duckdb 0.8.2-dev3458.0 → 0.8.2-dev3949.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/binding.gyp +2 -0
- package/package.json +1 -1
- package/src/duckdb/extension/icu/icu_extension.cpp +5 -5
- package/src/duckdb/extension/json/include/json_deserializer.hpp +7 -16
- package/src/duckdb/extension/json/include/json_serializer.hpp +9 -15
- package/src/duckdb/extension/json/json_deserializer.cpp +29 -67
- package/src/duckdb/extension/json/json_scan.cpp +1 -1
- package/src/duckdb/extension/json/json_serializer.cpp +26 -69
- package/src/duckdb/src/common/enum_util.cpp +119 -7
- package/src/duckdb/src/common/extra_type_info.cpp +7 -3
- package/src/duckdb/src/common/radix_partitioning.cpp +8 -31
- package/src/duckdb/src/common/row_operations/row_aggregate.cpp +18 -3
- package/src/duckdb/src/common/serializer/binary_deserializer.cpp +62 -77
- package/src/duckdb/src/common/serializer/binary_serializer.cpp +84 -84
- package/src/duckdb/src/common/serializer/format_serializer.cpp +1 -1
- package/src/duckdb/src/common/sort/partition_state.cpp +41 -33
- package/src/duckdb/src/common/types/data_chunk.cpp +44 -8
- package/src/duckdb/src/common/types/hyperloglog.cpp +21 -0
- package/src/duckdb/src/common/types/interval.cpp +3 -0
- package/src/duckdb/src/common/types/row/partitioned_tuple_data.cpp +252 -126
- package/src/duckdb/src/common/types/row/row_layout.cpp +3 -31
- package/src/duckdb/src/common/types/row/tuple_data_allocator.cpp +40 -32
- package/src/duckdb/src/common/types/row/tuple_data_collection.cpp +39 -26
- package/src/duckdb/src/common/types/row/tuple_data_layout.cpp +11 -1
- package/src/duckdb/src/common/types/row/tuple_data_segment.cpp +21 -16
- package/src/duckdb/src/common/types/value.cpp +63 -42
- package/src/duckdb/src/common/types/vector.cpp +33 -67
- package/src/duckdb/src/core_functions/scalar/list/list_lambdas.cpp +3 -2
- package/src/duckdb/src/execution/aggregate_hashtable.cpp +222 -364
- package/src/duckdb/src/execution/join_hashtable.cpp +5 -6
- package/src/duckdb/src/execution/operator/aggregate/physical_hash_aggregate.cpp +240 -310
- package/src/duckdb/src/execution/operator/aggregate/physical_ungrouped_aggregate.cpp +202 -173
- package/src/duckdb/src/execution/operator/aggregate/physical_window.cpp +36 -2
- package/src/duckdb/src/execution/operator/{persistent → csv_scanner}/base_csv_reader.cpp +58 -162
- package/src/duckdb/src/execution/operator/csv_scanner/buffered_csv_reader.cpp +434 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_buffer.cpp +80 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_buffer_manager.cpp +90 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_file_handle.cpp +95 -0
- package/src/duckdb/src/execution/operator/{persistent → csv_scanner}/csv_reader_options.cpp +47 -28
- package/src/duckdb/src/execution/operator/csv_scanner/csv_state_machine.cpp +35 -0
- package/src/duckdb/src/execution/operator/csv_scanner/csv_state_machine_cache.cpp +107 -0
- package/src/duckdb/src/execution/operator/{persistent → csv_scanner}/parallel_csv_reader.cpp +44 -44
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/csv_sniffer.cpp +52 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/dialect_detection.cpp +336 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/header_detection.cpp +165 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_detection.cpp +398 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_refinement.cpp +175 -0
- package/src/duckdb/src/execution/operator/csv_scanner/sniffer/type_replacement.cpp +39 -0
- package/src/duckdb/src/execution/operator/join/physical_asof_join.cpp +1 -1
- package/src/duckdb/src/execution/operator/set/physical_recursive_cte.cpp +1 -2
- package/src/duckdb/src/execution/radix_partitioned_hashtable.cpp +614 -574
- package/src/duckdb/src/execution/window_executor.cpp +6 -5
- package/src/duckdb/src/function/cast/cast_function_set.cpp +1 -0
- package/src/duckdb/src/function/scalar/strftime_format.cpp +4 -4
- package/src/duckdb/src/function/table/copy_csv.cpp +94 -96
- package/src/duckdb/src/function/table/read_csv.cpp +150 -136
- package/src/duckdb/src/function/table/table_scan.cpp +0 -2
- package/src/duckdb/src/function/table/version/pragma_version.cpp +2 -2
- package/src/duckdb/src/include/duckdb/common/enum_util.hpp +24 -0
- package/src/duckdb/src/include/duckdb/common/file_opener.hpp +9 -0
- package/src/duckdb/src/include/duckdb/common/fixed_size_map.hpp +208 -0
- package/src/duckdb/src/include/duckdb/common/optional_idx.hpp +3 -0
- package/src/duckdb/src/include/duckdb/common/perfect_map_set.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/printer.hpp +11 -0
- package/src/duckdb/src/include/duckdb/common/serializer/binary_deserializer.hpp +43 -30
- package/src/duckdb/src/include/duckdb/common/serializer/binary_serializer.hpp +36 -35
- package/src/duckdb/src/include/duckdb/common/serializer/deserialization_data.hpp +18 -0
- package/src/duckdb/src/include/duckdb/common/serializer/encoding_util.hpp +132 -0
- package/src/duckdb/src/include/duckdb/common/serializer/format_deserializer.hpp +125 -150
- package/src/duckdb/src/include/duckdb/common/serializer/format_serializer.hpp +119 -107
- package/src/duckdb/src/include/duckdb/common/serializer/serialization_traits.hpp +2 -1
- package/src/duckdb/src/include/duckdb/common/shared_ptr.hpp +8 -0
- package/src/duckdb/src/include/duckdb/common/sort/partition_state.hpp +13 -7
- package/src/duckdb/src/include/duckdb/common/types/data_chunk.hpp +5 -0
- package/src/duckdb/src/include/duckdb/common/types/hyperloglog.hpp +7 -1
- package/src/duckdb/src/include/duckdb/common/types/interval.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/row/partitioned_tuple_data.hpp +41 -9
- package/src/duckdb/src/include/duckdb/common/types/row/row_data_collection_scanner.hpp +5 -0
- package/src/duckdb/src/include/duckdb/common/types/row/row_layout.hpp +1 -23
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_allocator.hpp +14 -8
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_collection.hpp +6 -3
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_layout.hpp +7 -0
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_segment.hpp +13 -8
- package/src/duckdb/src/include/duckdb/common/types/row/tuple_data_states.hpp +3 -2
- package/src/duckdb/src/include/duckdb/common/types/vector.hpp +3 -3
- package/src/duckdb/src/include/duckdb/common/vector.hpp +2 -2
- package/src/duckdb/src/include/duckdb/execution/aggregate_hashtable.hpp +125 -146
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_hash_aggregate.hpp +5 -4
- package/src/duckdb/src/include/duckdb/execution/operator/aggregate/physical_window.hpp +4 -3
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/base_csv_reader.hpp +17 -17
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/buffered_csv_reader.hpp +72 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_buffer.hpp +110 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_buffer_manager.hpp +103 -0
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/csv_file_handle.hpp +8 -15
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/csv_line_info.hpp +1 -1
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/csv_reader_options.hpp +52 -28
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_sniffer.hpp +127 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_state_machine.hpp +75 -0
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/csv_state_machine_cache.hpp +51 -0
- package/src/duckdb/src/include/duckdb/execution/operator/{persistent → scan/csv}/parallel_csv_reader.hpp +21 -27
- package/src/duckdb/src/include/duckdb/execution/operator/scan/csv/quote_rules.hpp +21 -0
- package/src/duckdb/src/include/duckdb/execution/radix_partitioned_hashtable.hpp +18 -27
- package/src/duckdb/src/include/duckdb/function/function_serialization.hpp +5 -6
- package/src/duckdb/src/include/duckdb/function/scalar/strftime_format.hpp +4 -4
- package/src/duckdb/src/include/duckdb/function/table/read_csv.hpp +17 -12
- package/src/duckdb/src/include/duckdb/main/client_context_file_opener.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/client_data.hpp +2 -1
- package/src/duckdb/src/include/duckdb/main/config.hpp +1 -0
- package/src/duckdb/src/include/duckdb/main/connection.hpp +2 -2
- package/src/duckdb/src/include/duckdb/main/relation/read_csv_relation.hpp +6 -6
- package/src/duckdb/src/include/duckdb/parallel/event.hpp +12 -1
- package/src/duckdb/src/include/duckdb/storage/block.hpp +6 -0
- package/src/duckdb/src/include/duckdb/storage/buffer/block_handle.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/base_statistics.hpp +7 -3
- package/src/duckdb/src/include/duckdb/storage/statistics/column_statistics.hpp +4 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/distinct_statistics.hpp +5 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/list_stats.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/numeric_stats.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/string_stats.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/statistics/struct_stats.hpp +3 -0
- package/src/duckdb/src/include/duckdb/storage/table/chunk_info.hpp +15 -3
- package/src/duckdb/src/include/duckdb/storage/table/row_group.hpp +4 -0
- package/src/duckdb/src/include/duckdb/storage/table/table_statistics.hpp +5 -0
- package/src/duckdb/src/include/duckdb/verification/deserialized_statement_verifier_v2.hpp +6 -0
- package/src/duckdb/src/include/duckdb/verification/statement_verifier.hpp +1 -0
- package/src/duckdb/src/include/duckdb.h +12 -0
- package/src/duckdb/src/main/capi/logical_types-c.cpp +22 -0
- package/src/duckdb/src/main/client_context_file_opener.cpp +17 -0
- package/src/duckdb/src/main/client_verify.cpp +1 -0
- package/src/duckdb/src/main/config.cpp +2 -2
- package/src/duckdb/src/main/connection.cpp +3 -3
- package/src/duckdb/src/main/relation/read_csv_relation.cpp +19 -13
- package/src/duckdb/src/parallel/pipeline_finish_event.cpp +1 -1
- package/src/duckdb/src/parser/tableref/pivotref.cpp +0 -16
- package/src/duckdb/src/planner/binder/statement/bind_copy.cpp +1 -1
- package/src/duckdb/src/planner/binder/statement/bind_export.cpp +41 -25
- package/src/duckdb/src/planner/expression/bound_aggregate_expression.cpp +4 -4
- package/src/duckdb/src/planner/expression/bound_window_expression.cpp +10 -10
- package/src/duckdb/src/planner/logical_operator.cpp +1 -1
- package/src/duckdb/src/planner/planner.cpp +1 -1
- package/src/duckdb/src/storage/checkpoint_manager.cpp +4 -3
- package/src/duckdb/src/storage/serialization/serialize_constraint.cpp +1 -1
- package/src/duckdb/src/storage/serialization/serialize_create_info.cpp +5 -5
- package/src/duckdb/src/storage/serialization/serialize_expression.cpp +10 -10
- package/src/duckdb/src/storage/serialization/serialize_logical_operator.cpp +20 -20
- package/src/duckdb/src/storage/serialization/serialize_macro_function.cpp +2 -2
- package/src/duckdb/src/storage/serialization/serialize_nodes.cpp +118 -89
- package/src/duckdb/src/storage/serialization/serialize_parse_info.cpp +3 -3
- package/src/duckdb/src/storage/serialization/serialize_parsed_expression.cpp +27 -27
- package/src/duckdb/src/storage/serialization/serialize_query_node.cpp +16 -16
- package/src/duckdb/src/storage/serialization/serialize_result_modifier.cpp +8 -8
- package/src/duckdb/src/storage/serialization/serialize_statement.cpp +1 -1
- package/src/duckdb/src/storage/serialization/serialize_storage.cpp +39 -0
- package/src/duckdb/src/storage/serialization/serialize_tableref.cpp +9 -9
- package/src/duckdb/src/storage/statistics/base_statistics.cpp +67 -4
- package/src/duckdb/src/storage/statistics/column_statistics.cpp +16 -0
- package/src/duckdb/src/storage/statistics/list_stats.cpp +21 -0
- package/src/duckdb/src/storage/statistics/numeric_stats.cpp +126 -1
- package/src/duckdb/src/storage/statistics/string_stats.cpp +23 -0
- package/src/duckdb/src/storage/statistics/struct_stats.cpp +27 -0
- package/src/duckdb/src/storage/storage_info.cpp +1 -1
- package/src/duckdb/src/storage/table/chunk_info.cpp +82 -3
- package/src/duckdb/src/storage/table/row_group.cpp +68 -1
- package/src/duckdb/src/storage/table/table_statistics.cpp +21 -0
- package/src/duckdb/src/storage/wal_replay.cpp +2 -2
- package/src/duckdb/src/verification/deserialized_statement_verifier_v2.cpp +15 -1
- package/src/duckdb/src/verification/statement_verifier.cpp +2 -0
- package/src/duckdb/third_party/utf8proc/include/utf8proc_wrapper.hpp +8 -0
- package/src/duckdb/ub_src_execution.cpp +0 -2
- package/src/duckdb/ub_src_execution_operator_csv_scanner.cpp +18 -0
- package/src/duckdb/ub_src_execution_operator_csv_scanner_sniffer.cpp +12 -0
- package/src/duckdb/ub_src_execution_operator_persistent.cpp +0 -12
- package/src/duckdb/ub_src_storage_serialization.cpp +2 -0
- package/src/duckdb/src/execution/operator/persistent/buffered_csv_reader.cpp +0 -1487
- package/src/duckdb/src/execution/operator/persistent/csv_buffer.cpp +0 -72
- package/src/duckdb/src/execution/operator/persistent/csv_file_handle.cpp +0 -158
- package/src/duckdb/src/execution/partitionable_hashtable.cpp +0 -207
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/buffered_csv_reader.hpp +0 -133
- package/src/duckdb/src/include/duckdb/execution/operator/persistent/csv_buffer.hpp +0 -74
- package/src/duckdb/src/include/duckdb/execution/partitionable_hashtable.hpp +0 -73
@@ -1,73 +0,0 @@
|
|
1
|
-
//===----------------------------------------------------------------------===//
|
2
|
-
// DuckDB
|
3
|
-
//
|
4
|
-
// duckdb/execution/partitionable_hashtable.hpp
|
5
|
-
//
|
6
|
-
//
|
7
|
-
//===----------------------------------------------------------------------===//
|
8
|
-
|
9
|
-
#pragma once
|
10
|
-
|
11
|
-
#include "duckdb/execution/aggregate_hashtable.hpp"
|
12
|
-
|
13
|
-
namespace duckdb {
|
14
|
-
|
15
|
-
struct RadixPartitionInfo {
|
16
|
-
explicit RadixPartitionInfo(idx_t n_partitions_upper_bound);
|
17
|
-
const idx_t n_partitions;
|
18
|
-
const idx_t radix_bits;
|
19
|
-
const hash_t radix_mask;
|
20
|
-
const idx_t radix_shift;
|
21
|
-
|
22
|
-
inline hash_t GetHashPartition(hash_t hash) const {
|
23
|
-
return (hash & radix_mask) >> radix_shift;
|
24
|
-
}
|
25
|
-
};
|
26
|
-
|
27
|
-
typedef vector<unique_ptr<GroupedAggregateHashTable>> HashTableList; // NOLINT
|
28
|
-
|
29
|
-
class PartitionableHashTable {
|
30
|
-
public:
|
31
|
-
PartitionableHashTable(ClientContext &context, Allocator &allocator, RadixPartitionInfo &partition_info_p,
|
32
|
-
vector<LogicalType> group_types_p, vector<LogicalType> payload_types_p,
|
33
|
-
vector<BoundAggregateExpression *> bindings_p);
|
34
|
-
|
35
|
-
idx_t AddChunk(DataChunk &groups, DataChunk &payload, bool do_partition, const unsafe_vector<idx_t> &filter);
|
36
|
-
void Partition(bool sink_done);
|
37
|
-
bool IsPartitioned();
|
38
|
-
|
39
|
-
HashTableList GetPartition(idx_t partition);
|
40
|
-
HashTableList GetUnpartitioned();
|
41
|
-
idx_t GetPartitionCount(idx_t partition) const;
|
42
|
-
idx_t GetPartitionSize(idx_t partition) const;
|
43
|
-
|
44
|
-
void Finalize();
|
45
|
-
|
46
|
-
void Append(GroupedAggregateHashTable &ht);
|
47
|
-
|
48
|
-
private:
|
49
|
-
ClientContext &context;
|
50
|
-
Allocator &allocator;
|
51
|
-
vector<LogicalType> group_types;
|
52
|
-
vector<LogicalType> payload_types;
|
53
|
-
vector<BoundAggregateExpression *> bindings;
|
54
|
-
|
55
|
-
bool is_partitioned;
|
56
|
-
RadixPartitionInfo &partition_info;
|
57
|
-
vector<SelectionVector> sel_vectors;
|
58
|
-
unsafe_vector<idx_t> sel_vector_sizes;
|
59
|
-
DataChunk group_subset, payload_subset;
|
60
|
-
Vector hashes, hashes_subset;
|
61
|
-
AggregateHTAppendState append_state;
|
62
|
-
|
63
|
-
HashTableList unpartitioned_hts;
|
64
|
-
vector<HashTableList> radix_partitioned_hts;
|
65
|
-
idx_t tuple_size;
|
66
|
-
|
67
|
-
private:
|
68
|
-
idx_t ListAddChunk(HashTableList &list, DataChunk &groups, Vector &group_hashes, DataChunk &payload,
|
69
|
-
const unsafe_vector<idx_t> &filter);
|
70
|
-
//! Returns the HT entry size used for intermediate hash tables
|
71
|
-
HtEntryType GetHTEntrySize();
|
72
|
-
};
|
73
|
-
} // namespace duckdb
|