
|
577
|
+
while (match_pos >= rhs_scanner->Scanned()) {
|
578
|
+
rhs_payload.Reset();
|
579
|
+
rhs_scanner->Scan(rhs_payload);
|
499
580
|
}
|
500
581
|
// Append the individual values
|
501
582
|
// TODO: Batch the copies
|
502
|
-
const auto source_offset = match_pos - (
|
503
|
-
for (
|
504
|
-
const auto rhs_idx = right_projection_map[col_idx];
|
505
|
-
auto &source =
|
506
|
-
auto &target = chunk.data[
|
583
|
+
const auto source_offset = match_pos - (rhs_scanner->Scanned() - rhs_payload.size());
|
584
|
+
for (column_t col_idx = 0; col_idx < op.right_projection_map.size(); ++col_idx) {
|
585
|
+
const auto rhs_idx = op.right_projection_map[col_idx];
|
586
|
+
auto &source = rhs_payload.data[rhs_idx];
|
587
|
+
auto &target = chunk.data[lhs_payload.ColumnCount() + col_idx];
|
507
588
|
VectorOperations::Copy(source, target, source_offset + 1, source_offset, i);
|
508
589
|
}
|
509
590
|
}
|
510
591
|
|
511
|
-
// Slice the
|
512
|
-
|
513
|
-
|
514
|
-
// If we are doing a left join, come back for the NULLs
|
515
|
-
if (lstate.left_outer.Enabled()) {
|
516
|
-
lstate.fetch_next_left = false;
|
517
|
-
return OperatorResultType::HAVE_MORE_OUTPUT;
|
592
|
+
// Slice the left payload into the result
|
593
|
+
for (column_t i = 0; i < lhs_payload.ColumnCount(); ++i) {
|
594
|
+
chunk.data[i].Slice(lhs_payload.data[i], lhs_sel, lhs_match_count);
|
518
595
|
}
|
596
|
+
chunk.SetCardinality(lhs_match_count);
|
519
597
|
|
520
|
-
|
598
|
+
// If we are doing a left join, come back for the NULLs
|
599
|
+
fetch_next_left = !left_outer.Enabled();
|
521
600
|
}
|
522
601
|
|
523
|
-
|
524
|
-
|
525
|
-
|
526
|
-
|
527
|
-
|
528
|
-
|
529
|
-
|
530
|
-
|
531
|
-
|
532
|
-
} else {
|
533
|
-
return OperatorResultType::FINISHED;
|
602
|
+
void AsOfProbeBuffer::GetData(ExecutionContext &context, DataChunk &chunk) {
|
603
|
+
// Handle dangling left join results from current chunk
|
604
|
+
if (!fetch_next_left) {
|
605
|
+
fetch_next_left = true;
|
606
|
+
if (left_outer.Enabled()) {
|
607
|
+
// left join: before we move to the next chunk, see if we need to output any vectors that didn't
|
608
|
+
// have a match found
|
609
|
+
left_outer.ConstructLeftJoinResult(lhs_payload, chunk);
|
610
|
+
left_outer.Reset();
|
534
611
|
}
|
612
|
+
return;
|
535
613
|
}
|
536
614
|
|
537
|
-
|
538
|
-
|
615
|
+
// Stop if there is no more data
|
616
|
+
if (!NextLeft()) {
|
617
|
+
return;
|
618
|
+
}
|
619
|
+
|
620
|
+
switch (op.join_type) {
|
539
621
|
case JoinType::SEMI:
|
540
622
|
case JoinType::ANTI:
|
541
623
|
case JoinType::MARK:
|
542
624
|
// simple joins can have max STANDARD_VECTOR_SIZE matches per chunk
|
543
|
-
ResolveSimpleJoin(context,
|
544
|
-
|
625
|
+
ResolveSimpleJoin(context, chunk);
|
626
|
+
break;
|
545
627
|
case JoinType::LEFT:
|
546
628
|
case JoinType::INNER:
|
547
629
|
case JoinType::RIGHT:
|
548
630
|
case JoinType::OUTER:
|
549
|
-
|
631
|
+
ResolveComplexJoin(context, chunk);
|
632
|
+
break;
|
550
633
|
default:
|
551
634
|
throw NotImplementedException("Unimplemented type for as-of join!");
|
552
635
|
}
|
553
636
|
}
|
554
637
|
|
555
|
-
//===--------------------------------------------------------------------===//
|
556
|
-
// Source
|
557
|
-
//===--------------------------------------------------------------------===//
|
558
638
|
class AsOfGlobalSourceState : public GlobalSourceState {
|
559
639
|
public:
|
560
|
-
explicit AsOfGlobalSourceState(
|
640
|
+
explicit AsOfGlobalSourceState(AsOfGlobalSinkState &gsink_p)
|
641
|
+
: gsink(gsink_p), next_combine(0), combined(0), merged(0), mergers(0), next_left(0), flushed(0), next_right(0) {
|
561
642
|
}
|
562
643
|
|
563
|
-
|
564
|
-
|
565
|
-
|
566
|
-
|
567
|
-
public:
|
568
|
-
idx_t MaxThreads() override {
|
569
|
-
// If there is only one partition, we have to process it on one thread.
|
570
|
-
if (!gsink.grouping_data) {
|
571
|
-
return 1;
|
644
|
+
PartitionGlobalMergeStates &GetMergeStates() {
|
645
|
+
lock_guard<mutex> guard(lock);
|
646
|
+
if (!merge_states) {
|
647
|
+
merge_states = make_uniq<PartitionGlobalMergeStates>(*gsink.lhs_sink);
|
572
648
|
}
|
649
|
+
return *merge_states;
|
650
|
+
}
|
573
651
|
|
574
|
-
|
575
|
-
|
576
|
-
|
577
|
-
|
652
|
+
AsOfGlobalSinkState &gsink;
|
653
|
+
//! The next buffer to combine
|
654
|
+
atomic<size_t> next_combine;
|
655
|
+
//! The number of combined buffers
|
656
|
+
atomic<size_t> combined;
|
657
|
+
//! The number of combined buffers
|
658
|
+
atomic<size_t> merged;
|
659
|
+
//! The number of combined buffers
|
660
|
+
atomic<size_t> mergers;
|
661
|
+
//! The next buffer to flush
|
662
|
+
atomic<size_t> next_left;
|
663
|
+
//! The number of flushed buffers
|
664
|
+
atomic<size_t> flushed;
|
665
|
+
//! The right outer output read position.
|
666
|
+
atomic<idx_t> next_right;
|
667
|
+
//! The merge handler
|
668
|
+
mutex lock;
|
669
|
+
unique_ptr<PartitionGlobalMergeStates> merge_states;
|
578
670
|
|
579
|
-
|
671
|
+
public:
|
672
|
+
idx_t MaxThreads() override {
|
673
|
+
return gsink.lhs_buffers.size();
|
580
674
|
}
|
581
675
|
};
|
582
676
|
|
583
677
|
unique_ptr<GlobalSourceState> PhysicalAsOfJoin::GetGlobalSourceState(ClientContext &context) const {
|
584
678
|
auto &gsink = sink_state->Cast<AsOfGlobalSinkState>();
|
585
|
-
return make_uniq<AsOfGlobalSourceState>(gsink
|
679
|
+
return make_uniq<AsOfGlobalSourceState>(gsink);
|
586
680
|
}
|
587
681
|
|
588
682
|
class AsOfLocalSourceState : public LocalSourceState {
|
589
683
|
public:
|
590
684
|
using HashGroupPtr = unique_ptr<PartitionGlobalHashGroup>;
|
591
685
|
|
592
|
-
|
686
|
+
AsOfLocalSourceState(AsOfGlobalSourceState &gsource, const PhysicalAsOfJoin &op, ClientContext &client_p);
|
687
|
+
|
688
|
+
// Return true if we were not interrupted (another thread died)
|
689
|
+
bool CombineLeftPartitions();
|
690
|
+
bool MergeLeftPartitions();
|
593
691
|
|
594
|
-
idx_t
|
692
|
+
idx_t BeginRightScan(const idx_t hash_bin);
|
595
693
|
|
596
|
-
|
694
|
+
AsOfGlobalSourceState &gsource;
|
695
|
+
ClientContext &client;
|
696
|
+
|
697
|
+
//! The left side partition being probed
|
698
|
+
AsOfProbeBuffer probe_buffer;
|
597
699
|
|
598
700
|
//! The read partition
|
599
701
|
idx_t hash_bin;
|
600
702
|
HashGroupPtr hash_group;
|
601
|
-
|
602
703
|
//! The read cursor
|
603
704
|
unique_ptr<PayloadScanner> scanner;
|
604
|
-
//! Buffer for the inputs
|
605
|
-
DataChunk input_chunk;
|
606
705
|
//! Pointer to the matches
|
607
|
-
const bool *found_match;
|
706
|
+
const bool *found_match = {};
|
608
707
|
};
|
609
708
|
|
610
|
-
AsOfLocalSourceState::AsOfLocalSourceState(
|
611
|
-
|
709
|
+
AsOfLocalSourceState::AsOfLocalSourceState(AsOfGlobalSourceState &gsource, const PhysicalAsOfJoin &op,
|
710
|
+
ClientContext &client_p)
|
711
|
+
: gsource(gsource), client(client_p), probe_buffer(gsource.gsink.lhs_sink->context, op) {
|
712
|
+
gsource.mergers++;
|
612
713
|
}
|
613
714
|
|
614
|
-
|
615
|
-
|
715
|
+
bool AsOfLocalSourceState::CombineLeftPartitions() {
|
716
|
+
const auto buffer_count = gsource.gsink.lhs_buffers.size();
|
717
|
+
while (gsource.combined < buffer_count && !client.interrupted) {
|
718
|
+
const auto next_combine = gsource.next_combine++;
|
719
|
+
if (next_combine < buffer_count) {
|
720
|
+
gsource.gsink.lhs_buffers[next_combine]->Combine();
|
721
|
+
++gsource.combined;
|
722
|
+
} else {
|
723
|
+
TaskScheduler::GetScheduler(client).YieldThread();
|
724
|
+
}
|
725
|
+
}
|
726
|
+
|
727
|
+
return !client.interrupted;
|
728
|
+
}
|
729
|
+
|
730
|
+
bool AsOfLocalSourceState::MergeLeftPartitions() {
|
731
|
+
PartitionGlobalMergeStates::Callback local_callback;
|
732
|
+
PartitionLocalMergeState local_merge(*gsource.gsink.lhs_sink);
|
733
|
+
gsource.GetMergeStates().ExecuteTask(local_merge, local_callback);
|
734
|
+
gsource.merged++;
|
735
|
+
while (gsource.merged < gsource.mergers && !client.interrupted) {
|
736
|
+
TaskScheduler::GetScheduler(client).YieldThread();
|
737
|
+
}
|
738
|
+
return !client.interrupted;
|
739
|
+
}
|
740
|
+
|
741
|
+
idx_t AsOfLocalSourceState::BeginRightScan(const idx_t hash_bin_p) {
|
616
742
|
hash_bin = hash_bin_p;
|
617
743
|
|
618
|
-
hash_group = std::move(
|
744
|
+
hash_group = std::move(gsource.gsink.rhs_sink.hash_groups[hash_bin]);
|
745
|
+
if (hash_group->global_sort->sorted_blocks.empty()) {
|
746
|
+
return 0;
|
747
|
+
}
|
619
748
|
scanner = make_uniq<PayloadScanner>(*hash_group->global_sort);
|
620
|
-
found_match =
|
749
|
+
found_match = gsource.gsink.right_outers[hash_bin].GetMatches();
|
621
750
|
|
622
751
|
return scanner->Remaining();
|
623
752
|
}
|
624
753
|
|
625
754
|
unique_ptr<LocalSourceState> PhysicalAsOfJoin::GetLocalSourceState(ExecutionContext &context,
|
626
755
|
GlobalSourceState &gstate) const {
|
627
|
-
auto &
|
628
|
-
return make_uniq<AsOfLocalSourceState>(
|
756
|
+
auto &gsource = gstate.Cast<AsOfGlobalSourceState>();
|
757
|
+
return make_uniq<AsOfLocalSourceState>(gsource, *this, context.client);
|
629
758
|
}
|
630
759
|
|
631
760
|
SourceResultType PhysicalAsOfJoin::GetData(ExecutionContext &context, DataChunk &chunk,
|
632
761
|
OperatorSourceInput &input) const {
|
633
|
-
D_ASSERT(IsRightOuterJoin(join_type));
|
634
|
-
|
635
762
|
auto &gsource = input.global_state.Cast<AsOfGlobalSourceState>();
|
636
763
|
auto &lsource = input.local_state.Cast<AsOfLocalSourceState>();
|
637
|
-
auto &
|
764
|
+
auto &rhs_sink = gsource.gsink.rhs_sink;
|
765
|
+
auto &client = context.client;
|
766
|
+
|
767
|
+
// Step 1: Combine the partitions
|
768
|
+
if (!lsource.CombineLeftPartitions()) {
|
769
|
+
return SourceResultType::FINISHED;
|
770
|
+
}
|
771
|
+
|
772
|
+
// Step 2: Sort on all threads
|
773
|
+
if (!lsource.MergeLeftPartitions()) {
|
774
|
+
return SourceResultType::FINISHED;
|
775
|
+
}
|
776
|
+
|
777
|
+
// Step 3: Join the partitions
|
778
|
+
auto &lhs_sink = *gsource.gsink.lhs_sink;
|
779
|
+
const auto left_bins = lhs_sink.grouping_data ? lhs_sink.grouping_data->GetPartitions().size() : 1;
|
780
|
+
while (gsource.flushed < left_bins) {
|
781
|
+
// Make sure we have something to flush
|
782
|
+
if (!lsource.probe_buffer.Scanning()) {
|
783
|
+
const auto left_bin = gsource.next_left++;
|
784
|
+
if (left_bin < left_bins) {
|
785
|
+
// More to flush
|
786
|
+
lsource.probe_buffer.BeginLeftScan(left_bin);
|
787
|
+
} else if (!IsRightOuterJoin(join_type) || client.interrupted) {
|
788
|
+
return SourceResultType::FINISHED;
|
789
|
+
} else {
|
790
|
+
// Wait for all threads to finish
|
791
|
+
// TODO: How to implement a spin wait correctly?
|
792
|
+
// Returning BLOCKED seems to hang the system.
|
793
|
+
TaskScheduler::GetScheduler(client).YieldThread();
|
794
|
+
continue;
|
795
|
+
}
|
796
|
+
}
|
797
|
+
|
798
|
+
lsource.probe_buffer.GetData(context, chunk);
|
799
|
+
if (chunk.size()) {
|
800
|
+
return SourceResultType::HAVE_MORE_OUTPUT;
|
801
|
+
} else if (lsource.probe_buffer.HasMoreData()) {
|
802
|
+
// Join the next partition
|
803
|
+
continue;
|
804
|
+
} else {
|
805
|
+
lsource.probe_buffer.EndScan();
|
806
|
+
gsource.flushed++;
|
807
|
+
}
|
808
|
+
}
|
809
|
+
|
810
|
+
// Step 4: Emit right join matches
|
811
|
+
if (!IsRightOuterJoin(join_type)) {
|
812
|
+
return SourceResultType::FINISHED;
|
813
|
+
}
|
638
814
|
|
639
|
-
auto &hash_groups =
|
640
|
-
const auto
|
815
|
+
auto &hash_groups = rhs_sink.hash_groups;
|
816
|
+
const auto right_groups = hash_groups.size();
|
641
817
|
|
642
818
|
DataChunk rhs_chunk;
|
643
|
-
rhs_chunk.Initialize(Allocator::Get(context.client),
|
819
|
+
rhs_chunk.Initialize(Allocator::Get(context.client), rhs_sink.payload_types);
|
644
820
|
SelectionVector rsel(STANDARD_VECTOR_SIZE);
|
645
821
|
|
646
822
|
while (chunk.size() == 0) {
|
@@ -648,17 +824,17 @@ SourceResultType PhysicalAsOfJoin::GetData(ExecutionContext &context, DataChunk
|
|
648
824
|
while (!lsource.scanner || !lsource.scanner->Remaining()) {
|
649
825
|
lsource.scanner.reset();
|
650
826
|
lsource.hash_group.reset();
|
651
|
-
auto hash_bin = gsource.
|
652
|
-
if (hash_bin >=
|
827
|
+
auto hash_bin = gsource.next_right++;
|
828
|
+
if (hash_bin >= right_groups) {
|
653
829
|
return SourceResultType::FINISHED;
|
654
830
|
}
|
655
831
|
|
656
|
-
for (; hash_bin < hash_groups.size(); hash_bin = gsource.
|
832
|
+
for (; hash_bin < hash_groups.size(); hash_bin = gsource.next_right++) {
|
657
833
|
if (hash_groups[hash_bin]) {
|
658
834
|
break;
|
659
835
|
}
|
660
836
|
}
|
661
|
-
lsource.
|
837
|
+
lsource.BeginRightScan(hash_bin);
|
662
838
|
}
|
663
839
|
const auto rhs_position = lsource.scanner->Scanned();
|
664
840
|
lsource.scanner->Scan(rhs_chunk);
|