duckdb 1.0.1-dev22.0 → 1.0.1-dev27.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.github/workflows/NodeJS.yml +1 -1
- package/binding.gyp +41 -0
- package/package.json +1 -1
- package/src/duckdb/extension/icu/icu-dateadd.cpp +4 -2
- package/src/duckdb/extension/icu/icu-datefunc.cpp +6 -2
- package/src/duckdb/extension/icu/icu-datesub.cpp +13 -2
- package/src/duckdb/extension/icu/icu-strptime.cpp +6 -6
- package/src/duckdb/extension/icu/icu-table-range.cpp +92 -73
- package/src/duckdb/extension/icu/icu-timebucket.cpp +12 -2
- package/src/duckdb/extension/icu/icu-timezone.cpp +3 -3
- package/src/duckdb/extension/icu/icu_extension.cpp +61 -9
- package/src/duckdb/extension/json/include/json_executors.hpp +20 -23
- package/src/duckdb/extension/json/include/json_functions.hpp +4 -0
- package/src/duckdb/extension/json/include/json_scan.hpp +6 -2
- package/src/duckdb/extension/json/include/json_structure.hpp +12 -9
- package/src/duckdb/extension/json/json_common.cpp +66 -10
- package/src/duckdb/extension/json/json_extension.cpp +13 -5
- package/src/duckdb/extension/json/json_functions/json_array_length.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_create.cpp +21 -4
- package/src/duckdb/extension/json/json_functions/json_exists.cpp +32 -0
- package/src/duckdb/extension/json/json_functions/json_extract.cpp +2 -2
- package/src/duckdb/extension/json/json_functions/json_keys.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_pretty.cpp +32 -0
- package/src/duckdb/extension/json/json_functions/json_serialize_sql.cpp +5 -1
- package/src/duckdb/extension/json/json_functions/json_structure.cpp +305 -94
- package/src/duckdb/extension/json/json_functions/json_transform.cpp +1 -1
- package/src/duckdb/extension/json/json_functions/json_type.cpp +3 -3
- package/src/duckdb/extension/json/json_functions/json_value.cpp +42 -0
- package/src/duckdb/extension/json/json_functions/read_json.cpp +16 -2
- package/src/duckdb/extension/json/json_functions/read_json_objects.cpp +3 -2
- package/src/duckdb/extension/json/json_functions.cpp +5 -1
- package/src/duckdb/extension/json/json_scan.cpp +13 -12
- package/src/duckdb/extension/json/serialize_json.cpp +5 -3
- package/src/duckdb/extension/parquet/column_reader.cpp +206 -43
- package/src/duckdb/extension/parquet/column_writer.cpp +133 -62
- package/src/duckdb/extension/parquet/geo_parquet.cpp +391 -0
- package/src/duckdb/extension/parquet/include/boolean_column_reader.hpp +16 -5
- package/src/duckdb/extension/parquet/include/column_reader.hpp +37 -12
- package/src/duckdb/extension/parquet/include/column_writer.hpp +10 -11
- package/src/duckdb/extension/parquet/include/expression_column_reader.hpp +52 -0
- package/src/duckdb/extension/parquet/include/geo_parquet.hpp +139 -0
- package/src/duckdb/extension/parquet/include/parquet_crypto.hpp +13 -8
- package/src/duckdb/extension/parquet/include/parquet_decimal_utils.hpp +3 -0
- package/src/duckdb/extension/parquet/include/parquet_file_metadata_cache.hpp +7 -3
- package/src/duckdb/extension/parquet/include/parquet_reader.hpp +55 -8
- package/src/duckdb/extension/parquet/include/parquet_rle_bp_decoder.hpp +3 -3
- package/src/duckdb/extension/parquet/include/parquet_rle_bp_encoder.hpp +1 -1
- package/src/duckdb/extension/parquet/include/parquet_timestamp.hpp +8 -0
- package/src/duckdb/extension/parquet/include/parquet_writer.hpp +21 -7
- package/src/duckdb/extension/parquet/include/resizable_buffer.hpp +33 -11
- package/src/duckdb/extension/parquet/include/string_column_reader.hpp +5 -2
- package/src/duckdb/extension/parquet/include/templated_column_reader.hpp +48 -14
- package/src/duckdb/extension/parquet/parquet_crypto.cpp +109 -61
- package/src/duckdb/extension/parquet/parquet_extension.cpp +305 -72
- package/src/duckdb/extension/parquet/parquet_metadata.cpp +4 -4
- package/src/duckdb/extension/parquet/parquet_reader.cpp +151 -40
- package/src/duckdb/extension/parquet/parquet_statistics.cpp +50 -16
- package/src/duckdb/extension/parquet/parquet_timestamp.cpp +42 -1
- package/src/duckdb/extension/parquet/parquet_writer.cpp +67 -75
- package/src/duckdb/extension/parquet/serialize_parquet.cpp +3 -1
- package/src/duckdb/extension/parquet/zstd_file_system.cpp +5 -1
- package/src/duckdb/src/catalog/catalog.cpp +14 -16
- package/src/duckdb/src/catalog/catalog_entry/duck_index_entry.cpp +14 -11
- package/src/duckdb/src/catalog/catalog_entry/duck_schema_entry.cpp +39 -19
- package/src/duckdb/src/catalog/catalog_entry/duck_table_entry.cpp +92 -78
- package/src/duckdb/src/catalog/catalog_entry/index_catalog_entry.cpp +10 -2
- package/src/duckdb/src/catalog/catalog_entry/macro_catalog_entry.cpp +10 -3
- package/src/duckdb/src/catalog/catalog_entry/schema_catalog_entry.cpp +3 -3
- package/src/duckdb/src/catalog/catalog_entry/table_catalog_entry.cpp +7 -7
- package/src/duckdb/src/catalog/catalog_entry.cpp +6 -3
- package/src/duckdb/src/catalog/catalog_set.cpp +14 -19
- package/src/duckdb/src/catalog/default/default_functions.cpp +179 -166
- package/src/duckdb/src/catalog/default/default_generator.cpp +24 -0
- package/src/duckdb/src/catalog/default/default_schemas.cpp +4 -3
- package/src/duckdb/src/catalog/default/default_table_functions.cpp +148 -0
- package/src/duckdb/src/catalog/default/default_views.cpp +7 -3
- package/src/duckdb/src/catalog/duck_catalog.cpp +7 -1
- package/src/duckdb/src/common/adbc/adbc.cpp +120 -58
- package/src/duckdb/src/common/allocator.cpp +71 -6
- package/src/duckdb/src/common/arrow/appender/bool_data.cpp +8 -7
- package/src/duckdb/src/common/arrow/appender/fixed_size_list_data.cpp +1 -1
- package/src/duckdb/src/common/arrow/appender/union_data.cpp +4 -5
- package/src/duckdb/src/common/arrow/arrow_appender.cpp +55 -21
- package/src/duckdb/src/common/arrow/arrow_converter.cpp +85 -10
- package/src/duckdb/src/common/arrow/arrow_merge_event.cpp +142 -0
- package/src/duckdb/src/common/arrow/arrow_query_result.cpp +56 -0
- package/src/duckdb/src/common/arrow/physical_arrow_batch_collector.cpp +37 -0
- package/src/duckdb/src/common/arrow/physical_arrow_collector.cpp +128 -0
- package/src/duckdb/src/common/arrow/schema_metadata.cpp +101 -0
- package/src/duckdb/src/common/cgroups.cpp +189 -0
- package/src/duckdb/src/common/compressed_file_system.cpp +6 -3
- package/src/duckdb/src/common/encryption_state.cpp +38 -0
- package/src/duckdb/src/common/enum_util.cpp +682 -14
- package/src/duckdb/src/common/enums/file_compression_type.cpp +24 -0
- package/src/duckdb/src/common/enums/metric_type.cpp +208 -0
- package/src/duckdb/src/common/enums/optimizer_type.cpp +8 -2
- package/src/duckdb/src/common/enums/physical_operator_type.cpp +2 -0
- package/src/duckdb/src/common/enums/relation_type.cpp +4 -0
- package/src/duckdb/src/common/enums/statement_type.cpp +15 -0
- package/src/duckdb/src/common/error_data.cpp +22 -20
- package/src/duckdb/src/common/exception/binder_exception.cpp +5 -0
- package/src/duckdb/src/common/exception.cpp +11 -1
- package/src/duckdb/src/common/extra_type_info.cpp +3 -0
- package/src/duckdb/src/common/file_buffer.cpp +1 -1
- package/src/duckdb/src/common/file_system.cpp +25 -3
- package/src/duckdb/src/common/filename_pattern.cpp +1 -0
- package/src/duckdb/src/common/fsst.cpp +15 -14
- package/src/duckdb/src/common/gzip_file_system.cpp +3 -1
- package/src/duckdb/src/common/hive_partitioning.cpp +103 -43
- package/src/duckdb/src/common/http_util.cpp +25 -0
- package/src/duckdb/src/common/local_file_system.cpp +48 -27
- package/src/duckdb/src/common/multi_file_list.cpp +113 -22
- package/src/duckdb/src/common/multi_file_reader.cpp +59 -58
- package/src/duckdb/src/common/operator/cast_operators.cpp +133 -34
- package/src/duckdb/src/common/operator/string_cast.cpp +42 -11
- package/src/duckdb/src/common/progress_bar/progress_bar.cpp +2 -2
- package/src/duckdb/src/common/progress_bar/terminal_progress_bar_display.cpp +1 -1
- package/src/duckdb/src/common/radix_partitioning.cpp +31 -21
- package/src/duckdb/src/common/random_engine.cpp +4 -0
- package/src/duckdb/src/common/re2_regex.cpp +47 -12
- package/src/duckdb/src/common/render_tree.cpp +243 -0
- package/src/duckdb/src/common/row_operations/row_aggregate.cpp +1 -1
- package/src/duckdb/src/common/row_operations/row_gather.cpp +2 -2
- package/src/duckdb/src/common/row_operations/row_matcher.cpp +58 -5
- package/src/duckdb/src/common/row_operations/row_radix_scatter.cpp +79 -43
- package/src/duckdb/src/common/serializer/binary_deserializer.cpp +1 -1
- package/src/duckdb/src/common/serializer/buffered_file_reader.cpp +6 -4
- package/src/duckdb/src/common/serializer/buffered_file_writer.cpp +18 -9
- package/src/duckdb/src/common/serializer/memory_stream.cpp +1 -0
- package/src/duckdb/src/common/sort/partition_state.cpp +33 -18
- package/src/duckdb/src/common/sort/radix_sort.cpp +22 -15
- package/src/duckdb/src/common/sort/sort_state.cpp +19 -16
- package/src/duckdb/src/common/sort/sorted_block.cpp +11 -10
- package/src/duckdb/src/common/string_util.cpp +167 -10
- package/src/duckdb/src/common/tree_renderer/graphviz_tree_renderer.cpp +108 -0
- package/src/duckdb/src/common/tree_renderer/html_tree_renderer.cpp +267 -0
- package/src/duckdb/src/common/tree_renderer/json_tree_renderer.cpp +116 -0
- package/src/duckdb/src/common/tree_renderer/text_tree_renderer.cpp +482 -0
- package/src/duckdb/src/common/tree_renderer/tree_renderer.cpp +12 -0
- package/src/duckdb/src/common/tree_renderer.cpp +16 -508
- package/src/duckdb/src/common/types/batched_data_collection.cpp +78 -9
- package/src/duckdb/src/common/types/bit.cpp +24 -22
- package/src/duckdb/src/common/types/blob.cpp +15 -11
- package/src/duckdb/src/common/types/column/column_data_allocator.cpp +18 -9
- package/src/duckdb/src/common/types/column/column_data_collection.cpp +4 -4
- package/src/duckdb/src/common/types/column/column_data_collection_segment.cpp +3 -4
- package/src/duckdb/src/common/types/column/column_data_consumer.cpp +2 -2
- package/src/duckdb/src/common/types/column/partitioned_column_data.cpp +70 -21
- package/src/duckdb/src/common/types/data_chunk.cpp +10 -1
- package/src/duckdb/src/common/types/date.cpp +8 -19
- package/src/duckdb/src/common/types/decimal.cpp +3 -2
- package/src/duckdb/src/common/types/hugeint.cpp +11 -3
- package/src/duckdb/src/common/types/hyperloglog.cpp +212 -227
- package/src/duckdb/src/common/types/interval.cpp +1 -1
- package/src/duckdb/src/common/types/list_segment.cpp +83 -49
- package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +22 -83
- package/src/duckdb/src/common/types/row/row_data_collection.cpp +2 -2
- package/src/duckdb/src/common/types/row/row_data_collection_scanner.cpp +20 -4
- package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +28 -7
- package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +29 -14
- package/src/duckdb/src/common/types/row/tuple_data_scatter_gather.cpp +152 -102
- package/src/duckdb/src/common/types/row/tuple_data_segment.cpp +4 -1
- package/src/duckdb/src/common/types/selection_vector.cpp +17 -1
- package/src/duckdb/src/common/types/time.cpp +62 -31
- package/src/duckdb/src/common/types/timestamp.cpp +70 -12
- package/src/duckdb/src/common/types/uuid.cpp +1 -1
- package/src/duckdb/src/common/types/validity_mask.cpp +40 -5
- package/src/duckdb/src/common/types/value.cpp +50 -8
- package/src/duckdb/src/common/types/varint.cpp +295 -0
- package/src/duckdb/src/common/types/vector.cpp +165 -54
- package/src/duckdb/src/common/types/vector_buffer.cpp +5 -4
- package/src/duckdb/src/common/types.cpp +106 -26
- package/src/duckdb/src/common/vector_operations/vector_copy.cpp +13 -25
- package/src/duckdb/src/common/vector_operations/vector_hash.cpp +6 -0
- package/src/duckdb/src/common/virtual_file_system.cpp +3 -3
- package/src/duckdb/src/core_functions/aggregate/distributive/approx_count.cpp +35 -82
- package/src/duckdb/src/core_functions/aggregate/distributive/arg_min_max.cpp +283 -46
- package/src/duckdb/src/core_functions/aggregate/distributive/bitagg.cpp +4 -4
- package/src/duckdb/src/core_functions/aggregate/distributive/entropy.cpp +3 -2
- package/src/duckdb/src/core_functions/aggregate/distributive/minmax.cpp +226 -338
- package/src/duckdb/src/core_functions/aggregate/distributive/sum.cpp +2 -0
- package/src/duckdb/src/core_functions/aggregate/holistic/approx_top_k.cpp +388 -0
- package/src/duckdb/src/core_functions/aggregate/holistic/approximate_quantile.cpp +63 -21
- package/src/duckdb/src/core_functions/aggregate/holistic/mad.cpp +330 -0
- package/src/duckdb/src/core_functions/aggregate/holistic/mode.cpp +136 -97
- package/src/duckdb/src/core_functions/aggregate/holistic/quantile.cpp +601 -1485
- package/src/duckdb/src/core_functions/aggregate/nested/binned_histogram.cpp +405 -0
- package/src/duckdb/src/core_functions/aggregate/nested/histogram.cpp +136 -165
- package/src/duckdb/src/core_functions/function_list.cpp +35 -8
- package/src/duckdb/src/core_functions/lambda_functions.cpp +5 -7
- package/src/duckdb/src/core_functions/scalar/array/array_functions.cpp +172 -198
- package/src/duckdb/src/core_functions/scalar/blob/create_sort_key.cpp +341 -54
- package/src/duckdb/src/core_functions/scalar/date/date_diff.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/date/date_part.cpp +89 -29
- package/src/duckdb/src/core_functions/scalar/date/date_trunc.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/date/make_date.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/date/strftime.cpp +133 -71
- package/src/duckdb/src/core_functions/scalar/date/to_interval.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/enum/enum_functions.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/generic/can_implicitly_cast.cpp +40 -0
- package/src/duckdb/src/core_functions/scalar/generic/error.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/generic/least.cpp +161 -58
- package/src/duckdb/src/core_functions/scalar/generic/typeof.cpp +13 -0
- package/src/duckdb/src/core_functions/scalar/list/array_slice.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/list/list_aggregates.cpp +59 -75
- package/src/duckdb/src/core_functions/scalar/list/list_distance.cpp +93 -40
- package/src/duckdb/src/core_functions/scalar/list/list_has_any_or_all.cpp +227 -0
- package/src/duckdb/src/core_functions/scalar/list/list_reduce.cpp +20 -19
- package/src/duckdb/src/core_functions/scalar/list/list_sort.cpp +0 -2
- package/src/duckdb/src/core_functions/scalar/list/list_value.cpp +106 -8
- package/src/duckdb/src/core_functions/scalar/map/map_contains.cpp +56 -0
- package/src/duckdb/src/core_functions/scalar/map/map_extract.cpp +73 -118
- package/src/duckdb/src/core_functions/scalar/math/numeric.cpp +98 -2
- package/src/duckdb/src/core_functions/scalar/operators/bitwise.cpp +1 -2
- package/src/duckdb/src/core_functions/scalar/random/setseed.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/string/bar.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/string/hex.cpp +5 -1
- package/src/duckdb/src/core_functions/scalar/string/md5.cpp +10 -37
- package/src/duckdb/src/core_functions/scalar/string/printf.cpp +18 -2
- package/src/duckdb/src/core_functions/scalar/string/repeat.cpp +45 -0
- package/src/duckdb/src/core_functions/scalar/string/reverse.cpp +4 -5
- package/src/duckdb/src/core_functions/scalar/string/sha1.cpp +35 -0
- package/src/duckdb/src/core_functions/scalar/string/sha256.cpp +5 -2
- package/src/duckdb/src/core_functions/scalar/string/url_encode.cpp +49 -0
- package/src/duckdb/src/core_functions/scalar/struct/struct_pack.cpp +1 -2
- package/src/duckdb/src/core_functions/scalar/union/union_extract.cpp +4 -2
- package/src/duckdb/src/execution/adaptive_filter.cpp +30 -11
- package/src/duckdb/src/execution/aggregate_hashtable.cpp +13 -18
- package/src/duckdb/src/execution/expression_executor/execute_conjunction.cpp +4 -9
- package/src/duckdb/src/execution/expression_executor.cpp +1 -1
- package/src/duckdb/src/execution/index/art/art.cpp +683 -670
- package/src/duckdb/src/execution/index/art/art_key.cpp +121 -38
- package/src/duckdb/src/execution/index/art/base_leaf.cpp +168 -0
- package/src/duckdb/src/execution/index/art/base_node.cpp +163 -0
- package/src/duckdb/src/execution/index/art/iterator.cpp +148 -77
- package/src/duckdb/src/execution/index/art/leaf.cpp +159 -263
- package/src/duckdb/src/execution/index/art/node.cpp +493 -247
- package/src/duckdb/src/execution/index/art/node256.cpp +31 -91
- package/src/duckdb/src/execution/index/art/node256_leaf.cpp +71 -0
- package/src/duckdb/src/execution/index/art/node48.cpp +75 -143
- package/src/duckdb/src/execution/index/art/prefix.cpp +424 -244
- package/src/duckdb/src/execution/index/bound_index.cpp +7 -1
- package/src/duckdb/src/execution/index/fixed_size_allocator.cpp +22 -18
- package/src/duckdb/src/execution/index/fixed_size_buffer.cpp +22 -73
- package/src/duckdb/src/execution/join_hashtable.cpp +637 -179
- package/src/duckdb/src/execution/operator/aggregate/aggregate_object.cpp +4 -4
- package/src/duckdb/src/execution/operator/aggregate/physical_hash_aggregate.cpp +15 -10
- package/src/duckdb/src/execution/operator/aggregate/physical_perfecthash_aggregate.cpp +13 -8
- package/src/duckdb/src/execution/operator/aggregate/physical_streaming_window.cpp +525 -132
- package/src/duckdb/src/execution/operator/aggregate/physical_ungrouped_aggregate.cpp +147 -138
- package/src/duckdb/src/execution/operator/aggregate/physical_window.cpp +531 -312
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_buffer.cpp +1 -1
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_buffer_manager.cpp +4 -3
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_file_handle.cpp +9 -2
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/base_scanner.cpp +13 -17
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/column_count_scanner.cpp +60 -16
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/csv_schema.cpp +105 -0
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/scanner_boundary.cpp +24 -24
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/skip_scanner.cpp +25 -2
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/string_value_scanner.cpp +275 -112
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/csv_sniffer.cpp +106 -11
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp +253 -115
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp +93 -52
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp +116 -76
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_refinement.cpp +29 -14
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_replacement.cpp +1 -1
- package/src/duckdb/src/execution/operator/csv_scanner/state_machine/csv_state_machine_cache.cpp +70 -26
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/csv_file_scanner.cpp +81 -60
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/global_csv_state.cpp +88 -50
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_error.cpp +161 -51
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_reader_options.cpp +59 -17
- package/src/duckdb/src/execution/operator/filter/physical_filter.cpp +5 -5
- package/src/duckdb/src/execution/operator/helper/physical_batch_collector.cpp +0 -21
- package/src/duckdb/src/execution/operator/helper/physical_buffered_batch_collector.cpp +109 -0
- package/src/duckdb/src/execution/operator/helper/physical_buffered_collector.cpp +5 -13
- package/src/duckdb/src/execution/operator/helper/physical_explain_analyze.cpp +1 -1
- package/src/duckdb/src/execution/operator/helper/physical_load.cpp +12 -4
- package/src/duckdb/src/execution/operator/helper/physical_materialized_collector.cpp +0 -16
- package/src/duckdb/src/execution/operator/helper/physical_reservoir_sample.cpp +4 -2
- package/src/duckdb/src/execution/operator/helper/physical_reset.cpp +5 -0
- package/src/duckdb/src/execution/operator/helper/physical_result_collector.cpp +3 -1
- package/src/duckdb/src/execution/operator/helper/physical_set_variable.cpp +39 -0
- package/src/duckdb/src/execution/operator/helper/physical_streaming_sample.cpp +4 -2
- package/src/duckdb/src/execution/operator/helper/physical_transaction.cpp +16 -5
- package/src/duckdb/src/execution/operator/join/outer_join_marker.cpp +1 -1
- package/src/duckdb/src/execution/operator/join/perfect_hash_join_executor.cpp +1 -1
- package/src/duckdb/src/execution/operator/join/physical_asof_join.cpp +1 -1
- package/src/duckdb/src/execution/operator/join/physical_blockwise_nl_join.cpp +5 -4
- package/src/duckdb/src/execution/operator/join/physical_comparison_join.cpp +59 -21
- package/src/duckdb/src/execution/operator/join/physical_delim_join.cpp +7 -4
- package/src/duckdb/src/execution/operator/join/physical_hash_join.cpp +333 -176
- package/src/duckdb/src/execution/operator/join/physical_iejoin.cpp +57 -34
- package/src/duckdb/src/execution/operator/join/physical_join.cpp +16 -8
- package/src/duckdb/src/execution/operator/join/physical_left_delim_join.cpp +10 -4
- package/src/duckdb/src/execution/operator/join/physical_nested_loop_join.cpp +2 -5
- package/src/duckdb/src/execution/operator/join/physical_piecewise_merge_join.cpp +3 -3
- package/src/duckdb/src/execution/operator/join/physical_range_join.cpp +5 -5
- package/src/duckdb/src/execution/operator/join/physical_right_delim_join.cpp +7 -2
- package/src/duckdb/src/execution/operator/order/physical_order.cpp +17 -12
- package/src/duckdb/src/execution/operator/order/physical_top_n.cpp +12 -9
- package/src/duckdb/src/execution/operator/persistent/physical_batch_copy_to_file.cpp +35 -17
- package/src/duckdb/src/execution/operator/persistent/physical_batch_insert.cpp +17 -11
- package/src/duckdb/src/execution/operator/persistent/physical_copy_database.cpp +5 -1
- package/src/duckdb/src/execution/operator/persistent/physical_copy_to_file.cpp +156 -47
- package/src/duckdb/src/execution/operator/persistent/physical_insert.cpp +10 -2
- package/src/duckdb/src/execution/operator/persistent/physical_update.cpp +1 -3
- package/src/duckdb/src/execution/operator/projection/physical_pivot.cpp +2 -2
- package/src/duckdb/src/execution/operator/projection/physical_projection.cpp +13 -6
- package/src/duckdb/src/execution/operator/projection/physical_tableinout_function.cpp +22 -3
- package/src/duckdb/src/execution/operator/projection/physical_unnest.cpp +19 -3
- package/src/duckdb/src/execution/operator/scan/physical_column_data_scan.cpp +37 -22
- package/src/duckdb/src/execution/operator/scan/physical_table_scan.cpp +77 -21
- package/src/duckdb/src/execution/operator/schema/physical_attach.cpp +27 -55
- package/src/duckdb/src/execution/operator/schema/physical_create_art_index.cpp +41 -44
- package/src/duckdb/src/execution/operator/set/physical_cte.cpp +4 -6
- package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +4 -6
- package/src/duckdb/src/execution/operator/set/physical_union.cpp +18 -4
- package/src/duckdb/src/execution/perfect_aggregate_hashtable.cpp +3 -2
- package/src/duckdb/src/execution/physical_operator.cpp +45 -4
- package/src/duckdb/src/execution/physical_plan/plan_comparison_join.cpp +18 -7
- package/src/duckdb/src/execution/physical_plan/plan_copy_to_file.cpp +8 -3
- package/src/duckdb/src/execution/physical_plan/plan_delim_join.cpp +13 -6
- package/src/duckdb/src/execution/physical_plan/plan_explain.cpp +3 -3
- package/src/duckdb/src/execution/physical_plan/plan_get.cpp +111 -19
- package/src/duckdb/src/execution/physical_plan/plan_limit.cpp +19 -2
- package/src/duckdb/src/execution/physical_plan/plan_set.cpp +9 -0
- package/src/duckdb/src/execution/physical_plan/plan_window.cpp +3 -1
- package/src/duckdb/src/execution/physical_plan_generator.cpp +3 -3
- package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +49 -49
- package/src/duckdb/src/execution/reservoir_sample.cpp +2 -2
- package/src/duckdb/src/execution/window_executor.cpp +556 -318
- package/src/duckdb/src/execution/window_segment_tree.cpp +1058 -485
- package/src/duckdb/src/function/aggregate/distributive/count.cpp +5 -5
- package/src/duckdb/src/function/aggregate/distributive/first.cpp +92 -95
- package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp +10 -9
- package/src/duckdb/src/function/aggregate_function.cpp +8 -0
- package/src/duckdb/src/function/cast/cast_function_set.cpp +10 -1
- package/src/duckdb/src/function/cast/decimal_cast.cpp +10 -1
- package/src/duckdb/src/function/cast/default_casts.cpp +2 -0
- package/src/duckdb/src/function/cast/numeric_casts.cpp +3 -0
- package/src/duckdb/src/function/cast/string_cast.cpp +8 -5
- package/src/duckdb/src/function/cast/time_casts.cpp +2 -2
- package/src/duckdb/src/function/cast/union_casts.cpp +1 -1
- package/src/duckdb/src/function/cast/varint_casts.cpp +283 -0
- package/src/duckdb/src/function/cast/vector_cast_helpers.cpp +3 -1
- package/src/duckdb/src/function/cast_rules.cpp +104 -15
- package/src/duckdb/src/function/compression_config.cpp +35 -33
- package/src/duckdb/src/function/copy_function.cpp +27 -0
- package/src/duckdb/src/function/function_binder.cpp +39 -11
- package/src/duckdb/src/function/macro_function.cpp +75 -32
- package/src/duckdb/src/function/pragma/pragma_queries.cpp +10 -0
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_string.cpp +1 -0
- package/src/duckdb/src/function/scalar/generic/binning.cpp +507 -0
- package/src/duckdb/src/function/scalar/generic/getvariable.cpp +58 -0
- package/src/duckdb/src/function/scalar/generic_functions.cpp +1 -0
- package/src/duckdb/src/function/scalar/list/contains_or_position.cpp +33 -47
- package/src/duckdb/src/function/scalar/list/list_extract.cpp +70 -143
- package/src/duckdb/src/function/scalar/list/list_resize.cpp +93 -84
- package/src/duckdb/src/function/scalar/list/list_zip.cpp +3 -0
- package/src/duckdb/src/function/scalar/operators/arithmetic.cpp +24 -11
- package/src/duckdb/src/function/scalar/sequence/nextval.cpp +4 -4
- package/src/duckdb/src/function/scalar/strftime_format.cpp +196 -57
- package/src/duckdb/src/function/scalar/string/caseconvert.cpp +9 -7
- package/src/duckdb/src/function/scalar/string/concat.cpp +239 -123
- package/src/duckdb/src/function/scalar/string/concat_ws.cpp +149 -0
- package/src/duckdb/src/function/scalar/string/contains.cpp +18 -7
- package/src/duckdb/src/function/scalar/string/like.cpp +2 -2
- package/src/duckdb/src/function/scalar/string/substring.cpp +6 -11
- package/src/duckdb/src/function/scalar/string_functions.cpp +1 -0
- package/src/duckdb/src/function/scalar/struct/struct_extract.cpp +7 -3
- package/src/duckdb/src/function/scalar/system/aggregate_export.cpp +5 -5
- package/src/duckdb/src/function/scalar_function.cpp +5 -2
- package/src/duckdb/src/function/scalar_macro_function.cpp +2 -2
- package/src/duckdb/src/function/table/arrow/arrow_duck_schema.cpp +20 -39
- package/src/duckdb/src/function/table/arrow/arrow_type_info.cpp +135 -0
- package/src/duckdb/src/function/table/arrow.cpp +194 -52
- package/src/duckdb/src/function/table/arrow_conversion.cpp +212 -69
- package/src/duckdb/src/function/table/copy_csv.cpp +43 -14
- package/src/duckdb/src/function/table/query_function.cpp +80 -0
- package/src/duckdb/src/function/table/range.cpp +222 -142
- package/src/duckdb/src/function/table/read_csv.cpp +25 -13
- package/src/duckdb/src/function/table/sniff_csv.cpp +55 -35
- package/src/duckdb/src/function/table/system/duckdb_constraints.cpp +141 -129
- package/src/duckdb/src/function/table/system/duckdb_extensions.cpp +25 -14
- package/src/duckdb/src/function/table/system/duckdb_functions.cpp +20 -14
- package/src/duckdb/src/function/table/system/duckdb_indexes.cpp +15 -1
- package/src/duckdb/src/function/table/system/duckdb_variables.cpp +84 -0
- package/src/duckdb/src/function/table/system/test_all_types.cpp +1 -0
- package/src/duckdb/src/function/table/system/test_vector_types.cpp +33 -3
- package/src/duckdb/src/function/table/system_functions.cpp +1 -0
- package/src/duckdb/src/function/table/table_scan.cpp +45 -22
- package/src/duckdb/src/function/table/unnest.cpp +2 -2
- package/src/duckdb/src/function/table/version/pragma_version.cpp +4 -4
- package/src/duckdb/src/function/table_function.cpp +5 -4
- package/src/duckdb/src/function/table_macro_function.cpp +2 -2
- package/src/duckdb/src/include/duckdb/catalog/catalog.hpp +8 -4
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/duck_index_entry.hpp +5 -2
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/duck_schema_entry.hpp +3 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/index_catalog_entry.hpp +2 -2
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/macro_catalog_entry.hpp +3 -4
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/table_catalog_entry.hpp +5 -5
- package/src/duckdb/src/include/duckdb/catalog/default/builtin_types/types.hpp +2 -1
- package/src/duckdb/src/include/duckdb/catalog/default/default_functions.hpp +4 -5
- package/src/duckdb/src/include/duckdb/catalog/default/default_generator.hpp +4 -5
- package/src/duckdb/src/include/duckdb/catalog/default/default_schemas.hpp +2 -1
- package/src/duckdb/src/include/duckdb/catalog/default/default_table_functions.hpp +47 -0
- package/src/duckdb/src/include/duckdb/catalog/duck_catalog.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/similar_catalog_entry.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/allocator.hpp +9 -1
- package/src/duckdb/src/include/duckdb/common/array_ptr.hpp +120 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/append_data.hpp +37 -11
- package/src/duckdb/src/include/duckdb/common/arrow/appender/enum_data.hpp +9 -8
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list_data.hpp +6 -4
- package/src/duckdb/src/include/duckdb/common/arrow/appender/list_view_data.hpp +92 -0
- package/src/duckdb/src/include/duckdb/common/arrow/appender/map_data.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/arrow/appender/scalar_data.hpp +26 -4
- package/src/duckdb/src/include/duckdb/common/arrow/appender/varchar_data.hpp +90 -11
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_appender.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_buffer.hpp +8 -1
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_merge_event.hpp +62 -0
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_query_result.hpp +52 -0
- package/src/duckdb/src/include/duckdb/common/arrow/arrow_types_extension.hpp +42 -0
- package/src/duckdb/src/include/duckdb/common/arrow/physical_arrow_batch_collector.hpp +30 -0
- package/src/duckdb/src/include/duckdb/common/arrow/physical_arrow_collector.hpp +65 -0
- package/src/duckdb/src/include/duckdb/common/arrow/schema_metadata.hpp +43 -0
- package/src/duckdb/src/include/duckdb/common/bswap.hpp +18 -16
- package/src/duckdb/src/include/duckdb/common/cgroups.hpp +30 -0
- package/src/duckdb/src/include/duckdb/common/compressed_file_system.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/dl.hpp +8 -1
- package/src/duckdb/src/include/duckdb/common/encryption_state.hpp +48 -0
- package/src/duckdb/src/include/duckdb/common/enum_util.hpp +88 -0
- package/src/duckdb/src/include/duckdb/common/enums/checkpoint_type.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/enums/copy_overwrite_mode.hpp +6 -1
- package/src/duckdb/src/include/duckdb/common/enums/destroy_buffer_upon.hpp +21 -0
- package/src/duckdb/src/include/duckdb/common/enums/explain_format.hpp +17 -0
- package/src/duckdb/src/include/duckdb/common/enums/file_compression_type.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/enums/join_type.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/enums/metric_type.hpp +88 -0
- package/src/duckdb/src/include/duckdb/common/enums/optimizer_type.hpp +6 -1
- package/src/duckdb/src/include/duckdb/common/enums/pending_execution_result.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/physical_operator_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/enums/profiler_format.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/enums/relation_type.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/enums/set_scope.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/statement_type.hpp +23 -2
- package/src/duckdb/src/include/duckdb/common/enums/stream_execution_result.hpp +25 -0
- package/src/duckdb/src/include/duckdb/common/enums/tableref_type.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/enums/wal_type.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/error_data.hpp +5 -2
- package/src/duckdb/src/include/duckdb/common/exception/binder_exception.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/exception.hpp +20 -2
- package/src/duckdb/src/include/duckdb/common/extra_operator_info.hpp +12 -0
- package/src/duckdb/src/include/duckdb/common/file_buffer.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/file_open_flags.hpp +16 -0
- package/src/duckdb/src/include/duckdb/common/file_opener.hpp +18 -0
- package/src/duckdb/src/include/duckdb/common/file_system.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/filename_pattern.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/fixed_size_map.hpp +160 -96
- package/src/duckdb/src/include/duckdb/common/fsst.hpp +9 -2
- package/src/duckdb/src/include/duckdb/common/helper.hpp +22 -8
- package/src/duckdb/src/include/duckdb/common/hive_partitioning.hpp +16 -7
- package/src/duckdb/src/include/duckdb/common/http_util.hpp +19 -0
- package/src/duckdb/src/include/duckdb/common/insertion_order_preserving_map.hpp +19 -6
- package/src/duckdb/src/include/duckdb/common/limits.hpp +9 -2
- package/src/duckdb/src/include/duckdb/common/multi_file_list.hpp +38 -6
- package/src/duckdb/src/include/duckdb/common/multi_file_reader.hpp +9 -2
- package/src/duckdb/src/include/duckdb/common/multi_file_reader_options.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/numeric_utils.hpp +82 -50
- package/src/duckdb/src/include/duckdb/common/operator/abs.hpp +11 -0
- package/src/duckdb/src/include/duckdb/common/operator/cast_operators.hpp +7 -3
- package/src/duckdb/src/include/duckdb/common/operator/decimal_cast_operators.hpp +23 -1
- package/src/duckdb/src/include/duckdb/common/operator/double_cast_operator.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/operator/integer_cast_operator.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/operator/numeric_cast.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/operator/string_cast.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/optional_ptr.hpp +10 -5
- package/src/duckdb/src/include/duckdb/common/optionally_owned_ptr.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/owning_string_map.hpp +155 -0
- package/src/duckdb/src/include/duckdb/common/perfect_map_set.hpp +2 -3
- package/src/duckdb/src/include/duckdb/common/platform.hpp +58 -0
- package/src/duckdb/src/include/duckdb/common/radix.hpp +172 -27
- package/src/duckdb/src/include/duckdb/common/radix_partitioning.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/random_engine.hpp +1 -0
- package/src/duckdb/src/include/duckdb/common/re2_regex.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/render_tree.hpp +77 -0
- package/src/duckdb/src/include/duckdb/common/row_operations/row_matcher.hpp +12 -0
- package/src/duckdb/src/include/duckdb/common/serializer/binary_serializer.hpp +6 -2
- package/src/duckdb/src/include/duckdb/common/serializer/buffered_file_writer.hpp +5 -3
- package/src/duckdb/src/include/duckdb/common/serializer/deserializer.hpp +15 -7
- package/src/duckdb/src/include/duckdb/common/serializer/memory_stream.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/serializer/serialization_data.hpp +245 -0
- package/src/duckdb/src/include/duckdb/common/serializer/serializer.hpp +10 -0
- package/src/duckdb/src/include/duckdb/common/sort/duckdb_pdqsort.hpp +10 -11
- package/src/duckdb/src/include/duckdb/common/sort/partition_state.hpp +12 -6
- package/src/duckdb/src/include/duckdb/common/string_util.hpp +37 -7
- package/src/duckdb/src/include/duckdb/common/tree_renderer/graphviz_tree_renderer.hpp +44 -0
- package/src/duckdb/src/include/duckdb/common/tree_renderer/html_tree_renderer.hpp +44 -0
- package/src/duckdb/src/include/duckdb/common/tree_renderer/json_tree_renderer.hpp +44 -0
- package/src/duckdb/src/include/duckdb/common/tree_renderer/text_tree_renderer.hpp +119 -0
- package/src/duckdb/src/include/duckdb/common/tree_renderer.hpp +9 -123
- package/src/duckdb/src/include/duckdb/common/type_visitor.hpp +96 -0
- package/src/duckdb/src/include/duckdb/common/typedefs.hpp +11 -1
- package/src/duckdb/src/include/duckdb/common/types/arrow_string_view_type.hpp +84 -0
- package/src/duckdb/src/include/duckdb/common/types/batched_data_collection.hpp +36 -1
- package/src/duckdb/src/include/duckdb/common/types/bit.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/cast_helpers.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_allocator.hpp +4 -2
- package/src/duckdb/src/include/duckdb/common/types/column/partitioned_column_data.hpp +52 -0
- package/src/duckdb/src/include/duckdb/common/types/data_chunk.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/types/date.hpp +0 -3
- package/src/duckdb/src/include/duckdb/common/types/date_lookup_cache.hpp +65 -0
- package/src/duckdb/src/include/duckdb/common/types/datetime.hpp +5 -2
- package/src/duckdb/src/include/duckdb/common/types/hyperloglog.hpp +49 -40
- package/src/duckdb/src/include/duckdb/common/types/interval.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/types/list_segment.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +41 -9
- package/src/duckdb/src/include/duckdb/common/types/row/row_data_collection.hpp +4 -3
- package/src/duckdb/src/include/duckdb/common/types/row/row_data_collection_scanner.hpp +3 -1
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_allocator.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_collection.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/selection_vector.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/types/string_type.hpp +4 -1
- package/src/duckdb/src/include/duckdb/common/types/time.hpp +11 -6
- package/src/duckdb/src/include/duckdb/common/types/timestamp.hpp +13 -3
- package/src/duckdb/src/include/duckdb/common/types/validity_mask.hpp +103 -12
- package/src/duckdb/src/include/duckdb/common/types/value.hpp +12 -3
- package/src/duckdb/src/include/duckdb/common/types/varint.hpp +107 -0
- package/src/duckdb/src/include/duckdb/common/types/vector.hpp +5 -1
- package/src/duckdb/src/include/duckdb/common/types/vector_buffer.hpp +7 -2
- package/src/duckdb/src/include/duckdb/common/types.hpp +6 -39
- package/src/duckdb/src/include/duckdb/common/union_by_name.hpp +42 -10
- package/src/duckdb/src/include/duckdb/common/vector_operations/generic_executor.hpp +29 -0
- package/src/duckdb/src/include/duckdb/common/vector_operations/unary_executor.hpp +0 -7
- package/src/duckdb/src/include/duckdb/common/vector_operations/vector_operations.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/winapi.hpp +8 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/algebraic/covar.hpp +8 -4
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/algebraic/stddev.hpp +8 -4
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/distributive_functions.hpp +4 -2
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/histogram_helpers.hpp +99 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/holistic_functions.hpp +16 -7
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/minmax_n_helpers.hpp +396 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/nested_functions.hpp +10 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/quantile_helpers.hpp +65 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/quantile_sort_tree.hpp +349 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/quantile_state.hpp +300 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/regression/regr_slope.hpp +1 -1
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/sort_key_helpers.hpp +55 -0
- package/src/duckdb/src/include/duckdb/core_functions/array_kernels.hpp +107 -0
- package/src/duckdb/src/include/duckdb/core_functions/create_sort_key.hpp +55 -0
- package/src/duckdb/src/include/duckdb/core_functions/lambda_functions.hpp +1 -2
- package/src/duckdb/src/include/duckdb/core_functions/scalar/array_functions.hpp +24 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/date_functions.hpp +9 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/generic_functions.hpp +27 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/list_functions.hpp +80 -8
- package/src/duckdb/src/include/duckdb/core_functions/scalar/map_functions.hpp +9 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/math_functions.hpp +54 -0
- package/src/duckdb/src/include/duckdb/core_functions/scalar/string_functions.hpp +30 -21
- package/src/duckdb/src/include/duckdb/execution/adaptive_filter.hpp +25 -14
- package/src/duckdb/src/include/duckdb/execution/aggregate_hashtable.hpp +2 -48
- package/src/duckdb/src/include/duckdb/execution/executor.hpp +25 -2
- package/src/duckdb/src/include/duckdb/execution/ht_entry.hpp +102 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/art.hpp +94 -101
- package/src/duckdb/src/include/duckdb/execution/index/art/art_key.hpp +43 -25
- package/src/duckdb/src/include/duckdb/execution/index/art/base_leaf.hpp +109 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/base_node.hpp +140 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/iterator.hpp +43 -24
- package/src/duckdb/src/include/duckdb/execution/index/art/leaf.hpp +41 -52
- package/src/duckdb/src/include/duckdb/execution/index/art/node.hpp +133 -74
- package/src/duckdb/src/include/duckdb/execution/index/art/node256.hpp +46 -29
- package/src/duckdb/src/include/duckdb/execution/index/art/node256_leaf.hpp +53 -0
- package/src/duckdb/src/include/duckdb/execution/index/art/node48.hpp +52 -35
- package/src/duckdb/src/include/duckdb/execution/index/art/prefix.hpp +96 -57
- package/src/duckdb/src/include/duckdb/execution/index/bound_index.hpp +9 -4
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_allocator.hpp +48 -10
- package/src/duckdb/src/include/duckdb/execution/index/fixed_size_buffer.hpp +0 -2
- package/src/duckdb/src/include/duckdb/execution/index/index_pointer.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/join_hashtable.hpp +114 -36
- package/src/duckdb/src/include/duckdb/execution/merge_sort_tree.hpp +158 -67
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/aggregate_object.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_hash_aggregate.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_perfecthash_aggregate.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_streaming_window.hpp +19 -2
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_ungrouped_aggregate.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_window.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/ungrouped_aggregate_state.hpp +75 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/base_scanner.hpp +81 -23
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/column_count_scanner.hpp +27 -8
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_buffer_manager.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_error.hpp +31 -22
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_file_handle.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_file_scanner.hpp +48 -5
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_option.hpp +7 -3
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_reader_options.hpp +22 -12
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_schema.hpp +35 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_sniffer.hpp +81 -39
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state_machine.hpp +18 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state_machine_cache.hpp +9 -7
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/global_csv_state.hpp +5 -4
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/header_value.hpp +26 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner_boundary.hpp +6 -9
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/skip_scanner.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/state_machine_options.hpp +5 -3
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/string_value_scanner.hpp +36 -19
- package/src/duckdb/src/include/duckdb/execution/operator/filter/physical_filter.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_batch_collector.hpp +21 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_buffered_batch_collector.hpp +53 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_buffered_collector.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_explain_analyze.hpp +6 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_materialized_collector.hpp +18 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_reservoir_sample.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_result_collector.hpp +6 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_set.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_set_variable.hpp +43 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_streaming_sample.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/join_filter_pushdown.hpp +59 -0
- 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_comparison_join.hpp +8 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_delim_join.hpp +5 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_hash_join.hpp +4 -2
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_iejoin.hpp +2 -0
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_join.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_left_delim_join.hpp +3 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_range_join.hpp +4 -1
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_right_delim_join.hpp +3 -1
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_order.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/order/physical_top_n.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/batch_memory_manager.hpp +5 -37
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_batch_copy_to_file.hpp +5 -4
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_to_file.hpp +8 -2
- package/src/duckdb/src/include/duckdb/execution/operator/projection/physical_projection.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/projection/physical_tableinout_function.hpp +2 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_column_data_scan.hpp +9 -3
- package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_table_scan.hpp +8 -6
- package/src/duckdb/src/include/duckdb/execution/operator/schema/physical_create_art_index.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_cte.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/set/physical_recursive_cte.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/physical_operator.hpp +21 -6
- package/src/duckdb/src/include/duckdb/execution/physical_operator_states.hpp +3 -2
- package/src/duckdb/src/include/duckdb/execution/physical_plan_generator.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/window_executor.hpp +137 -110
- package/src/duckdb/src/include/duckdb/execution/window_segment_tree.hpp +57 -126
- package/src/duckdb/src/include/duckdb/function/aggregate_function.hpp +21 -4
- package/src/duckdb/src/include/duckdb/function/cast/default_casts.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/compression/compression.hpp +10 -10
- package/src/duckdb/src/include/duckdb/function/compression_function.hpp +37 -7
- package/src/duckdb/src/include/duckdb/function/copy_function.hpp +24 -11
- package/src/duckdb/src/include/duckdb/function/function_binder.hpp +4 -4
- package/src/duckdb/src/include/duckdb/function/function_serialization.hpp +41 -1
- package/src/duckdb/src/include/duckdb/function/macro_function.hpp +15 -5
- package/src/duckdb/src/include/duckdb/function/pragma/pragma_functions.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/replacement_scan.hpp +20 -4
- package/src/duckdb/src/include/duckdb/function/scalar/generic_functions.hpp +6 -0
- package/src/duckdb/src/include/duckdb/function/scalar/list/contains_or_position.hpp +77 -109
- package/src/duckdb/src/include/duckdb/function/scalar/nested_functions.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/scalar/regexp.hpp +6 -3
- package/src/duckdb/src/include/duckdb/function/scalar/strftime_format.hpp +25 -12
- package/src/duckdb/src/include/duckdb/function/scalar/string_functions.hpp +9 -8
- package/src/duckdb/src/include/duckdb/function/scalar_function.hpp +38 -4
- package/src/duckdb/src/include/duckdb/function/scalar_macro_function.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/table/arrow/arrow_duck_schema.hpp +11 -57
- package/src/duckdb/src/include/duckdb/function/table/arrow/arrow_type_info.hpp +142 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow/enum/arrow_datetime_type.hpp +18 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow/enum/arrow_type_info_type.hpp +7 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow/enum/arrow_variable_size_type.hpp +10 -0
- package/src/duckdb/src/include/duckdb/function/table/arrow.hpp +2 -0
- package/src/duckdb/src/include/duckdb/function/table/range.hpp +4 -0
- package/src/duckdb/src/include/duckdb/function/table/read_csv.hpp +4 -1
- package/src/duckdb/src/include/duckdb/function/table/system_functions.hpp +4 -0
- package/src/duckdb/src/include/duckdb/function/table/table_scan.hpp +5 -5
- package/src/duckdb/src/include/duckdb/function/table_function.hpp +14 -2
- package/src/duckdb/src/include/duckdb/function/table_macro_function.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/appender.hpp +14 -4
- package/src/duckdb/src/include/duckdb/main/attached_database.hpp +25 -7
- package/src/duckdb/src/include/duckdb/main/buffered_data/batched_buffered_data.hpp +79 -0
- package/src/duckdb/src/include/duckdb/main/buffered_data/buffered_data.hpp +10 -20
- package/src/duckdb/src/include/duckdb/main/buffered_data/simple_buffered_data.hpp +11 -12
- package/src/duckdb/src/include/duckdb/main/capi/capi_internal.hpp +7 -2
- package/src/duckdb/src/include/duckdb/main/capi/cast/generic.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/capi/cast/utils.hpp +2 -2
- package/src/duckdb/src/include/duckdb/main/capi/extension_api.hpp +809 -0
- package/src/duckdb/src/include/duckdb/main/chunk_scan_state/batched_data_collection.hpp +35 -0
- package/src/duckdb/src/include/duckdb/main/client_config.hpp +68 -2
- package/src/duckdb/src/include/duckdb/main/client_context.hpp +30 -22
- package/src/duckdb/src/include/duckdb/main/client_context_state.hpp +79 -1
- package/src/duckdb/src/include/duckdb/main/client_properties.hpp +9 -3
- package/src/duckdb/src/include/duckdb/main/config.hpp +55 -7
- package/src/duckdb/src/include/duckdb/main/connection.hpp +5 -1
- package/src/duckdb/src/include/duckdb/main/database.hpp +16 -5
- package/src/duckdb/src/include/duckdb/main/database_manager.hpp +9 -8
- package/src/duckdb/src/include/duckdb/main/db_instance_cache.hpp +21 -6
- package/src/duckdb/src/include/duckdb/main/extension.hpp +20 -0
- package/src/duckdb/src/include/duckdb/main/extension_entries.hpp +25 -0
- package/src/duckdb/src/include/duckdb/main/extension_helper.hpp +29 -23
- package/src/duckdb/src/include/duckdb/main/extension_install_info.hpp +6 -0
- package/src/duckdb/src/include/duckdb/main/extension_util.hpp +3 -0
- package/src/duckdb/src/include/duckdb/main/pending_query_result.hpp +4 -2
- package/src/duckdb/src/include/duckdb/main/prepared_statement.hpp +5 -6
- package/src/duckdb/src/include/duckdb/main/prepared_statement_data.hpp +2 -5
- package/src/duckdb/src/include/duckdb/main/profiling_info.hpp +87 -0
- package/src/duckdb/src/include/duckdb/main/profiling_node.hpp +60 -0
- package/src/duckdb/src/include/duckdb/main/query_profiler.hpp +72 -34
- package/src/duckdb/src/include/duckdb/main/query_result.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/relation/create_table_relation.hpp +2 -1
- package/src/duckdb/src/include/duckdb/main/relation/delim_get_relation.hpp +30 -0
- package/src/duckdb/src/include/duckdb/main/relation/explain_relation.hpp +3 -1
- package/src/duckdb/src/include/duckdb/main/relation/join_relation.hpp +3 -0
- package/src/duckdb/src/include/duckdb/main/relation/materialized_relation.hpp +1 -4
- package/src/duckdb/src/include/duckdb/main/relation/query_relation.hpp +4 -1
- package/src/duckdb/src/include/duckdb/main/relation/read_json_relation.hpp +6 -0
- package/src/duckdb/src/include/duckdb/main/relation/table_function_relation.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/relation/view_relation.hpp +2 -0
- package/src/duckdb/src/include/duckdb/main/relation.hpp +7 -4
- package/src/duckdb/src/include/duckdb/main/secret/default_secrets.hpp +36 -0
- package/src/duckdb/src/include/duckdb/main/secret/secret.hpp +108 -0
- package/src/duckdb/src/include/duckdb/main/secret/secret_manager.hpp +14 -4
- package/src/duckdb/src/include/duckdb/main/settings.hpp +227 -3
- package/src/duckdb/src/include/duckdb/main/stream_query_result.hpp +8 -0
- package/src/duckdb/src/include/duckdb/optimizer/build_probe_side_optimizer.hpp +51 -0
- package/src/duckdb/src/include/duckdb/optimizer/compressed_materialization.hpp +7 -0
- package/src/duckdb/src/include/duckdb/optimizer/cte_filter_pusher.hpp +46 -0
- package/src/duckdb/src/include/duckdb/optimizer/filter_combiner.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/filter_pushdown.hpp +7 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_filter_pushdown_optimizer.hpp +31 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/cardinality_estimator.hpp +51 -10
- package/src/duckdb/src/include/duckdb/optimizer/join_order/cost_model.hpp +1 -0
- package/src/duckdb/src/include/duckdb/optimizer/join_order/join_order_optimizer.hpp +17 -5
- package/src/duckdb/src/include/duckdb/optimizer/join_order/query_graph.hpp +1 -1
- package/src/duckdb/src/include/duckdb/optimizer/join_order/query_graph_manager.hpp +15 -13
- package/src/duckdb/src/include/duckdb/optimizer/join_order/relation_manager.hpp +9 -4
- package/src/duckdb/src/include/duckdb/optimizer/limit_pushdown.hpp +25 -0
- package/src/duckdb/src/include/duckdb/optimizer/optimizer.hpp +1 -0
- package/src/duckdb/src/include/duckdb/optimizer/rule/join_dependent_filter.hpp +37 -0
- package/src/duckdb/src/include/duckdb/parallel/executor_task.hpp +6 -1
- package/src/duckdb/src/include/duckdb/parallel/interrupt.hpp +54 -2
- package/src/duckdb/src/include/duckdb/parallel/meta_pipeline.hpp +27 -8
- package/src/duckdb/src/include/duckdb/parallel/pipeline.hpp +1 -0
- package/src/duckdb/src/include/duckdb/parallel/pipeline_prepare_finish_event.hpp +25 -0
- package/src/duckdb/src/include/duckdb/parallel/task_executor.hpp +63 -0
- package/src/duckdb/src/include/duckdb/parallel/task_scheduler.hpp +10 -1
- package/src/duckdb/src/include/duckdb/parser/expression/function_expression.hpp +4 -1
- package/src/duckdb/src/include/duckdb/parser/expression/star_expression.hpp +5 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_table_info.hpp +5 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/attach_info.hpp +5 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_index_info.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_macro_info.hpp +11 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/transaction_info.hpp +9 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_expression_iterator.hpp +13 -6
- package/src/duckdb/src/include/duckdb/parser/parser_extension.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parser/sql_statement.hpp +1 -3
- package/src/duckdb/src/include/duckdb/parser/statement/copy_statement.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/statement/explain_statement.hpp +5 -1
- package/src/duckdb/src/include/duckdb/parser/statement/set_statement.hpp +2 -2
- package/src/duckdb/src/include/duckdb/parser/statement/transaction_statement.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parser/tableref/basetableref.hpp +0 -2
- package/src/duckdb/src/include/duckdb/parser/tableref/column_data_ref.hpp +9 -7
- package/src/duckdb/src/include/duckdb/parser/tableref/delimgetref.hpp +37 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/joinref.hpp +4 -0
- package/src/duckdb/src/include/duckdb/parser/tableref/pivotref.hpp +0 -2
- package/src/duckdb/src/include/duckdb/parser/tableref/subqueryref.hpp +0 -2
- package/src/duckdb/src/include/duckdb/parser/tableref/table_function_ref.hpp +0 -1
- package/src/duckdb/src/include/duckdb/parser/tableref.hpp +3 -1
- package/src/duckdb/src/include/duckdb/parser/transformer.hpp +17 -9
- package/src/duckdb/src/include/duckdb/planner/binder.hpp +24 -14
- package/src/duckdb/src/include/duckdb/planner/collation_binding.hpp +44 -0
- package/src/duckdb/src/include/duckdb/planner/expression/bound_aggregate_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_between_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_case_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_cast_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_columnref_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_comparison_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_conjunction_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_constant_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_default_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_expanded_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_function_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_lambda_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_lambdaref_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_operator_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_parameter_data.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/expression/bound_parameter_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_reference_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_subquery_expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression/bound_unnest_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression/bound_window_expression.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/expression.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression_binder/column_alias_binder.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/expression_binder/group_binder.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/expression_binder/order_binder.hpp +6 -5
- package/src/duckdb/src/include/duckdb/planner/expression_binder/where_binder.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/expression_binder.hpp +19 -11
- package/src/duckdb/src/include/duckdb/planner/filter/conjunction_filter.hpp +4 -0
- package/src/duckdb/src/include/duckdb/planner/filter/constant_filter.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/filter/null_filter.hpp +4 -0
- package/src/duckdb/src/include/duckdb/planner/filter/struct_filter.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/logical_operator.hpp +7 -2
- package/src/duckdb/src/include/duckdb/planner/logical_operator_visitor.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_aggregate.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_any_join.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_comparison_join.hpp +6 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_copy_to_file.hpp +10 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_cteref.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_delim_get.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_distinct.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_execute.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_explain.hpp +4 -2
- package/src/duckdb/src/include/duckdb/planner/operator/logical_get.hpp +15 -5
- package/src/duckdb/src/include/duckdb/planner/operator/logical_materialized_cte.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/operator/logical_order.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/subquery/flatten_dependent_join.hpp +2 -1
- package/src/duckdb/src/include/duckdb/planner/table_filter.hpp +24 -2
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_delimgetref.hpp +26 -0
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_joinref.hpp +6 -0
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_subqueryref.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/tableref/bound_table_function.hpp +2 -0
- package/src/duckdb/src/include/duckdb/planner/tableref/list.hpp +2 -0
- package/src/duckdb/src/include/duckdb/storage/arena_allocator.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/block.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/block_manager.hpp +48 -3
- package/src/duckdb/src/include/duckdb/storage/buffer/block_handle.hpp +21 -7
- package/src/duckdb/src/include/duckdb/storage/buffer/buffer_pool.hpp +65 -51
- package/src/duckdb/src/include/duckdb/storage/buffer_manager.hpp +14 -5
- package/src/duckdb/src/include/duckdb/storage/checkpoint/row_group_writer.hpp +0 -4
- package/src/duckdb/src/include/duckdb/storage/checkpoint/string_checkpoint_state.hpp +3 -2
- package/src/duckdb/src/include/duckdb/storage/checkpoint/table_data_writer.hpp +1 -0
- package/src/duckdb/src/include/duckdb/storage/checkpoint/write_overflow_strings_to_disk.hpp +3 -4
- package/src/duckdb/src/include/duckdb/storage/checkpoint_manager.hpp +2 -0
- package/src/duckdb/src/include/duckdb/storage/compression/alp/algorithm/alp.hpp +4 -4
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_analyze.hpp +6 -4
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_compress.hpp +19 -17
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_constants.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_scan.hpp +3 -4
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_utils.hpp +3 -2
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/algorithm/alprd.hpp +3 -2
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_analyze.hpp +13 -11
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_compress.hpp +19 -19
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_scan.hpp +3 -4
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/chimp_scan.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/patas/patas_scan.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/data_pointer.hpp +10 -2
- package/src/duckdb/src/include/duckdb/storage/data_table.hpp +3 -2
- package/src/duckdb/src/include/duckdb/storage/in_memory_block_manager.hpp +15 -0
- package/src/duckdb/src/include/duckdb/storage/index_storage_info.hpp +14 -10
- package/src/duckdb/src/include/duckdb/storage/metadata/metadata_manager.hpp +6 -8
- package/src/duckdb/src/include/duckdb/storage/partial_block_manager.hpp +7 -4
- package/src/duckdb/src/include/duckdb/storage/segment/uncompressed.hpp +4 -7
- package/src/duckdb/src/include/duckdb/storage/single_file_block_manager.hpp +29 -4
- package/src/duckdb/src/include/duckdb/storage/standard_buffer_manager.hpp +22 -7
- package/src/duckdb/src/include/duckdb/storage/statistics/base_statistics.hpp +15 -2
- package/src/duckdb/src/include/duckdb/storage/statistics/distinct_statistics.hpp +8 -2
- package/src/duckdb/src/include/duckdb/storage/statistics/numeric_stats.hpp +5 -16
- package/src/duckdb/src/include/duckdb/storage/statistics/numeric_stats_union.hpp +51 -13
- package/src/duckdb/src/include/duckdb/storage/statistics/string_stats.hpp +6 -3
- package/src/duckdb/src/include/duckdb/storage/storage_info.hpp +29 -19
- package/src/duckdb/src/include/duckdb/storage/storage_manager.hpp +23 -7
- package/src/duckdb/src/include/duckdb/storage/string_uncompressed.hpp +27 -18
- package/src/duckdb/src/include/duckdb/storage/table/append_state.hpp +6 -3
- package/src/duckdb/src/include/duckdb/storage/table/array_column_data.hpp +5 -2
- package/src/duckdb/src/include/duckdb/storage/table/chunk_info.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/table/column_checkpoint_state.hpp +5 -1
- package/src/duckdb/src/include/duckdb/storage/table/column_data.hpp +77 -6
- package/src/duckdb/src/include/duckdb/storage/table/column_segment.hpp +23 -11
- package/src/duckdb/src/include/duckdb/storage/table/data_table_info.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/table/list_column_data.hpp +5 -2
- package/src/duckdb/src/include/duckdb/storage/table/row_group.hpp +18 -4
- package/src/duckdb/src/include/duckdb/storage/table/row_group_collection.hpp +7 -1
- package/src/duckdb/src/include/duckdb/storage/table/row_version_manager.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/table/scan_state.hpp +89 -14
- package/src/duckdb/src/include/duckdb/storage/table/standard_column_data.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/table/struct_column_data.hpp +4 -2
- package/src/duckdb/src/include/duckdb/storage/table/table_index_list.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/table/validity_column_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/temporary_memory_manager.hpp +33 -15
- package/src/duckdb/src/include/duckdb/storage/write_ahead_log.hpp +9 -9
- package/src/duckdb/src/include/duckdb/transaction/cleanup_state.hpp +3 -1
- package/src/duckdb/src/include/duckdb/transaction/commit_state.hpp +4 -16
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction.hpp +27 -4
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction_manager.hpp +11 -0
- package/src/duckdb/src/include/duckdb/transaction/local_storage.hpp +6 -2
- package/src/duckdb/src/include/duckdb/transaction/meta_transaction.hpp +5 -5
- package/src/duckdb/src/include/duckdb/transaction/transaction_context.hpp +6 -2
- package/src/duckdb/src/include/duckdb/transaction/undo_buffer.hpp +5 -3
- package/src/duckdb/src/include/duckdb/transaction/wal_write_state.hpp +48 -0
- package/src/duckdb/src/include/duckdb.h +1779 -739
- package/src/duckdb/src/include/duckdb_extension.h +921 -0
- package/src/duckdb/src/main/appender.cpp +53 -7
- package/src/duckdb/src/main/attached_database.cpp +87 -17
- package/src/duckdb/src/main/buffered_data/batched_buffered_data.cpp +226 -0
- package/src/duckdb/src/main/buffered_data/buffered_data.cpp +35 -0
- package/src/duckdb/src/main/buffered_data/simple_buffered_data.cpp +48 -23
- package/src/duckdb/src/main/capi/aggregate_function-c.cpp +327 -0
- package/src/duckdb/src/main/capi/appender-c.cpp +18 -0
- package/src/duckdb/src/main/capi/cast/utils-c.cpp +2 -2
- package/src/duckdb/src/main/capi/cast_function-c.cpp +210 -0
- package/src/duckdb/src/main/capi/config-c.cpp +3 -3
- package/src/duckdb/src/main/capi/data_chunk-c.cpp +18 -7
- package/src/duckdb/src/main/capi/duckdb_value-c.cpp +223 -24
- package/src/duckdb/src/main/capi/helper-c.cpp +51 -11
- package/src/duckdb/src/main/capi/logical_types-c.cpp +105 -46
- package/src/duckdb/src/main/capi/pending-c.cpp +7 -6
- package/src/duckdb/src/main/capi/prepared-c.cpp +18 -7
- package/src/duckdb/src/main/capi/profiling_info-c.cpp +84 -0
- package/src/duckdb/src/main/capi/result-c.cpp +139 -37
- package/src/duckdb/src/main/capi/scalar_function-c.cpp +269 -0
- package/src/duckdb/src/main/capi/table_description-c.cpp +82 -0
- package/src/duckdb/src/main/capi/table_function-c.cpp +161 -95
- package/src/duckdb/src/main/capi/value-c.cpp +2 -2
- package/src/duckdb/src/main/chunk_scan_state/batched_data_collection.cpp +57 -0
- package/src/duckdb/src/main/client_config.cpp +17 -0
- package/src/duckdb/src/main/client_context.cpp +67 -52
- package/src/duckdb/src/main/client_data.cpp +3 -3
- package/src/duckdb/src/main/config.cpp +120 -62
- package/src/duckdb/src/main/connection.cpp +14 -2
- package/src/duckdb/src/main/database.cpp +96 -35
- package/src/duckdb/src/main/database_manager.cpp +25 -23
- package/src/duckdb/src/main/database_path_and_type.cpp +2 -2
- package/src/duckdb/src/main/db_instance_cache.cpp +54 -19
- package/src/duckdb/src/main/extension/extension_helper.cpp +47 -42
- package/src/duckdb/src/main/extension/extension_install.cpp +155 -87
- package/src/duckdb/src/main/extension/extension_load.cpp +180 -26
- package/src/duckdb/src/main/extension/extension_util.cpp +8 -0
- package/src/duckdb/src/main/extension.cpp +72 -5
- package/src/duckdb/src/main/pending_query_result.cpp +20 -12
- package/src/duckdb/src/main/prepared_statement.cpp +6 -6
- package/src/duckdb/src/main/prepared_statement_data.cpp +28 -17
- package/src/duckdb/src/main/profiling_info.cpp +196 -0
- package/src/duckdb/src/main/query_profiler.cpp +413 -224
- package/src/duckdb/src/main/query_result.cpp +1 -1
- package/src/duckdb/src/main/relation/create_table_relation.cpp +4 -2
- package/src/duckdb/src/main/relation/create_view_relation.cpp +0 -6
- package/src/duckdb/src/main/relation/delim_get_relation.cpp +44 -0
- package/src/duckdb/src/main/relation/explain_relation.cpp +4 -3
- package/src/duckdb/src/main/relation/join_relation.cpp +5 -0
- package/src/duckdb/src/main/relation/limit_relation.cpp +1 -1
- package/src/duckdb/src/main/relation/materialized_relation.cpp +3 -3
- package/src/duckdb/src/main/relation/query_relation.cpp +42 -15
- package/src/duckdb/src/main/relation/read_csv_relation.cpp +7 -14
- package/src/duckdb/src/main/relation/read_json_relation.cpp +20 -0
- package/src/duckdb/src/main/relation/setop_relation.cpp +1 -1
- package/src/duckdb/src/main/relation/table_function_relation.cpp +6 -0
- package/src/duckdb/src/main/relation/view_relation.cpp +10 -0
- package/src/duckdb/src/main/relation.cpp +12 -8
- package/src/duckdb/src/main/secret/default_secrets.cpp +108 -0
- package/src/duckdb/src/main/secret/secret.cpp +145 -2
- package/src/duckdb/src/main/secret/secret_manager.cpp +85 -35
- package/src/duckdb/src/main/secret/secret_storage.cpp +29 -17
- package/src/duckdb/src/main/settings/settings.cpp +503 -11
- package/src/duckdb/src/main/stream_query_result.cpp +75 -2
- package/src/duckdb/src/optimizer/build_probe_side_optimizer.cpp +248 -0
- package/src/duckdb/src/optimizer/column_lifetime_analyzer.cpp +28 -6
- package/src/duckdb/src/optimizer/compressed_materialization/compress_comparison_join.cpp +152 -0
- package/src/duckdb/src/optimizer/compressed_materialization.cpp +11 -1
- package/src/duckdb/src/optimizer/cse_optimizer.cpp +3 -0
- package/src/duckdb/src/optimizer/cte_filter_pusher.cpp +117 -0
- package/src/duckdb/src/optimizer/filter_combiner.cpp +30 -9
- package/src/duckdb/src/optimizer/filter_pullup.cpp +54 -2
- package/src/duckdb/src/optimizer/filter_pushdown.cpp +71 -3
- package/src/duckdb/src/optimizer/join_filter_pushdown_optimizer.cpp +154 -0
- package/src/duckdb/src/optimizer/join_order/cardinality_estimator.cpp +245 -114
- package/src/duckdb/src/optimizer/join_order/join_order_optimizer.cpp +42 -20
- package/src/duckdb/src/optimizer/join_order/join_relation_set.cpp +6 -2
- package/src/duckdb/src/optimizer/join_order/plan_enumerator.cpp +32 -10
- package/src/duckdb/src/optimizer/join_order/query_graph_manager.cpp +97 -131
- package/src/duckdb/src/optimizer/join_order/relation_manager.cpp +265 -51
- package/src/duckdb/src/optimizer/join_order/relation_statistics_helper.cpp +21 -17
- package/src/duckdb/src/optimizer/limit_pushdown.cpp +42 -0
- package/src/duckdb/src/optimizer/optimizer.cpp +51 -8
- package/src/duckdb/src/optimizer/pushdown/pushdown_aggregate.cpp +17 -17
- package/src/duckdb/src/optimizer/pushdown/pushdown_cross_product.cpp +22 -4
- package/src/duckdb/src/optimizer/pushdown/pushdown_get.cpp +1 -18
- package/src/duckdb/src/optimizer/pushdown/pushdown_inner_join.cpp +6 -0
- package/src/duckdb/src/optimizer/pushdown/pushdown_mark_join.cpp +4 -2
- package/src/duckdb/src/optimizer/pushdown/pushdown_window.cpp +91 -0
- package/src/duckdb/src/optimizer/remove_unused_columns.cpp +21 -25
- package/src/duckdb/src/optimizer/rule/comparison_simplification.cpp +1 -0
- package/src/duckdb/src/optimizer/rule/empty_needle_removal.cpp +3 -0
- package/src/duckdb/src/optimizer/rule/equal_or_null_simplification.cpp +2 -2
- package/src/duckdb/src/optimizer/rule/in_clause_simplification_rule.cpp +8 -2
- package/src/duckdb/src/optimizer/rule/join_dependent_filter.cpp +135 -0
- package/src/duckdb/src/optimizer/rule/like_optimizations.cpp +1 -1
- package/src/duckdb/src/optimizer/rule/regex_optimizations.cpp +1 -1
- package/src/duckdb/src/optimizer/statistics/operator/propagate_filter.cpp +6 -1
- package/src/duckdb/src/optimizer/statistics/operator/propagate_get.cpp +7 -6
- package/src/duckdb/src/optimizer/statistics/operator/propagate_join.cpp +1 -1
- package/src/duckdb/src/optimizer/topn_optimizer.cpp +46 -7
- package/src/duckdb/src/parallel/executor.cpp +129 -51
- package/src/duckdb/src/parallel/executor_task.cpp +16 -3
- package/src/duckdb/src/parallel/meta_pipeline.cpp +98 -29
- package/src/duckdb/src/parallel/pipeline.cpp +17 -3
- package/src/duckdb/src/parallel/pipeline_executor.cpp +14 -2
- package/src/duckdb/src/parallel/pipeline_prepare_finish_event.cpp +34 -0
- package/src/duckdb/src/parallel/task_executor.cpp +84 -0
- package/src/duckdb/src/parallel/task_scheduler.cpp +94 -16
- package/src/duckdb/src/parallel/thread_context.cpp +1 -1
- package/src/duckdb/src/parser/expression/function_expression.cpp +14 -0
- package/src/duckdb/src/parser/expression/star_expression.cpp +35 -2
- package/src/duckdb/src/parser/parsed_data/alter_table_info.cpp +5 -1
- package/src/duckdb/src/parser/parsed_data/attach_info.cpp +17 -0
- package/src/duckdb/src/parser/parsed_data/create_index_info.cpp +37 -28
- package/src/duckdb/src/parser/parsed_data/create_macro_info.cpp +44 -2
- package/src/duckdb/src/parser/parsed_data/transaction_info.cpp +21 -1
- package/src/duckdb/src/parser/parsed_expression_iterator.cpp +29 -25
- package/src/duckdb/src/parser/parser.cpp +41 -1
- package/src/duckdb/src/parser/query_node/recursive_cte_node.cpp +1 -0
- package/src/duckdb/src/parser/statement/explain_statement.cpp +28 -13
- package/src/duckdb/src/parser/statement/relation_statement.cpp +5 -0
- package/src/duckdb/src/parser/statement/set_statement.cpp +4 -2
- package/src/duckdb/src/parser/statement/transaction_statement.cpp +3 -3
- package/src/duckdb/src/parser/tableref/column_data_ref.cpp +1 -27
- package/src/duckdb/src/parser/tableref/delimgetref.cpp +30 -0
- package/src/duckdb/src/parser/tableref/joinref.cpp +4 -0
- package/src/duckdb/src/parser/transform/constraint/transform_constraint.cpp +35 -29
- package/src/duckdb/src/parser/transform/expression/transform_array_access.cpp +32 -32
- package/src/duckdb/src/parser/transform/expression/transform_columnref.cpp +2 -1
- package/src/duckdb/src/parser/transform/expression/transform_constant.cpp +17 -0
- package/src/duckdb/src/parser/transform/expression/transform_function.cpp +5 -0
- package/src/duckdb/src/parser/transform/expression/transform_multi_assign_reference.cpp +36 -34
- package/src/duckdb/src/parser/transform/expression/transform_operator.cpp +30 -14
- package/src/duckdb/src/parser/transform/expression/transform_subquery.cpp +1 -1
- package/src/duckdb/src/parser/transform/helpers/transform_alias.cpp +2 -1
- package/src/duckdb/src/parser/transform/helpers/transform_cte.cpp +27 -19
- package/src/duckdb/src/parser/transform/helpers/transform_orderby.cpp +31 -28
- package/src/duckdb/src/parser/transform/statement/transform_alter_table.cpp +25 -27
- package/src/duckdb/src/parser/transform/statement/transform_copy.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_create_function.cpp +53 -42
- package/src/duckdb/src/parser/transform/statement/transform_create_table.cpp +6 -6
- package/src/duckdb/src/parser/transform/statement/transform_create_table_as.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_create_type.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_create_view.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_explain.cpp +38 -3
- package/src/duckdb/src/parser/transform/statement/transform_insert.cpp +1 -2
- package/src/duckdb/src/parser/transform/statement/transform_pivot_stmt.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_prepare.cpp +1 -1
- package/src/duckdb/src/parser/transform/statement/transform_select.cpp +26 -21
- package/src/duckdb/src/parser/transform/statement/transform_set.cpp +8 -8
- package/src/duckdb/src/parser/transform/statement/transform_show.cpp +5 -2
- package/src/duckdb/src/parser/transform/statement/transform_show_select.cpp +6 -4
- package/src/duckdb/src/parser/transform/statement/transform_transaction.cpp +27 -6
- package/src/duckdb/src/parser/transform/statement/transform_update.cpp +8 -9
- package/src/duckdb/src/parser/transform/statement/transform_upsert.cpp +11 -12
- package/src/duckdb/src/parser/transform/statement/transform_vacuum.cpp +3 -3
- package/src/duckdb/src/parser/transform/tableref/transform_join.cpp +16 -10
- package/src/duckdb/src/parser/transform/tableref/transform_pivot.cpp +1 -1
- package/src/duckdb/src/parser/transform/tableref/transform_subquery.cpp +1 -1
- package/src/duckdb/src/parser/transformer.cpp +11 -7
- package/src/duckdb/src/planner/bind_context.cpp +3 -3
- package/src/duckdb/src/planner/binder/expression/bind_aggregate_expression.cpp +22 -7
- package/src/duckdb/src/planner/binder/expression/bind_between_expression.cpp +3 -3
- package/src/duckdb/src/planner/binder/expression/bind_collate_expression.cpp +3 -2
- package/src/duckdb/src/planner/binder/expression/bind_columnref_expression.cpp +11 -4
- package/src/duckdb/src/planner/binder/expression/bind_comparison_expression.cpp +9 -54
- package/src/duckdb/src/planner/binder/expression/bind_function_expression.cpp +3 -5
- package/src/duckdb/src/planner/binder/expression/bind_macro_expression.cpp +24 -27
- package/src/duckdb/src/planner/binder/expression/bind_operator_expression.cpp +7 -7
- package/src/duckdb/src/planner/binder/expression/bind_parameter_expression.cpp +9 -2
- package/src/duckdb/src/planner/binder/expression/bind_star_expression.cpp +26 -7
- package/src/duckdb/src/planner/binder/expression/bind_unnest_expression.cpp +5 -0
- package/src/duckdb/src/planner/binder/expression/bind_unpacked_star_expression.cpp +91 -0
- package/src/duckdb/src/planner/binder/expression/bind_window_expression.cpp +2 -2
- package/src/duckdb/src/planner/binder/query_node/bind_select_node.cpp +11 -8
- package/src/duckdb/src/planner/binder/query_node/bind_setop_node.cpp +1 -1
- package/src/duckdb/src/planner/binder/query_node/bind_table_macro_node.cpp +6 -10
- package/src/duckdb/src/planner/binder/query_node/plan_cte_node.cpp +14 -10
- package/src/duckdb/src/planner/binder/query_node/plan_setop.cpp +3 -3
- package/src/duckdb/src/planner/binder/query_node/plan_subquery.cpp +46 -7
- package/src/duckdb/src/planner/binder/statement/bind_call.cpp +13 -20
- package/src/duckdb/src/planner/binder/statement/bind_copy.cpp +105 -13
- package/src/duckdb/src/planner/binder/statement/bind_copy_database.cpp +7 -3
- package/src/duckdb/src/planner/binder/statement/bind_create.cpp +75 -55
- package/src/duckdb/src/planner/binder/statement/bind_create_table.cpp +1 -1
- package/src/duckdb/src/planner/binder/statement/bind_delete.cpp +5 -4
- package/src/duckdb/src/planner/binder/statement/bind_drop.cpp +2 -2
- package/src/duckdb/src/planner/binder/statement/bind_execute.cpp +24 -8
- package/src/duckdb/src/planner/binder/statement/bind_explain.cpp +2 -2
- package/src/duckdb/src/planner/binder/statement/bind_export.cpp +5 -105
- package/src/duckdb/src/planner/binder/statement/bind_extension.cpp +2 -2
- package/src/duckdb/src/planner/binder/statement/bind_insert.cpp +109 -41
- package/src/duckdb/src/planner/binder/statement/bind_set.cpp +23 -7
- package/src/duckdb/src/planner/binder/statement/bind_simple.cpp +4 -1
- package/src/duckdb/src/planner/binder/statement/bind_summarize.cpp +17 -3
- package/src/duckdb/src/planner/binder/statement/bind_update.cpp +5 -4
- package/src/duckdb/src/planner/binder/statement/bind_vacuum.cpp +8 -6
- package/src/duckdb/src/planner/binder/tableref/bind_basetableref.cpp +55 -42
- package/src/duckdb/src/planner/binder/tableref/bind_column_data_ref.cpp +3 -2
- package/src/duckdb/src/planner/binder/tableref/bind_delimgetref.cpp +16 -0
- package/src/duckdb/src/planner/binder/tableref/bind_joinref.cpp +31 -1
- package/src/duckdb/src/planner/binder/tableref/bind_pivot.cpp +6 -0
- package/src/duckdb/src/planner/binder/tableref/bind_showref.cpp +2 -0
- package/src/duckdb/src/planner/binder/tableref/bind_table_function.cpp +106 -46
- package/src/duckdb/src/planner/binder/tableref/plan_delimgetref.cpp +11 -0
- package/src/duckdb/src/planner/binder/tableref/plan_joinref.cpp +15 -2
- package/src/duckdb/src/planner/binder/tableref/plan_table_function.cpp +4 -0
- package/src/duckdb/src/planner/binder.cpp +172 -15
- package/src/duckdb/src/planner/collation_binding.cpp +99 -0
- package/src/duckdb/src/planner/expression/bound_aggregate_expression.cpp +10 -4
- package/src/duckdb/src/planner/expression/bound_between_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_case_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_cast_expression.cpp +14 -12
- package/src/duckdb/src/planner/expression/bound_columnref_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_comparison_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_conjunction_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_constant_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_expanded_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_function_expression.cpp +8 -2
- package/src/duckdb/src/planner/expression/bound_lambda_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_lambdaref_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_operator_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_parameter_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_reference_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_subquery_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_unnest_expression.cpp +1 -1
- package/src/duckdb/src/planner/expression/bound_window_expression.cpp +6 -6
- package/src/duckdb/src/planner/expression_binder/aggregate_binder.cpp +1 -1
- package/src/duckdb/src/planner/expression_binder/alter_binder.cpp +2 -2
- package/src/duckdb/src/planner/expression_binder/base_select_binder.cpp +1 -1
- package/src/duckdb/src/planner/expression_binder/column_alias_binder.cpp +7 -0
- package/src/duckdb/src/planner/expression_binder/constant_binder.cpp +3 -3
- package/src/duckdb/src/planner/expression_binder/group_binder.cpp +26 -22
- package/src/duckdb/src/planner/expression_binder/having_binder.cpp +7 -1
- package/src/duckdb/src/planner/expression_binder/index_binder.cpp +2 -2
- package/src/duckdb/src/planner/expression_binder/insert_binder.cpp +2 -2
- package/src/duckdb/src/planner/expression_binder/lateral_binder.cpp +2 -2
- package/src/duckdb/src/planner/expression_binder/order_binder.cpp +61 -43
- package/src/duckdb/src/planner/expression_binder/qualify_binder.cpp +2 -2
- package/src/duckdb/src/planner/expression_binder/relation_binder.cpp +4 -4
- package/src/duckdb/src/planner/expression_binder/returning_binder.cpp +3 -2
- package/src/duckdb/src/planner/expression_binder/table_function_binder.cpp +10 -3
- package/src/duckdb/src/planner/expression_binder/update_binder.cpp +1 -1
- package/src/duckdb/src/planner/expression_binder/where_binder.cpp +9 -2
- package/src/duckdb/src/planner/expression_binder.cpp +121 -21
- package/src/duckdb/src/planner/expression_iterator.cpp +26 -1
- package/src/duckdb/src/planner/filter/conjunction_filter.cpp +33 -0
- package/src/duckdb/src/planner/filter/constant_filter.cpp +15 -0
- package/src/duckdb/src/planner/filter/null_filter.cpp +22 -0
- package/src/duckdb/src/planner/filter/struct_filter.cpp +16 -0
- package/src/duckdb/src/planner/logical_operator.cpp +24 -7
- package/src/duckdb/src/planner/operator/logical_aggregate.cpp +13 -7
- package/src/duckdb/src/planner/operator/logical_any_join.cpp +5 -2
- package/src/duckdb/src/planner/operator/logical_comparison_join.cpp +13 -5
- package/src/duckdb/src/planner/operator/logical_copy_to_file.cpp +64 -8
- package/src/duckdb/src/planner/operator/logical_cteref.cpp +7 -0
- package/src/duckdb/src/planner/operator/logical_distinct.cpp +6 -5
- package/src/duckdb/src/planner/operator/logical_get.cpp +60 -18
- package/src/duckdb/src/planner/operator/logical_materialized_cte.cpp +7 -0
- package/src/duckdb/src/planner/operator/logical_order.cpp +7 -4
- package/src/duckdb/src/planner/operator/logical_top_n.cpp +2 -2
- package/src/duckdb/src/planner/operator/logical_vacuum.cpp +1 -1
- package/src/duckdb/src/planner/planner.cpp +2 -3
- package/src/duckdb/src/planner/subquery/flatten_dependent_join.cpp +27 -10
- package/src/duckdb/src/planner/table_filter.cpp +51 -0
- package/src/duckdb/src/storage/arena_allocator.cpp +28 -10
- package/src/duckdb/src/storage/block.cpp +3 -2
- package/src/duckdb/src/storage/buffer/block_handle.cpp +29 -14
- package/src/duckdb/src/storage/buffer/block_manager.cpp +6 -5
- package/src/duckdb/src/storage/buffer/buffer_handle.cpp +1 -1
- package/src/duckdb/src/storage/buffer/buffer_pool.cpp +264 -125
- package/src/duckdb/src/storage/buffer_manager.cpp +5 -1
- package/src/duckdb/src/storage/checkpoint/row_group_writer.cpp +0 -6
- package/src/duckdb/src/storage/checkpoint/table_data_writer.cpp +26 -3
- package/src/duckdb/src/storage/checkpoint/write_overflow_strings_to_disk.cpp +21 -9
- package/src/duckdb/src/storage/checkpoint_manager.cpp +49 -24
- package/src/duckdb/src/storage/compression/alp/alp.cpp +6 -11
- package/src/duckdb/src/storage/compression/alprd.cpp +5 -9
- package/src/duckdb/src/storage/compression/bitpacking.cpp +35 -31
- package/src/duckdb/src/storage/compression/chimp/chimp.cpp +6 -8
- package/src/duckdb/src/storage/compression/dictionary_compression.cpp +71 -58
- package/src/duckdb/src/storage/compression/fixed_size_uncompressed.cpp +15 -13
- package/src/duckdb/src/storage/compression/fsst.cpp +66 -53
- package/src/duckdb/src/storage/compression/numeric_constant.cpp +4 -5
- package/src/duckdb/src/storage/compression/patas.cpp +6 -17
- package/src/duckdb/src/storage/compression/rle.cpp +20 -18
- package/src/duckdb/src/storage/compression/string_uncompressed.cpp +71 -52
- package/src/duckdb/src/storage/compression/uncompressed.cpp +2 -2
- package/src/duckdb/src/storage/compression/validity_uncompressed.cpp +8 -7
- package/src/duckdb/src/storage/data_pointer.cpp +22 -0
- package/src/duckdb/src/storage/data_table.cpp +41 -12
- package/src/duckdb/src/storage/local_storage.cpp +22 -8
- package/src/duckdb/src/storage/metadata/metadata_manager.cpp +33 -17
- package/src/duckdb/src/storage/metadata/metadata_reader.cpp +4 -4
- package/src/duckdb/src/storage/metadata/metadata_writer.cpp +3 -3
- package/src/duckdb/src/storage/partial_block_manager.cpp +19 -8
- package/src/duckdb/src/storage/serialization/serialize_create_info.cpp +11 -8
- package/src/duckdb/src/storage/serialization/serialize_expression.cpp +1 -1
- package/src/duckdb/src/storage/serialization/serialize_extension_install_info.cpp +2 -0
- package/src/duckdb/src/storage/serialization/serialize_logical_operator.cpp +3 -3
- package/src/duckdb/src/storage/serialization/serialize_nodes.cpp +19 -5
- package/src/duckdb/src/storage/serialization/serialize_parse_info.cpp +21 -1
- package/src/duckdb/src/storage/serialization/serialize_parsed_expression.cpp +4 -2
- package/src/duckdb/src/storage/serialization/serialize_query_node.cpp +2 -2
- package/src/duckdb/src/storage/serialization/serialize_storage.cpp +2 -0
- package/src/duckdb/src/storage/serialization/serialize_tableref.cpp +8 -4
- package/src/duckdb/src/storage/serialization/serialize_types.cpp +4 -4
- package/src/duckdb/src/storage/single_file_block_manager.cpp +170 -34
- package/src/duckdb/src/storage/standard_buffer_manager.cpp +221 -64
- package/src/duckdb/src/storage/statistics/column_statistics.cpp +4 -3
- package/src/duckdb/src/storage/statistics/distinct_statistics.cpp +36 -26
- package/src/duckdb/src/storage/statistics/numeric_stats.cpp +4 -15
- package/src/duckdb/src/storage/statistics/string_stats.cpp +14 -8
- package/src/duckdb/src/storage/statistics/struct_stats.cpp +2 -1
- package/src/duckdb/src/storage/storage_info.cpp +34 -9
- package/src/duckdb/src/storage/storage_manager.cpp +147 -74
- package/src/duckdb/src/storage/table/array_column_data.cpp +37 -17
- package/src/duckdb/src/storage/table/chunk_info.cpp +38 -0
- package/src/duckdb/src/storage/table/column_checkpoint_state.cpp +10 -6
- package/src/duckdb/src/storage/table/column_data.cpp +252 -31
- package/src/duckdb/src/storage/table/column_data_checkpointer.cpp +2 -12
- package/src/duckdb/src/storage/table/column_segment.cpp +63 -34
- package/src/duckdb/src/storage/table/list_column_data.cpp +34 -15
- package/src/duckdb/src/storage/table/row_group.cpp +228 -120
- package/src/duckdb/src/storage/table/row_group_collection.cpp +122 -120
- package/src/duckdb/src/storage/table/row_version_manager.cpp +27 -1
- package/src/duckdb/src/storage/table/scan_state.cpp +101 -18
- package/src/duckdb/src/storage/table/standard_column_data.cpp +20 -34
- package/src/duckdb/src/storage/table/struct_column_data.cpp +39 -42
- package/src/duckdb/src/storage/table/table_statistics.cpp +2 -1
- package/src/duckdb/src/storage/table/update_segment.cpp +9 -8
- package/src/duckdb/src/storage/table/validity_column_data.cpp +2 -2
- package/src/duckdb/src/storage/table_index_list.cpp +8 -7
- package/src/duckdb/src/storage/temporary_file_manager.cpp +11 -9
- package/src/duckdb/src/storage/temporary_memory_manager.cpp +227 -39
- package/src/duckdb/src/storage/wal_replay.cpp +68 -28
- package/src/duckdb/src/storage/write_ahead_log.cpp +56 -47
- package/src/duckdb/src/transaction/cleanup_state.cpp +9 -1
- package/src/duckdb/src/transaction/commit_state.cpp +7 -170
- package/src/duckdb/src/transaction/duck_transaction.cpp +87 -19
- package/src/duckdb/src/transaction/duck_transaction_manager.cpp +65 -10
- package/src/duckdb/src/transaction/meta_transaction.cpp +18 -3
- package/src/duckdb/src/transaction/transaction_context.cpp +21 -17
- package/src/duckdb/src/transaction/undo_buffer.cpp +20 -14
- package/src/duckdb/src/transaction/wal_write_state.cpp +292 -0
- package/src/duckdb/src/verification/prepared_statement_verifier.cpp +0 -1
- package/src/duckdb/third_party/brotli/common/brotli_constants.h +204 -0
- package/src/duckdb/third_party/brotli/common/brotli_platform.h +543 -0
- package/src/duckdb/third_party/brotli/common/constants.cpp +17 -0
- package/src/duckdb/third_party/brotli/common/context.cpp +156 -0
- package/src/duckdb/third_party/brotli/common/context.h +110 -0
- package/src/duckdb/third_party/brotli/common/dictionary.cpp +5912 -0
- package/src/duckdb/third_party/brotli/common/dictionary.h +60 -0
- package/src/duckdb/third_party/brotli/common/platform.cpp +24 -0
- package/src/duckdb/third_party/brotli/common/shared_dictionary.cpp +517 -0
- package/src/duckdb/third_party/brotli/common/shared_dictionary_internal.h +71 -0
- package/src/duckdb/third_party/brotli/common/transform.cpp +287 -0
- package/src/duckdb/third_party/brotli/common/transform.h +77 -0
- package/src/duckdb/third_party/brotli/common/version.h +51 -0
- package/src/duckdb/third_party/brotli/dec/bit_reader.cpp +74 -0
- package/src/duckdb/third_party/brotli/dec/bit_reader.h +419 -0
- package/src/duckdb/third_party/brotli/dec/decode.cpp +2758 -0
- package/src/duckdb/third_party/brotli/dec/huffman.cpp +338 -0
- package/src/duckdb/third_party/brotli/dec/huffman.h +118 -0
- package/src/duckdb/third_party/brotli/dec/prefix.h +733 -0
- package/src/duckdb/third_party/brotli/dec/state.cpp +178 -0
- package/src/duckdb/third_party/brotli/dec/state.h +386 -0
- package/src/duckdb/third_party/brotli/enc/backward_references.cpp +3775 -0
- package/src/duckdb/third_party/brotli/enc/backward_references.h +36 -0
- package/src/duckdb/third_party/brotli/enc/backward_references_hq.cpp +935 -0
- package/src/duckdb/third_party/brotli/enc/backward_references_hq.h +92 -0
- package/src/duckdb/third_party/brotli/enc/bit_cost.cpp +410 -0
- package/src/duckdb/third_party/brotli/enc/bit_cost.h +60 -0
- package/src/duckdb/third_party/brotli/enc/block_splitter.cpp +1653 -0
- package/src/duckdb/third_party/brotli/enc/block_splitter.h +48 -0
- package/src/duckdb/third_party/brotli/enc/brotli_bit_stream.cpp +1431 -0
- package/src/duckdb/third_party/brotli/enc/brotli_bit_stream.h +85 -0
- package/src/duckdb/third_party/brotli/enc/brotli_hash.h +4352 -0
- package/src/duckdb/third_party/brotli/enc/brotli_params.h +47 -0
- package/src/duckdb/third_party/brotli/enc/cluster.cpp +1025 -0
- package/src/duckdb/third_party/brotli/enc/cluster.h +1017 -0
- package/src/duckdb/third_party/brotli/enc/command.cpp +24 -0
- package/src/duckdb/third_party/brotli/enc/command.h +187 -0
- package/src/duckdb/third_party/brotli/enc/compound_dictionary.cpp +209 -0
- package/src/duckdb/third_party/brotli/enc/compound_dictionary.h +75 -0
- package/src/duckdb/third_party/brotli/enc/compress_fragment.cpp +796 -0
- package/src/duckdb/third_party/brotli/enc/compress_fragment.h +82 -0
- package/src/duckdb/third_party/brotli/enc/compress_fragment_two_pass.cpp +653 -0
- package/src/duckdb/third_party/brotli/enc/compress_fragment_two_pass.h +68 -0
- package/src/duckdb/third_party/brotli/enc/dictionary_hash.cpp +1844 -0
- package/src/duckdb/third_party/brotli/enc/dictionary_hash.h +21 -0
- package/src/duckdb/third_party/brotli/enc/encode.cpp +1990 -0
- package/src/duckdb/third_party/brotli/enc/encoder_dict.cpp +636 -0
- package/src/duckdb/third_party/brotli/enc/encoder_dict.h +153 -0
- package/src/duckdb/third_party/brotli/enc/entropy_encode.cpp +500 -0
- package/src/duckdb/third_party/brotli/enc/entropy_encode.h +119 -0
- package/src/duckdb/third_party/brotli/enc/entropy_encode_static.h +538 -0
- package/src/duckdb/third_party/brotli/enc/fast_log.cpp +101 -0
- package/src/duckdb/third_party/brotli/enc/fast_log.h +63 -0
- package/src/duckdb/third_party/brotli/enc/find_match_length.h +68 -0
- package/src/duckdb/third_party/brotli/enc/histogram.cpp +96 -0
- package/src/duckdb/third_party/brotli/enc/histogram.h +210 -0
- package/src/duckdb/third_party/brotli/enc/literal_cost.cpp +176 -0
- package/src/duckdb/third_party/brotli/enc/literal_cost.h +28 -0
- package/src/duckdb/third_party/brotli/enc/memory.cpp +190 -0
- package/src/duckdb/third_party/brotli/enc/memory.h +127 -0
- package/src/duckdb/third_party/brotli/enc/metablock.cpp +1225 -0
- package/src/duckdb/third_party/brotli/enc/metablock.h +102 -0
- package/src/duckdb/third_party/brotli/enc/prefix.h +50 -0
- package/src/duckdb/third_party/brotli/enc/quality.h +202 -0
- package/src/duckdb/third_party/brotli/enc/ringbuffer.h +164 -0
- package/src/duckdb/third_party/brotli/enc/state.h +106 -0
- package/src/duckdb/third_party/brotli/enc/static_dict.cpp +538 -0
- package/src/duckdb/third_party/brotli/enc/static_dict.h +37 -0
- package/src/duckdb/third_party/brotli/enc/static_dict_lut.h +5862 -0
- package/src/duckdb/third_party/brotli/enc/utf8_util.cpp +81 -0
- package/src/duckdb/third_party/brotli/enc/utf8_util.h +29 -0
- package/src/duckdb/third_party/brotli/enc/write_bits.h +84 -0
- package/src/duckdb/third_party/brotli/include/brotli/decode.h +405 -0
- package/src/duckdb/third_party/brotli/include/brotli/encode.h +489 -0
- package/src/duckdb/third_party/brotli/include/brotli/port.h +238 -0
- package/src/duckdb/third_party/brotli/include/brotli/shared_dictionary.h +96 -0
- package/src/duckdb/third_party/brotli/include/brotli/types.h +83 -0
- package/src/duckdb/third_party/fast_float/fast_float/fast_float.h +20 -4
- package/src/duckdb/third_party/fmt/include/fmt/format.h +54 -10
- package/src/duckdb/third_party/fsst/fsst.h +2 -2
- package/src/duckdb/third_party/fsst/libfsst.hpp +2 -2
- package/src/duckdb/third_party/httplib/httplib.hpp +6763 -5580
- package/src/duckdb/third_party/hyperloglog/hyperloglog.cpp +13 -30
- package/src/duckdb/third_party/hyperloglog/hyperloglog.hpp +8 -2
- package/src/duckdb/third_party/libpg_query/include/nodes/nodes.hpp +1 -0
- package/src/duckdb/third_party/libpg_query/include/nodes/parsenodes.hpp +22 -9
- package/src/duckdb/third_party/libpg_query/include/parser/gram.hpp +1041 -554
- package/src/duckdb/third_party/libpg_query/include/parser/kwlist.hpp +1 -0
- package/src/duckdb/third_party/libpg_query/postgres_parser.cpp +2 -1
- package/src/duckdb/third_party/libpg_query/src_backend_parser_gram.cpp +21605 -21752
- package/src/duckdb/third_party/libpg_query/src_backend_parser_scan.cpp +538 -299
- package/src/duckdb/third_party/mbedtls/include/mbedtls/mbedtls_config.h +1 -0
- package/src/duckdb/third_party/mbedtls/include/mbedtls_wrapper.hpp +36 -12
- package/src/duckdb/third_party/mbedtls/library/md.cpp +6 -6
- package/src/duckdb/third_party/mbedtls/library/sha1.cpp +2 -0
- package/src/duckdb/third_party/mbedtls/library/sha256.cpp +3 -0
- package/src/duckdb/third_party/mbedtls/mbedtls_wrapper.cpp +99 -47
- package/src/duckdb/third_party/pcg/pcg_extras.hpp +1 -1
- package/src/duckdb/third_party/re2/re2/prog.cc +2 -2
- package/src/duckdb/third_party/snappy/snappy-internal.h +398 -0
- package/src/duckdb/third_party/snappy/snappy-sinksource.cc +111 -9
- package/src/duckdb/third_party/snappy/snappy-sinksource.h +158 -0
- package/src/duckdb/third_party/snappy/snappy-stubs-internal.h +523 -3
- package/src/duckdb/third_party/snappy/snappy-stubs-public.h +34 -1
- package/src/duckdb/third_party/snappy/snappy.cc +2626 -0
- package/src/duckdb/third_party/snappy/snappy.h +223 -0
- package/src/duckdb/third_party/snappy/snappy_version.hpp +11 -0
- package/src/duckdb/third_party/utf8proc/include/utf8proc.hpp +69 -101
- package/src/duckdb/third_party/utf8proc/include/utf8proc_wrapper.hpp +53 -0
- package/src/duckdb/third_party/utf8proc/utf8proc.cpp +627 -678
- package/src/duckdb/third_party/utf8proc/utf8proc_data.cpp +15008 -12868
- package/src/duckdb/third_party/utf8proc/utf8proc_wrapper.cpp +185 -29
- package/src/duckdb/ub_extension_json_json_functions.cpp +6 -0
- package/src/duckdb/ub_src_catalog_default.cpp +4 -0
- package/src/duckdb/ub_src_common.cpp +7 -1
- package/src/duckdb/ub_src_common_arrow.cpp +10 -0
- package/src/duckdb/ub_src_common_enums.cpp +2 -0
- package/src/duckdb/ub_src_common_tree_renderer.cpp +10 -0
- package/src/duckdb/ub_src_common_types.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_aggregate_holistic.cpp +4 -0
- package/src/duckdb/ub_src_core_functions_aggregate_nested.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_generic.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_list.cpp +2 -4
- package/src/duckdb/ub_src_core_functions_scalar_map.cpp +2 -0
- package/src/duckdb/ub_src_core_functions_scalar_string.cpp +4 -0
- package/src/duckdb/ub_src_execution_index_art.cpp +5 -3
- package/src/duckdb/ub_src_execution_operator_csv_scanner_scanner.cpp +2 -0
- package/src/duckdb/ub_src_execution_operator_helper.cpp +4 -0
- package/src/duckdb/ub_src_function.cpp +4 -0
- package/src/duckdb/ub_src_function_cast.cpp +2 -0
- package/src/duckdb/ub_src_function_scalar_generic.cpp +4 -0
- package/src/duckdb/ub_src_function_scalar_list.cpp +0 -2
- package/src/duckdb/ub_src_function_scalar_string.cpp +2 -0
- package/src/duckdb/ub_src_function_table.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 +4 -0
- package/src/duckdb/ub_src_main_buffered_data.cpp +4 -0
- package/src/duckdb/ub_src_main_capi.cpp +10 -0
- package/src/duckdb/ub_src_main_chunk_scan_state.cpp +2 -0
- package/src/duckdb/ub_src_main_relation.cpp +2 -0
- package/src/duckdb/ub_src_main_secret.cpp +2 -0
- package/src/duckdb/ub_src_optimizer.cpp +8 -0
- package/src/duckdb/ub_src_optimizer_compressed_materialization.cpp +2 -0
- package/src/duckdb/ub_src_optimizer_pushdown.cpp +2 -0
- package/src/duckdb/ub_src_optimizer_rule.cpp +2 -0
- package/src/duckdb/ub_src_parallel.cpp +4 -0
- package/src/duckdb/ub_src_parser_tableref.cpp +2 -0
- package/src/duckdb/ub_src_planner.cpp +2 -0
- package/src/duckdb/ub_src_planner_binder_expression.cpp +2 -0
- package/src/duckdb/ub_src_planner_binder_tableref.cpp +4 -0
- package/src/duckdb/ub_src_storage_statistics.cpp +0 -2
- package/src/duckdb/ub_src_transaction.cpp +2 -0
- package/test/columns.test.ts +1 -1
- package/test/prepare.test.ts +1 -1
- package/test/test_all_types.test.ts +1 -1
@@ -6,7 +6,6 @@
|
|
6
6
|
#include "utf8proc.hpp"
|
7
7
|
|
8
8
|
namespace duckdb {
|
9
|
-
|
10
9
|
// Helper function to generate column names
|
11
10
|
static string GenerateColumnName(const idx_t total_cols, const idx_t col_number, const string &prefix = "column") {
|
12
11
|
auto max_digits = NumericHelper::UnsignedLength(total_cols - 1);
|
@@ -98,26 +97,33 @@ static string NormalizeColumnName(const string &col_name) {
|
|
98
97
|
}
|
99
98
|
|
100
99
|
// If our columns were set by the user, we verify if their names match with the first row
|
101
|
-
bool CSVSniffer::DetectHeaderWithSetColumn(
|
100
|
+
bool CSVSniffer::DetectHeaderWithSetColumn(ClientContext &context, vector<HeaderValue> &best_header_row,
|
101
|
+
SetColumns &set_columns, CSVReaderOptions &options) {
|
102
102
|
bool has_header = true;
|
103
103
|
bool all_varchar = true;
|
104
104
|
bool first_row_consistent = true;
|
105
|
+
std::ostringstream error;
|
105
106
|
// User set the names, we must check if they match the first row
|
106
107
|
// We do a +1 to check for situations where the csv file has an extra all null column
|
107
108
|
if (set_columns.Size() != best_header_row.size() && set_columns.Size() + 1 != best_header_row.size()) {
|
108
109
|
return false;
|
109
|
-
}
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
110
|
+
}
|
111
|
+
|
112
|
+
// Let's do a match-aroo
|
113
|
+
for (idx_t i = 0; i < set_columns.Size(); i++) {
|
114
|
+
if (best_header_row[i].IsNull()) {
|
115
|
+
return false;
|
116
|
+
}
|
117
|
+
if (best_header_row[i].value != (*set_columns.names)[i]) {
|
118
|
+
error << "Header Mismatch at position:" << i << "\n";
|
119
|
+
error << "Expected Name: \"" << (*set_columns.names)[i] << "\".";
|
120
|
+
error << "Actual Name: \"" << best_header_row[i].value << "\"."
|
121
|
+
<< "\n";
|
122
|
+
has_header = false;
|
123
|
+
break;
|
119
124
|
}
|
120
125
|
}
|
126
|
+
|
121
127
|
if (!has_header) {
|
122
128
|
// We verify if the types are consistent
|
123
129
|
for (idx_t col = 0; col < set_columns.Size(); col++) {
|
@@ -125,32 +131,60 @@ bool CSVSniffer::DetectHeaderWithSetColumn() {
|
|
125
131
|
const auto &sql_type = (*set_columns.types)[col];
|
126
132
|
if (sql_type != LogicalType::VARCHAR) {
|
127
133
|
all_varchar = false;
|
128
|
-
if (!CanYouCastIt(best_header_row[col].value, sql_type, options.dialect_options,
|
129
|
-
|
134
|
+
if (!CSVSniffer::CanYouCastIt(context, best_header_row[col].value, sql_type, options.dialect_options,
|
135
|
+
best_header_row[col].IsNull(), options.decimal_separator[0])) {
|
130
136
|
first_row_consistent = false;
|
131
137
|
}
|
132
138
|
}
|
133
139
|
}
|
140
|
+
if (!first_row_consistent) {
|
141
|
+
options.sniffer_user_mismatch_error += error.str();
|
142
|
+
}
|
134
143
|
if (all_varchar) {
|
135
|
-
|
136
|
-
return false;
|
144
|
+
return true;
|
137
145
|
}
|
138
146
|
return !first_row_consistent;
|
139
147
|
}
|
140
148
|
return has_header;
|
141
149
|
}
|
142
|
-
|
143
|
-
|
150
|
+
|
151
|
+
bool EmptyHeader(const string &col_name, bool is_null, bool normalize) {
|
152
|
+
if (col_name.empty() || is_null) {
|
153
|
+
return true;
|
154
|
+
}
|
155
|
+
if (normalize) {
|
156
|
+
// normalize has special logic to trim white spaces and generate names
|
157
|
+
return false;
|
158
|
+
}
|
159
|
+
// check if it's all white spaces
|
160
|
+
for (auto &c : col_name) {
|
161
|
+
if (!StringUtil::CharacterIsSpace(c)) {
|
162
|
+
return false;
|
163
|
+
}
|
164
|
+
}
|
165
|
+
// if we are not normalizing the name and is all white spaces, then we generate a name
|
166
|
+
return true;
|
167
|
+
}
|
168
|
+
|
169
|
+
vector<string>
|
170
|
+
CSVSniffer::DetectHeaderInternal(ClientContext &context, vector<HeaderValue> &best_header_row,
|
171
|
+
CSVStateMachine &state_machine, SetColumns &set_columns,
|
172
|
+
unordered_map<idx_t, vector<LogicalType>> &best_sql_types_candidates_per_column_idx,
|
173
|
+
CSVReaderOptions &options, CSVErrorHandler &error_handler) {
|
174
|
+
vector<string> detected_names;
|
175
|
+
auto &dialect_options = state_machine.dialect_options;
|
144
176
|
if (best_header_row.empty()) {
|
145
|
-
|
146
|
-
for (idx_t col = 0; col <
|
147
|
-
|
177
|
+
dialect_options.header = false;
|
178
|
+
for (idx_t col = 0; col < dialect_options.num_cols; col++) {
|
179
|
+
detected_names.push_back(GenerateColumnName(dialect_options.num_cols, col));
|
148
180
|
}
|
149
181
|
// If the user provided names, we must replace our header with the user provided names
|
150
|
-
|
151
|
-
|
182
|
+
if (!options.columns_set) {
|
183
|
+
for (idx_t i = 0; i < MinValue<idx_t>(best_header_row.size(), options.name_list.size()); i++) {
|
184
|
+
detected_names[i] = options.name_list[i];
|
185
|
+
}
|
152
186
|
}
|
153
|
-
return;
|
187
|
+
return detected_names;
|
154
188
|
}
|
155
189
|
// information for header detection
|
156
190
|
bool first_row_consistent = true;
|
@@ -158,16 +192,17 @@ void CSVSniffer::DetectHeader() {
|
|
158
192
|
bool first_row_nulls = true;
|
159
193
|
// If null-padding is not allowed and there is a mismatch between our header candidate and the number of columns
|
160
194
|
// We can't detect the dialect/type options properly
|
161
|
-
if (!
|
162
|
-
|
163
|
-
|
164
|
-
|
195
|
+
if (!options.null_padding && best_sql_types_candidates_per_column_idx.size() != best_header_row.size()) {
|
196
|
+
auto error =
|
197
|
+
CSVError::HeaderSniffingError(options, best_header_row, best_sql_types_candidates_per_column_idx.size(),
|
198
|
+
state_machine.dialect_options.state_machine_options.delimiter.GetValue());
|
199
|
+
error_handler.Error(error);
|
165
200
|
}
|
166
201
|
bool all_varchar = true;
|
167
202
|
bool has_header;
|
168
203
|
|
169
204
|
if (set_columns.IsSet()) {
|
170
|
-
has_header = DetectHeaderWithSetColumn();
|
205
|
+
has_header = DetectHeaderWithSetColumn(context, best_header_row, set_columns, options);
|
171
206
|
} else {
|
172
207
|
for (idx_t col = 0; col < best_header_row.size(); col++) {
|
173
208
|
if (!best_header_row[col].IsNull()) {
|
@@ -177,7 +212,7 @@ void CSVSniffer::DetectHeader() {
|
|
177
212
|
const auto &sql_type = best_sql_types_candidates_per_column_idx[col].back();
|
178
213
|
if (sql_type != LogicalType::VARCHAR) {
|
179
214
|
all_varchar = false;
|
180
|
-
if (!CanYouCastIt(best_header_row[col].value, sql_type,
|
215
|
+
if (!CanYouCastIt(context, best_header_row[col].value, sql_type, dialect_options,
|
181
216
|
best_header_row[col].IsNull(), options.decimal_separator[0])) {
|
182
217
|
first_row_consistent = false;
|
183
218
|
}
|
@@ -191,33 +226,31 @@ void CSVSniffer::DetectHeader() {
|
|
191
226
|
}
|
192
227
|
}
|
193
228
|
|
194
|
-
if (
|
229
|
+
if (options.dialect_options.header.IsSetByUser()) {
|
195
230
|
// Header is defined by user, use that.
|
196
|
-
has_header =
|
231
|
+
has_header = options.dialect_options.header.GetValue();
|
197
232
|
}
|
198
233
|
// update parser info, and read, generate & set col_names based on previous findings
|
199
234
|
if (has_header) {
|
200
|
-
|
201
|
-
if (
|
202
|
-
|
203
|
-
|
204
|
-
sniffer_state_machine.dialect_options.skip_rows =
|
205
|
-
sniffer_state_machine.dialect_options.skip_rows.GetValue() - 1;
|
235
|
+
dialect_options.header = true;
|
236
|
+
if (options.null_padding && !options.dialect_options.skip_rows.IsSetByUser()) {
|
237
|
+
if (dialect_options.skip_rows.GetValue() > 0) {
|
238
|
+
dialect_options.skip_rows = dialect_options.skip_rows.GetValue() - 1;
|
206
239
|
}
|
207
240
|
}
|
208
241
|
case_insensitive_map_t<idx_t> name_collision_count;
|
209
242
|
|
210
243
|
// get header names from CSV
|
211
244
|
for (idx_t col = 0; col < best_header_row.size(); col++) {
|
212
|
-
string col_name = best_header_row[col].value
|
245
|
+
string &col_name = best_header_row[col].value;
|
213
246
|
|
214
247
|
// generate name if field is empty
|
215
|
-
if (col_name
|
216
|
-
col_name = GenerateColumnName(
|
248
|
+
if (EmptyHeader(col_name, best_header_row[col].is_null, options.normalize_names)) {
|
249
|
+
col_name = GenerateColumnName(dialect_options.num_cols, col);
|
217
250
|
}
|
218
251
|
|
219
252
|
// normalize names or at least trim whitespace
|
220
|
-
if (
|
253
|
+
if (options.normalize_names) {
|
221
254
|
col_name = NormalizeColumnName(col_name);
|
222
255
|
} else {
|
223
256
|
col_name = TrimWhitespace(col_name);
|
@@ -228,27 +261,35 @@ void CSVSniffer::DetectHeader() {
|
|
228
261
|
name_collision_count[col_name] += 1;
|
229
262
|
col_name = col_name + "_" + to_string(name_collision_count[col_name]);
|
230
263
|
}
|
231
|
-
|
264
|
+
detected_names.push_back(col_name);
|
232
265
|
name_collision_count[col_name] = 0;
|
233
266
|
}
|
234
|
-
if (best_header_row.size() <
|
235
|
-
for (idx_t col = best_header_row.size(); col <
|
236
|
-
|
267
|
+
if (best_header_row.size() < dialect_options.num_cols && options.null_padding) {
|
268
|
+
for (idx_t col = best_header_row.size(); col < dialect_options.num_cols; col++) {
|
269
|
+
detected_names.push_back(GenerateColumnName(dialect_options.num_cols, col));
|
237
270
|
}
|
238
|
-
} else if (best_header_row.size() <
|
271
|
+
} else if (best_header_row.size() < dialect_options.num_cols) {
|
239
272
|
throw InternalException("Detected header has number of columns inferior to dialect detection");
|
240
273
|
}
|
241
274
|
|
242
275
|
} else {
|
243
|
-
|
244
|
-
for (idx_t col = 0; col <
|
245
|
-
|
276
|
+
dialect_options.header = false;
|
277
|
+
for (idx_t col = 0; col < dialect_options.num_cols; col++) {
|
278
|
+
detected_names.push_back(GenerateColumnName(dialect_options.num_cols, col));
|
246
279
|
}
|
247
280
|
}
|
248
281
|
|
249
282
|
// If the user provided names, we must replace our header with the user provided names
|
250
|
-
|
251
|
-
|
283
|
+
if (!options.columns_set) {
|
284
|
+
for (idx_t i = 0; i < MinValue<idx_t>(detected_names.size(), options.name_list.size()); i++) {
|
285
|
+
detected_names[i] = options.name_list[i];
|
286
|
+
}
|
252
287
|
}
|
288
|
+
return detected_names;
|
289
|
+
}
|
290
|
+
void CSVSniffer::DetectHeader() {
|
291
|
+
auto &sniffer_state_machine = best_candidate->GetStateMachine();
|
292
|
+
names = DetectHeaderInternal(buffer_manager->context, best_header_row, sniffer_state_machine, set_columns,
|
293
|
+
best_sql_types_candidates_per_column_idx, options, *error_handler);
|
253
294
|
}
|
254
295
|
} // namespace duckdb
|
@@ -95,8 +95,8 @@ void CSVSniffer::SetDateFormat(CSVStateMachine &candidate, const string &format_
|
|
95
95
|
candidate.dialect_options.date_format[sql_type].Set(strpformat, false);
|
96
96
|
}
|
97
97
|
|
98
|
-
bool CSVSniffer::CanYouCastIt(const string_t value, const LogicalType &type,
|
99
|
-
const bool is_null, const char decimal_separator) {
|
98
|
+
bool CSVSniffer::CanYouCastIt(ClientContext &context, const string_t value, const LogicalType &type,
|
99
|
+
const DialectOptions &dialect_options, const bool is_null, const char decimal_separator) {
|
100
100
|
if (is_null) {
|
101
101
|
return true;
|
102
102
|
}
|
@@ -137,11 +137,11 @@ bool CSVSniffer::CanYouCastIt(const string_t value, const LogicalType &type, con
|
|
137
137
|
}
|
138
138
|
case LogicalTypeId::DOUBLE: {
|
139
139
|
double dummy_value;
|
140
|
-
return TryDoubleCast<double>(value_ptr, value_size, dummy_value, true,
|
140
|
+
return TryDoubleCast<double>(value_ptr, value_size, dummy_value, true, decimal_separator);
|
141
141
|
}
|
142
142
|
case LogicalTypeId::FLOAT: {
|
143
143
|
float dummy_value;
|
144
|
-
return TryDoubleCast<float>(value_ptr, value_size, dummy_value, true,
|
144
|
+
return TryDoubleCast<float>(value_ptr, value_size, dummy_value, true, decimal_separator);
|
145
145
|
}
|
146
146
|
case LogicalTypeId::DATE: {
|
147
147
|
if (!dialect_options.date_format.find(LogicalTypeId::DATE)->second.GetValue().Empty()) {
|
@@ -150,12 +150,11 @@ bool CSVSniffer::CanYouCastIt(const string_t value, const LogicalType &type, con
|
|
150
150
|
return dialect_options.date_format.find(LogicalTypeId::DATE)
|
151
151
|
->second.GetValue()
|
152
152
|
.TryParseDate(value, result, error_message);
|
153
|
-
} else {
|
154
|
-
idx_t pos;
|
155
|
-
bool special;
|
156
|
-
date_t dummy_value;
|
157
|
-
return Date::TryConvertDate(value_ptr, value_size, pos, dummy_value, special, true);
|
158
153
|
}
|
154
|
+
idx_t pos;
|
155
|
+
bool special;
|
156
|
+
date_t dummy_value;
|
157
|
+
return Date::TryConvertDate(value_ptr, value_size, pos, dummy_value, special, true);
|
159
158
|
}
|
160
159
|
case LogicalTypeId::TIMESTAMP: {
|
161
160
|
timestamp_t dummy_value;
|
@@ -164,9 +163,8 @@ bool CSVSniffer::CanYouCastIt(const string_t value, const LogicalType &type, con
|
|
164
163
|
return dialect_options.date_format.find(LogicalTypeId::TIMESTAMP)
|
165
164
|
->second.GetValue()
|
166
165
|
.TryParseTimestamp(value, dummy_value, error_message);
|
167
|
-
} else {
|
168
|
-
return Timestamp::TryConvertTimestamp(value_ptr, value_size, dummy_value) == TimestampCastResult::SUCCESS;
|
169
166
|
}
|
167
|
+
return Timestamp::TryConvertTimestamp(value_ptr, value_size, dummy_value) == TimestampCastResult::SUCCESS;
|
170
168
|
}
|
171
169
|
case LogicalTypeId::TIME: {
|
172
170
|
idx_t pos;
|
@@ -229,9 +227,8 @@ bool CSVSniffer::CanYouCastIt(const string_t value, const LogicalType &type, con
|
|
229
227
|
throw InternalException("Invalid Physical Type for Decimal Value. Physical Type: " +
|
230
228
|
TypeIdToString(type.InternalType()));
|
231
229
|
}
|
232
|
-
} else {
|
233
|
-
throw InvalidInputException("Decimals can only have ',' and '.' as decimal separators");
|
234
230
|
}
|
231
|
+
throw InvalidInputException("Decimals can only have ',' and '.' as decimal separators");
|
235
232
|
}
|
236
233
|
case LogicalTypeId::VARCHAR:
|
237
234
|
return true;
|
@@ -240,7 +237,7 @@ bool CSVSniffer::CanYouCastIt(const string_t value, const LogicalType &type, con
|
|
240
237
|
Value new_value;
|
241
238
|
string error_message;
|
242
239
|
Value str_value(value);
|
243
|
-
return str_value.TryCastAs(
|
240
|
+
return str_value.TryCastAs(context, type, new_value, &error_message, true);
|
244
241
|
}
|
245
242
|
}
|
246
243
|
}
|
@@ -274,8 +271,15 @@ void CSVSniffer::InitializeDateAndTimeStampDetection(CSVStateMachine &candidate,
|
|
274
271
|
SetDateFormat(candidate, format_candidate.format.back(), sql_type.id());
|
275
272
|
}
|
276
273
|
|
274
|
+
bool ValidSeparator(const string &separator) {
|
275
|
+
// We use https://en.wikipedia.org/wiki/List_of_date_formats_by_country as reference
|
276
|
+
return separator == "-" || separator == "." || separator == "/" || separator == " ";
|
277
|
+
}
|
277
278
|
void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate, const LogicalType &sql_type,
|
278
|
-
const string &separator, string_t &dummy_val) {
|
279
|
+
const string &separator, const string_t &dummy_val) {
|
280
|
+
if (!ValidSeparator(separator)) {
|
281
|
+
return;
|
282
|
+
}
|
279
283
|
// If it is the first time running date/timestamp detection we must initialize the format variables
|
280
284
|
InitializeDateAndTimeStampDetection(candidate, separator, sql_type);
|
281
285
|
// generate date format candidates the first time through
|
@@ -289,7 +293,7 @@ void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate, const
|
|
289
293
|
while (!type_format_candidates.empty()) {
|
290
294
|
// avoid using exceptions for flow control...
|
291
295
|
auto ¤t_format = candidate.dialect_options.date_format[sql_type.id()].GetValue();
|
292
|
-
if (current_format.Parse(dummy_val, result)) {
|
296
|
+
if (current_format.Parse(dummy_val, result, true)) {
|
293
297
|
format_candidates[sql_type.id()].had_match = true;
|
294
298
|
break;
|
295
299
|
}
|
@@ -317,6 +321,76 @@ void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate, const
|
|
317
321
|
}
|
318
322
|
}
|
319
323
|
|
324
|
+
void CSVSniffer::SniffTypes(DataChunk &data_chunk, CSVStateMachine &state_machine,
|
325
|
+
unordered_map<idx_t, vector<LogicalType>> &info_sql_types_candidates,
|
326
|
+
idx_t start_idx_detection) {
|
327
|
+
const idx_t chunk_size = data_chunk.size();
|
328
|
+
HasType has_type;
|
329
|
+
for (idx_t col_idx = 0; col_idx < data_chunk.ColumnCount(); col_idx++) {
|
330
|
+
auto &cur_vector = data_chunk.data[col_idx];
|
331
|
+
D_ASSERT(cur_vector.GetVectorType() == VectorType::FLAT_VECTOR);
|
332
|
+
D_ASSERT(cur_vector.GetType() == LogicalType::VARCHAR);
|
333
|
+
auto vector_data = FlatVector::GetData<string_t>(cur_vector);
|
334
|
+
auto null_mask = FlatVector::Validity(cur_vector);
|
335
|
+
auto &col_type_candidates = info_sql_types_candidates[col_idx];
|
336
|
+
for (idx_t row_idx = start_idx_detection; row_idx < chunk_size; row_idx++) {
|
337
|
+
// col_type_candidates can't be empty since anything in a CSV file should at least be a string
|
338
|
+
// and we validate utf-8 compatibility when creating the type
|
339
|
+
D_ASSERT(!col_type_candidates.empty());
|
340
|
+
auto cur_top_candidate = col_type_candidates.back();
|
341
|
+
// try cast from string to sql_type
|
342
|
+
while (col_type_candidates.size() > 1) {
|
343
|
+
const auto &sql_type = col_type_candidates.back();
|
344
|
+
// try formatting for date types if the user did not specify one and it starts with numeric
|
345
|
+
// values.
|
346
|
+
string separator;
|
347
|
+
// If Value is not Null, Has a numeric date format, and the current investigated candidate is
|
348
|
+
// either a timestamp or a date
|
349
|
+
if (null_mask.RowIsValid(row_idx) && StartsWithNumericDate(separator, vector_data[row_idx]) &&
|
350
|
+
((col_type_candidates.back().id() == LogicalTypeId::TIMESTAMP && !has_type.timestamp) ||
|
351
|
+
(col_type_candidates.back().id() == LogicalTypeId::DATE && !has_type.date))) {
|
352
|
+
DetectDateAndTimeStampFormats(state_machine, sql_type, separator, vector_data[row_idx]);
|
353
|
+
}
|
354
|
+
// try cast from string to sql_type
|
355
|
+
if (sql_type == LogicalType::VARCHAR) {
|
356
|
+
// Nothing to convert it to
|
357
|
+
continue;
|
358
|
+
}
|
359
|
+
if (CanYouCastIt(buffer_manager->context, vector_data[row_idx], sql_type, state_machine.dialect_options,
|
360
|
+
!null_mask.RowIsValid(row_idx), state_machine.options.decimal_separator[0])) {
|
361
|
+
break;
|
362
|
+
}
|
363
|
+
|
364
|
+
if (row_idx != start_idx_detection && cur_top_candidate == LogicalType::BOOLEAN) {
|
365
|
+
// If we thought this was a boolean value (i.e., T,F, True, False) and it is not, we
|
366
|
+
// immediately pop to varchar.
|
367
|
+
while (col_type_candidates.back() != LogicalType::VARCHAR) {
|
368
|
+
col_type_candidates.pop_back();
|
369
|
+
}
|
370
|
+
break;
|
371
|
+
}
|
372
|
+
col_type_candidates.pop_back();
|
373
|
+
}
|
374
|
+
}
|
375
|
+
if (col_type_candidates.back().id() == LogicalTypeId::DATE) {
|
376
|
+
has_type.date = true;
|
377
|
+
}
|
378
|
+
if (col_type_candidates.back().id() == LogicalTypeId::TIMESTAMP) {
|
379
|
+
has_type.timestamp = true;
|
380
|
+
}
|
381
|
+
}
|
382
|
+
}
|
383
|
+
|
384
|
+
// If we have a predefined date/timestamp format we set it
|
385
|
+
void CSVSniffer::SetUserDefinedDateTimeFormat(CSVStateMachine &candidate) {
|
386
|
+
const vector<LogicalTypeId> data_time_formats {LogicalTypeId::DATE, LogicalTypeId::TIMESTAMP};
|
387
|
+
for (auto &date_time_format : data_time_formats) {
|
388
|
+
auto &user_option = options.dialect_options.date_format.at(date_time_format);
|
389
|
+
if (user_option.IsSetByUser()) {
|
390
|
+
SetDateFormat(candidate, user_option.GetValue().format_specifier, date_time_format);
|
391
|
+
}
|
392
|
+
}
|
393
|
+
}
|
320
394
|
void CSVSniffer::DetectTypes() {
|
321
395
|
idx_t min_varchar_cols = max_columns_found + 1;
|
322
396
|
idx_t min_errors = NumericLimits<idx_t>::Maximum();
|
@@ -336,72 +410,36 @@ void CSVSniffer::DetectTypes() {
|
|
336
410
|
|
337
411
|
// Reset candidate for parsing
|
338
412
|
auto candidate = candidate_cc->UpgradeToStringValueScanner();
|
339
|
-
|
413
|
+
SetUserDefinedDateTimeFormat(*candidate->state_machine);
|
340
414
|
// Parse chunk and read csv with info candidate
|
341
415
|
auto &data_chunk = candidate->ParseChunk().ToChunk();
|
342
|
-
|
416
|
+
if (!candidate->error_handler->errors.empty()) {
|
417
|
+
bool break_loop = false;
|
418
|
+
for (auto &errors : candidate->error_handler->errors) {
|
419
|
+
for (auto &error : errors.second) {
|
420
|
+
if (error.type != CSVErrorType::MAXIMUM_LINE_SIZE) {
|
421
|
+
break_loop = true;
|
422
|
+
break;
|
423
|
+
}
|
424
|
+
}
|
425
|
+
}
|
426
|
+
if (break_loop) {
|
427
|
+
continue;
|
428
|
+
}
|
429
|
+
}
|
430
|
+
idx_t start_idx_detection = 0;
|
343
431
|
idx_t chunk_size = data_chunk.size();
|
344
432
|
if (chunk_size > 1 &&
|
345
433
|
(!options.dialect_options.header.IsSetByUser() ||
|
346
434
|
(options.dialect_options.header.IsSetByUser() && options.dialect_options.header.GetValue()))) {
|
347
435
|
// This means we have more than one row, hence we can use the first row to detect if we have a header
|
348
|
-
|
436
|
+
start_idx_detection = 1;
|
349
437
|
}
|
350
438
|
// First line where we start our type detection
|
351
|
-
|
352
|
-
|
353
|
-
for (idx_t col_idx = 0; col_idx < data_chunk.ColumnCount(); col_idx++) {
|
354
|
-
auto &cur_vector = data_chunk.data[col_idx];
|
355
|
-
D_ASSERT(cur_vector.GetVectorType() == VectorType::FLAT_VECTOR);
|
356
|
-
D_ASSERT(cur_vector.GetType() == LogicalType::VARCHAR);
|
357
|
-
auto vector_data = FlatVector::GetData<string_t>(cur_vector);
|
358
|
-
auto null_mask = FlatVector::Validity(cur_vector);
|
359
|
-
auto &col_type_candidates = info_sql_types_candidates[col_idx];
|
360
|
-
for (row_idx = start_idx_detection; row_idx < chunk_size; row_idx++) {
|
361
|
-
// col_type_candidates can't be empty since anything in a CSV file should at least be a string
|
362
|
-
// and we validate utf-8 compatibility when creating the type
|
363
|
-
D_ASSERT(!col_type_candidates.empty());
|
364
|
-
auto cur_top_candidate = col_type_candidates.back();
|
365
|
-
// try cast from string to sql_type
|
366
|
-
while (col_type_candidates.size() > 1) {
|
367
|
-
const auto &sql_type = col_type_candidates.back();
|
368
|
-
// try formatting for date types if the user did not specify one and it starts with numeric
|
369
|
-
// values.
|
370
|
-
string separator;
|
371
|
-
// If Value is not Null, Has a numeric date format, and the current investigated candidate is
|
372
|
-
// either a timestamp or a date
|
373
|
-
if (null_mask.RowIsValid(row_idx) && StartsWithNumericDate(separator, vector_data[row_idx]) &&
|
374
|
-
(col_type_candidates.back().id() == LogicalTypeId::TIMESTAMP ||
|
375
|
-
col_type_candidates.back().id() == LogicalTypeId::DATE)) {
|
376
|
-
DetectDateAndTimeStampFormats(candidate->GetStateMachine(), sql_type, separator,
|
377
|
-
vector_data[row_idx]);
|
378
|
-
}
|
379
|
-
// try cast from string to sql_type
|
380
|
-
if (sql_type == LogicalType::VARCHAR) {
|
381
|
-
// Nothing to convert it to
|
382
|
-
continue;
|
383
|
-
}
|
384
|
-
if (CanYouCastIt(vector_data[row_idx], sql_type, sniffing_state_machine.dialect_options,
|
385
|
-
!null_mask.RowIsValid(row_idx),
|
386
|
-
sniffing_state_machine.options.decimal_separator[0])) {
|
387
|
-
break;
|
388
|
-
} else {
|
389
|
-
if (row_idx != start_idx_detection && cur_top_candidate == LogicalType::BOOLEAN) {
|
390
|
-
// If we thought this was a boolean value (i.e., T,F, True, False) and it is not, we
|
391
|
-
// immediately pop to varchar.
|
392
|
-
while (col_type_candidates.back() != LogicalType::VARCHAR) {
|
393
|
-
col_type_candidates.pop_back();
|
394
|
-
}
|
395
|
-
break;
|
396
|
-
}
|
397
|
-
col_type_candidates.pop_back();
|
398
|
-
}
|
399
|
-
}
|
400
|
-
}
|
401
|
-
}
|
439
|
+
SniffTypes(data_chunk, sniffing_state_machine, info_sql_types_candidates, start_idx_detection);
|
402
440
|
|
441
|
+
// Count the number of varchar columns
|
403
442
|
idx_t varchar_cols = 0;
|
404
|
-
|
405
443
|
for (idx_t col = 0; col < info_sql_types_candidates.size(); col++) {
|
406
444
|
auto &col_type_candidates = info_sql_types_candidates[col];
|
407
445
|
// check number of varchar columns
|
@@ -413,9 +451,10 @@ void CSVSniffer::DetectTypes() {
|
|
413
451
|
|
414
452
|
// it's good if the dialect creates more non-varchar columns, but only if we sacrifice < 30% of
|
415
453
|
// best_num_cols.
|
416
|
-
if (
|
417
|
-
|
418
|
-
|
454
|
+
if (!best_candidate ||
|
455
|
+
(varchar_cols<min_varchar_cols &&static_cast<double>(info_sql_types_candidates.size())>(
|
456
|
+
static_cast<double>(max_columns_found) * 0.7) &&
|
457
|
+
(!options.ignore_errors.GetValue() || candidate->error_handler->errors.size() < min_errors))) {
|
419
458
|
min_errors = candidate->error_handler->errors.size();
|
420
459
|
best_header_row.clear();
|
421
460
|
// we have a new best_options candidate
|
@@ -441,8 +480,9 @@ void CSVSniffer::DetectTypes() {
|
|
441
480
|
}
|
442
481
|
}
|
443
482
|
if (!best_candidate) {
|
444
|
-
|
445
|
-
|
483
|
+
DialectCandidates dialect_candidates(options.dialect_options.state_machine_options);
|
484
|
+
auto error = CSVError::SniffingError(options, dialect_candidates.Print());
|
485
|
+
error_handler->Error(error);
|
446
486
|
}
|
447
487
|
// Assert that it's all good at this point.
|
448
488
|
D_ASSERT(best_candidate && !best_format_candidates.empty());
|
@@ -2,13 +2,12 @@
|
|
2
2
|
#include "duckdb/execution/operator/csv_scanner/csv_casting.hpp"
|
3
3
|
|
4
4
|
namespace duckdb {
|
5
|
-
|
6
5
|
bool CSVSniffer::TryCastVector(Vector &parse_chunk_col, idx_t size, const LogicalType &sql_type) {
|
7
6
|
auto &sniffing_state_machine = best_candidate->GetStateMachine();
|
8
7
|
// try vector-cast from string to sql_type
|
9
|
-
Vector dummy_result(sql_type);
|
8
|
+
Vector dummy_result(sql_type, size);
|
10
9
|
if (!sniffing_state_machine.dialect_options.date_format[LogicalTypeId::DATE].GetValue().Empty() &&
|
11
|
-
sql_type == LogicalTypeId::DATE) {
|
10
|
+
sql_type.id() == LogicalTypeId::DATE) {
|
12
11
|
// use the date format to cast the chunk
|
13
12
|
string error_message;
|
14
13
|
CastParameters parameters(false, &error_message);
|
@@ -17,13 +16,28 @@ bool CSVSniffer::TryCastVector(Vector &parse_chunk_col, idx_t size, const Logica
|
|
17
16
|
dummy_result, size, parameters, line_error);
|
18
17
|
}
|
19
18
|
if (!sniffing_state_machine.dialect_options.date_format[LogicalTypeId::TIMESTAMP].GetValue().Empty() &&
|
20
|
-
sql_type == LogicalTypeId::TIMESTAMP) {
|
19
|
+
sql_type.id() == LogicalTypeId::TIMESTAMP) {
|
21
20
|
// use the timestamp format to cast the chunk
|
22
21
|
string error_message;
|
23
22
|
CastParameters parameters(false, &error_message);
|
24
23
|
return CSVCast::TryCastTimestampVector(sniffing_state_machine.dialect_options.date_format, parse_chunk_col,
|
25
24
|
dummy_result, size, parameters);
|
26
25
|
}
|
26
|
+
if ((sql_type.id() == LogicalTypeId::DOUBLE || sql_type.id() == LogicalTypeId::FLOAT) &&
|
27
|
+
options.decimal_separator == ",") {
|
28
|
+
string error_message;
|
29
|
+
CastParameters parameters(false, &error_message);
|
30
|
+
idx_t line_error;
|
31
|
+
return CSVCast::TryCastFloatingVectorCommaSeparated(options, parse_chunk_col, dummy_result, size, parameters,
|
32
|
+
sql_type, line_error);
|
33
|
+
}
|
34
|
+
if (sql_type.id() == LogicalTypeId::DECIMAL && options.decimal_separator == ",") {
|
35
|
+
string error_message;
|
36
|
+
CastParameters parameters(false, &error_message);
|
37
|
+
idx_t line_error;
|
38
|
+
return CSVCast::TryCastDecimalVectorCommaSeparated(options, parse_chunk_col, dummy_result, size, parameters,
|
39
|
+
sql_type, line_error);
|
40
|
+
}
|
27
41
|
// target type is not varchar: perform a cast
|
28
42
|
string error_message;
|
29
43
|
return VectorOperations::DefaultTryCast(parse_chunk_col, dummy_result, size, &error_message, true);
|
@@ -62,28 +76,29 @@ void CSVSniffer::RefineTypes() {
|
|
62
76
|
const auto &sql_type = col_type_candidates.back();
|
63
77
|
if (TryCastVector(parse_chunk.data[col], parse_chunk.size(), sql_type)) {
|
64
78
|
break;
|
65
|
-
}
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
}
|
72
|
-
break;
|
79
|
+
}
|
80
|
+
if (col_type_candidates.back() == LogicalType::BOOLEAN && is_bool_type) {
|
81
|
+
// If we thought this was a boolean value (i.e., T,F, True, False) and it is not, we
|
82
|
+
// immediately pop to varchar.
|
83
|
+
while (col_type_candidates.back() != LogicalType::VARCHAR) {
|
84
|
+
col_type_candidates.pop_back();
|
73
85
|
}
|
74
|
-
|
86
|
+
break;
|
75
87
|
}
|
88
|
+
col_type_candidates.pop_back();
|
76
89
|
}
|
77
90
|
}
|
78
91
|
// reset parse chunk for the next iteration
|
79
92
|
parse_chunk.Reset();
|
93
|
+
parse_chunk.SetCapacity(CSVReaderOptions::sniff_size);
|
80
94
|
}
|
81
95
|
detected_types.clear();
|
82
96
|
// set sql types
|
83
97
|
for (idx_t column_idx = 0; column_idx < best_sql_types_candidates_per_column_idx.size(); column_idx++) {
|
84
98
|
LogicalType d_type = best_sql_types_candidates_per_column_idx[column_idx].back();
|
85
99
|
if (best_sql_types_candidates_per_column_idx[column_idx].size() ==
|
86
|
-
|
100
|
+
best_candidate->GetStateMachine().options.auto_type_candidates.size() &&
|
101
|
+
default_null_to_varchar) {
|
87
102
|
d_type = LogicalType::VARCHAR;
|
88
103
|
}
|
89
104
|
detected_types.push_back(d_type);
|
@@ -4,7 +4,7 @@ namespace duckdb {
|
|
4
4
|
void CSVSniffer::ReplaceTypes() {
|
5
5
|
auto &sniffing_state_machine = best_candidate->GetStateMachine();
|
6
6
|
manually_set = vector<bool>(detected_types.size(), false);
|
7
|
-
if (sniffing_state_machine.options.sql_type_list.empty()) {
|
7
|
+
if (sniffing_state_machine.options.sql_type_list.empty() || sniffing_state_machine.options.columns_set) {
|
8
8
|
return;
|
9
9
|
}
|
10
10
|
// user-defined types were supplied for certain columns
|