be/src/format/table/fileset_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 <cstddef> |
21 | | #include <map> |
22 | | #include <string> |
23 | | #include <unordered_map> |
24 | | #include <vector> |
25 | | |
26 | | #include "common/factory_creator.h" |
27 | | #include "format/generic_reader.h" |
28 | | #include "io/file_factory.h" |
29 | | #include "runtime/runtime_profile.h" |
30 | | |
31 | | namespace doris { |
32 | | class RuntimeProfile; |
33 | | class RuntimeState; |
34 | | class SlotDescriptor; |
35 | | |
36 | | class FilesetReader : public GenericReader { |
37 | | ENABLE_FACTORY_CREATOR(FilesetReader); |
38 | | |
39 | | public: |
40 | | FilesetReader(const std::vector<SlotDescriptor*>& file_slot_descs, RuntimeState* state, |
41 | | RuntimeProfile* profile, |
42 | | const std::map<std::string, std::string>& fileset_params); |
43 | 8 | ~FilesetReader() override = default; |
44 | | |
45 | | Status init_reader(); |
46 | | Status _do_get_next_block(Block* block, size_t* read_rows, bool* eof) override; |
47 | | Status _get_columns_impl(std::unordered_map<std::string, DataTypePtr>* name_to_type) override; |
48 | | |
49 | | private: |
50 | | struct FilesetProfile { |
51 | | RuntimeProfile::Counter* listed_files = nullptr; |
52 | | RuntimeProfile::Counter* listed_bytes = nullptr; |
53 | | RuntimeProfile::Counter* emitted_rows = nullptr; |
54 | | RuntimeProfile::Counter* list_files_time = nullptr; |
55 | | RuntimeProfile::Counter* serialize_time = nullptr; |
56 | | }; |
57 | | |
58 | | Status _build_files(); |
59 | | // Lists files in the directory and filters by the glob pattern from _fileset_params. |
60 | | // Uses POSIX fnmatch(3) for pattern matching (supports *, ?, [...]). |
61 | | Status _list_files(const io::FileSystemSPtr& fs, const std::string& table_path); |
62 | | static Result<TFileType::type> _parse_file_type(const std::string& file_type); |
63 | | static std::string _build_uri(const std::string& table_path, const std::string& listed_name); |
64 | | void _init_profile(); |
65 | | void _write_file_jsonb(JsonbWriter& writer, const io::FileInfo& file); |
66 | | |
67 | | const std::vector<SlotDescriptor*>& _file_slot_descs; |
68 | | RuntimeState* _state; |
69 | | RuntimeProfile* _profile; |
70 | | FilesetProfile _fileset_profile; |
71 | | std::map<std::string, std::string> _fileset_params; |
72 | | std::vector<io::FileInfo> _files; |
73 | | size_t _next_file_idx = 0; |
74 | | }; |
75 | | } // namespace doris |