be/src/format_v2/table/es_reader.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 <functional> |
21 | | #include <map> |
22 | | #include <memory> |
23 | | #include <string> |
24 | | #include <vector> |
25 | | |
26 | | #include "format_v2/file_reader.h" |
27 | | #include "format_v2/table_reader.h" |
28 | | |
29 | | namespace doris { |
30 | | class ScrollParser; |
31 | | class SlotDescriptor; |
32 | | } // namespace doris |
33 | | |
34 | | namespace doris::format::es { |
35 | | |
36 | | // The transport boundary allows reader tests to use real ES responses without a running server. |
37 | | class EsScrollStream { |
38 | | public: |
39 | 23 | virtual ~EsScrollStream() = default; |
40 | | virtual Status open() = 0; |
41 | | virtual Status next(bool* eof, std::unique_ptr<ScrollParser>& parser) = 0; |
42 | | virtual Status close() = 0; |
43 | | }; |
44 | | using EsScrollStreamFactory = std::function<std::unique_ptr<EsScrollStream>( |
45 | | const std::string&, const std::map<std::string, std::string>&, bool)>; |
46 | | |
47 | | class EsFileReader final : public FileReader { |
48 | | public: |
49 | | EsFileReader(std::shared_ptr<io::FileSystemProperties>& system_properties, |
50 | | std::unique_ptr<io::FileDescription>& file_description, |
51 | | std::shared_ptr<io::IOContext> io_ctx, RuntimeProfile* profile, |
52 | | TFileRangeDesc range, const TFileScanRangeParams& params, |
53 | | std::vector<SlotDescriptor*> file_slot_descs, |
54 | | EsScrollStreamFactory stream_factory = {}); |
55 | | ~EsFileReader() override; |
56 | | |
57 | | Status init(RuntimeState* state) override; |
58 | | Status get_schema(std::vector<ColumnDefinition>* schema) const override; |
59 | | std::unique_ptr<TableColumnMapper> create_column_mapper( |
60 | | TableColumnMapperOptions options) const override; |
61 | | void set_batch_size(size_t batch_size) override; |
62 | | Status open(std::shared_ptr<FileScanRequest> request) override; |
63 | | Status get_block(Block* block, size_t* rows, bool* eof) override; |
64 | | Status close() override; |
65 | | |
66 | | private: |
67 | | void _init_profile() override; |
68 | | Status _open_stream(); |
69 | | Status _next_page(); |
70 | | Status _read_block(Block* block, size_t* rows, bool* eof); |
71 | | |
72 | | const TFileRangeDesc _range; |
73 | | const TFileScanRangeParams& _params; |
74 | | const std::vector<SlotDescriptor*> _file_slots; |
75 | | EsScrollStreamFactory _stream_factory; |
76 | | RuntimeState* _state = nullptr; |
77 | | size_t _batch_size = 1024; |
78 | | std::unique_ptr<EsScrollStream> _stream; |
79 | | std::unique_ptr<ScrollParser> _parser; |
80 | | std::vector<SlotDescriptor*> _read_slots; |
81 | | std::vector<size_t> _read_positions; |
82 | | std::map<std::string, std::string> _docvalue_context; |
83 | | size_t _page_rows_remaining = 0; |
84 | | bool _source_eof = false; |
85 | | RuntimeProfile::Counter* _total_time = nullptr; |
86 | | RuntimeProfile::Counter* _read_time = nullptr; |
87 | | RuntimeProfile::Counter* _materialize_time = nullptr; |
88 | | RuntimeProfile::Counter* _filter_time = nullptr; |
89 | | RuntimeProfile::Counter* _io_time = nullptr; |
90 | | RuntimeProfile::Counter* _batches_read = nullptr; |
91 | | RuntimeProfile::Counter* _rows_read = nullptr; |
92 | | }; |
93 | | |
94 | | class EsReader final : public TableReader { |
95 | | public: |
96 | | explicit EsReader(EsScrollStreamFactory stream_factory = {}); |
97 | | Status init(TableReadOptions&& options) override; |
98 | | Status prepare_split(const SplitReadOptions& options) override; |
99 | | |
100 | | protected: |
101 | | Status create_file_reader(std::unique_ptr<FileReader>* reader) override; |
102 | | |
103 | | private: |
104 | | EsScrollStreamFactory _stream_factory; |
105 | | }; |
106 | | |
107 | | } // namespace doris::format::es |