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 "parquet/column_scanner.h" |
19 | |
20 | #include <cstdint> |
21 | #include <memory> |
22 | |
23 | #include "parquet/column_reader.h" |
24 | |
25 | using arrow::MemoryPool; |
26 | |
27 | namespace parquet { |
28 | |
29 | std::shared_ptr<Scanner> Scanner::Make(std::shared_ptr<ColumnReader> col_reader, |
30 | int64_t batch_size, MemoryPool* pool) { |
31 | switch (col_reader->type()) { |
32 | case Type::BOOLEAN: |
33 | return std::make_shared<BoolScanner>(col_reader, batch_size, pool); |
34 | case Type::INT32: |
35 | return std::make_shared<Int32Scanner>(col_reader, batch_size, pool); |
36 | case Type::INT64: |
37 | return std::make_shared<Int64Scanner>(col_reader, batch_size, pool); |
38 | case Type::INT96: |
39 | return std::make_shared<Int96Scanner>(col_reader, batch_size, pool); |
40 | case Type::FLOAT: |
41 | return std::make_shared<FloatScanner>(col_reader, batch_size, pool); |
42 | case Type::DOUBLE: |
43 | return std::make_shared<DoubleScanner>(col_reader, batch_size, pool); |
44 | case Type::BYTE_ARRAY: |
45 | return std::make_shared<ByteArrayScanner>(col_reader, batch_size, pool); |
46 | case Type::FIXED_LEN_BYTE_ARRAY: |
47 | return std::make_shared<FixedLenByteArrayScanner>(col_reader, batch_size, pool); |
48 | default: |
49 | ParquetException::NYI("type reader not implemented" ); |
50 | } |
51 | // Unreachable code, but supress compiler warning |
52 | return std::shared_ptr<Scanner>(nullptr); |
53 | } |
54 | |
55 | int64_t ScanAllValues(int32_t batch_size, int16_t* def_levels, int16_t* rep_levels, |
56 | uint8_t* values, int64_t* values_buffered, |
57 | parquet::ColumnReader* reader) { |
58 | switch (reader->type()) { |
59 | case parquet::Type::BOOLEAN: |
60 | return ScanAll<parquet::BoolReader>(batch_size, def_levels, rep_levels, values, |
61 | values_buffered, reader); |
62 | case parquet::Type::INT32: |
63 | return ScanAll<parquet::Int32Reader>(batch_size, def_levels, rep_levels, values, |
64 | values_buffered, reader); |
65 | case parquet::Type::INT64: |
66 | return ScanAll<parquet::Int64Reader>(batch_size, def_levels, rep_levels, values, |
67 | values_buffered, reader); |
68 | case parquet::Type::INT96: |
69 | return ScanAll<parquet::Int96Reader>(batch_size, def_levels, rep_levels, values, |
70 | values_buffered, reader); |
71 | case parquet::Type::FLOAT: |
72 | return ScanAll<parquet::FloatReader>(batch_size, def_levels, rep_levels, values, |
73 | values_buffered, reader); |
74 | case parquet::Type::DOUBLE: |
75 | return ScanAll<parquet::DoubleReader>(batch_size, def_levels, rep_levels, values, |
76 | values_buffered, reader); |
77 | case parquet::Type::BYTE_ARRAY: |
78 | return ScanAll<parquet::ByteArrayReader>(batch_size, def_levels, rep_levels, values, |
79 | values_buffered, reader); |
80 | case parquet::Type::FIXED_LEN_BYTE_ARRAY: |
81 | return ScanAll<parquet::FixedLenByteArrayReader>(batch_size, def_levels, rep_levels, |
82 | values, values_buffered, reader); |
83 | default: |
84 | parquet::ParquetException::NYI("type reader not implemented" ); |
85 | } |
86 | // Unreachable code, but supress compiler warning |
87 | return 0; |
88 | } |
89 | |
90 | } // namespace parquet |
91 | |