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 | // This module contains the logical parquet-cpp types (independent of Thrift |
19 | // structures), schema nodes, and related type tools |
20 | |
21 | #ifndef PARQUET_SCHEMA_INTERNAL_H |
22 | #define PARQUET_SCHEMA_INTERNAL_H |
23 | |
24 | #include <cstdint> |
25 | #include <memory> |
26 | #include <vector> |
27 | |
28 | #include "parquet/schema.h" |
29 | #include "parquet/types.h" |
30 | #include "parquet/util/macros.h" |
31 | |
32 | namespace parquet { |
33 | |
34 | namespace format { |
35 | class SchemaElement; |
36 | } |
37 | |
38 | namespace schema { |
39 | |
40 | // ---------------------------------------------------------------------- |
41 | // Conversion from Parquet Thrift metadata |
42 | |
43 | std::shared_ptr<SchemaDescriptor> FromParquet( |
44 | const std::vector<format::SchemaElement>& schema); |
45 | |
46 | class FlatSchemaConverter { |
47 | public: |
48 | FlatSchemaConverter(const format::SchemaElement* elements, int length) |
49 | : elements_(elements), length_(length), pos_(0), current_id_(0) {} |
50 | |
51 | std::unique_ptr<Node> Convert(); |
52 | |
53 | private: |
54 | const format::SchemaElement* elements_; |
55 | int length_; |
56 | int pos_; |
57 | int current_id_; |
58 | |
59 | int next_id() { return current_id_++; } |
60 | |
61 | const format::SchemaElement& Next(); |
62 | |
63 | std::unique_ptr<Node> NextNode(); |
64 | }; |
65 | |
66 | // ---------------------------------------------------------------------- |
67 | // Conversion to Parquet Thrift metadata |
68 | |
69 | void ToParquet(const GroupNode* schema, std::vector<format::SchemaElement>* out); |
70 | |
71 | // Converts nested parquet schema back to a flat vector of Thrift structs |
72 | class SchemaFlattener { |
73 | public: |
74 | SchemaFlattener(const GroupNode* schema, std::vector<format::SchemaElement>* out); |
75 | |
76 | void Flatten(); |
77 | |
78 | private: |
79 | const GroupNode* root_; |
80 | std::vector<format::SchemaElement>* elements_; |
81 | }; |
82 | |
83 | } // namespace schema |
84 | } // namespace parquet |
85 | |
86 | #endif // PARQUET_SCHEMA_INTERNAL_H |
87 | |