duckdb 0.10.1-dev6.0 → 0.10.1
Sign up to get free protection for your applications and to get access to all the features.
- package/.github/workflows/NodeJS.yml +11 -18
- package/binding.gyp +4 -1
- package/package.json +1 -1
- package/src/database.cpp +1 -0
- package/src/duckdb/extension/icu/icu-strptime.cpp +46 -4
- package/src/duckdb/extension/icu/icu-table-range.cpp +5 -0
- package/src/duckdb/extension/icu/icu-timezone.cpp +28 -4
- package/src/duckdb/extension/json/buffered_json_reader.cpp +6 -5
- package/src/duckdb/extension/json/include/buffered_json_reader.hpp +3 -3
- package/src/duckdb/extension/json/include/json_transform.hpp +2 -0
- package/src/duckdb/extension/json/json_functions/json_create.cpp +6 -0
- package/src/duckdb/extension/json/json_functions/json_transform.cpp +8 -9
- package/src/duckdb/extension/json/json_functions.cpp +1 -2
- package/src/duckdb/extension/json/json_scan.cpp +1 -0
- package/src/duckdb/extension/parquet/column_reader.cpp +17 -1
- package/src/duckdb/extension/parquet/column_writer.cpp +151 -20
- package/src/duckdb/extension/parquet/include/column_writer.hpp +3 -4
- package/src/duckdb/extension/parquet/parquet_extension.cpp +14 -9
- package/src/duckdb/extension/parquet/parquet_timestamp.cpp +10 -0
- package/src/duckdb/extension/parquet/parquet_writer.cpp +4 -0
- package/src/duckdb/src/catalog/catalog.cpp +94 -10
- package/src/duckdb/src/catalog/catalog_entry/duck_table_entry.cpp +9 -5
- package/src/duckdb/src/catalog/catalog_entry/table_catalog_entry.cpp +1 -0
- package/src/duckdb/src/catalog/catalog_entry/ub_duckdb_catalog_entries.cpp +16 -0
- package/src/duckdb/src/catalog/catalog_entry/view_catalog_entry.cpp +28 -0
- package/src/duckdb/src/catalog/default/default_functions.cpp +3 -0
- package/src/duckdb/src/catalog/default/default_views.cpp +3 -3
- package/src/duckdb/src/catalog/default/ub_duckdb_catalog_default_entries.cpp +5 -0
- package/src/duckdb/src/catalog/dependency_catalog_set.cpp +1 -3
- package/src/duckdb/src/catalog/dependency_manager.cpp +2 -5
- package/src/duckdb/src/catalog/ub_duckdb_catalog.cpp +10 -0
- package/src/duckdb/src/common/adbc/adbc.cpp +1 -1
- package/src/duckdb/src/common/adbc/driver_manager.cpp +2 -1
- package/src/duckdb/src/common/adbc/nanoarrow/ub_duckdb_adbc_nanoarrow.cpp +5 -0
- package/src/duckdb/src/common/adbc/ub_duckdb_adbc.cpp +3 -0
- package/src/duckdb/src/common/allocator.cpp +34 -8
- package/src/duckdb/src/common/arrow/appender/fixed_size_list_data.cpp +39 -0
- package/src/duckdb/src/common/arrow/appender/ub_duckdb_common_arrow_appender.cpp +6 -0
- package/src/duckdb/src/common/arrow/appender/union_data.cpp +2 -1
- package/src/duckdb/src/common/arrow/arrow_appender.cpp +5 -5
- package/src/duckdb/src/common/arrow/arrow_converter.cpp +17 -0
- package/src/duckdb/src/common/arrow/ub_duckdb_common_arrow.cpp +4 -0
- package/src/duckdb/src/common/compressed_file_system.cpp +1 -0
- package/src/duckdb/src/common/crypto/ub_duckdb_common_crypto.cpp +2 -0
- package/src/duckdb/src/common/enum_util.cpp +153 -13
- package/src/duckdb/src/common/enums/logical_operator_type.cpp +0 -2
- package/src/duckdb/src/common/enums/physical_operator_type.cpp +2 -2
- package/src/duckdb/src/common/enums/ub_duckdb_common_enums.cpp +12 -0
- package/src/duckdb/src/common/exception/conversion_exception.cpp +23 -0
- package/src/duckdb/src/common/exception.cpp +7 -14
- package/src/duckdb/src/common/extra_type_info.cpp +6 -5
- package/src/duckdb/src/common/gzip_file_system.cpp +5 -4
- package/src/duckdb/src/common/local_file_system.cpp +85 -10
- package/src/duckdb/src/common/operator/cast_operators.cpp +413 -305
- package/src/duckdb/src/common/operator/ub_duckdb_common_operators.cpp +4 -0
- package/src/duckdb/src/common/progress_bar/ub_duckdb_progress_bar.cpp +3 -0
- package/src/duckdb/src/common/re2_regex.cpp +2 -1
- package/src/duckdb/src/common/row_operations/row_heap_scatter.cpp +2 -2
- package/src/duckdb/src/common/row_operations/row_matcher.cpp +1 -0
- package/src/duckdb/src/common/row_operations/row_scatter.cpp +2 -2
- package/src/duckdb/src/common/row_operations/ub_duckdb_row_operations.cpp +9 -0
- package/src/duckdb/src/common/serializer/binary_serializer.cpp +3 -3
- package/src/duckdb/src/common/serializer/ub_duckdb_common_serializer.cpp +7 -0
- package/src/duckdb/src/common/sort/partition_state.cpp +2 -3
- package/src/duckdb/src/common/sort/ub_duckdb_sort.cpp +7 -0
- package/src/duckdb/src/common/string_util.cpp +3 -3
- package/src/duckdb/src/common/types/bit.cpp +7 -6
- package/src/duckdb/src/common/types/blob.cpp +20 -9
- package/src/duckdb/src/common/types/column/column_data_allocator.cpp +8 -6
- package/src/duckdb/src/common/types/column/column_data_collection.cpp +11 -1
- package/src/duckdb/src/common/types/column/column_data_collection_segment.cpp +5 -0
- package/src/duckdb/src/common/types/column/partitioned_column_data.cpp +1 -1
- package/src/duckdb/src/common/types/column/ub_duckdb_common_types_column.cpp +6 -0
- package/src/duckdb/src/common/types/data_chunk.cpp +1 -1
- package/src/duckdb/src/common/types/date.cpp +1 -1
- package/src/duckdb/src/common/types/hugeint.cpp +3 -2
- package/src/duckdb/src/common/types/interval.cpp +1 -1
- package/src/duckdb/src/common/types/list_segment.cpp +2 -1
- package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +3 -9
- package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +7 -7
- package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +10 -27
- package/src/duckdb/src/common/types/row/tuple_data_scatter_gather.cpp +168 -88
- package/src/duckdb/src/common/types/row/ub_duckdb_common_types_row.cpp +11 -0
- package/src/duckdb/src/common/types/selection_vector.cpp +1 -1
- package/src/duckdb/src/common/types/string_heap.cpp +5 -1
- package/src/duckdb/src/common/types/string_type.cpp +18 -4
- package/src/duckdb/src/common/types/time.cpp +4 -2
- package/src/duckdb/src/common/types/timestamp.cpp +32 -6
- package/src/duckdb/src/common/types/ub_duckdb_common_types.cpp +28 -0
- package/src/duckdb/src/common/types/uhugeint.cpp +3 -2
- package/src/duckdb/src/common/types/uuid.cpp +11 -0
- package/src/duckdb/src/common/types/validity_mask.cpp +4 -3
- package/src/duckdb/src/common/types/value.cpp +17 -6
- package/src/duckdb/src/common/types/vector.cpp +243 -68
- package/src/duckdb/src/common/types.cpp +7 -5
- package/src/duckdb/src/common/ub_duckdb_common.cpp +34 -0
- package/src/duckdb/src/common/value_operations/ub_duckdb_value_operations.cpp +2 -0
- package/src/duckdb/src/common/vector_operations/generators.cpp +2 -1
- package/src/duckdb/src/common/vector_operations/vector_cast.cpp +4 -4
- package/src/duckdb/src/common/vector_operations/vector_copy.cpp +2 -2
- package/src/duckdb/src/common/vector_operations/vector_hash.cpp +17 -6
- package/src/duckdb/src/core_functions/aggregate/algebraic/ub_duckdb_aggr_algebraic.cpp +5 -0
- package/src/duckdb/src/core_functions/aggregate/distributive/arg_min_max.cpp +30 -6
- package/src/duckdb/src/core_functions/aggregate/distributive/bitagg.cpp +1 -1
- package/src/duckdb/src/core_functions/aggregate/distributive/bitstring_agg.cpp +12 -5
- package/src/duckdb/src/core_functions/aggregate/distributive/minmax.cpp +2 -2
- package/src/duckdb/src/core_functions/aggregate/distributive/string_agg.cpp +2 -1
- package/src/duckdb/src/core_functions/aggregate/distributive/ub_duckdb_aggr_distributive.cpp +13 -0
- package/src/duckdb/src/core_functions/aggregate/holistic/mode.cpp +2 -1
- package/src/duckdb/src/core_functions/aggregate/holistic/quantile.cpp +2 -9
- package/src/duckdb/src/core_functions/aggregate/holistic/ub_duckdb_aggr_holistic.cpp +5 -0
- package/src/duckdb/src/core_functions/aggregate/nested/ub_duckdb_aggr_nested.cpp +3 -0
- package/src/duckdb/src/core_functions/aggregate/regression/ub_duckdb_aggr_regr.cpp +8 -0
- package/src/duckdb/src/core_functions/function_list.cpp +1 -0
- package/src/duckdb/src/core_functions/scalar/bit/bitstring.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/bit/ub_duckdb_func_bit.cpp +2 -0
- package/src/duckdb/src/core_functions/scalar/blob/ub_duckdb_func_blob.cpp +3 -0
- package/src/duckdb/src/core_functions/scalar/date/date_diff.cpp +8 -0
- package/src/duckdb/src/core_functions/scalar/date/date_part.cpp +22 -3
- package/src/duckdb/src/core_functions/scalar/date/make_date.cpp +29 -7
- package/src/duckdb/src/core_functions/scalar/date/to_interval.cpp +3 -1
- package/src/duckdb/src/core_functions/scalar/date/ub_duckdb_func_date.cpp +12 -0
- package/src/duckdb/src/core_functions/scalar/debug/ub_duckdb_func_debug.cpp +2 -0
- package/src/duckdb/src/core_functions/scalar/enum/ub_duckdb_func_enum.cpp +2 -0
- package/src/duckdb/src/core_functions/scalar/generic/ub_duckdb_func_generic.cpp +9 -0
- package/src/duckdb/src/core_functions/scalar/list/array_slice.cpp +12 -8
- package/src/duckdb/src/core_functions/scalar/list/list_aggregates.cpp +2 -1
- package/src/duckdb/src/core_functions/scalar/list/list_reduce.cpp +6 -5
- package/src/duckdb/src/core_functions/scalar/list/list_sort.cpp +5 -3
- package/src/duckdb/src/core_functions/scalar/list/list_value.cpp +28 -12
- package/src/duckdb/src/core_functions/scalar/list/ub_duckdb_func_list.cpp +11 -0
- package/src/duckdb/src/core_functions/scalar/map/map.cpp +129 -160
- package/src/duckdb/src/core_functions/scalar/map/ub_duckdb_func_map_nested.cpp +8 -0
- package/src/duckdb/src/core_functions/scalar/math/numeric.cpp +19 -16
- package/src/duckdb/src/core_functions/scalar/math/ub_duckdb_func_math.cpp +1 -0
- package/src/duckdb/src/core_functions/scalar/operators/bitwise.cpp +4 -4
- package/src/duckdb/src/core_functions/scalar/operators/ub_duckdb_func_ops.cpp +1 -0
- package/src/duckdb/src/core_functions/scalar/random/ub_duckdb_func_random.cpp +3 -0
- package/src/duckdb/src/core_functions/scalar/string/hex.cpp +2 -1
- package/src/duckdb/src/core_functions/scalar/string/pad.cpp +2 -2
- package/src/duckdb/src/core_functions/scalar/string/repeat.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/string/replace.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/string/string_split.cpp +2 -1
- package/src/duckdb/src/core_functions/scalar/string/translate.cpp +1 -1
- package/src/duckdb/src/core_functions/scalar/string/ub_duckdb_func_string.cpp +26 -0
- package/src/duckdb/src/core_functions/scalar/struct/ub_duckdb_func_struct.cpp +3 -0
- package/src/duckdb/src/core_functions/scalar/union/ub_duckdb_func_union.cpp +4 -0
- package/src/duckdb/src/core_functions/ub_duckdb_core_functions.cpp +3 -0
- package/src/duckdb/src/execution/adaptive_filter.cpp +1 -1
- package/src/duckdb/src/execution/aggregate_hashtable.cpp +1 -1
- package/src/duckdb/src/execution/column_binding_resolver.cpp +7 -1
- package/src/duckdb/src/execution/expression_executor/execute_case.cpp +2 -2
- package/src/duckdb/src/execution/expression_executor/execute_cast.cpp +2 -0
- package/src/duckdb/src/execution/expression_executor/execute_function.cpp +2 -2
- package/src/duckdb/src/execution/expression_executor/execute_operator.cpp +1 -1
- package/src/duckdb/src/execution/expression_executor/ub_duckdb_expression_executor.cpp +11 -0
- package/src/duckdb/src/execution/expression_executor.cpp +5 -2
- package/src/duckdb/src/execution/index/art/art.cpp +12 -6
- package/src/duckdb/src/execution/index/art/art_key.cpp +3 -3
- package/src/duckdb/src/execution/index/art/leaf.cpp +2 -2
- package/src/duckdb/src/execution/index/art/node16.cpp +2 -2
- package/src/duckdb/src/execution/index/art/node256.cpp +3 -3
- package/src/duckdb/src/execution/index/art/node48.cpp +5 -5
- package/src/duckdb/src/execution/index/art/prefix.cpp +1 -1
- package/src/duckdb/src/execution/index/art/ub_duckdb_art_index_execution.cpp +12 -0
- package/src/duckdb/src/execution/index/art/ub_duckdb_execution_index_art.cpp +11 -0
- package/src/duckdb/src/execution/index/fixed_size_buffer.cpp +6 -5
- package/src/duckdb/src/execution/index/ub_duckdb_execution_index.cpp +3 -0
- package/src/duckdb/src/execution/nested_loop_join/ub_duckdb_nested_loop_join.cpp +3 -0
- package/src/duckdb/src/execution/operator/aggregate/aggregate_object.cpp +1 -1
- package/src/duckdb/src/execution/operator/aggregate/physical_hash_aggregate.cpp +3 -4
- package/src/duckdb/src/execution/operator/aggregate/physical_streaming_window.cpp +0 -1
- package/src/duckdb/src/execution/operator/aggregate/physical_ungrouped_aggregate.cpp +3 -4
- package/src/duckdb/src/execution/operator/aggregate/ub_duckdb_operator_aggregate.cpp +9 -0
- 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 +8 -3
- package/src/duckdb/src/execution/operator/csv_scanner/buffer_manager/csv_file_handle.cpp +1 -1
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/base_scanner.cpp +5 -5
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/column_count_scanner.cpp +2 -3
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/scanner_boundary.cpp +5 -1
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/skip_scanner.cpp +2 -2
- package/src/duckdb/src/execution/operator/csv_scanner/scanner/string_value_scanner.cpp +151 -79
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/csv_sniffer.cpp +11 -6
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp +27 -6
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp +71 -18
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp +22 -11
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_refinement.cpp +6 -4
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_replacement.cpp +5 -3
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/ub_duckdb_operator_csv_sniffer.cpp +7 -0
- package/src/duckdb/src/execution/operator/csv_scanner/state_machine/csv_state_machine.cpp +3 -3
- package/src/duckdb/src/execution/operator/csv_scanner/state_machine/csv_state_machine_cache.cpp +30 -5
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/csv_file_scanner.cpp +6 -2
- package/src/duckdb/src/execution/operator/csv_scanner/table_function/global_csv_state.cpp +47 -46
- package/src/duckdb/src/execution/operator/csv_scanner/ub_duckdb_operator_csv_scanner.cpp +10 -0
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_error.cpp +102 -54
- package/src/duckdb/src/execution/operator/csv_scanner/util/csv_reader_options.cpp +8 -1
- package/src/duckdb/src/execution/operator/filter/ub_duckdb_operator_filter.cpp +2 -0
- package/src/duckdb/src/execution/operator/helper/physical_limit.cpp +54 -36
- package/src/duckdb/src/execution/operator/helper/physical_limit_percent.cpp +56 -32
- package/src/duckdb/src/execution/operator/helper/physical_streaming_limit.cpp +9 -13
- package/src/duckdb/src/execution/operator/helper/physical_transaction.cpp +12 -0
- package/src/duckdb/src/execution/operator/helper/physical_verify_vector.cpp +221 -0
- package/src/duckdb/src/execution/operator/helper/ub_duckdb_operator_helper.cpp +18 -0
- package/src/duckdb/src/execution/operator/join/physical_asof_join.cpp +1 -0
- package/src/duckdb/src/execution/operator/join/physical_hash_join.cpp +23 -8
- package/src/duckdb/src/execution/operator/join/physical_range_join.cpp +8 -3
- package/src/duckdb/src/execution/operator/join/ub_duckdb_operator_join.cpp +16 -0
- package/src/duckdb/src/execution/operator/order/physical_order.cpp +2 -3
- package/src/duckdb/src/execution/operator/order/physical_top_n.cpp +2 -7
- package/src/duckdb/src/execution/operator/order/ub_duckdb_operator_order.cpp +3 -0
- package/src/duckdb/src/execution/operator/persistent/physical_batch_copy_to_file.cpp +451 -55
- package/src/duckdb/src/execution/operator/persistent/physical_batch_insert.cpp +312 -150
- package/src/duckdb/src/execution/operator/persistent/physical_copy_to_file.cpp +200 -75
- package/src/duckdb/src/execution/operator/persistent/physical_delete.cpp +1 -0
- package/src/duckdb/src/execution/operator/persistent/physical_insert.cpp +6 -5
- package/src/duckdb/src/execution/operator/persistent/ub_duckdb_operator_persistent.cpp +10 -0
- package/src/duckdb/src/execution/operator/projection/physical_pivot.cpp +3 -2
- package/src/duckdb/src/execution/operator/projection/ub_duckdb_operator_projection.cpp +5 -0
- package/src/duckdb/src/execution/operator/scan/ub_duckdb_operator_scan.cpp +7 -0
- package/src/duckdb/src/execution/operator/schema/ub_duckdb_operator_schema.cpp +12 -0
- package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +25 -0
- package/src/duckdb/src/execution/operator/set/ub_duckdb_operator_set.cpp +4 -0
- package/src/duckdb/src/execution/perfect_aggregate_hashtable.cpp +4 -4
- package/src/duckdb/src/execution/physical_plan/plan_aggregate.cpp +2 -2
- package/src/duckdb/src/execution/physical_plan/plan_comparison_join.cpp +2 -2
- package/src/duckdb/src/execution/physical_plan/plan_copy_to_file.cpp +7 -17
- package/src/duckdb/src/execution/physical_plan/plan_distinct.cpp +10 -0
- package/src/duckdb/src/execution/physical_plan/plan_insert.cpp +7 -0
- package/src/duckdb/src/execution/physical_plan/plan_limit.cpp +45 -13
- package/src/duckdb/src/execution/physical_plan/ub_duckdb_physical_plan.cpp +44 -0
- package/src/duckdb/src/execution/physical_plan_generator.cpp +5 -3
- package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +13 -12
- package/src/duckdb/src/execution/ub_duckdb_execution.cpp +15 -0
- package/src/duckdb/src/execution/window_executor.cpp +71 -61
- package/src/duckdb/src/execution/window_segment_tree.cpp +6 -6
- package/src/duckdb/src/extension_forward_decl/icu.cpp +59 -0
- package/src/duckdb/src/function/aggregate/algebraic/ub_duckdb_aggr_algebraic.cpp +5 -0
- package/src/duckdb/src/function/aggregate/distributive/first.cpp +2 -2
- package/src/duckdb/src/function/aggregate/distributive/ub_duckdb_aggr_distr.cpp +3 -0
- package/src/duckdb/src/function/aggregate/holistic/ub_duckdb_aggr_holistic.cpp +5 -0
- package/src/duckdb/src/function/aggregate/nested/ub_duckdb_aggr_nested.cpp +3 -0
- package/src/duckdb/src/function/aggregate/regression/ub_duckdb_aggr_regr.cpp +8 -0
- package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp +3 -2
- package/src/duckdb/src/function/aggregate/ub_duckdb_func_aggr.cpp +3 -0
- package/src/duckdb/src/function/cast/array_casts.cpp +2 -4
- package/src/duckdb/src/function/cast/bit_cast.cpp +13 -13
- package/src/duckdb/src/function/cast/cast_function_set.cpp +2 -0
- package/src/duckdb/src/function/cast/decimal_cast.cpp +38 -44
- package/src/duckdb/src/function/cast/default_casts.cpp +5 -2
- package/src/duckdb/src/function/cast/enum_casts.cpp +5 -5
- package/src/duckdb/src/function/cast/list_casts.cpp +24 -14
- package/src/duckdb/src/function/cast/string_cast.cpp +48 -30
- package/src/duckdb/src/function/cast/struct_cast.cpp +2 -2
- package/src/duckdb/src/function/cast/time_casts.cpp +12 -0
- package/src/duckdb/src/function/cast/ub_duckdb_func_cast.cpp +17 -0
- package/src/duckdb/src/function/cast/union/ub_duckdb_union_cast.cpp +2 -0
- package/src/duckdb/src/function/cast/union_casts.cpp +13 -15
- package/src/duckdb/src/function/cast/vector_cast_helpers.cpp +1 -1
- package/src/duckdb/src/function/cast_rules.cpp +2 -1
- package/src/duckdb/src/function/pragma/ub_duckdb_func_pragma.cpp +3 -0
- package/src/duckdb/src/function/scalar/bit/ub_duckdb_func_bit.cpp +2 -0
- package/src/duckdb/src/function/scalar/blob/ub_duckdb_func_blob.cpp +3 -0
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_integral.cpp +7 -6
- package/src/duckdb/src/function/scalar/compressed_materialization/compress_string.cpp +3 -3
- package/src/duckdb/src/function/scalar/compressed_materialization/ub_duckdb_func_compressed_materialization.cpp +3 -0
- package/src/duckdb/src/function/scalar/date/ub_duckdb_func_date.cpp +12 -0
- package/src/duckdb/src/function/scalar/enum/ub_duckdb_func_enum.cpp +2 -0
- package/src/duckdb/src/function/scalar/generic/ub_duckdb_func_generic.cpp +8 -0
- package/src/duckdb/src/function/scalar/generic/ub_duckdb_func_generic_main.cpp +2 -0
- package/src/duckdb/src/function/scalar/list/list_resize.cpp +3 -1
- package/src/duckdb/src/function/scalar/list/list_zip.cpp +3 -4
- package/src/duckdb/src/function/scalar/list/ub_duckdb_func_list.cpp +11 -0
- package/src/duckdb/src/function/scalar/list/ub_duckdb_func_list_nested.cpp +5 -0
- package/src/duckdb/src/function/scalar/map/ub_duckdb_func_map_nested.cpp +7 -0
- package/src/duckdb/src/function/scalar/math/ub_duckdb_func_math.cpp +4 -0
- package/src/duckdb/src/function/scalar/nested_functions.cpp +7 -3
- package/src/duckdb/src/function/scalar/operators/arithmetic.cpp +1 -1
- package/src/duckdb/src/function/scalar/operators/multiply.cpp +4 -2
- package/src/duckdb/src/function/scalar/operators/subtract.cpp +9 -3
- package/src/duckdb/src/function/scalar/operators/ub_duckdb_func_ops.cpp +6 -0
- package/src/duckdb/src/function/scalar/operators/ub_duckdb_func_ops_main.cpp +5 -0
- package/src/duckdb/src/function/scalar/sequence/ub_duckdb_func_seq.cpp +2 -0
- package/src/duckdb/src/function/scalar/strftime_format.cpp +21 -20
- package/src/duckdb/src/function/scalar/string/like.cpp +14 -3
- package/src/duckdb/src/function/scalar/string/regexp/regexp_extract_all.cpp +4 -2
- package/src/duckdb/src/function/scalar/string/regexp/ub_duckdb_func_string_regexp.cpp +3 -0
- package/src/duckdb/src/function/scalar/string/regexp.cpp +6 -4
- package/src/duckdb/src/function/scalar/string/suffix.cpp +1 -1
- package/src/duckdb/src/function/scalar/string/ub_duckdb_func_string.cpp +31 -0
- package/src/duckdb/src/function/scalar/string/ub_duckdb_func_string_main.cpp +12 -0
- package/src/duckdb/src/function/scalar/struct/ub_duckdb_func_struct.cpp +4 -0
- package/src/duckdb/src/function/scalar/struct/ub_duckdb_func_struct_main.cpp +2 -0
- package/src/duckdb/src/function/scalar/system/ub_duckdb_func_system.cpp +2 -0
- package/src/duckdb/src/function/scalar/ub_duckdb_func_scalar.cpp +9 -0
- package/src/duckdb/src/function/scalar/union/ub_duckdb_func_union.cpp +4 -0
- package/src/duckdb/src/function/table/arrow/arrow_array_scan_state.cpp +28 -2
- package/src/duckdb/src/function/table/arrow/ub_duckdb_arrow_conversion.cpp +2 -0
- package/src/duckdb/src/function/table/arrow.cpp +23 -6
- package/src/duckdb/src/function/table/arrow_conversion.cpp +75 -33
- package/src/duckdb/src/function/table/copy_csv.cpp +8 -3
- package/src/duckdb/src/function/table/range.cpp +5 -0
- package/src/duckdb/src/function/table/read_csv.cpp +9 -8
- package/src/duckdb/src/function/table/read_file.cpp +1 -1
- package/src/duckdb/src/function/table/sniff_csv.cpp +5 -5
- package/src/duckdb/src/function/table/system/duckdb_columns.cpp +6 -2
- package/src/duckdb/src/function/table/system/duckdb_secrets.cpp +5 -1
- package/src/duckdb/src/function/table/system/duckdb_sequences.cpp +3 -1
- package/src/duckdb/src/function/table/system/duckdb_settings.cpp +13 -1
- package/src/duckdb/src/function/table/system/test_all_types.cpp +64 -0
- package/src/duckdb/src/function/table/system/ub_duckdb_table_func_system.cpp +23 -0
- package/src/duckdb/src/function/table/ub_duckdb_func_table.cpp +16 -0
- package/src/duckdb/src/function/table/version/pragma_version.cpp +11 -2
- package/src/duckdb/src/function/table/version/ub_duckdb_func_table_version.cpp +2 -0
- package/src/duckdb/src/function/ub_duckdb_function.cpp +14 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog.hpp +11 -1
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry/view_catalog_entry.hpp +2 -0
- package/src/duckdb/src/include/duckdb/catalog/catalog_entry.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/allocator.hpp +8 -11
- package/src/duckdb/src/include/duckdb/common/arrow/appender/enum_data.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/arrow/appender/fixed_size_list_data.hpp +14 -0
- 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 +1 -1
- package/src/duckdb/src/include/duckdb/common/arrow/appender/varchar_data.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/bitpacking.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/bswap.hpp +6 -2
- package/src/duckdb/src/include/duckdb/common/enum_util.hpp +32 -0
- package/src/duckdb/src/include/duckdb/common/enums/catalog_lookup_behavior.hpp +21 -0
- package/src/duckdb/src/include/duckdb/common/enums/logical_operator_type.hpp +0 -1
- package/src/duckdb/src/include/duckdb/common/enums/physical_operator_type.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/enums/prepared_statement_mode.hpp +20 -0
- package/src/duckdb/src/include/duckdb/common/enums/statement_type.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/exception/conversion_exception.hpp +6 -0
- package/src/duckdb/src/include/duckdb/common/exception/parser_exception.hpp +4 -0
- package/src/duckdb/src/include/duckdb/common/exception.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/extra_type_info.hpp +3 -3
- package/src/duckdb/src/include/duckdb/common/file_opener.hpp +6 -5
- package/src/duckdb/src/include/duckdb/common/file_system.hpp +4 -2
- package/src/duckdb/src/include/duckdb/common/helper.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/limits.hpp +2 -2
- package/src/duckdb/src/include/duckdb/common/local_file_system.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/numeric_utils.hpp +64 -0
- package/src/duckdb/src/include/duckdb/common/operator/cast_operators.hpp +34 -33
- package/src/duckdb/src/include/duckdb/common/operator/decimal_cast_operators.hpp +150 -124
- package/src/duckdb/src/include/duckdb/common/operator/integer_cast_operator.hpp +5 -5
- package/src/duckdb/src/include/duckdb/common/radix.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/serializer/deserializer.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/sort/duckdb_pdqsort.hpp +4 -4
- package/src/duckdb/src/include/duckdb/common/types/bit.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/blob.hpp +4 -1
- package/src/duckdb/src/include/duckdb/common/types/cast_helpers.hpp +15 -13
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_allocator.hpp +5 -0
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_collection.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/types/column/column_data_collection_segment.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/types/column/partitioned_column_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +4 -1
- package/src/duckdb/src/include/duckdb/common/types/selection_vector.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/types/string_heap.hpp +2 -0
- package/src/duckdb/src/include/duckdb/common/types/string_type.hpp +11 -4
- package/src/duckdb/src/include/duckdb/common/types/time.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types/timestamp.hpp +7 -2
- package/src/duckdb/src/include/duckdb/common/types/uuid.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/types/value.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/vector.hpp +40 -7
- package/src/duckdb/src/include/duckdb/common/types/vector_buffer.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/types.hpp +1 -1
- package/src/duckdb/src/include/duckdb/common/vector_operations/general_cast.hpp +12 -4
- package/src/duckdb/src/include/duckdb/common/vector_operations/generic_executor.hpp +6 -6
- package/src/duckdb/src/include/duckdb/common/vector_operations/vector_operations.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/windows_undefs.hpp +4 -0
- package/src/duckdb/src/include/duckdb/core_functions/aggregate/regression/regr_count.hpp +1 -1
- package/src/duckdb/src/include/duckdb/core_functions/scalar/list_functions.hpp +9 -0
- package/src/duckdb/src/include/duckdb/execution/column_binding_resolver.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/executor.hpp +10 -0
- package/src/duckdb/src/include/duckdb/execution/expression_executor_state.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/base_scanner.hpp +262 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/column_count_scanner.hpp +70 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_buffer.hpp +103 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_buffer_manager.hpp +74 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_casting.hpp +154 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_error.hpp +130 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_file_handle.hpp +60 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_file_scanner.hpp +70 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_option.hpp +155 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_reader_options.hpp +166 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_sniffer.hpp +191 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state.hpp +30 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state_machine.hpp +99 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/csv_state_machine_cache.hpp +91 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/global_csv_state.hpp +80 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/quote_rules.hpp +21 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/scanner_boundary.hpp +93 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/skip_scanner.hpp +60 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/state_machine_options.hpp +35 -0
- package/src/duckdb/src/include/duckdb/execution/operator/csv_scanner/string_value_scanner.hpp +200 -0
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_limit.hpp +13 -10
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_limit_percent.hpp +5 -11
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_streaming_limit.hpp +4 -6
- package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_verify_vector.hpp +51 -0
- package/src/duckdb/src/include/duckdb/execution/operator/join/physical_hash_join.hpp +3 -0
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/batch_memory_manager.hpp +165 -0
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/batch_task_manager.hpp +48 -0
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_batch_copy_to_file.hpp +10 -17
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_batch_insert.hpp +4 -0
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_to_file.hpp +2 -0
- package/src/duckdb/src/include/duckdb/execution/physical_operator_states.hpp +10 -6
- package/src/duckdb/src/include/duckdb/execution/physical_plan_generator.hpp +0 -2
- package/src/duckdb/src/include/duckdb/execution/window_executor.hpp +2 -1
- package/src/duckdb/src/include/duckdb/execution/window_segment_tree.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/cast/cast_function_set.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/cast/default_casts.hpp +14 -5
- package/src/duckdb/src/include/duckdb/function/cast/vector_cast_helpers.hpp +27 -43
- package/src/duckdb/src/include/duckdb/function/compression_function.hpp +4 -4
- package/src/duckdb/src/include/duckdb/function/copy_function.hpp +3 -3
- package/src/duckdb/src/include/duckdb/function/function.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/scalar/list/contains_or_position.hpp +1 -0
- package/src/duckdb/src/include/duckdb/function/scalar/nested_functions.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/scalar_function.hpp +1 -1
- package/src/duckdb/src/include/duckdb/function/table/arrow.hpp +10 -4
- package/src/duckdb/src/include/duckdb/function/table/read_csv.hpp +8 -6
- package/src/duckdb/src/include/duckdb/function/table_function.hpp +3 -3
- package/src/duckdb/src/include/duckdb/main/attached_database.hpp +3 -0
- package/src/duckdb/src/include/duckdb/main/capi/cast/from_decimal.hpp +6 -4
- package/src/duckdb/src/include/duckdb/main/capi/cast/to_decimal.hpp +17 -10
- package/src/duckdb/src/include/duckdb/main/client_config.hpp +2 -0
- package/src/duckdb/src/include/duckdb/main/client_context.hpp +17 -3
- package/src/duckdb/src/include/duckdb/main/client_context_file_opener.hpp +2 -2
- package/src/duckdb/src/include/duckdb/main/client_context_state.hpp +20 -0
- package/src/duckdb/src/include/duckdb/main/client_data.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/database.hpp +3 -2
- package/src/duckdb/src/include/duckdb/main/database_manager.hpp +2 -1
- package/src/duckdb/src/include/duckdb/main/extension/generated_extension_loader.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/extension_entries.hpp +230 -199
- package/src/duckdb/src/include/duckdb/main/extension_helper.hpp +18 -0
- package/src/duckdb/src/include/duckdb/main/relation/read_csv_relation.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/relation/table_function_relation.hpp +2 -0
- package/src/duckdb/src/include/duckdb/main/relation.hpp +1 -1
- package/src/duckdb/src/include/duckdb/main/secret/secret_manager.hpp +4 -0
- package/src/duckdb/src/include/duckdb/main/settings.hpp +54 -10
- package/src/duckdb/src/include/duckdb/optimizer/join_order/relation_manager.hpp +2 -1
- package/src/duckdb/src/include/duckdb/optimizer/rule/ordered_aggregate_optimizer.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parallel/concurrentqueue.hpp +21 -5
- package/src/duckdb/src/include/duckdb/parallel/event.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parallel/executor_task.hpp +37 -0
- package/src/duckdb/src/include/duckdb/parallel/interrupt.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parallel/pipeline.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parallel/task.hpp +0 -20
- package/src/duckdb/src/include/duckdb/parallel/task_scheduler.hpp +4 -2
- package/src/duckdb/src/include/duckdb/parser/expression/window_expression.hpp +10 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_info.hpp +2 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/alter_table_info.hpp +0 -24
- package/src/duckdb/src/include/duckdb/parser/parsed_data/comment_on_column_info.hpp +46 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/create_view_info.hpp +2 -0
- package/src/duckdb/src/include/duckdb/parser/parsed_data/extra_drop_info.hpp +1 -1
- package/src/duckdb/src/include/duckdb/parser/parsed_data/parse_info.hpp +3 -2
- package/src/duckdb/src/include/duckdb/parser/tableref/pivotref.hpp +3 -3
- package/src/duckdb/src/include/duckdb/parser/transformer.hpp +3 -3
- package/src/duckdb/src/include/duckdb/planner/binder.hpp +11 -4
- package/src/duckdb/src/include/duckdb/planner/bound_result_modifier.hpp +59 -23
- package/src/duckdb/src/include/duckdb/planner/expression.hpp +1 -0
- package/src/duckdb/src/include/duckdb/planner/expression_binder/column_alias_binder.hpp +2 -2
- package/src/duckdb/src/include/duckdb/planner/expression_iterator.hpp +11 -3
- package/src/duckdb/src/include/duckdb/planner/extension_callback.hpp +6 -0
- package/src/duckdb/src/include/duckdb/planner/operator/list.hpp +0 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_insert.hpp +1 -1
- package/src/duckdb/src/include/duckdb/planner/operator/logical_limit.hpp +5 -9
- package/src/duckdb/src/include/duckdb/planner/subquery/rewrite_correlated_expressions.hpp +0 -15
- package/src/duckdb/src/include/duckdb/storage/arena_allocator.hpp +5 -0
- package/src/duckdb/src/include/duckdb/storage/buffer/buffer_pool.hpp +40 -5
- package/src/duckdb/src/include/duckdb/storage/compression/alp/algorithm/alp.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_analyze.hpp +5 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_compress.hpp +4 -4
- package/src/duckdb/src/include/duckdb/storage/compression/alp/alp_utils.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/algorithm/alprd.hpp +10 -8
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_analyze.hpp +5 -1
- package/src/duckdb/src/include/duckdb/storage/compression/alprd/alprd_compress.hpp +3 -3
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/algorithm/bit_reader.hpp +11 -10
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/algorithm/bit_utils.hpp +3 -1
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/algorithm/chimp128.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/algorithm/leading_zero_buffer.hpp +5 -3
- package/src/duckdb/src/include/duckdb/storage/compression/chimp/chimp_scan.hpp +2 -1
- package/src/duckdb/src/include/duckdb/storage/data_pointer.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/data_table.hpp +3 -1
- package/src/duckdb/src/include/duckdb/storage/index.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/partial_block_manager.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/standard_buffer_manager.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/storage_manager.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/append_state.hpp +0 -2
- package/src/duckdb/src/include/duckdb/storage/table/column_checkpoint_state.hpp +1 -1
- package/src/duckdb/src/include/duckdb/storage/table/column_data.hpp +5 -3
- package/src/duckdb/src/include/duckdb/storage/table/column_segment.hpp +2 -2
- package/src/duckdb/src/include/duckdb/storage/table/row_group.hpp +5 -0
- package/src/duckdb/src/include/duckdb/storage/table/row_group_collection.hpp +9 -2
- package/src/duckdb/src/include/duckdb/storage/table/scan_state.hpp +2 -6
- package/src/duckdb/src/include/duckdb/storage/table/segment_tree.hpp +3 -3
- package/src/duckdb/src/include/duckdb/storage/temporary_file_manager.hpp +169 -0
- package/src/duckdb/src/include/duckdb/transaction/duck_transaction_manager.hpp +11 -1
- package/src/duckdb/src/include/duckdb/transaction/meta_transaction.hpp +6 -1
- package/src/duckdb/src/include/duckdb/transaction/transaction.hpp +1 -1
- package/src/duckdb/src/include/duckdb.h +119 -67
- package/src/duckdb/src/main/appender.cpp +2 -1
- package/src/duckdb/src/main/attached_database.cpp +49 -27
- package/src/duckdb/src/main/capi/appender-c.cpp +1 -1
- package/src/duckdb/src/main/capi/cast/ub_duckdb_main_capi_cast.cpp +3 -0
- package/src/duckdb/src/main/capi/cast/utils-c.cpp +1 -1
- package/src/duckdb/src/main/capi/data_chunk-c.cpp +9 -1
- package/src/duckdb/src/main/capi/datetime-c.cpp +14 -8
- package/src/duckdb/src/main/capi/duckdb_value-c.cpp +29 -2
- package/src/duckdb/src/main/capi/helper-c.cpp +2 -0
- package/src/duckdb/src/main/capi/hugeint-c.cpp +2 -1
- package/src/duckdb/src/main/capi/logical_types-c.cpp +35 -1
- package/src/duckdb/src/main/capi/result-c.cpp +9 -0
- package/src/duckdb/src/main/capi/ub_duckdb_main_capi.cpp +19 -0
- package/src/duckdb/src/main/chunk_scan_state/ub_duckdb_main_chunk_scan_state.cpp +2 -0
- package/src/duckdb/src/main/client_context.cpp +133 -33
- package/src/duckdb/src/main/client_context_file_opener.cpp +8 -7
- package/src/duckdb/src/main/config.cpp +2 -0
- package/src/duckdb/src/main/connection_manager.cpp +8 -0
- package/src/duckdb/src/main/database.cpp +13 -4
- package/src/duckdb/src/main/database_manager.cpp +10 -1
- package/src/duckdb/src/main/extension/extension_helper.cpp +8 -5
- package/src/duckdb/src/main/extension/extension_install.cpp +1 -1
- package/src/duckdb/src/main/extension/ub_duckdb_main_extension.cpp +6 -0
- package/src/duckdb/src/main/prepared_statement_data.cpp +23 -6
- package/src/duckdb/src/main/query_profiler.cpp +9 -7
- package/src/duckdb/src/main/relation/read_csv_relation.cpp +17 -12
- package/src/duckdb/src/main/relation/ub_duckdb_main_relation.cpp +26 -0
- package/src/duckdb/src/main/relation/value_relation.cpp +2 -0
- package/src/duckdb/src/main/secret/secret.cpp +1 -1
- package/src/duckdb/src/main/secret/secret_manager.cpp +41 -8
- package/src/duckdb/src/main/secret/secret_storage.cpp +8 -2
- package/src/duckdb/src/main/settings/settings.cpp +42 -2
- package/src/duckdb/src/main/settings/ub_duckdb_main_settings.cpp +2 -0
- package/src/duckdb/src/main/ub_duckdb_main.cpp +25 -0
- package/src/duckdb/src/optimizer/compressed_materialization/ub_duckdb_optimizer_compressed_materialization.cpp +4 -0
- package/src/duckdb/src/optimizer/filter_combiner.cpp +20 -14
- package/src/duckdb/src/optimizer/in_clause_rewriter.cpp +5 -1
- package/src/duckdb/src/optimizer/join_order/relation_manager.cpp +23 -11
- package/src/duckdb/src/optimizer/join_order/ub_duckdb_optimizer_join_order.cpp +12 -0
- package/src/duckdb/src/optimizer/matcher/ub_duckdb_optimizer_matcher.cpp +2 -0
- package/src/duckdb/src/optimizer/pullup/ub_duckdb_optimizer_pullup.cpp +6 -0
- package/src/duckdb/src/optimizer/pushdown/pushdown_limit.cpp +1 -1
- package/src/duckdb/src/optimizer/pushdown/ub_duckdb_optimizer_pushdown.cpp +12 -0
- package/src/duckdb/src/optimizer/remove_unused_columns.cpp +7 -6
- package/src/duckdb/src/optimizer/rule/ordered_aggregate_optimizer.cpp +8 -6
- package/src/duckdb/src/optimizer/rule/regex_optimizations.cpp +1 -1
- package/src/duckdb/src/optimizer/rule/ub_duckdb_optimizer_rules.cpp +16 -0
- package/src/duckdb/src/optimizer/statistics/expression/propagate_cast.cpp +71 -1
- package/src/duckdb/src/optimizer/statistics/expression/ub_duckdb_optimizer_statistics_expr.cpp +11 -0
- package/src/duckdb/src/optimizer/statistics/operator/propagate_join.cpp +1 -1
- package/src/duckdb/src/optimizer/statistics/operator/propagate_limit.cpp +5 -1
- package/src/duckdb/src/optimizer/statistics/operator/ub_duckdb_optimizer_statistics_op.cpp +11 -0
- package/src/duckdb/src/optimizer/topn_optimizer.cpp +12 -11
- package/src/duckdb/src/optimizer/ub_duckdb_optimizer.cpp +20 -0
- package/src/duckdb/src/parallel/executor.cpp +8 -19
- package/src/duckdb/src/parallel/executor_task.cpp +6 -2
- package/src/duckdb/src/parallel/pipeline.cpp +12 -6
- package/src/duckdb/src/parallel/pipeline_executor.cpp +1 -1
- package/src/duckdb/src/parallel/pipeline_finish_event.cpp +2 -2
- package/src/duckdb/src/parallel/pipeline_initialize_event.cpp +1 -2
- package/src/duckdb/src/parallel/task_scheduler.cpp +15 -8
- package/src/duckdb/src/parallel/ub_duckdb_parallel.cpp +15 -0
- package/src/duckdb/src/parser/constraints/ub_duckdb_constraints.cpp +5 -0
- package/src/duckdb/src/parser/expression/ub_duckdb_expression.cpp +18 -0
- package/src/duckdb/src/parser/parsed_data/alter_table_info.cpp +0 -18
- package/src/duckdb/src/parser/parsed_data/comment_on_column_info.cpp +44 -0
- package/src/duckdb/src/parser/parsed_data/create_view_info.cpp +1 -0
- package/src/duckdb/src/parser/parsed_data/extra_drop_info.cpp +2 -0
- package/src/duckdb/src/parser/parsed_data/ub_duckdb_parsed_data.cpp +24 -0
- package/src/duckdb/src/parser/parser.cpp +1 -1
- package/src/duckdb/src/parser/query_error_context.cpp +15 -1
- package/src/duckdb/src/parser/query_node/ub_duckdb_query_node.cpp +5 -0
- package/src/duckdb/src/parser/statement/export_statement.cpp +2 -1
- package/src/duckdb/src/parser/statement/relation_statement.cpp +2 -2
- package/src/duckdb/src/parser/statement/ub_duckdb_statement.cpp +25 -0
- package/src/duckdb/src/parser/tableref/pivotref.cpp +3 -3
- package/src/duckdb/src/parser/tableref/showref.cpp +2 -0
- package/src/duckdb/src/parser/tableref/ub_duckdb_parser_tableref.cpp +8 -0
- package/src/duckdb/src/parser/transform/constraint/ub_duckdb_transformer_constraint.cpp +2 -0
- package/src/duckdb/src/parser/transform/expression/transform_boolean_test.cpp +1 -1
- package/src/duckdb/src/parser/transform/expression/transform_cast.cpp +10 -2
- package/src/duckdb/src/parser/transform/expression/transform_constant.cpp +7 -7
- package/src/duckdb/src/parser/transform/expression/transform_interval.cpp +2 -1
- package/src/duckdb/src/parser/transform/expression/ub_duckdb_transformer_expression.cpp +20 -0
- package/src/duckdb/src/parser/transform/helpers/transform_typename.cpp +2 -2
- package/src/duckdb/src/parser/transform/helpers/ub_duckdb_transformer_helpers.cpp +8 -0
- package/src/duckdb/src/parser/transform/statement/transform_comment_on.cpp +3 -8
- package/src/duckdb/src/parser/transform/statement/transform_pivot_stmt.cpp +3 -1
- package/src/duckdb/src/parser/transform/statement/transform_show_select.cpp +2 -3
- package/src/duckdb/src/parser/transform/statement/ub_duckdb_transformer_statement.cpp +37 -0
- package/src/duckdb/src/parser/transform/tableref/transform_join.cpp +16 -0
- package/src/duckdb/src/parser/transform/tableref/transform_pivot.cpp +49 -32
- package/src/duckdb/src/parser/transform/tableref/ub_duckdb_transformer_tableref.cpp +8 -0
- package/src/duckdb/src/parser/ub_duckdb_parser.cpp +15 -0
- package/src/duckdb/src/planner/binder/expression/bind_lambda.cpp +11 -4
- package/src/duckdb/src/planner/binder/expression/bind_operator_expression.cpp +4 -1
- package/src/duckdb/src/planner/binder/expression/bind_star_expression.cpp +71 -5
- package/src/duckdb/src/planner/binder/expression/bind_window_expression.cpp +35 -1
- package/src/duckdb/src/planner/binder/expression/ub_duckdb_bind_expression.cpp +20 -0
- package/src/duckdb/src/planner/binder/query_node/bind_select_node.cpp +55 -51
- package/src/duckdb/src/planner/binder/query_node/plan_query_node.cpp +1 -11
- package/src/duckdb/src/planner/binder/query_node/plan_subquery.cpp +2 -2
- package/src/duckdb/src/planner/binder/query_node/ub_duckdb_bind_query_node.cpp +12 -0
- package/src/duckdb/src/planner/binder/statement/bind_create.cpp +12 -6
- package/src/duckdb/src/planner/binder/statement/bind_drop.cpp +1 -1
- package/src/duckdb/src/planner/binder/statement/bind_export.cpp +8 -2
- package/src/duckdb/src/planner/binder/statement/bind_insert.cpp +6 -3
- package/src/duckdb/src/planner/binder/statement/bind_simple.cpp +13 -2
- package/src/duckdb/src/planner/binder/statement/ub_duckdb_bind_statement.cpp +26 -0
- package/src/duckdb/src/planner/binder/tableref/bind_basetableref.cpp +15 -4
- package/src/duckdb/src/planner/binder/tableref/bind_joinref.cpp +9 -2
- package/src/duckdb/src/planner/binder/tableref/bind_pivot.cpp +93 -45
- package/src/duckdb/src/planner/binder/tableref/bind_subqueryref.cpp +6 -1
- package/src/duckdb/src/planner/binder/tableref/ub_duckdb_bind_tableref.cpp +17 -0
- package/src/duckdb/src/planner/binder.cpp +22 -23
- package/src/duckdb/src/planner/bound_result_modifier.cpp +67 -4
- package/src/duckdb/src/planner/expression/bound_cast_expression.cpp +5 -1
- package/src/duckdb/src/planner/expression/bound_window_expression.cpp +3 -0
- package/src/duckdb/src/planner/expression/ub_duckdb_planner_expression.cpp +19 -0
- package/src/duckdb/src/planner/expression_binder/column_alias_binder.cpp +14 -9
- package/src/duckdb/src/planner/expression_binder/having_binder.cpp +17 -9
- package/src/duckdb/src/planner/expression_binder/lateral_binder.cpp +61 -37
- package/src/duckdb/src/planner/expression_binder/qualify_binder.cpp +8 -4
- package/src/duckdb/src/planner/expression_binder/ub_duckdb_expression_binders.cpp +20 -0
- package/src/duckdb/src/planner/expression_binder/where_binder.cpp +3 -2
- package/src/duckdb/src/planner/expression_iterator.cpp +73 -52
- package/src/duckdb/src/planner/filter/ub_duckdb_planner_filter.cpp +4 -0
- package/src/duckdb/src/planner/logical_operator_visitor.cpp +4 -14
- package/src/duckdb/src/planner/operator/logical_limit.cpp +14 -6
- package/src/duckdb/src/planner/operator/ub_duckdb_planner_operator.cpp +43 -0
- package/src/duckdb/src/planner/parsed_data/ub_duckdb_planner_parsed_data.cpp +2 -0
- package/src/duckdb/src/planner/planner.cpp +3 -0
- package/src/duckdb/src/planner/subquery/flatten_dependent_join.cpp +46 -18
- package/src/duckdb/src/planner/subquery/rewrite_correlated_expressions.cpp +39 -33
- package/src/duckdb/src/planner/subquery/ub_duckdb_planner_subquery.cpp +4 -0
- package/src/duckdb/src/planner/ub_duckdb_planner.cpp +15 -0
- package/src/duckdb/src/storage/arena_allocator.cpp +9 -0
- package/src/duckdb/src/storage/buffer/block_handle.cpp +7 -2
- package/src/duckdb/src/storage/buffer/block_manager.cpp +7 -3
- package/src/duckdb/src/storage/buffer/buffer_pool.cpp +121 -24
- package/src/duckdb/src/storage/buffer/ub_duckdb_storage_buffer.cpp +6 -0
- package/src/duckdb/src/storage/checkpoint/ub_duckdb_storage_checkpoint.cpp +5 -0
- package/src/duckdb/src/storage/checkpoint/write_overflow_strings_to_disk.cpp +4 -4
- package/src/duckdb/src/storage/compression/chimp/ub_duckdb_storage_compression_chimp.cpp +6 -0
- package/src/duckdb/src/storage/compression/dictionary_compression.cpp +6 -5
- package/src/duckdb/src/storage/compression/fsst.cpp +3 -2
- package/src/duckdb/src/storage/compression/rle.cpp +1 -1
- package/src/duckdb/src/storage/compression/string_uncompressed.cpp +4 -4
- package/src/duckdb/src/storage/compression/ub_duckdb_storage_compression.cpp +12 -0
- package/src/duckdb/src/storage/data_table.cpp +6 -3
- package/src/duckdb/src/storage/local_storage.cpp +5 -2
- package/src/duckdb/src/storage/metadata/metadata_manager.cpp +4 -4
- package/src/duckdb/src/storage/metadata/metadata_reader.cpp +1 -1
- package/src/duckdb/src/storage/metadata/metadata_writer.cpp +1 -1
- package/src/duckdb/src/storage/metadata/ub_duckdb_storage_metadata.cpp +4 -0
- package/src/duckdb/src/storage/partial_block_manager.cpp +1 -1
- package/src/duckdb/src/storage/serialization/serialize_create_info.cpp +2 -0
- package/src/duckdb/src/storage/serialization/serialize_expression.cpp +3 -0
- package/src/duckdb/src/storage/serialization/serialize_logical_operator.cpp +5 -29
- package/src/duckdb/src/storage/serialization/serialize_nodes.cpp +22 -4
- package/src/duckdb/src/storage/serialization/serialize_parse_info.cpp +12 -32
- package/src/duckdb/src/storage/serialization/ub_duckdb_storage_serialization.cpp +16 -0
- package/src/duckdb/src/storage/standard_buffer_manager.cpp +29 -397
- package/src/duckdb/src/storage/statistics/string_stats.cpp +1 -1
- package/src/duckdb/src/storage/statistics/ub_duckdb_storage_statistics.cpp +10 -0
- package/src/duckdb/src/storage/storage_info.cpp +1 -1
- package/src/duckdb/src/storage/table/column_checkpoint_state.cpp +3 -3
- package/src/duckdb/src/storage/table/column_data.cpp +7 -16
- package/src/duckdb/src/storage/table/column_data_checkpointer.cpp +4 -1
- package/src/duckdb/src/storage/table/column_segment.cpp +68 -78
- package/src/duckdb/src/storage/table/list_column_data.cpp +1 -0
- package/src/duckdb/src/storage/table/row_group.cpp +17 -7
- package/src/duckdb/src/storage/table/row_group_collection.cpp +28 -27
- package/src/duckdb/src/storage/table/ub_duckdb_storage_table.cpp +17 -0
- package/src/duckdb/src/storage/table/update_segment.cpp +7 -7
- package/src/duckdb/src/storage/temporary_file_manager.cpp +334 -0
- package/src/duckdb/src/storage/ub_duckdb_storage.cpp +20 -0
- package/src/duckdb/src/storage/write_ahead_log.cpp +3 -2
- package/src/duckdb/src/transaction/commit_state.cpp +4 -2
- package/src/duckdb/src/transaction/duck_transaction_manager.cpp +32 -17
- package/src/duckdb/src/transaction/meta_transaction.cpp +24 -0
- package/src/duckdb/src/transaction/transaction_context.cpp +0 -9
- package/src/duckdb/src/transaction/ub_duckdb_transaction.cpp +11 -0
- package/src/duckdb/src/transaction/undo_buffer.cpp +1 -1
- package/src/duckdb/third_party/jaro_winkler/details/common.hpp +1 -1
- package/src/duckdb/third_party/libpg_query/include/nodes/parsenodes.hpp +2 -0
- package/src/duckdb/third_party/libpg_query/include/parser/gram.hpp +1032 -551
- package/src/duckdb/third_party/libpg_query/src_backend_parser_gram.cpp +24122 -24304
- package/src/duckdb/third_party/mbedtls/include/mbedtls/mbedtls_config.h +0 -3
- package/src/duckdb/third_party/mbedtls/library/entropy_poll.cpp +32 -4
- package/src/duckdb/third_party/miniz/miniz_wrapper.hpp +4 -4
- package/src/duckdb/third_party/tdigest/t_digest.hpp +3 -3
- package/src/duckdb/ub_src_common_arrow_appender.cpp +2 -0
- package/src/duckdb/ub_src_common_exception.cpp +2 -0
- package/src/duckdb/ub_src_execution_operator_helper.cpp +2 -0
- package/src/duckdb/ub_src_execution_operator_persistent.cpp +0 -2
- package/src/duckdb/ub_src_execution_physical_plan.cpp +0 -2
- package/src/duckdb/ub_src_parser_parsed_data.cpp +1 -1
- package/src/duckdb/ub_src_planner_operator.cpp +0 -2
- package/src/duckdb/ub_src_storage.cpp +2 -0
- package/test/columns.test.ts +1 -1
- package/test/test_all_types.test.ts +1 -1
@@ -1,6 +1,6 @@
|
|
1
1
|
#include "duckdb/common/types/cast_helpers.hpp"
|
2
|
-
#include "duckdb/execution/operator/csv_scanner/
|
3
|
-
#include "duckdb/execution/operator/csv_scanner/
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
3
|
+
#include "duckdb/execution/operator/csv_scanner/csv_reader_options.hpp"
|
4
4
|
#include "utf8proc.hpp"
|
5
5
|
|
6
6
|
namespace duckdb {
|
@@ -93,9 +93,51 @@ static string NormalizeColumnName(const string &col_name) {
|
|
93
93
|
}
|
94
94
|
return col_name_cleaned;
|
95
95
|
}
|
96
|
+
|
97
|
+
// If our columns were set by the user, we verify if their names match with the first row
|
98
|
+
bool CSVSniffer::DetectHeaderWithSetColumn() {
|
99
|
+
bool has_header = true;
|
100
|
+
bool all_varchar = true;
|
101
|
+
bool first_row_consistent = true;
|
102
|
+
// User set the names, we must check if they match the first row
|
103
|
+
// We do a +1 to check for situations where the csv file has an extra all null column
|
104
|
+
if (set_columns.Size() != best_header_row.size() && set_columns.Size() + 1 != best_header_row.size()) {
|
105
|
+
return false;
|
106
|
+
} else {
|
107
|
+
// Let's do a match-aroo
|
108
|
+
for (idx_t i = 0; i < set_columns.Size(); i++) {
|
109
|
+
if (best_header_row[i].IsNull()) {
|
110
|
+
return false;
|
111
|
+
}
|
112
|
+
if (best_header_row[i] != (*set_columns.names)[i]) {
|
113
|
+
has_header = false;
|
114
|
+
break;
|
115
|
+
}
|
116
|
+
}
|
117
|
+
}
|
118
|
+
if (!has_header) {
|
119
|
+
// We verify if the types are consistent
|
120
|
+
for (idx_t col = 0; col < set_columns.Size(); col++) {
|
121
|
+
auto dummy_val = best_header_row[col];
|
122
|
+
// try cast to sql_type of column
|
123
|
+
const auto &sql_type = (*set_columns.types)[col];
|
124
|
+
if (sql_type != LogicalType::VARCHAR) {
|
125
|
+
all_varchar = false;
|
126
|
+
if (!TryCastValue(options.dialect_options, options.decimal_separator, dummy_val, sql_type)) {
|
127
|
+
first_row_consistent = false;
|
128
|
+
}
|
129
|
+
}
|
130
|
+
}
|
131
|
+
if (all_varchar) {
|
132
|
+
// Can't be the header
|
133
|
+
return false;
|
134
|
+
}
|
135
|
+
return !first_row_consistent;
|
136
|
+
}
|
137
|
+
return has_header;
|
138
|
+
}
|
96
139
|
void CSVSniffer::DetectHeader() {
|
97
140
|
auto &sniffer_state_machine = best_candidate->GetStateMachine();
|
98
|
-
|
99
141
|
if (best_header_row.empty()) {
|
100
142
|
sniffer_state_machine.dialect_options.header = false;
|
101
143
|
for (idx_t col = 0; col < sniffer_state_machine.dialect_options.num_cols; col++) {
|
@@ -119,25 +161,36 @@ void CSVSniffer::DetectHeader() {
|
|
119
161
|
error_handler->Error(error);
|
120
162
|
}
|
121
163
|
bool all_varchar = true;
|
122
|
-
|
123
|
-
auto dummy_val = best_header_row[col];
|
124
|
-
if (!dummy_val.IsNull()) {
|
125
|
-
first_row_nulls = false;
|
126
|
-
}
|
164
|
+
bool has_header;
|
127
165
|
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
|
132
|
-
|
133
|
-
|
166
|
+
if (set_columns.IsSet()) {
|
167
|
+
has_header = DetectHeaderWithSetColumn();
|
168
|
+
} else {
|
169
|
+
for (idx_t col = 0; col < best_header_row.size(); col++) {
|
170
|
+
auto dummy_val = best_header_row[col];
|
171
|
+
if (!dummy_val.IsNull()) {
|
172
|
+
first_row_nulls = false;
|
134
173
|
}
|
174
|
+
// try cast to sql_type of column
|
175
|
+
const auto &sql_type = best_sql_types_candidates_per_column_idx[col].back();
|
176
|
+
if (sql_type != LogicalType::VARCHAR) {
|
177
|
+
all_varchar = false;
|
178
|
+
if (!TryCastValue(sniffer_state_machine.dialect_options,
|
179
|
+
sniffer_state_machine.options.decimal_separator, dummy_val, sql_type)) {
|
180
|
+
first_row_consistent = false;
|
181
|
+
}
|
182
|
+
}
|
183
|
+
}
|
184
|
+
// Our header is only false if types are not all varchar, and rows are consistent
|
185
|
+
if (all_varchar || first_row_nulls) {
|
186
|
+
has_header = true;
|
187
|
+
} else {
|
188
|
+
has_header = !first_row_consistent;
|
135
189
|
}
|
136
190
|
}
|
137
|
-
|
138
|
-
if (
|
139
|
-
|
140
|
-
} else {
|
191
|
+
|
192
|
+
if (sniffer_state_machine.options.dialect_options.header.IsSetByUser()) {
|
193
|
+
// Header is defined by user, use that.
|
141
194
|
has_header = sniffer_state_machine.options.dialect_options.header.GetValue();
|
142
195
|
}
|
143
196
|
// update parser info, and read, generate & set col_names based on previous findings
|
@@ -1,5 +1,5 @@
|
|
1
1
|
#include "duckdb/common/operator/decimal_cast_operators.hpp"
|
2
|
-
#include "duckdb/execution/operator/csv_scanner/
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
3
3
|
#include "duckdb/common/algorithm.hpp"
|
4
4
|
#include "duckdb/common/string.hpp"
|
5
5
|
|
@@ -9,7 +9,8 @@ struct TryCastFloatingOperator {
|
|
9
9
|
static bool Operation(string_t input) {
|
10
10
|
T result;
|
11
11
|
string error_message;
|
12
|
-
|
12
|
+
CastParameters parameters(false, &error_message);
|
13
|
+
return OP::Operation(input, result, parameters);
|
13
14
|
}
|
14
15
|
};
|
15
16
|
|
@@ -83,27 +84,28 @@ string GenerateDateFormat(const string &separator, const char *format_template)
|
|
83
84
|
return result;
|
84
85
|
}
|
85
86
|
|
86
|
-
bool CSVSniffer::TryCastValue(
|
87
|
+
bool CSVSniffer::TryCastValue(const DialectOptions &dialect_options, const string &decimal_separator,
|
88
|
+
const Value &value, const LogicalType &sql_type) {
|
87
89
|
if (value.IsNull()) {
|
88
90
|
return true;
|
89
91
|
}
|
90
|
-
if (!
|
92
|
+
if (!dialect_options.date_format.find(LogicalTypeId::DATE)->second.GetValue().Empty() &&
|
91
93
|
sql_type.id() == LogicalTypeId::DATE) {
|
92
94
|
date_t result;
|
93
95
|
string error_message;
|
94
|
-
return
|
96
|
+
return dialect_options.date_format.find(LogicalTypeId::DATE)
|
95
97
|
->second.GetValue()
|
96
98
|
.TryParseDate(string_t(StringValue::Get(value)), result, error_message);
|
97
99
|
}
|
98
|
-
if (!
|
100
|
+
if (!dialect_options.date_format.find(LogicalTypeId::TIMESTAMP)->second.GetValue().Empty() &&
|
99
101
|
sql_type.id() == LogicalTypeId::TIMESTAMP) {
|
100
102
|
timestamp_t result;
|
101
103
|
string error_message;
|
102
|
-
return
|
104
|
+
return dialect_options.date_format.find(LogicalTypeId::TIMESTAMP)
|
103
105
|
->second.GetValue()
|
104
106
|
.TryParseTimestamp(string_t(StringValue::Get(value)), result, error_message);
|
105
107
|
}
|
106
|
-
if (
|
108
|
+
if (decimal_separator != "." && (sql_type.id() == LogicalTypeId::DOUBLE)) {
|
107
109
|
return TryCastFloatingOperator::Operation<TryCastErrorMessageCommaSeparated, double>(StringValue::Get(value));
|
108
110
|
}
|
109
111
|
Value new_value;
|
@@ -123,6 +125,11 @@ void CSVSniffer::InitializeDateAndTimeStampDetection(CSVStateMachine &candidate,
|
|
123
125
|
auto &format_candidate = format_candidates[sql_type.id()];
|
124
126
|
if (!format_candidate.initialized) {
|
125
127
|
format_candidate.initialized = true;
|
128
|
+
// if user set a format, we add that as well
|
129
|
+
auto user_format = options.dialect_options.date_format.find(sql_type.id());
|
130
|
+
if (user_format->second.IsSetByUser()) {
|
131
|
+
format_candidate.format.emplace_back(user_format->second.GetValue().format_specifier);
|
132
|
+
}
|
126
133
|
// order by preference
|
127
134
|
auto entry = format_template_candidates.find(sql_type.id());
|
128
135
|
if (entry != format_template_candidates.end()) {
|
@@ -184,6 +191,7 @@ void CSVSniffer::DetectDateAndTimeStampFormats(CSVStateMachine &candidate, const
|
|
184
191
|
|
185
192
|
void CSVSniffer::DetectTypes() {
|
186
193
|
idx_t min_varchar_cols = max_columns_found + 1;
|
194
|
+
idx_t min_errors = NumericLimits<idx_t>::Maximum();
|
187
195
|
vector<LogicalType> return_types;
|
188
196
|
// check which info candidate leads to minimum amount of non-varchar columns...
|
189
197
|
for (auto &candidate_cc : candidates) {
|
@@ -238,7 +246,8 @@ void CSVSniffer::DetectTypes() {
|
|
238
246
|
// Nothing to convert it to
|
239
247
|
continue;
|
240
248
|
}
|
241
|
-
if (TryCastValue(sniffing_state_machine,
|
249
|
+
if (TryCastValue(sniffing_state_machine.dialect_options,
|
250
|
+
sniffing_state_machine.options.decimal_separator, dummy_val, sql_type)) {
|
242
251
|
break;
|
243
252
|
} else {
|
244
253
|
if (row_idx != start_idx_detection && cur_top_candidate == LogicalType::BOOLEAN) {
|
@@ -268,7 +277,9 @@ void CSVSniffer::DetectTypes() {
|
|
268
277
|
|
269
278
|
// it's good if the dialect creates more non-varchar columns, but only if we sacrifice < 30% of
|
270
279
|
// best_num_cols.
|
271
|
-
if (varchar_cols < min_varchar_cols && info_sql_types_candidates.size() > (max_columns_found * 0.7)
|
280
|
+
if (varchar_cols < min_varchar_cols && info_sql_types_candidates.size() > (max_columns_found * 0.7) &&
|
281
|
+
(!options.ignore_errors || candidate->error_handler->errors.size() < min_errors)) {
|
282
|
+
min_errors = candidate->error_handler->errors.size();
|
272
283
|
best_header_row.clear();
|
273
284
|
// we have a new best_options candidate
|
274
285
|
best_candidate = std::move(candidate);
|
@@ -286,7 +297,7 @@ void CSVSniffer::DetectTypes() {
|
|
286
297
|
}
|
287
298
|
if (!best_candidate) {
|
288
299
|
auto error = CSVError::SniffingError(options.file_path);
|
289
|
-
error_handler->Error(error);
|
300
|
+
error_handler->Error(error, true);
|
290
301
|
}
|
291
302
|
// Assert that it's all good at this point.
|
292
303
|
D_ASSERT(best_candidate && !best_format_candidates.empty());
|
@@ -1,5 +1,5 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
2
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/csv_casting.hpp"
|
3
3
|
|
4
4
|
namespace duckdb {
|
5
5
|
|
@@ -11,16 +11,18 @@ bool CSVSniffer::TryCastVector(Vector &parse_chunk_col, idx_t size, const Logica
|
|
11
11
|
sql_type == LogicalTypeId::DATE) {
|
12
12
|
// use the date format to cast the chunk
|
13
13
|
string error_message;
|
14
|
+
CastParameters parameters(false, &error_message);
|
14
15
|
idx_t line_error;
|
15
16
|
return CSVCast::TryCastDateVector(sniffing_state_machine.dialect_options.date_format, parse_chunk_col,
|
16
|
-
dummy_result, size,
|
17
|
+
dummy_result, size, parameters, line_error);
|
17
18
|
}
|
18
19
|
if (!sniffing_state_machine.dialect_options.date_format[LogicalTypeId::TIMESTAMP].GetValue().Empty() &&
|
19
20
|
sql_type == LogicalTypeId::TIMESTAMP) {
|
20
21
|
// use the timestamp format to cast the chunk
|
21
22
|
string error_message;
|
23
|
+
CastParameters parameters(false, &error_message);
|
22
24
|
return CSVCast::TryCastTimestampVector(sniffing_state_machine.dialect_options.date_format, parse_chunk_col,
|
23
|
-
dummy_result, size,
|
25
|
+
dummy_result, size, parameters);
|
24
26
|
}
|
25
27
|
// target type is not varchar: perform a cast
|
26
28
|
string error_message;
|
@@ -1,8 +1,9 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
2
2
|
|
3
3
|
namespace duckdb {
|
4
4
|
void CSVSniffer::ReplaceTypes() {
|
5
5
|
auto &sniffing_state_machine = best_candidate->GetStateMachine();
|
6
|
+
manually_set = vector<bool>(detected_types.size(), false);
|
6
7
|
if (sniffing_state_machine.options.sql_type_list.empty()) {
|
7
8
|
return;
|
8
9
|
}
|
@@ -17,14 +18,14 @@ void CSVSniffer::ReplaceTypes() {
|
|
17
18
|
best_sql_types_candidates_per_column_idx[i] = {
|
18
19
|
sniffing_state_machine.options.sql_type_list[it->second]};
|
19
20
|
detected_types[i] = sniffing_state_machine.options.sql_type_list[it->second];
|
21
|
+
manually_set[i] = true;
|
20
22
|
found++;
|
21
23
|
}
|
22
24
|
}
|
23
25
|
if (!sniffing_state_machine.options.file_options.union_by_name &&
|
24
26
|
found < sniffing_state_machine.options.sql_types_per_column.size()) {
|
25
27
|
auto error_msg = CSVError::ColumnTypesError(options.sql_types_per_column, names);
|
26
|
-
|
27
|
-
error_handler->Error(error_line, error_msg);
|
28
|
+
error_handler->Error(error_msg);
|
28
29
|
}
|
29
30
|
return;
|
30
31
|
}
|
@@ -35,6 +36,7 @@ void CSVSniffer::ReplaceTypes() {
|
|
35
36
|
}
|
36
37
|
for (idx_t i = 0; i < sniffing_state_machine.options.sql_type_list.size(); i++) {
|
37
38
|
detected_types[i] = sniffing_state_machine.options.sql_type_list[i];
|
39
|
+
manually_set[i] = true;
|
38
40
|
}
|
39
41
|
}
|
40
42
|
} // namespace duckdb
|
package/src/duckdb/src/execution/operator/csv_scanner/sniffer/ub_duckdb_operator_csv_sniffer.cpp
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
// Unity Build generated by CMake
|
2
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/sniffer/csv_sniffer.cpp>
|
3
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp>
|
4
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp>
|
5
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp>
|
6
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/sniffer/type_refinement.cpp>
|
7
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/sniffer/type_replacement.cpp>
|
@@ -1,8 +1,8 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
2
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_state_machine.hpp"
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
3
3
|
#include "utf8proc_wrapper.hpp"
|
4
4
|
#include "duckdb/main/error_manager.hpp"
|
5
|
-
#include "duckdb/execution/operator/csv_scanner/
|
5
|
+
#include "duckdb/execution/operator/csv_scanner/csv_state_machine_cache.hpp"
|
6
6
|
|
7
7
|
namespace duckdb {
|
8
8
|
|
package/src/duckdb/src/execution/operator/csv_scanner/state_machine/csv_state_machine_cache.cpp
CHANGED
@@ -1,10 +1,8 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
2
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_state_machine.hpp"
|
2
|
+
#include "duckdb/execution/operator/csv_scanner/csv_state_machine_cache.hpp"
|
3
3
|
|
4
4
|
namespace duckdb {
|
5
5
|
|
6
|
-
const string CSVStateMachineCache::STATE_KEY = "CSV_STATE_MACHINE_CACHE";
|
7
|
-
|
8
6
|
void InitializeTransitionArray(StateMachine &transition_array, const CSVState cur_state, const CSVState state) {
|
9
7
|
for (uint32_t i = 0; i < StateMachine::NUM_TRANSITIONS; i++) {
|
10
8
|
transition_array[i][static_cast<uint8_t>(cur_state)] = state;
|
@@ -165,6 +163,33 @@ void CSVStateMachineCache::Insert(const CSVStateMachineOptions &state_machine_op
|
|
165
163
|
transition_array.skip_quoted[escape] = false;
|
166
164
|
transition_array.skip_quoted[static_cast<uint8_t>('\n')] = false;
|
167
165
|
transition_array.skip_quoted[static_cast<uint8_t>('\r')] = false;
|
166
|
+
|
167
|
+
transition_array.delimiter = delimiter;
|
168
|
+
transition_array.new_line = static_cast<uint8_t>('\n');
|
169
|
+
transition_array.carriage_return = static_cast<uint8_t>('\r');
|
170
|
+
transition_array.quote = quote;
|
171
|
+
transition_array.escape = escape;
|
172
|
+
|
173
|
+
// Shift and OR to replicate across all bytes
|
174
|
+
transition_array.delimiter |= transition_array.delimiter << 8;
|
175
|
+
transition_array.delimiter |= transition_array.delimiter << 16;
|
176
|
+
transition_array.delimiter |= transition_array.delimiter << 32;
|
177
|
+
|
178
|
+
transition_array.new_line |= transition_array.new_line << 8;
|
179
|
+
transition_array.new_line |= transition_array.new_line << 16;
|
180
|
+
transition_array.new_line |= transition_array.new_line << 32;
|
181
|
+
|
182
|
+
transition_array.carriage_return |= transition_array.carriage_return << 8;
|
183
|
+
transition_array.carriage_return |= transition_array.carriage_return << 16;
|
184
|
+
transition_array.carriage_return |= transition_array.carriage_return << 32;
|
185
|
+
|
186
|
+
transition_array.quote |= transition_array.quote << 8;
|
187
|
+
transition_array.quote |= transition_array.quote << 16;
|
188
|
+
transition_array.quote |= transition_array.quote << 32;
|
189
|
+
|
190
|
+
transition_array.escape |= transition_array.escape << 8;
|
191
|
+
transition_array.escape |= transition_array.escape << 16;
|
192
|
+
transition_array.escape |= transition_array.escape << 32;
|
168
193
|
}
|
169
194
|
|
170
195
|
CSVStateMachineCache::CSVStateMachineCache() {
|
@@ -195,7 +220,7 @@ const StateMachine &CSVStateMachineCache::Get(const CSVStateMachineOptions &stat
|
|
195
220
|
CSVStateMachineCache &CSVStateMachineCache::Get(ClientContext &context) {
|
196
221
|
|
197
222
|
auto &cache = ObjectCache::GetObjectCache(context);
|
198
|
-
return *cache.GetOrCreate<CSVStateMachineCache>(CSVStateMachineCache::
|
223
|
+
return *cache.GetOrCreate<CSVStateMachineCache>(CSVStateMachineCache::ObjectType());
|
199
224
|
}
|
200
225
|
|
201
226
|
} // namespace duckdb
|
@@ -1,6 +1,6 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_file_scanner.hpp"
|
2
2
|
#include "duckdb/function/table/read_csv.hpp"
|
3
|
-
#include "duckdb/execution/operator/csv_scanner/
|
3
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
4
4
|
|
5
5
|
namespace duckdb {
|
6
6
|
|
@@ -85,6 +85,10 @@ CSVFileScan::CSVFileScan(ClientContext &context, const string &file_path_p, cons
|
|
85
85
|
names = bind_data.column_info[file_idx].names;
|
86
86
|
types = bind_data.column_info[file_idx].types;
|
87
87
|
options.dialect_options.num_cols = names.size();
|
88
|
+
if (options.auto_detect) {
|
89
|
+
CSVSniffer sniffer(options, buffer_manager, state_machine_cache);
|
90
|
+
sniffer.SniffCSV();
|
91
|
+
}
|
88
92
|
state_machine = make_shared<CSVStateMachine>(
|
89
93
|
state_machine_cache.Get(options.dialect_options.state_machine_options), options);
|
90
94
|
|
@@ -1,7 +1,7 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/global_csv_state.hpp"
|
2
2
|
#include "duckdb/main/client_data.hpp"
|
3
|
-
#include "duckdb/execution/operator/csv_scanner/
|
4
|
-
#include "duckdb/execution/operator/csv_scanner/
|
3
|
+
#include "duckdb/execution/operator/csv_scanner/scanner_boundary.hpp"
|
4
|
+
#include "duckdb/execution/operator/csv_scanner/csv_sniffer.hpp"
|
5
5
|
#include "duckdb/execution/operator/persistent/csv_rejects_table.hpp"
|
6
6
|
#include "duckdb/main/appender.hpp"
|
7
7
|
|
@@ -40,7 +40,7 @@ CSVGlobalState::CSVGlobalState(ClientContext &context_p, const shared_ptr<CSVBuf
|
|
40
40
|
}
|
41
41
|
|
42
42
|
double CSVGlobalState::GetProgress(const ReadCSVData &bind_data_p) const {
|
43
|
-
|
43
|
+
lock_guard<mutex> parallel_lock(main_mutex);
|
44
44
|
idx_t total_files = bind_data.files.size();
|
45
45
|
// get the progress WITHIN the current file
|
46
46
|
double progress;
|
@@ -71,7 +71,7 @@ unique_ptr<StringValueScanner> CSVGlobalState::Next() {
|
|
71
71
|
}
|
72
72
|
auto csv_scanner =
|
73
73
|
make_uniq<StringValueScanner>(scanner_idx++, current_file->buffer_manager, current_file->state_machine,
|
74
|
-
current_file->error_handler, current_file, current_boundary);
|
74
|
+
current_file->error_handler, current_file, false, current_boundary);
|
75
75
|
return csv_scanner;
|
76
76
|
}
|
77
77
|
lock_guard<mutex> parallel_lock(main_mutex);
|
@@ -86,7 +86,7 @@ unique_ptr<StringValueScanner> CSVGlobalState::Next() {
|
|
86
86
|
auto ¤t_file = *file_scans.back();
|
87
87
|
auto csv_scanner =
|
88
88
|
make_uniq<StringValueScanner>(scanner_idx++, current_file.buffer_manager, current_file.state_machine,
|
89
|
-
current_file.error_handler, file_scans.back(), current_boundary);
|
89
|
+
current_file.error_handler, file_scans.back(), false, current_boundary);
|
90
90
|
|
91
91
|
csv_scanner->buffer_tracker = current_buffer_in_use;
|
92
92
|
|
@@ -151,51 +151,52 @@ void CSVGlobalState::FillRejectsTable() {
|
|
151
151
|
for (auto &file : file_scans) {
|
152
152
|
auto file_name = file->file_path;
|
153
153
|
auto &errors = file->error_handler->errors;
|
154
|
-
for (auto &
|
155
|
-
|
156
|
-
|
157
|
-
|
158
|
-
|
159
|
-
// short circuit if we already have too many rejects
|
160
|
-
if (limit == 0 || rejects->count < limit) {
|
161
|
-
if (limit != 0 && rejects->count >= limit) {
|
162
|
-
break;
|
154
|
+
for (auto &error_vector : errors) {
|
155
|
+
for (auto &error : error_vector.second) {
|
156
|
+
if (error.type != CSVErrorType::CAST_ERROR) {
|
157
|
+
// For now we only will use it for casting errors
|
158
|
+
continue;
|
163
159
|
}
|
164
|
-
rejects
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
|
182
|
-
|
183
|
-
|
184
|
-
|
185
|
-
|
186
|
-
|
160
|
+
// short circuit if we already have too many rejects
|
161
|
+
if (limit == 0 || rejects->count < limit) {
|
162
|
+
if (limit != 0 && rejects->count >= limit) {
|
163
|
+
break;
|
164
|
+
}
|
165
|
+
rejects->count++;
|
166
|
+
auto row_line = file->error_handler->GetLine(error.error_info);
|
167
|
+
auto col_idx = error.column_idx;
|
168
|
+
auto col_name = bind_data.return_names[col_idx];
|
169
|
+
// Add the row to the rejects table
|
170
|
+
appender.BeginRow();
|
171
|
+
appender.Append(string_t(file_name));
|
172
|
+
appender.Append(row_line);
|
173
|
+
appender.Append(col_idx);
|
174
|
+
appender.Append(string_t("\"" + col_name + "\""));
|
175
|
+
appender.Append(error.row[col_idx]);
|
176
|
+
|
177
|
+
if (!options.rejects_recovery_columns.empty()) {
|
178
|
+
child_list_t<Value> recovery_key;
|
179
|
+
for (auto &key_idx : options.rejects_recovery_column_ids) {
|
180
|
+
// Figure out if the recovery key is valid.
|
181
|
+
// If not, error out for real.
|
182
|
+
auto &value = error.row[key_idx];
|
183
|
+
if (value.IsNull()) {
|
184
|
+
throw InvalidInputException("%s at line %llu in column %s. Parser options:\n%s ",
|
185
|
+
"Could not parse recovery column", row_line, col_name,
|
186
|
+
options.ToString());
|
187
|
+
}
|
188
|
+
recovery_key.emplace_back(bind_data.return_names[key_idx], value);
|
187
189
|
}
|
188
|
-
|
190
|
+
appender.Append(Value::STRUCT(recovery_key));
|
189
191
|
}
|
190
|
-
|
192
|
+
auto row_error_msg =
|
193
|
+
StringUtil::Format("Could not convert string '%s' to '%s'", error.row[col_idx].ToString(),
|
194
|
+
file->types[col_idx].ToString());
|
195
|
+
appender.Append(string_t(row_error_msg));
|
196
|
+
appender.EndRow();
|
191
197
|
}
|
192
|
-
|
193
|
-
StringUtil::Format("Could not convert string '%s' to '%s'", error->row[col_idx].ToString(),
|
194
|
-
file->types[col_idx].ToString());
|
195
|
-
appender.Append(string_t(row_error_msg));
|
196
|
-
appender.EndRow();
|
198
|
+
appender.Close();
|
197
199
|
}
|
198
|
-
appender.Close();
|
199
200
|
}
|
200
201
|
}
|
201
202
|
}
|
@@ -0,0 +1,10 @@
|
|
1
|
+
// Unity Build generated by CMake
|
2
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/base_csv_reader.cpp>
|
3
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/buffered_csv_reader.cpp>
|
4
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/csv_buffer.cpp>
|
5
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/csv_buffer_manager.cpp>
|
6
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/csv_file_handle.cpp>
|
7
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/csv_reader_options.cpp>
|
8
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/csv_state_machine.cpp>
|
9
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/csv_state_machine_cache.cpp>
|
10
|
+
#include </Users/carlo/duckdb/src/execution/operator/csv_scanner/parallel_csv_reader.cpp>
|