be/src/format/table/hive_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 | | #include <memory> |
20 | | #include <utility> |
21 | | #include <vector> |
22 | | |
23 | | #include "format/orc/vorc_reader.h" |
24 | | #include "format/parquet/vparquet_reader.h" |
25 | | #include "format/table/table_schema_change_helper.h" |
26 | | namespace doris { |
27 | | |
28 | | class HiveOrcReader final : public OrcReader, public TableSchemaChangeHelper { |
29 | | public: |
30 | | ENABLE_FACTORY_CREATOR(HiveOrcReader); |
31 | | HiveOrcReader(RuntimeProfile* profile, RuntimeState* state, const TFileScanRangeParams& params, |
32 | | const TFileRangeDesc& range, size_t batch_size, const std::string& ctz, |
33 | | io::IOContext* io_ctx, const std::set<TSlotId>* is_file_slot, |
34 | | FileMetaCache* meta_cache = nullptr, bool enable_lazy_mat = true) |
35 | | : OrcReader(profile, state, params, range, batch_size, ctz, io_ctx, meta_cache, |
36 | | enable_lazy_mat), |
37 | | _is_file_slot(is_file_slot) {} |
38 | | |
39 | | HiveOrcReader(RuntimeProfile* profile, RuntimeState* state, const TFileScanRangeParams& params, |
40 | | const TFileRangeDesc& range, size_t batch_size, const std::string& ctz, |
41 | | std::shared_ptr<io::IOContext> io_ctx_holder, |
42 | | const std::set<TSlotId>* is_file_slot, FileMetaCache* meta_cache = nullptr, |
43 | | bool enable_lazy_mat = true) |
44 | 15.3k | : OrcReader(profile, state, params, range, batch_size, ctz, std::move(io_ctx_holder), |
45 | 15.3k | meta_cache, enable_lazy_mat), |
46 | 15.3k | _is_file_slot(is_file_slot) {} |
47 | | |
48 | 15.4k | ~HiveOrcReader() final = default; |
49 | | |
50 | | protected: |
51 | | Status on_before_init_reader(ReaderInitContext* ctx) override; |
52 | | |
53 | | private: |
54 | | static ColumnIdResult _create_column_ids(const orc::Type* orc_type, |
55 | | const TupleDescriptor* tuple_descriptor); |
56 | | |
57 | | static ColumnIdResult _create_column_ids_by_top_level_col_index( |
58 | | const orc::Type* orc_type, const TupleDescriptor* tuple_descriptor); |
59 | | |
60 | | const std::set<TSlotId>* _is_file_slot = nullptr; |
61 | | }; |
62 | | |
63 | | class HiveParquetReader final : public ParquetReader, public TableSchemaChangeHelper { |
64 | | public: |
65 | | ENABLE_FACTORY_CREATOR(HiveParquetReader); |
66 | | HiveParquetReader(RuntimeProfile* profile, const TFileScanRangeParams& params, |
67 | | const TFileRangeDesc& range, size_t batch_size, const cctz::time_zone* ctz, |
68 | | io::IOContext* io_ctx, RuntimeState* state, |
69 | | const std::set<TSlotId>* is_file_slot, FileMetaCache* meta_cache = nullptr, |
70 | | bool enable_lazy_mat = true) |
71 | | : ParquetReader(profile, params, range, batch_size, ctz, io_ctx, state, meta_cache, |
72 | | enable_lazy_mat), |
73 | | _is_file_slot(is_file_slot) {} |
74 | | |
75 | | HiveParquetReader(RuntimeProfile* profile, const TFileScanRangeParams& params, |
76 | | const TFileRangeDesc& range, size_t batch_size, const cctz::time_zone* ctz, |
77 | | std::shared_ptr<io::IOContext> io_ctx_holder, RuntimeState* state, |
78 | | const std::set<TSlotId>* is_file_slot, FileMetaCache* meta_cache = nullptr, |
79 | | bool enable_lazy_mat = true) |
80 | 10.4k | : ParquetReader(profile, params, range, batch_size, ctz, std::move(io_ctx_holder), |
81 | 10.4k | state, meta_cache, enable_lazy_mat), |
82 | 10.4k | _is_file_slot(is_file_slot) {} |
83 | | |
84 | 10.4k | ~HiveParquetReader() final = default; |
85 | | |
86 | | protected: |
87 | | Status on_before_init_reader(ReaderInitContext* ctx) override; |
88 | | |
89 | | private: |
90 | | static ColumnIdResult _create_column_ids(const FieldDescriptor* field_desc, |
91 | | const TupleDescriptor* tuple_descriptor); |
92 | | |
93 | | static ColumnIdResult _create_column_ids_by_top_level_col_index( |
94 | | const FieldDescriptor* field_desc, const TupleDescriptor* tuple_descriptor); |
95 | | |
96 | | const std::set<TSlotId>* _is_file_slot = nullptr; |
97 | | }; |
98 | | } // namespace doris |