be/src/format/text/text_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 <gen_cpp/PlanNodes_types.h> |
21 | | #include <gen_cpp/internal_service.pb.h> |
22 | | |
23 | | #include <cstddef> |
24 | | #include <string> |
25 | | #include <vector> |
26 | | |
27 | | #include "common/status.h" |
28 | | #include "format/csv/csv_reader.h" |
29 | | #include "io/file_factory.h" |
30 | | |
31 | | namespace doris { |
32 | | #include "common/compile_check_begin.h" |
33 | | |
34 | | class HiveTextFieldSplitter : public BaseCsvTextFieldSplitter<HiveTextFieldSplitter> { |
35 | | public: |
36 | | explicit HiveTextFieldSplitter(bool trim_tailing_space, bool trim_ends, std::string value_sep, |
37 | | size_t value_sep_len = 1, char trimming_char = 0, |
38 | | char escape_char = 0) |
39 | 27 | : BaseCsvTextFieldSplitter(trim_tailing_space, trim_ends, value_sep_len, trimming_char), |
40 | 27 | _value_sep(std::move(value_sep)), |
41 | 27 | _escape_char(escape_char) {} |
42 | | |
43 | | void do_split(const Slice& line, std::vector<Slice>* splitted_values); |
44 | | |
45 | | private: |
46 | | void _split_field_single_char(const Slice& line, std::vector<Slice>* splitted_values); |
47 | | void _split_field_multi_char(const Slice& line, std::vector<Slice>* splitted_values); |
48 | | |
49 | | std::string _value_sep; |
50 | | char _escape_char; |
51 | | }; |
52 | | |
53 | | class TextReader : public CsvReader { |
54 | | ENABLE_FACTORY_CREATOR(TextReader); |
55 | | |
56 | | public: |
57 | | TextReader(RuntimeState* state, RuntimeProfile* profile, ScannerCounter* counter, |
58 | | const TFileScanRangeParams& params, const TFileRangeDesc& range, |
59 | | const std::vector<SlotDescriptor*>& file_slot_descs, io::IOContext* io_ctx); |
60 | | |
61 | | ~TextReader() override = default; |
62 | | |
63 | | private: |
64 | | Status _init_options() override; |
65 | | Status _create_line_reader() override; |
66 | | Status _deserialize_one_cell(DataTypeSerDeSPtr serde, IColumn& column, Slice& slice) override; |
67 | | Status _validate_line(const Slice& line, bool* success) override; |
68 | | Status _deserialize_nullable_string(IColumn& column, Slice& slice) override; |
69 | | }; |
70 | | |
71 | | #include "common/compile_check_end.h" |
72 | | } // namespace doris |