duckdb 0.7.2-dev1901.0 → 0.7.2-dev2144.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (179) hide show
  1. package/binding.gyp +2 -0
  2. package/package.json +1 -1
  3. package/src/duckdb/extension/parquet/include/parquet_writer.hpp +1 -1
  4. package/src/duckdb/extension/parquet/parquet_metadata.cpp +4 -2
  5. package/src/duckdb/src/catalog/catalog_entry/duck_index_entry.cpp +1 -1
  6. package/src/duckdb/src/common/arrow/arrow_appender.cpp +69 -44
  7. package/src/duckdb/src/common/arrow/arrow_converter.cpp +1 -1
  8. package/src/duckdb/src/common/arrow/arrow_wrapper.cpp +20 -2
  9. package/src/duckdb/src/common/box_renderer.cpp +4 -2
  10. package/src/duckdb/src/common/constants.cpp +10 -1
  11. package/src/duckdb/src/common/filename_pattern.cpp +41 -0
  12. package/src/duckdb/src/common/hive_partitioning.cpp +144 -15
  13. package/src/duckdb/src/common/radix_partitioning.cpp +101 -369
  14. package/src/duckdb/src/common/row_operations/row_aggregate.cpp +8 -9
  15. package/src/duckdb/src/common/row_operations/row_external.cpp +1 -1
  16. package/src/duckdb/src/common/row_operations/row_gather.cpp +5 -3
  17. package/src/duckdb/src/common/row_operations/row_match.cpp +117 -22
  18. package/src/duckdb/src/common/row_operations/row_scatter.cpp +2 -2
  19. package/src/duckdb/src/common/sort/partition_state.cpp +1 -1
  20. package/src/duckdb/src/common/sort/sort_state.cpp +2 -1
  21. package/src/duckdb/src/common/sort/sorted_block.cpp +1 -1
  22. package/src/duckdb/src/common/types/{column_data_allocator.cpp → column/column_data_allocator.cpp} +2 -2
  23. package/src/duckdb/src/common/types/{column_data_collection.cpp → column/column_data_collection.cpp} +22 -4
  24. package/src/duckdb/src/common/types/{column_data_collection_segment.cpp → column/column_data_collection_segment.cpp} +2 -1
  25. package/src/duckdb/src/common/types/{column_data_consumer.cpp → column/column_data_consumer.cpp} +1 -1
  26. package/src/duckdb/src/common/types/{partitioned_column_data.cpp → column/partitioned_column_data.cpp} +11 -9
  27. package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +316 -0
  28. package/src/duckdb/src/common/types/{row_data_collection.cpp → row/row_data_collection.cpp} +1 -1
  29. package/src/duckdb/src/common/types/{row_data_collection_scanner.cpp → row/row_data_collection_scanner.cpp} +2 -2
  30. package/src/duckdb/src/common/types/{row_layout.cpp → row/row_layout.cpp} +1 -1
  31. package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +465 -0
  32. package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +511 -0
  33. package/src/duckdb/src/common/types/row/tuple_data_iterator.cpp +96 -0
  34. package/src/duckdb/src/common/types/row/tuple_data_layout.cpp +119 -0
  35. package/src/duckdb/src/common/types/row/tuple_data_scatter_gather.cpp +1200 -0
  36. package/src/duckdb/src/common/types/row/tuple_data_segment.cpp +170 -0
  37. package/src/duckdb/src/common/types/vector.cpp +1 -1
  38. package/src/duckdb/src/execution/aggregate_hashtable.cpp +252 -290
  39. package/src/duckdb/src/execution/join_hashtable.cpp +192 -328
  40. package/src/duckdb/src/execution/operator/aggregate/physical_window.cpp +4 -4
  41. package/src/duckdb/src/execution/operator/helper/physical_execute.cpp +3 -3
  42. package/src/duckdb/src/execution/operator/helper/physical_limit_percent.cpp +2 -3
  43. package/src/duckdb/src/execution/operator/helper/physical_result_collector.cpp +2 -3
  44. package/src/duckdb/src/execution/operator/join/perfect_hash_join_executor.cpp +36 -21
  45. package/src/duckdb/src/execution/operator/join/physical_blockwise_nl_join.cpp +2 -2
  46. package/src/duckdb/src/execution/operator/join/physical_cross_product.cpp +1 -1
  47. package/src/duckdb/src/execution/operator/join/physical_delim_join.cpp +2 -2
  48. package/src/duckdb/src/execution/operator/join/physical_hash_join.cpp +166 -144
  49. package/src/duckdb/src/execution/operator/join/physical_index_join.cpp +5 -5
  50. package/src/duckdb/src/execution/operator/join/physical_join.cpp +2 -10
  51. package/src/duckdb/src/execution/operator/join/physical_positional_join.cpp +0 -1
  52. package/src/duckdb/src/execution/operator/order/physical_top_n.cpp +2 -2
  53. package/src/duckdb/src/execution/operator/persistent/physical_copy_to_file.cpp +13 -11
  54. package/src/duckdb/src/execution/operator/persistent/physical_delete.cpp +3 -2
  55. package/src/duckdb/src/execution/operator/persistent/physical_export.cpp +25 -24
  56. package/src/duckdb/src/execution/operator/persistent/physical_insert.cpp +1 -1
  57. package/src/duckdb/src/execution/operator/persistent/physical_update.cpp +4 -3
  58. package/src/duckdb/src/execution/operator/schema/physical_create_type.cpp +1 -1
  59. package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +3 -3
  60. package/src/duckdb/src/execution/partitionable_hashtable.cpp +9 -37
  61. package/src/duckdb/src/execution/physical_operator.cpp +1 -1
  62. package/src/duckdb/src/execution/physical_plan/plan_comparison_join.cpp +19 -18
  63. package/src/duckdb/src/execution/physical_plan/plan_copy_to_file.cpp +2 -1
  64. package/src/duckdb/src/execution/physical_plan/plan_execute.cpp +2 -2
  65. package/src/duckdb/src/execution/physical_plan/plan_explain.cpp +5 -6
  66. package/src/duckdb/src/execution/physical_plan/plan_expression_get.cpp +2 -2
  67. package/src/duckdb/src/execution/physical_plan/plan_recursive_cte.cpp +3 -3
  68. package/src/duckdb/src/execution/physical_plan_generator.cpp +1 -1
  69. package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +39 -17
  70. package/src/duckdb/src/function/aggregate/sorted_aggregate_function.cpp +2 -2
  71. package/src/duckdb/src/function/table/pragma_detailed_profiling_output.cpp +5 -5
  72. package/src/duckdb/src/function/table/pragma_last_profiling_output.cpp +2 -2
  73. package/src/duckdb/src/function/table/version/pragma_version.cpp +2 -2
  74. package/src/duckdb/src/include/duckdb/catalog/catalog_entry/index_catalog_entry.hpp +1 -1
  75. package/src/duckdb/src/include/duckdb/common/arrow/arrow_appender.hpp +1 -1
  76. package/src/duckdb/src/include/duckdb/common/constants.hpp +2 -0
  77. package/src/duckdb/src/include/duckdb/common/exception.hpp +3 -0
  78. package/src/duckdb/src/include/duckdb/common/fast_mem.hpp +528 -0
  79. package/src/duckdb/src/include/duckdb/common/filename_pattern.hpp +34 -0
  80. package/src/duckdb/src/include/duckdb/common/helper.hpp +10 -0
  81. package/src/duckdb/src/include/duckdb/common/hive_partitioning.hpp +13 -3
  82. package/src/duckdb/src/include/duckdb/common/optional_ptr.hpp +8 -0
  83. package/src/duckdb/src/include/duckdb/common/perfect_map_set.hpp +34 -0
  84. package/src/duckdb/src/include/duckdb/common/radix_partitioning.hpp +80 -27
  85. package/src/duckdb/src/include/duckdb/common/reference_map.hpp +38 -0
  86. package/src/duckdb/src/include/duckdb/common/row_operations/row_operations.hpp +7 -6
  87. package/src/duckdb/src/include/duckdb/common/sort/comparators.hpp +1 -1
  88. package/src/duckdb/src/include/duckdb/common/sort/partition_state.hpp +1 -1
  89. package/src/duckdb/src/include/duckdb/common/sort/sort.hpp +1 -1
  90. package/src/duckdb/src/include/duckdb/common/sort/sorted_block.hpp +2 -2
  91. package/src/duckdb/src/include/duckdb/common/types/batched_data_collection.hpp +1 -1
  92. package/src/duckdb/src/include/duckdb/common/types/{column_data_allocator.hpp → column/column_data_allocator.hpp} +4 -4
  93. package/src/duckdb/src/include/duckdb/common/types/{column_data_collection.hpp → column/column_data_collection.hpp} +2 -2
  94. package/src/duckdb/src/include/duckdb/common/types/{column_data_collection_iterators.hpp → column/column_data_collection_iterators.hpp} +2 -2
  95. package/src/duckdb/src/include/duckdb/common/types/{column_data_collection_segment.hpp → column/column_data_collection_segment.hpp} +3 -3
  96. package/src/duckdb/src/include/duckdb/common/types/{column_data_consumer.hpp → column/column_data_consumer.hpp} +8 -4
  97. package/src/duckdb/src/include/duckdb/common/types/{column_data_scan_states.hpp → column/column_data_scan_states.hpp} +1 -1
  98. package/src/duckdb/src/include/duckdb/common/types/{partitioned_column_data.hpp → column/partitioned_column_data.hpp} +15 -7
  99. package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +140 -0
  100. package/src/duckdb/src/include/duckdb/common/types/{row_data_collection.hpp → row/row_data_collection.hpp} +1 -1
  101. package/src/duckdb/src/include/duckdb/common/types/{row_data_collection_scanner.hpp → row/row_data_collection_scanner.hpp} +2 -2
  102. package/src/duckdb/src/include/duckdb/common/types/{row_layout.hpp → row/row_layout.hpp} +3 -1
  103. package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_allocator.hpp +116 -0
  104. package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_collection.hpp +239 -0
  105. package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_iterator.hpp +64 -0
  106. package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_layout.hpp +113 -0
  107. package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_segment.hpp +124 -0
  108. package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +74 -0
  109. package/src/duckdb/src/include/duckdb/common/types/validity_mask.hpp +3 -0
  110. package/src/duckdb/src/include/duckdb/common/types/value.hpp +4 -12
  111. package/src/duckdb/src/include/duckdb/execution/aggregate_hashtable.hpp +34 -31
  112. package/src/duckdb/src/include/duckdb/execution/base_aggregate_hashtable.hpp +2 -2
  113. package/src/duckdb/src/include/duckdb/execution/execution_context.hpp +3 -2
  114. package/src/duckdb/src/include/duckdb/execution/expression_executor.hpp +1 -1
  115. package/src/duckdb/src/include/duckdb/execution/join_hashtable.hpp +41 -67
  116. package/src/duckdb/src/include/duckdb/execution/nested_loop_join.hpp +1 -1
  117. package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_execute.hpp +2 -2
  118. package/src/duckdb/src/include/duckdb/execution/operator/helper/physical_result_collector.hpp +1 -1
  119. package/src/duckdb/src/include/duckdb/execution/operator/join/outer_join_marker.hpp +2 -2
  120. package/src/duckdb/src/include/duckdb/execution/operator/join/perfect_hash_join_executor.hpp +1 -1
  121. package/src/duckdb/src/include/duckdb/execution/operator/join/physical_cross_product.hpp +1 -1
  122. package/src/duckdb/src/include/duckdb/execution/operator/join/physical_hash_join.hpp +0 -2
  123. package/src/duckdb/src/include/duckdb/execution/operator/join/physical_index_join.hpp +2 -2
  124. package/src/duckdb/src/include/duckdb/execution/operator/join/physical_positional_join.hpp +1 -1
  125. package/src/duckdb/src/include/duckdb/execution/operator/persistent/physical_copy_to_file.hpp +4 -1
  126. package/src/duckdb/src/include/duckdb/execution/operator/scan/physical_column_data_scan.hpp +1 -1
  127. package/src/duckdb/src/include/duckdb/execution/operator/set/physical_recursive_cte.hpp +1 -1
  128. package/src/duckdb/src/include/duckdb/execution/partitionable_hashtable.hpp +2 -2
  129. package/src/duckdb/src/include/duckdb/main/materialized_query_result.hpp +1 -1
  130. package/src/duckdb/src/include/duckdb/main/query_result.hpp +14 -1
  131. package/src/duckdb/src/include/duckdb/optimizer/expression_rewriter.hpp +3 -3
  132. package/src/duckdb/src/include/duckdb/optimizer/join_order/cardinality_estimator.hpp +16 -16
  133. package/src/duckdb/src/include/duckdb/optimizer/join_order/join_node.hpp +8 -8
  134. package/src/duckdb/src/include/duckdb/optimizer/join_order/join_order_optimizer.hpp +23 -15
  135. package/src/duckdb/src/include/duckdb/optimizer/join_order/join_relation.hpp +9 -10
  136. package/src/duckdb/src/include/duckdb/optimizer/join_order/query_graph.hpp +18 -11
  137. package/src/duckdb/src/include/duckdb/parallel/meta_pipeline.hpp +1 -1
  138. package/src/duckdb/src/include/duckdb/parser/parsed_data/exported_table_data.hpp +5 -1
  139. package/src/duckdb/src/include/duckdb/parser/parsed_data/vacuum_info.hpp +3 -2
  140. package/src/duckdb/src/include/duckdb/parser/query_error_context.hpp +4 -2
  141. package/src/duckdb/src/include/duckdb/parser/transformer.hpp +9 -35
  142. package/src/duckdb/src/include/duckdb/planner/binder.hpp +24 -23
  143. package/src/duckdb/src/include/duckdb/planner/expression_binder.hpp +3 -3
  144. package/src/duckdb/src/include/duckdb/planner/operator/logical_column_data_get.hpp +1 -1
  145. package/src/duckdb/src/include/duckdb/planner/operator/logical_copy_to_file.hpp +3 -1
  146. package/src/duckdb/src/include/duckdb/storage/table/table_index_list.hpp +1 -1
  147. package/src/duckdb/src/main/appender.cpp +6 -6
  148. package/src/duckdb/src/main/client_context.cpp +1 -1
  149. package/src/duckdb/src/main/connection.cpp +2 -2
  150. package/src/duckdb/src/main/query_result.cpp +13 -0
  151. package/src/duckdb/src/optimizer/expression_rewriter.cpp +4 -4
  152. package/src/duckdb/src/optimizer/join_order/cardinality_estimator.cpp +91 -105
  153. package/src/duckdb/src/optimizer/join_order/join_node.cpp +5 -8
  154. package/src/duckdb/src/optimizer/join_order/join_order_optimizer.cpp +163 -160
  155. package/src/duckdb/src/optimizer/join_order/join_relation_set.cpp +30 -30
  156. package/src/duckdb/src/optimizer/join_order/query_graph.cpp +37 -38
  157. package/src/duckdb/src/parallel/executor.cpp +1 -1
  158. package/src/duckdb/src/parallel/meta_pipeline.cpp +2 -2
  159. package/src/duckdb/src/parser/transform/helpers/transform_cte.cpp +1 -1
  160. package/src/duckdb/src/parser/transform/tableref/transform_subquery.cpp +1 -1
  161. package/src/duckdb/src/parser/transformer.cpp +50 -9
  162. package/src/duckdb/src/planner/binder/statement/bind_copy.cpp +15 -5
  163. package/src/duckdb/src/planner/binder/statement/bind_create.cpp +19 -17
  164. package/src/duckdb/src/planner/binder/statement/bind_create_table.cpp +4 -4
  165. package/src/duckdb/src/planner/binder/statement/bind_export.cpp +20 -21
  166. package/src/duckdb/src/planner/binder/tableref/bind_basetableref.cpp +24 -22
  167. package/src/duckdb/src/planner/binder/tableref/bind_subqueryref.cpp +2 -2
  168. package/src/duckdb/src/planner/binder.cpp +16 -19
  169. package/src/duckdb/src/planner/expression_binder.cpp +8 -8
  170. package/src/duckdb/src/planner/operator/logical_copy_to_file.cpp +3 -3
  171. package/src/duckdb/src/storage/checkpoint_manager.cpp +23 -23
  172. package/src/duckdb/src/storage/standard_buffer_manager.cpp +1 -1
  173. package/src/duckdb/src/storage/table_index_list.cpp +3 -3
  174. package/src/duckdb/src/verification/statement_verifier.cpp +1 -1
  175. package/src/duckdb/third_party/libpg_query/src_backend_parser_gram.cpp +5552 -5598
  176. package/src/duckdb/ub_src_common.cpp +2 -0
  177. package/src/duckdb/ub_src_common_types.cpp +0 -16
  178. package/src/duckdb/ub_src_common_types_column.cpp +10 -0
  179. package/src/duckdb/ub_src_common_types_row.cpp +20 -0
@@ -0,0 +1,119 @@
1
+ #include "duckdb/common/types/row/tuple_data_layout.hpp"
2
+
3
+ #include "duckdb/planner/expression/bound_aggregate_expression.hpp"
4
+
5
+ namespace duckdb {
6
+
7
+ TupleDataLayout::TupleDataLayout()
8
+ : flag_width(0), data_width(0), aggr_width(0), row_width(0), all_constant(true), heap_size_offset(0) {
9
+ }
10
+
11
+ TupleDataLayout TupleDataLayout::Copy() const {
12
+ TupleDataLayout result;
13
+ result.types = this->types;
14
+ result.aggregates = this->aggregates;
15
+ if (this->struct_layouts) {
16
+ result.struct_layouts = make_uniq<unordered_map<idx_t, TupleDataLayout>>();
17
+ for (const auto &entry : *this->struct_layouts) {
18
+ result.struct_layouts->emplace(entry.first, entry.second.Copy());
19
+ }
20
+ }
21
+ result.flag_width = this->flag_width;
22
+ result.data_width = this->data_width;
23
+ result.aggr_width = this->aggr_width;
24
+ result.row_width = this->row_width;
25
+ result.offsets = this->offsets;
26
+ result.all_constant = this->all_constant;
27
+ result.heap_size_offset = this->heap_size_offset;
28
+ return result;
29
+ }
30
+
31
+ void TupleDataLayout::Initialize(vector<LogicalType> types_p, Aggregates aggregates_p, bool align, bool heap_offset_p) {
32
+ offsets.clear();
33
+ types = std::move(types_p);
34
+
35
+ // Null mask at the front - 1 bit per value.
36
+ flag_width = ValidityBytes::ValidityMaskSize(types.size());
37
+ row_width = flag_width;
38
+
39
+ // Whether all columns are constant size.
40
+ for (idx_t col_idx = 0; col_idx < types.size(); col_idx++) {
41
+ const auto &type = types[col_idx];
42
+ if (type.InternalType() == PhysicalType::STRUCT) {
43
+ // structs are recursively stored as a TupleDataLayout again
44
+ const auto &child_types = StructType::GetChildTypes(type);
45
+ vector<LogicalType> child_type_vector;
46
+ child_type_vector.reserve(child_types.size());
47
+ for (auto &ct : child_types) {
48
+ child_type_vector.emplace_back(ct.second);
49
+ }
50
+ if (!struct_layouts) {
51
+ struct_layouts = make_uniq<unordered_map<idx_t, TupleDataLayout>>();
52
+ }
53
+ auto struct_entry = struct_layouts->emplace(col_idx, TupleDataLayout());
54
+ struct_entry.first->second.Initialize(std::move(child_type_vector), false, false);
55
+ all_constant = all_constant && struct_entry.first->second.AllConstant();
56
+ } else {
57
+ all_constant = all_constant && TypeIsConstantSize(type.InternalType());
58
+ }
59
+ }
60
+
61
+ // This enables pointer swizzling for out-of-core computation.
62
+ if (heap_offset_p && !all_constant) {
63
+ heap_size_offset = row_width;
64
+ row_width += sizeof(uint32_t);
65
+ }
66
+
67
+ // Data columns. No alignment required.
68
+ for (idx_t col_idx = 0; col_idx < types.size(); col_idx++) {
69
+ const auto &type = types[col_idx];
70
+ offsets.push_back(row_width);
71
+ const auto internal_type = type.InternalType();
72
+ if (TypeIsConstantSize(internal_type) || internal_type == PhysicalType::VARCHAR) {
73
+ row_width += GetTypeIdSize(type.InternalType());
74
+ } else if (internal_type == PhysicalType::STRUCT) {
75
+ // Just get the size of the TupleDataLayout of the struct
76
+ row_width += GetStructLayout(col_idx).GetRowWidth();
77
+ } else {
78
+ // Variable size types use pointers to the actual data (can be swizzled).
79
+ // Again, we would use sizeof(data_ptr_t), but this is not guaranteed to be equal to sizeof(idx_t).
80
+ row_width += sizeof(idx_t);
81
+ }
82
+ }
83
+
84
+ // Alignment padding for aggregates
85
+ #ifndef DUCKDB_ALLOW_UNDEFINED
86
+ if (align) {
87
+ row_width = AlignValue(row_width);
88
+ }
89
+ #endif
90
+ data_width = row_width - flag_width;
91
+
92
+ // Aggregate fields.
93
+ aggregates = std::move(aggregates_p);
94
+ for (auto &aggregate : aggregates) {
95
+ offsets.push_back(row_width);
96
+ row_width += aggregate.payload_size;
97
+ #ifndef DUCKDB_ALLOW_UNDEFINED
98
+ D_ASSERT(aggregate.payload_size == AlignValue(aggregate.payload_size));
99
+ #endif
100
+ }
101
+ aggr_width = row_width - data_width - flag_width;
102
+
103
+ // Alignment padding for the next row
104
+ #ifndef DUCKDB_ALLOW_UNDEFINED
105
+ if (align) {
106
+ row_width = AlignValue(row_width);
107
+ }
108
+ #endif
109
+ }
110
+
111
+ void TupleDataLayout::Initialize(vector<LogicalType> types_p, bool align, bool heap_offset_p) {
112
+ Initialize(std::move(types_p), Aggregates(), align, heap_offset_p);
113
+ }
114
+
115
+ void TupleDataLayout::Initialize(Aggregates aggregates_p, bool align, bool heap_offset_p) {
116
+ Initialize(vector<LogicalType>(), std::move(aggregates_p), align, heap_offset_p);
117
+ }
118
+
119
+ } // namespace duckdb