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
@@ -1,4 +1,4 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_error.hpp"
|
2
2
|
#include "duckdb/common/exception/conversion_exception.hpp"
|
3
3
|
#include <sstream>
|
4
4
|
|
@@ -13,25 +13,10 @@ LinesPerBoundary::LinesPerBoundary(idx_t boundary_idx_p, idx_t lines_in_batch_p)
|
|
13
13
|
CSVErrorHandler::CSVErrorHandler(bool ignore_errors_p) : ignore_errors(ignore_errors_p) {
|
14
14
|
}
|
15
15
|
|
16
|
-
void CSVErrorHandler::
|
17
|
-
LinesPerBoundary mock;
|
18
|
-
Error(mock, csv_error, true);
|
19
|
-
}
|
20
|
-
void CSVErrorHandler::Error(LinesPerBoundary &error_info, CSVError &csv_error, bool force_error) {
|
21
|
-
if (ignore_errors && !force_error) {
|
22
|
-
lock_guard<mutex> parallel_lock(main_mutex);
|
23
|
-
// We store this error
|
24
|
-
errors.push_back({error_info, csv_error});
|
25
|
-
return;
|
26
|
-
}
|
27
|
-
|
16
|
+
void CSVErrorHandler::ThrowError(CSVError csv_error) {
|
28
17
|
std::ostringstream error;
|
29
18
|
if (PrintLineNumber(csv_error)) {
|
30
|
-
error << "CSV Error on Line: " << GetLine(error_info) << std::endl;
|
31
|
-
}
|
32
|
-
{
|
33
|
-
lock_guard<mutex> parallel_lock(main_mutex);
|
34
|
-
got_borked = true;
|
19
|
+
error << "CSV Error on Line: " << GetLine(csv_error.error_info) << std::endl;
|
35
20
|
}
|
36
21
|
error << csv_error.error_message;
|
37
22
|
switch (csv_error.type) {
|
@@ -46,6 +31,33 @@ void CSVErrorHandler::Error(LinesPerBoundary &error_info, CSVError &csv_error, b
|
|
46
31
|
}
|
47
32
|
}
|
48
33
|
|
34
|
+
void CSVErrorHandler::Error(CSVError csv_error, bool force_error) {
|
35
|
+
if ((ignore_errors && !force_error) || (PrintLineNumber(csv_error) && !CanGetLine(csv_error.GetBoundaryIndex()))) {
|
36
|
+
lock_guard<mutex> parallel_lock(main_mutex);
|
37
|
+
// We store this error, we can't throw it now, or we are ignoring it
|
38
|
+
errors[csv_error.error_info].push_back(std::move(csv_error));
|
39
|
+
return;
|
40
|
+
}
|
41
|
+
// Otherwise we can throw directly
|
42
|
+
ThrowError(csv_error);
|
43
|
+
}
|
44
|
+
|
45
|
+
void CSVErrorHandler::ErrorIfNeeded() {
|
46
|
+
CSVError first_error;
|
47
|
+
{
|
48
|
+
lock_guard<mutex> parallel_lock(main_mutex);
|
49
|
+
if (ignore_errors || errors.empty()) {
|
50
|
+
// Nothing to error
|
51
|
+
return;
|
52
|
+
}
|
53
|
+
first_error = errors.begin()->second[0];
|
54
|
+
}
|
55
|
+
|
56
|
+
if (CanGetLine(first_error.error_info.boundary_idx)) {
|
57
|
+
ThrowError(first_error);
|
58
|
+
}
|
59
|
+
}
|
60
|
+
|
49
61
|
void CSVErrorHandler::Insert(idx_t boundary_idx, idx_t rows) {
|
50
62
|
lock_guard<mutex> parallel_lock(main_mutex);
|
51
63
|
if (lines_per_batch_map.find(boundary_idx) == lines_per_batch_map.end()) {
|
@@ -60,12 +72,14 @@ void CSVErrorHandler::NewMaxLineSize(idx_t scan_line_size) {
|
|
60
72
|
max_line_length = std::max(scan_line_size, max_line_length);
|
61
73
|
}
|
62
74
|
|
63
|
-
CSVError::CSVError(string error_message_p, CSVErrorType type_p)
|
64
|
-
: error_message(std::move(error_message_p)), type(type_p) {
|
75
|
+
CSVError::CSVError(string error_message_p, CSVErrorType type_p, LinesPerBoundary error_info_p)
|
76
|
+
: error_message(std::move(error_message_p)), type(type_p), error_info(error_info_p) {
|
65
77
|
}
|
66
78
|
|
67
|
-
CSVError::CSVError(string error_message_p, CSVErrorType type_p, idx_t column_idx_p, vector<Value> row_p
|
68
|
-
|
79
|
+
CSVError::CSVError(string error_message_p, CSVErrorType type_p, idx_t column_idx_p, vector<Value> row_p,
|
80
|
+
LinesPerBoundary error_info_p)
|
81
|
+
: error_message(std::move(error_message_p)), type(type_p), column_idx(column_idx_p), row(std::move(row_p)),
|
82
|
+
error_info(error_info_p) {
|
69
83
|
}
|
70
84
|
|
71
85
|
CSVError CSVError::ColumnTypesError(case_insensitive_map_t<idx_t> sql_types_per_column, const vector<string> &names) {
|
@@ -77,7 +91,7 @@ CSVError CSVError::ColumnTypesError(case_insensitive_map_t<idx_t> sql_types_per_
|
|
77
91
|
}
|
78
92
|
}
|
79
93
|
if (sql_types_per_column.empty()) {
|
80
|
-
return CSVError("", CSVErrorType::COLUMN_NAME_TYPE_MISMATCH);
|
94
|
+
return CSVError("", CSVErrorType::COLUMN_NAME_TYPE_MISMATCH, {});
|
81
95
|
}
|
82
96
|
string exception = "COLUMN_TYPES error: Columns with names: ";
|
83
97
|
for (auto &col : sql_types_per_column) {
|
@@ -85,28 +99,43 @@ CSVError CSVError::ColumnTypesError(case_insensitive_map_t<idx_t> sql_types_per_
|
|
85
99
|
}
|
86
100
|
exception.pop_back();
|
87
101
|
exception += " do not exist in the CSV File";
|
88
|
-
return CSVError(exception, CSVErrorType::COLUMN_NAME_TYPE_MISMATCH);
|
102
|
+
return CSVError(exception, CSVErrorType::COLUMN_NAME_TYPE_MISMATCH, {});
|
89
103
|
}
|
90
104
|
|
91
105
|
CSVError CSVError::CastError(const CSVReaderOptions &options, string &column_name, string &cast_error, idx_t column_idx,
|
92
|
-
vector<Value> &row) {
|
106
|
+
vector<Value> &row, LinesPerBoundary error_info, LogicalTypeId type) {
|
93
107
|
std::ostringstream error;
|
94
108
|
// Which column
|
95
109
|
error << "Error when converting column \"" << column_name << "\"." << std::endl;
|
96
110
|
// What was the cast error
|
97
111
|
error << cast_error << std::endl;
|
98
|
-
|
99
|
-
|
112
|
+
|
113
|
+
error << "Column " << column_name << " is being converted as type " << LogicalTypeIdToString(type) << std::endl;
|
114
|
+
if (!options.WasTypeManuallySet(column_idx)) {
|
115
|
+
error << "This type was auto-detected from the CSV file." << std::endl;
|
116
|
+
error << "Possible solutions:" << std::endl;
|
117
|
+
error << "* Override the type for this column manually by setting the type explicitly, e.g. types={'"
|
118
|
+
<< column_name << "': 'VARCHAR'}" << std::endl;
|
119
|
+
error << "* Set the sample size to a larger value to enable the auto-detection to scan more values, e.g. "
|
120
|
+
"sample_size=-1"
|
121
|
+
<< std::endl;
|
122
|
+
error << "* Use a COPY statement to automatically derive types from an existing table." << std::endl;
|
123
|
+
} else {
|
124
|
+
error << "This type was either manually set or derived from an existing table. Select a different type to "
|
125
|
+
"correctly parse this column."
|
126
|
+
<< std::endl;
|
127
|
+
}
|
100
128
|
error << options.ToString();
|
101
|
-
|
129
|
+
|
130
|
+
return CSVError(error.str(), CSVErrorType::CAST_ERROR, column_idx, row, error_info);
|
102
131
|
}
|
103
132
|
|
104
|
-
CSVError CSVError::LineSizeError(const CSVReaderOptions &options, idx_t actual_size) {
|
133
|
+
CSVError CSVError::LineSizeError(const CSVReaderOptions &options, idx_t actual_size, LinesPerBoundary error_info) {
|
105
134
|
std::ostringstream error;
|
106
135
|
error << "Maximum line size of " << options.maximum_line_size << " bytes exceeded. ";
|
107
136
|
error << "Actual Size:" << actual_size << " bytes." << std::endl;
|
108
137
|
error << options.ToString();
|
109
|
-
return CSVError(error.str(), CSVErrorType::MAXIMUM_LINE_SIZE);
|
138
|
+
return CSVError(error.str(), CSVErrorType::MAXIMUM_LINE_SIZE, error_info);
|
110
139
|
}
|
111
140
|
|
112
141
|
CSVError CSVError::SniffingError(string &file_path) {
|
@@ -114,72 +143,91 @@ CSVError CSVError::SniffingError(string &file_path) {
|
|
114
143
|
// Which column
|
115
144
|
error << "Error when sniffing file \"" << file_path << "\"." << std::endl;
|
116
145
|
error << "CSV options could not be auto-detected. Consider setting parser options manually." << std::endl;
|
117
|
-
return CSVError(error.str(), CSVErrorType::SNIFFING);
|
146
|
+
return CSVError(error.str(), CSVErrorType::SNIFFING, {});
|
118
147
|
}
|
119
148
|
|
120
|
-
CSVError CSVError::NullPaddingFail(const CSVReaderOptions &options) {
|
149
|
+
CSVError CSVError::NullPaddingFail(const CSVReaderOptions &options, LinesPerBoundary error_info) {
|
121
150
|
std::ostringstream error;
|
122
151
|
error << " The parallel scanner does not support null_padding in conjunction with quoted new lines. Please "
|
123
152
|
"disable the parallel csv reader with parallel=false"
|
124
153
|
<< std::endl;
|
125
154
|
// What were the options
|
126
155
|
error << options.ToString();
|
127
|
-
return CSVError(error.str(), CSVErrorType::NULLPADDED_QUOTED_NEW_VALUE);
|
156
|
+
return CSVError(error.str(), CSVErrorType::NULLPADDED_QUOTED_NEW_VALUE, error_info);
|
128
157
|
}
|
129
158
|
|
130
159
|
CSVError CSVError::UnterminatedQuotesError(const CSVReaderOptions &options, string_t *vector_ptr,
|
131
|
-
idx_t vector_line_start, idx_t current_column) {
|
160
|
+
idx_t vector_line_start, idx_t current_column, LinesPerBoundary error_info) {
|
132
161
|
std::ostringstream error;
|
133
162
|
error << "Value with unterminated quote found." << std::endl;
|
134
163
|
error << std::endl;
|
135
164
|
// What were the options
|
136
165
|
error << options.ToString();
|
137
|
-
return CSVError(error.str(), CSVErrorType::UNTERMINATED_QUOTES);
|
166
|
+
return CSVError(error.str(), CSVErrorType::UNTERMINATED_QUOTES, error_info);
|
138
167
|
}
|
139
168
|
|
140
169
|
CSVError CSVError::IncorrectColumnAmountError(const CSVReaderOptions &options, string_t *vector_ptr,
|
141
|
-
idx_t vector_line_start, idx_t actual_columns
|
170
|
+
idx_t vector_line_start, idx_t actual_columns,
|
171
|
+
LinesPerBoundary error_info) {
|
142
172
|
std::ostringstream error;
|
143
173
|
// How many columns were expected and how many were found
|
144
174
|
error << "Expected Number of Columns: " << options.dialect_options.num_cols << " Found: " << actual_columns
|
145
175
|
<< std::endl;
|
176
|
+
error << std::endl << "Possible fixes:" << std::endl;
|
177
|
+
if (!options.null_padding) {
|
178
|
+
error << "* Enable null padding (null_padding=true) to replace missing values with NULL" << std::endl;
|
179
|
+
}
|
180
|
+
if (!options.ignore_errors) {
|
181
|
+
error << "* Enable ignore errors (ignore_errors=true) to skip this row" << std::endl;
|
182
|
+
}
|
183
|
+
error << std::endl;
|
184
|
+
// What were the options
|
185
|
+
error << options.ToString();
|
186
|
+
return CSVError(error.str(), CSVErrorType::INCORRECT_COLUMN_AMOUNT, error_info);
|
187
|
+
}
|
188
|
+
|
189
|
+
CSVError CSVError::InvalidUTF8(const CSVReaderOptions &options, LinesPerBoundary error_info) {
|
190
|
+
std::ostringstream error;
|
191
|
+
// How many columns were expected and how many were found
|
192
|
+
error << "Invalid unicode (byte sequence mismatch) detected." << std::endl;
|
146
193
|
// What were the options
|
147
194
|
error << options.ToString();
|
148
|
-
return CSVError(error.str(), CSVErrorType::
|
195
|
+
return CSVError(error.str(), CSVErrorType::INVALID_UNICODE, error_info);
|
149
196
|
}
|
150
197
|
|
151
198
|
bool CSVErrorHandler::PrintLineNumber(CSVError &error) {
|
199
|
+
if (!print_line) {
|
200
|
+
return false;
|
201
|
+
}
|
152
202
|
switch (error.type) {
|
153
203
|
case CSVErrorType::CAST_ERROR:
|
154
204
|
case CSVErrorType::UNTERMINATED_QUOTES:
|
155
205
|
case CSVErrorType::INCORRECT_COLUMN_AMOUNT:
|
156
206
|
case CSVErrorType::MAXIMUM_LINE_SIZE:
|
157
207
|
case CSVErrorType::NULLPADDED_QUOTED_NEW_VALUE:
|
208
|
+
case CSVErrorType::INVALID_UNICODE:
|
158
209
|
return true;
|
159
210
|
default:
|
160
211
|
return false;
|
161
212
|
}
|
162
213
|
}
|
163
214
|
|
164
|
-
|
165
|
-
idx_t
|
166
|
-
|
167
|
-
|
168
|
-
while (!batch_done) {
|
169
|
-
if (boundary_idx == 0) {
|
170
|
-
// if it's the first boundary, we just return
|
171
|
-
break;
|
172
|
-
}
|
173
|
-
lock_guard<mutex> parallel_lock(main_mutex);
|
174
|
-
if (lines_per_batch_map.find(boundary_idx) != lines_per_batch_map.end()) {
|
175
|
-
batch_done = true;
|
176
|
-
current_line += lines_per_batch_map[boundary_idx].lines_in_batch;
|
177
|
-
}
|
178
|
-
if (got_borked) {
|
179
|
-
return current_line;
|
180
|
-
}
|
215
|
+
bool CSVErrorHandler::CanGetLine(idx_t boundary_index) {
|
216
|
+
for (idx_t i = 0; i < boundary_index; i++) {
|
217
|
+
if (lines_per_batch_map.find(i) == lines_per_batch_map.end()) {
|
218
|
+
return false;
|
181
219
|
}
|
182
220
|
}
|
221
|
+
return true;
|
222
|
+
}
|
223
|
+
|
224
|
+
idx_t CSVErrorHandler::GetLine(const LinesPerBoundary &error_info) {
|
225
|
+
lock_guard<mutex> parallel_lock(main_mutex);
|
226
|
+
// We start from one, since the lines are 1-indexed
|
227
|
+
idx_t current_line = 1 + error_info.lines_in_batch;
|
228
|
+
for (idx_t boundary_idx = 0; boundary_idx < error_info.boundary_idx; boundary_idx++) {
|
229
|
+
current_line += lines_per_batch_map[boundary_idx].lines_in_batch;
|
230
|
+
}
|
183
231
|
return current_line;
|
184
232
|
}
|
185
233
|
|
@@ -1,4 +1,4 @@
|
|
1
|
-
#include "duckdb/execution/operator/csv_scanner/
|
1
|
+
#include "duckdb/execution/operator/csv_scanner/csv_reader_options.hpp"
|
2
2
|
#include "duckdb/common/bind_helpers.hpp"
|
3
3
|
#include "duckdb/common/vector_size.hpp"
|
4
4
|
#include "duckdb/common/string_util.hpp"
|
@@ -297,6 +297,13 @@ template <class T>
|
|
297
297
|
string FormatOptionLine(const string &name, const CSVOption<T> option) {
|
298
298
|
return name + " = " + option.FormatValue() + " " + option.FormatSet() + "\n ";
|
299
299
|
}
|
300
|
+
bool CSVReaderOptions::WasTypeManuallySet(idx_t i) const {
|
301
|
+
if (i >= was_type_manually_set.size()) {
|
302
|
+
return false;
|
303
|
+
}
|
304
|
+
return was_type_manually_set[i];
|
305
|
+
}
|
306
|
+
|
300
307
|
string CSVReaderOptions::ToString() const {
|
301
308
|
auto &delimiter = dialect_options.state_machine_options.delimiter;
|
302
309
|
auto "e = dialect_options.state_machine_options.quote;
|
@@ -8,12 +8,10 @@
|
|
8
8
|
|
9
9
|
namespace duckdb {
|
10
10
|
|
11
|
-
PhysicalLimit::PhysicalLimit(vector<LogicalType> types,
|
12
|
-
unique_ptr<Expression> limit_expression, unique_ptr<Expression> offset_expression,
|
11
|
+
PhysicalLimit::PhysicalLimit(vector<LogicalType> types, BoundLimitNode limit_val_p, BoundLimitNode offset_val_p,
|
13
12
|
idx_t estimated_cardinality)
|
14
|
-
: PhysicalOperator(PhysicalOperatorType::LIMIT, std::move(types), estimated_cardinality),
|
15
|
-
|
16
|
-
offset_expression(std::move(offset_expression)) {
|
13
|
+
: PhysicalOperator(PhysicalOperatorType::LIMIT, std::move(types), estimated_cardinality),
|
14
|
+
limit_val(std::move(limit_val_p)), offset_val(std::move(offset_val_p)) {
|
17
15
|
}
|
18
16
|
|
19
17
|
//===--------------------------------------------------------------------===//
|
@@ -36,13 +34,12 @@ class LimitLocalState : public LocalSinkState {
|
|
36
34
|
public:
|
37
35
|
explicit LimitLocalState(ClientContext &context, const PhysicalLimit &op)
|
38
36
|
: current_offset(0), data(context, op.types, true) {
|
39
|
-
|
40
|
-
this->offset = op.offset_expression ? DConstants::INVALID_INDEX : op.offset_value;
|
37
|
+
PhysicalLimit::SetInitialLimits(op.limit_val, op.offset_val, limit, offset);
|
41
38
|
}
|
42
39
|
|
43
40
|
idx_t current_offset;
|
44
|
-
|
45
|
-
|
41
|
+
optional_idx limit;
|
42
|
+
optional_idx offset;
|
46
43
|
BatchedDataCollection data;
|
47
44
|
};
|
48
45
|
|
@@ -54,38 +51,56 @@ unique_ptr<LocalSinkState> PhysicalLimit::GetLocalSinkState(ExecutionContext &co
|
|
54
51
|
return make_uniq<LimitLocalState>(context.client, *this);
|
55
52
|
}
|
56
53
|
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
54
|
+
void PhysicalLimit::SetInitialLimits(const BoundLimitNode &limit_val, const BoundLimitNode &offset_val,
|
55
|
+
optional_idx &limit, optional_idx &offset) {
|
56
|
+
switch (limit_val.Type()) {
|
57
|
+
case LimitNodeType::CONSTANT_VALUE:
|
58
|
+
limit = limit_val.GetConstantValue();
|
59
|
+
break;
|
60
|
+
case LimitNodeType::UNSET:
|
61
|
+
limit = MAX_LIMIT_VALUE;
|
62
|
+
break;
|
63
|
+
default:
|
64
|
+
break;
|
65
65
|
}
|
66
|
+
switch (offset_val.Type()) {
|
67
|
+
case LimitNodeType::CONSTANT_VALUE:
|
68
|
+
offset = offset_val.GetConstantValue();
|
69
|
+
break;
|
70
|
+
case LimitNodeType::UNSET:
|
71
|
+
offset = 0;
|
72
|
+
break;
|
73
|
+
default:
|
74
|
+
break;
|
75
|
+
}
|
76
|
+
}
|
66
77
|
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
78
|
+
bool PhysicalLimit::ComputeOffset(ExecutionContext &context, DataChunk &input, optional_idx &limit,
|
79
|
+
optional_idx &offset, idx_t current_offset, idx_t &max_element,
|
80
|
+
const BoundLimitNode &limit_val, const BoundLimitNode &offset_val) {
|
81
|
+
if (!limit.IsValid()) {
|
82
|
+
Value val = GetDelimiter(context, input, limit_val.GetValueExpression());
|
71
83
|
if (!val.IsNull()) {
|
72
84
|
limit = val.GetValue<idx_t>();
|
85
|
+
} else {
|
86
|
+
limit = MAX_LIMIT_VALUE;
|
73
87
|
}
|
74
|
-
if (limit >
|
75
|
-
throw BinderException("Max value %lld for LIMIT/OFFSET is %lld", limit,
|
88
|
+
if (limit.GetIndex() > MAX_LIMIT_VALUE) {
|
89
|
+
throw BinderException("Max value %lld for LIMIT/OFFSET is %lld", limit.GetIndex(), MAX_LIMIT_VALUE);
|
76
90
|
}
|
77
91
|
}
|
78
|
-
if (offset
|
79
|
-
|
80
|
-
Value val = GetDelimiter(context, input, offset_expression);
|
92
|
+
if (!offset.IsValid()) {
|
93
|
+
Value val = GetDelimiter(context, input, offset_val.GetValueExpression());
|
81
94
|
if (!val.IsNull()) {
|
82
95
|
offset = val.GetValue<idx_t>();
|
96
|
+
} else {
|
97
|
+
offset = 0;
|
83
98
|
}
|
84
|
-
if (offset >
|
85
|
-
throw BinderException("Max value %lld for LIMIT/OFFSET is %lld", offset,
|
99
|
+
if (offset.GetIndex() > MAX_LIMIT_VALUE) {
|
100
|
+
throw BinderException("Max value %lld for LIMIT/OFFSET is %lld", offset.GetIndex(), MAX_LIMIT_VALUE);
|
86
101
|
}
|
87
102
|
}
|
88
|
-
max_element = limit + offset;
|
103
|
+
max_element = limit.GetIndex() + offset.GetIndex();
|
89
104
|
if (limit == 0 || current_offset >= max_element) {
|
90
105
|
return false;
|
91
106
|
}
|
@@ -100,8 +115,7 @@ SinkResultType PhysicalLimit::Sink(ExecutionContext &context, DataChunk &chunk,
|
|
100
115
|
auto &offset = state.offset;
|
101
116
|
|
102
117
|
idx_t max_element;
|
103
|
-
if (!ComputeOffset(context, chunk, limit, offset, state.current_offset, max_element,
|
104
|
-
offset_expression.get())) {
|
118
|
+
if (!ComputeOffset(context, chunk, limit, offset, state.current_offset, max_element, limit_val, offset_val)) {
|
105
119
|
return SinkResultType::FINISHED;
|
106
120
|
}
|
107
121
|
auto max_cardinality = max_element - state.current_offset;
|
@@ -121,8 +135,12 @@ SinkCombineResultType PhysicalLimit::Combine(ExecutionContext &context, Operator
|
|
121
135
|
auto &state = input.local_state.Cast<LimitLocalState>();
|
122
136
|
|
123
137
|
lock_guard<mutex> lock(gstate.glock);
|
124
|
-
|
125
|
-
|
138
|
+
if (state.limit.IsValid()) {
|
139
|
+
gstate.limit = state.limit.GetIndex();
|
140
|
+
}
|
141
|
+
if (state.offset.IsValid()) {
|
142
|
+
gstate.offset = state.offset.GetIndex();
|
143
|
+
}
|
126
144
|
gstate.data.Merge(state.data);
|
127
145
|
|
128
146
|
return SinkCombineResultType::FINISHED;
|
@@ -209,12 +227,12 @@ bool PhysicalLimit::HandleOffset(DataChunk &input, idx_t ¤t_offset, idx_t
|
|
209
227
|
return true;
|
210
228
|
}
|
211
229
|
|
212
|
-
Value PhysicalLimit::GetDelimiter(ExecutionContext &context, DataChunk &input, Expression
|
230
|
+
Value PhysicalLimit::GetDelimiter(ExecutionContext &context, DataChunk &input, const Expression &expr) {
|
213
231
|
DataChunk limit_chunk;
|
214
|
-
vector<LogicalType> types {expr
|
232
|
+
vector<LogicalType> types {expr.return_type};
|
215
233
|
auto &allocator = Allocator::Get(context.client);
|
216
234
|
limit_chunk.Initialize(allocator, types);
|
217
|
-
ExpressionExecutor limit_executor(context.client, expr);
|
235
|
+
ExpressionExecutor limit_executor(context.client, &expr);
|
218
236
|
auto input_size = input.size();
|
219
237
|
input.SetCardinality(1);
|
220
238
|
limit_executor.Execute(input, limit_chunk);
|
@@ -7,6 +7,13 @@
|
|
7
7
|
|
8
8
|
namespace duckdb {
|
9
9
|
|
10
|
+
PhysicalLimitPercent::PhysicalLimitPercent(vector<LogicalType> types, BoundLimitNode limit_val_p,
|
11
|
+
BoundLimitNode offset_val_p, idx_t estimated_cardinality)
|
12
|
+
: PhysicalOperator(PhysicalOperatorType::LIMIT_PERCENT, std::move(types), estimated_cardinality),
|
13
|
+
limit_val(std::move(limit_val_p)), offset_val(std::move(offset_val_p)) {
|
14
|
+
D_ASSERT(limit_val.Type() == LimitNodeType::CONSTANT_PERCENTAGE ||
|
15
|
+
limit_val.Type() == LimitNodeType::EXPRESSION_PERCENTAGE);
|
16
|
+
}
|
10
17
|
//===--------------------------------------------------------------------===//
|
11
18
|
// Sink
|
12
19
|
//===--------------------------------------------------------------------===//
|
@@ -14,28 +21,37 @@ class LimitPercentGlobalState : public GlobalSinkState {
|
|
14
21
|
public:
|
15
22
|
explicit LimitPercentGlobalState(ClientContext &context, const PhysicalLimitPercent &op)
|
16
23
|
: current_offset(0), data(context, op.GetTypes()) {
|
17
|
-
|
18
|
-
|
19
|
-
|
20
|
-
|
21
|
-
|
24
|
+
switch (op.limit_val.Type()) {
|
25
|
+
case LimitNodeType::CONSTANT_PERCENTAGE:
|
26
|
+
this->limit_percent = op.limit_val.GetConstantPercentage();
|
27
|
+
this->is_limit_set = true;
|
28
|
+
break;
|
29
|
+
case LimitNodeType::EXPRESSION_PERCENTAGE:
|
30
|
+
this->is_limit_set = false;
|
31
|
+
break;
|
32
|
+
default:
|
33
|
+
throw InternalException("Unsupported type for limit value in PhysicalLimitPercent");
|
22
34
|
}
|
23
|
-
|
24
|
-
|
25
|
-
this->offset = op.
|
26
|
-
|
27
|
-
|
35
|
+
switch (op.offset_val.Type()) {
|
36
|
+
case LimitNodeType::CONSTANT_VALUE:
|
37
|
+
this->offset = op.offset_val.GetConstantValue();
|
38
|
+
break;
|
39
|
+
case LimitNodeType::UNSET:
|
28
40
|
this->offset = 0;
|
41
|
+
break;
|
42
|
+
case LimitNodeType::EXPRESSION_VALUE:
|
43
|
+
break;
|
44
|
+
default:
|
45
|
+
throw InternalException("Unsupported type for offset value in PhysicalLimitPercent");
|
29
46
|
}
|
30
47
|
}
|
31
48
|
|
32
49
|
idx_t current_offset;
|
33
50
|
double limit_percent;
|
34
|
-
|
51
|
+
optional_idx offset;
|
35
52
|
ColumnDataCollection data;
|
36
53
|
|
37
|
-
bool
|
38
|
-
bool is_offset_delimited = false;
|
54
|
+
bool is_limit_set = false;
|
39
55
|
};
|
40
56
|
|
41
57
|
unique_ptr<GlobalSinkState> PhysicalLimitPercent::GetGlobalSinkState(ClientContext &context) const {
|
@@ -49,28 +65,31 @@ SinkResultType PhysicalLimitPercent::Sink(ExecutionContext &context, DataChunk &
|
|
49
65
|
auto &offset = state.offset;
|
50
66
|
|
51
67
|
// get the next chunk from the child
|
52
|
-
if (!state.
|
53
|
-
Value val = PhysicalLimit::GetDelimiter(context, chunk,
|
68
|
+
if (!state.is_limit_set) {
|
69
|
+
Value val = PhysicalLimit::GetDelimiter(context, chunk, limit_val.GetPercentageExpression());
|
54
70
|
if (!val.IsNull()) {
|
55
71
|
limit_percent = val.GetValue<double>();
|
72
|
+
} else {
|
73
|
+
limit_percent = 100.0;
|
56
74
|
}
|
57
75
|
if (limit_percent < 0.0) {
|
58
76
|
throw BinderException("Percentage value(%f) can't be negative", limit_percent);
|
59
77
|
}
|
60
|
-
state.
|
78
|
+
state.is_limit_set = true;
|
61
79
|
}
|
62
|
-
if (!state.
|
63
|
-
Value val = PhysicalLimit::GetDelimiter(context, chunk,
|
80
|
+
if (!state.offset.IsValid()) {
|
81
|
+
Value val = PhysicalLimit::GetDelimiter(context, chunk, offset_val.GetValueExpression());
|
64
82
|
if (!val.IsNull()) {
|
65
83
|
offset = val.GetValue<idx_t>();
|
84
|
+
} else {
|
85
|
+
offset = 0;
|
66
86
|
}
|
67
|
-
if (offset > 1ULL << 62ULL) {
|
68
|
-
throw BinderException("Max value %lld for LIMIT/OFFSET is %lld", offset, 1ULL << 62ULL);
|
87
|
+
if (offset.GetIndex() > 1ULL << 62ULL) {
|
88
|
+
throw BinderException("Max value %lld for LIMIT/OFFSET is %lld", offset.GetIndex(), 1ULL << 62ULL);
|
69
89
|
}
|
70
|
-
state.is_offset_delimited = true;
|
71
90
|
}
|
72
91
|
|
73
|
-
if (!PhysicalLimit::HandleOffset(chunk, state.current_offset, offset,
|
92
|
+
if (!PhysicalLimit::HandleOffset(chunk, state.current_offset, offset.GetIndex(), NumericLimits<idx_t>::Maximum())) {
|
74
93
|
return SinkResultType::NEED_MORE_INPUT;
|
75
94
|
}
|
76
95
|
|
@@ -83,15 +102,14 @@ SinkResultType PhysicalLimitPercent::Sink(ExecutionContext &context, DataChunk &
|
|
83
102
|
//===--------------------------------------------------------------------===//
|
84
103
|
class LimitPercentOperatorState : public GlobalSourceState {
|
85
104
|
public:
|
86
|
-
explicit LimitPercentOperatorState(const PhysicalLimitPercent &op)
|
87
|
-
: limit(DConstants::INVALID_INDEX), current_offset(0) {
|
105
|
+
explicit LimitPercentOperatorState(const PhysicalLimitPercent &op) : current_offset(0) {
|
88
106
|
D_ASSERT(op.sink_state);
|
89
107
|
auto &gstate = op.sink_state->Cast<LimitPercentGlobalState>();
|
90
108
|
gstate.data.InitializeScan(scan_state);
|
91
109
|
}
|
92
110
|
|
93
111
|
ColumnDataScanState scan_state;
|
94
|
-
|
112
|
+
optional_idx limit;
|
95
113
|
idx_t current_offset;
|
96
114
|
};
|
97
115
|
|
@@ -108,33 +126,39 @@ SourceResultType PhysicalLimitPercent::GetData(ExecutionContext &context, DataCh
|
|
108
126
|
auto &limit = state.limit;
|
109
127
|
auto ¤t_offset = state.current_offset;
|
110
128
|
|
111
|
-
if (
|
129
|
+
if (!limit.IsValid()) {
|
130
|
+
if (!gstate.is_limit_set) {
|
131
|
+
// no limit value and we have not set limit_percent
|
132
|
+
// we are running LIMIT % with a subquery over an empty table
|
133
|
+
D_ASSERT(gstate.data.Count() == 0);
|
134
|
+
return SourceResultType::FINISHED;
|
135
|
+
}
|
112
136
|
idx_t count = gstate.data.Count();
|
113
137
|
if (count > 0) {
|
114
|
-
count += offset;
|
138
|
+
count += offset.GetIndex();
|
115
139
|
}
|
116
140
|
if (Value::IsNan(percent_limit) || percent_limit < 0 || percent_limit > 100) {
|
117
141
|
throw OutOfRangeException("Limit percent out of range, should be between 0% and 100%");
|
118
142
|
}
|
119
|
-
|
120
|
-
if (
|
143
|
+
auto limit_percentage = idx_t(percent_limit / 100.0 * double(count));
|
144
|
+
if (limit_percentage > count) {
|
121
145
|
limit = count;
|
122
146
|
} else {
|
123
|
-
limit = idx_t(
|
147
|
+
limit = idx_t(limit_percentage);
|
124
148
|
}
|
125
149
|
if (limit == 0) {
|
126
150
|
return SourceResultType::FINISHED;
|
127
151
|
}
|
128
152
|
}
|
129
153
|
|
130
|
-
if (current_offset >= limit) {
|
154
|
+
if (current_offset >= limit.GetIndex()) {
|
131
155
|
return SourceResultType::FINISHED;
|
132
156
|
}
|
133
157
|
if (!gstate.data.Scan(state.scan_state, chunk)) {
|
134
158
|
return SourceResultType::FINISHED;
|
135
159
|
}
|
136
160
|
|
137
|
-
PhysicalLimit::HandleOffset(chunk, current_offset, 0, limit);
|
161
|
+
PhysicalLimit::HandleOffset(chunk, current_offset, 0, limit.GetIndex());
|
138
162
|
|
139
163
|
return SourceResultType::HAVE_MORE_OUTPUT;
|
140
164
|
}
|
@@ -3,13 +3,10 @@
|
|
3
3
|
|
4
4
|
namespace duckdb {
|
5
5
|
|
6
|
-
PhysicalStreamingLimit::PhysicalStreamingLimit(vector<LogicalType> types,
|
7
|
-
|
8
|
-
unique_ptr<Expression> offset_expression, idx_t estimated_cardinality,
|
9
|
-
bool parallel)
|
6
|
+
PhysicalStreamingLimit::PhysicalStreamingLimit(vector<LogicalType> types, BoundLimitNode limit_val_p,
|
7
|
+
BoundLimitNode offset_val_p, idx_t estimated_cardinality, bool parallel)
|
10
8
|
: PhysicalOperator(PhysicalOperatorType::STREAMING_LIMIT, std::move(types), estimated_cardinality),
|
11
|
-
|
12
|
-
offset_expression(std::move(offset_expression)), parallel(parallel) {
|
9
|
+
limit_val(std::move(limit_val_p)), offset_val(std::move(offset_val_p)), parallel(parallel) {
|
13
10
|
}
|
14
11
|
|
15
12
|
//===--------------------------------------------------------------------===//
|
@@ -18,12 +15,11 @@ PhysicalStreamingLimit::PhysicalStreamingLimit(vector<LogicalType> types, idx_t
|
|
18
15
|
class StreamingLimitOperatorState : public OperatorState {
|
19
16
|
public:
|
20
17
|
explicit StreamingLimitOperatorState(const PhysicalStreamingLimit &op) {
|
21
|
-
|
22
|
-
this->offset = op.offset_expression ? DConstants::INVALID_INDEX : op.offset_value;
|
18
|
+
PhysicalLimit::SetInitialLimits(op.limit_val, op.offset_val, limit, offset);
|
23
19
|
}
|
24
20
|
|
25
|
-
|
26
|
-
|
21
|
+
optional_idx limit;
|
22
|
+
optional_idx offset;
|
27
23
|
};
|
28
24
|
|
29
25
|
class StreamingLimitGlobalState : public GlobalOperatorState {
|
@@ -50,11 +46,11 @@ OperatorResultType PhysicalStreamingLimit::Execute(ExecutionContext &context, Da
|
|
50
46
|
auto &offset = state.offset;
|
51
47
|
idx_t current_offset = gstate.current_offset.fetch_add(input.size());
|
52
48
|
idx_t max_element;
|
53
|
-
if (!PhysicalLimit::ComputeOffset(context, input, limit, offset, current_offset, max_element,
|
54
|
-
|
49
|
+
if (!PhysicalLimit::ComputeOffset(context, input, limit, offset, current_offset, max_element, limit_val,
|
50
|
+
offset_val)) {
|
55
51
|
return OperatorResultType::FINISHED;
|
56
52
|
}
|
57
|
-
if (PhysicalLimit::HandleOffset(input, current_offset, offset, limit)) {
|
53
|
+
if (PhysicalLimit::HandleOffset(input, current_offset, offset.GetIndex(), limit.GetIndex())) {
|
58
54
|
chunk.Reference(input);
|
59
55
|
}
|
60
56
|
return OperatorResultType::NEED_MORE_INPUT;
|