be/src/format/table/transactional_hive_common.h
Line | Count | Source |
1 | | // Licensed to the Apache Software Foundation (ASF) under one |
2 | | // or more contributor license agreements. See the NOTICE file |
3 | | // distributed with this work for additional information |
4 | | // regarding copyright ownership. The ASF licenses this file |
5 | | // to you under the Apache License, Version 2.0 (the |
6 | | // "License"); you may not use this file except in compliance |
7 | | // with the License. You may obtain a copy of the License at |
8 | | // |
9 | | // http://www.apache.org/licenses/LICENSE-2.0 |
10 | | // |
11 | | // Unless required by applicable law or agreed to in writing, |
12 | | // software distributed under the License is distributed on an |
13 | | // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
14 | | // KIND, either express or implied. See the License for the |
15 | | // specific language governing permissions and limitations |
16 | | // under the License. |
17 | | |
18 | | #pragma once |
19 | | |
20 | | #include <cstddef> |
21 | | #include <cstdint> |
22 | | #include <string> |
23 | | #include <unordered_map> |
24 | | #include <vector> |
25 | | |
26 | | #include "core/data_type/define_primitive_type.h" |
27 | | #include "exec/common/hash_table/phmap_fwd_decl.h" |
28 | | |
29 | | namespace doris { |
30 | | struct TransactionalHive { |
31 | | static const std::string OPERATION; |
32 | | static const std::string ORIGINAL_TRANSACTION; |
33 | | static const std::string BUCKET; |
34 | | static const std::string ROW_ID; |
35 | | static const std::string CURRENT_TRANSACTION; |
36 | | static const std::string ROW; |
37 | | static const std::string OPERATION_LOWER_CASE; |
38 | | static const std::string ORIGINAL_TRANSACTION_LOWER_CASE; |
39 | | static const std::string BUCKET_LOWER_CASE; |
40 | | static const std::string ROW_ID_LOWER_CASE; |
41 | | static const std::string CURRENT_TRANSACTION_LOWER_CASE; |
42 | | static const std::string ROW_LOWER_CASE; |
43 | | static const int ROW_OFFSET; |
44 | | struct Param { |
45 | | const std::string column_name; |
46 | | const std::string column_lower_case; |
47 | | const PrimitiveType type; |
48 | | }; |
49 | | static const std::vector<Param> DELETE_ROW_PARAMS; |
50 | | static const std::vector<Param> READ_PARAMS; |
51 | | static const std::vector<std::string> DELETE_ROW_COLUMN_NAMES; |
52 | | static const std::vector<std::string> DELETE_ROW_COLUMN_NAMES_LOWER_CASE; |
53 | | static const std::vector<std::string> READ_ROW_COLUMN_NAMES; |
54 | | static const std::vector<std::string> READ_ROW_COLUMN_NAMES_LOWER_CASE; |
55 | | static const std::vector<std::string> ACID_COLUMN_NAMES; |
56 | | static const std::vector<std::string> ACID_COLUMN_NAMES_LOWER_CASE; |
57 | | |
58 | | static const std::unordered_map<std::string, uint32_t> DELETE_COL_NAME_TO_BLOCK_IDX; |
59 | | }; |
60 | | |
61 | | // ACID row identifier for transactional Hive tables, used for delete row matching. |
62 | | // Placed here (not in TransactionalHiveReader) to avoid circular dependency with OrcReader. |
63 | | struct AcidRowID { |
64 | | int64_t original_transaction; |
65 | | int64_t bucket; |
66 | | int64_t row_id; |
67 | | |
68 | | struct Hash { |
69 | 2 | size_t operator()(const AcidRowID& transactional_row_id) const { |
70 | 2 | size_t hash_value = 0; |
71 | 2 | hash_value ^= std::hash<int64_t> {}(transactional_row_id.original_transaction) + |
72 | 2 | 0x9e3779b9 + (hash_value << 6) + (hash_value >> 2); |
73 | 2 | hash_value ^= std::hash<int64_t> {}(transactional_row_id.bucket) + 0x9e3779b9 + |
74 | 2 | (hash_value << 6) + (hash_value >> 2); |
75 | 2 | hash_value ^= std::hash<int64_t> {}(transactional_row_id.row_id) + 0x9e3779b9 + |
76 | 2 | (hash_value << 6) + (hash_value >> 2); |
77 | 2 | return hash_value; |
78 | 2 | } |
79 | | }; |
80 | | |
81 | | struct Eq { |
82 | 1 | bool operator()(const AcidRowID& lhs, const AcidRowID& rhs) const { |
83 | 1 | return lhs.original_transaction == rhs.original_transaction && |
84 | 1 | lhs.bucket == rhs.bucket && lhs.row_id == rhs.row_id; |
85 | 1 | } |
86 | | }; |
87 | | }; |
88 | | |
89 | | using AcidRowIDSet = flat_hash_set<AcidRowID, AcidRowID::Hash, AcidRowID::Eq>; |
90 | | |
91 | 0 | inline bool operator<(const AcidRowID& lhs, const AcidRowID& rhs) { |
92 | 0 | if (lhs.original_transaction != rhs.original_transaction) { |
93 | 0 | return lhs.original_transaction < rhs.original_transaction; |
94 | 0 | } else if (lhs.bucket != rhs.bucket) { |
95 | 0 | return lhs.bucket < rhs.bucket; |
96 | 0 | } else if (lhs.row_id != rhs.row_id) { |
97 | 0 | return lhs.row_id < rhs.row_id; |
98 | 0 | } else { |
99 | 0 | return false; |
100 | 0 | } |
101 | 0 | } |
102 | | |
103 | | } // namespace doris |