be/src/exec/sink/viceberg_merge_sink.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 <gen_cpp/DataSinks_types.h> |
21 | | |
22 | | #include <map> |
23 | | #include <memory> |
24 | | #include <string> |
25 | | #include <vector> |
26 | | |
27 | | #include "common/status.h" |
28 | | #include "exec/sink/writer/async_result_writer.h" |
29 | | #include "exprs/vexpr_fwd.h" |
30 | | #include "roaring/roaring64map.hh" |
31 | | #include "runtime/descriptors.h" |
32 | | #include "runtime/runtime_profile.h" |
33 | | |
34 | | namespace doris { |
35 | | |
36 | | class ObjectPool; |
37 | | class RuntimeState; |
38 | | class Dependency; |
39 | | |
40 | | class VIcebergDeleteSink; |
41 | | class VIcebergTableWriter; |
42 | | |
43 | | class VIcebergMergeSink final : public AsyncResultWriter { |
44 | | public: |
45 | | VIcebergMergeSink(const TDataSink& t_sink, const VExprContextSPtrs& output_exprs, |
46 | | std::shared_ptr<Dependency> dep, std::shared_ptr<Dependency> fin_dep); |
47 | | |
48 | | ~VIcebergMergeSink() override; |
49 | | |
50 | | Status init_properties(ObjectPool* pool, const RowDescriptor& row_desc); |
51 | | |
52 | | Status open(RuntimeState* state, RuntimeProfile* profile) override; |
53 | | |
54 | | Status write(RuntimeState* state, Block& block) override; |
55 | | |
56 | | Status close(Status) override; |
57 | | |
58 | | #ifdef BE_TEST |
59 | 11 | void set_skip_io(bool skip) { _skip_io = skip; } |
60 | | #endif |
61 | | |
62 | | private: |
63 | | Status _build_inner_sinks(); |
64 | | Status _prepare_output_layout(); |
65 | | Status _validate_matched_row_ids(const Block& block, const uint8_t* delete_filter); |
66 | | |
67 | | TDataSink _t_sink; |
68 | | TDataSink _table_sink; |
69 | | TDataSink _delete_sink; |
70 | | |
71 | | std::unique_ptr<VIcebergTableWriter> _table_writer; |
72 | | std::unique_ptr<VIcebergDeleteSink> _delete_writer; |
73 | | |
74 | | RuntimeState* _state = nullptr; |
75 | | |
76 | | int _operation_idx = -1; |
77 | | int _row_id_idx = -1; |
78 | | std::vector<int> _data_column_indices; |
79 | | std::map<std::string, roaring::Roaring64Map> _matched_row_positions; |
80 | | size_t _matched_row_id_state_size = sizeof(std::map<std::string, roaring::Roaring64Map>); |
81 | | bool _require_merge_cardinality_check = false; |
82 | | |
83 | | VExprContextSPtrs _table_output_expr_ctxs; |
84 | | VExprContextSPtrs _delete_output_expr_ctxs; |
85 | | |
86 | | size_t _row_count = 0; |
87 | | size_t _insert_row_count = 0; |
88 | | size_t _delete_row_count = 0; |
89 | | |
90 | | RuntimeProfile::Counter* _written_rows_counter = nullptr; |
91 | | RuntimeProfile::Counter* _insert_rows_counter = nullptr; |
92 | | RuntimeProfile::Counter* _delete_rows_counter = nullptr; |
93 | | RuntimeProfile::Counter* _matched_row_id_state_bytes_counter = nullptr; |
94 | | RuntimeProfile::Counter* _send_data_timer = nullptr; |
95 | | RuntimeProfile::Counter* _open_timer = nullptr; |
96 | | RuntimeProfile::Counter* _close_timer = nullptr; |
97 | | |
98 | | #ifdef BE_TEST |
99 | | bool _skip_io = false; |
100 | | #endif |
101 | | }; |
102 | | |
103 | | } // namespace doris |