be/src/format_v2/file_reader.cpp
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 | | #include "format_v2/file_reader.h" |
19 | | |
20 | | #include <sstream> |
21 | | |
22 | | #include "format_v2/column_mapper.h" |
23 | | #include "io/fs/buffered_reader.h" |
24 | | #include "io/fs/tracing_file_reader.h" |
25 | | #include "runtime/runtime_state.h" |
26 | | |
27 | | namespace doris::format { |
28 | | namespace { |
29 | | |
30 | | template <typename T, typename Formatter> |
31 | 0 | std::string join_debug_strings(const std::vector<T>& values, Formatter formatter) { |
32 | 0 | std::ostringstream out; |
33 | 0 | out << "["; |
34 | 0 | for (size_t i = 0; i < values.size(); ++i) { |
35 | 0 | if (i > 0) { |
36 | 0 | out << ", "; |
37 | 0 | } |
38 | 0 | out << formatter(values[i]); |
39 | 0 | } |
40 | 0 | out << "]"; |
41 | 0 | return out.str(); |
42 | 0 | } Unexecuted instantiation: file_reader.cpp:_ZN5doris6format12_GLOBAL__N_118join_debug_stringsINS0_16LocalColumnIndexEZNKS0_15FileScanRequest12debug_stringB5cxx11EvE3$_0EENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKSt6vectorIT_SaISD_EET0_ Unexecuted instantiation: file_reader.cpp:_ZN5doris6format12_GLOBAL__N_118join_debug_stringsINS0_16LocalColumnIndexEZNKS0_15FileScanRequest12debug_stringB5cxx11EvE3$_1EENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKSt6vectorIT_SaISD_EET0_ Unexecuted instantiation: file_reader.cpp:_ZN5doris6format12_GLOBAL__N_118join_debug_stringsINS0_25FileColumnPredicateFilterEZNKS0_15FileScanRequest12debug_stringB5cxx11EvE3$_2EENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEERKSt6vectorIT_SaISD_EET0_ |
43 | | |
44 | | } // namespace |
45 | | |
46 | 0 | std::string FileColumnPredicateFilter::debug_string() const { |
47 | 0 | std::ostringstream out; |
48 | 0 | out << "FileColumnPredicateFilter{file_column_id=" << file_column_id |
49 | 0 | << ", predicate_count=" << predicates.size() << "}"; |
50 | 0 | return out.str(); |
51 | 0 | } |
52 | | |
53 | 0 | std::string FileScanRequest::debug_string() const { |
54 | 0 | std::ostringstream out; |
55 | 0 | out << "FileScanRequest{predicate_columns=" |
56 | 0 | << join_debug_strings( |
57 | 0 | predicate_columns, |
58 | 0 | [](const LocalColumnIndex& projection) { return projection.debug_string(); }) |
59 | 0 | << ", non_predicate_columns=" |
60 | 0 | << join_debug_strings( |
61 | 0 | non_predicate_columns, |
62 | 0 | [](const LocalColumnIndex& projection) { return projection.debug_string(); }) |
63 | 0 | << ", local_positions={"; |
64 | 0 | size_t position_idx = 0; |
65 | 0 | for (const auto& [column_id, block_position] : local_positions) { |
66 | 0 | if (position_idx++ > 0) { |
67 | 0 | out << ", "; |
68 | 0 | } |
69 | 0 | out << column_id << ":" << block_position; |
70 | 0 | } |
71 | 0 | out << "}, conjunct_count=" << conjuncts.size() |
72 | 0 | << ", delete_conjunct_count=" << delete_conjuncts.size() << ", column_predicate_filters=" |
73 | 0 | << join_debug_strings( |
74 | 0 | column_predicate_filters, |
75 | 0 | [](const FileColumnPredicateFilter& filter) { return filter.debug_string(); }) |
76 | 0 | << "}"; |
77 | 0 | return out.str(); |
78 | 0 | } |
79 | | |
80 | 230 | Status FileReader::init(RuntimeState* state) { |
81 | 230 | _init_profile(); |
82 | 230 | SCOPED_RAW_TIMER(&_reader_statistics.file_reader_create_time); |
83 | 230 | ++_reader_statistics.open_file_num; |
84 | 230 | io::FileReaderOptions reader_options = |
85 | 230 | FileFactory::get_reader_options(state->query_options(), *_file_description); |
86 | 230 | _file_reader = DORIS_TRY(io::DelegateReader::create_file_reader( |
87 | 230 | _profile, *_system_properties, *_file_description, reader_options, |
88 | 230 | io::DelegateReader::AccessMode::RANDOM, _io_ctx)); |
89 | | // IOContext can be present without file_reader_stats in standalone tests or callers that only |
90 | | // need extra IO state. TracingFileReader dereferences the stats pointer on every read, so only |
91 | | // wrap the physical reader when stats collection is actually available. |
92 | 230 | _tracing_file_reader = _io_ctx && _io_ctx->file_reader_stats |
93 | 230 | ? std::make_shared<io::TracingFileReader>( |
94 | 131 | _file_reader, _io_ctx->file_reader_stats) |
95 | 230 | : _file_reader; |
96 | 230 | _eof = false; |
97 | 230 | return Status::OK(); |
98 | 230 | } |
99 | | |
100 | | std::unique_ptr<TableColumnMapper> FileReader::create_column_mapper( |
101 | 8 | TableColumnMapperOptions options) const { |
102 | 8 | return std::make_unique<TableColumnMapper>(std::move(options)); |
103 | 8 | } |
104 | | |
105 | | } // namespace doris::format |