parquet/
thrift.rs

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//! Custom thrift definitions
19
20pub use thrift::protocol::TCompactOutputProtocol;
21use thrift::protocol::{TInputProtocol, TOutputProtocol};
22
23/// Reads and writes the struct to Thrift protocols.
24///
25/// Unlike [`thrift::protocol::TSerializable`] this uses generics instead of trait objects
26pub trait TSerializable: Sized {
27    /// Reads the struct from the input Thrift protocol
28    fn read_from_in_protocol<T: TInputProtocol>(i_prot: &mut T) -> thrift::Result<Self>;
29    /// Writes the struct to the output Thrift protocol
30    fn write_to_out_protocol<T: TOutputProtocol>(&self, o_prot: &mut T) -> thrift::Result<()>;
31}
32
33#[cfg(test)]
34mod tests {
35    use crate::{
36        basic::Type,
37        file::page_index::{column_index::ColumnIndexMetaData, index_reader::decode_column_index},
38    };
39
40    #[test]
41    pub fn read_boolean_list_field_type() {
42        // Boolean collection type encoded as 0x01, as used by this crate when writing.
43        // Values encoded as 1 (true) or 2 (false) as in the current version of the thrift
44        // documentation.
45        let bytes = vec![
46            0x19, 0x21, 2, 1, 0x19, 0x28, 1, 0, 0, 0x19, 0x28, 1, 1, 0, 0x15, 0, 0,
47        ];
48        let index = decode_column_index(&bytes, Type::BOOLEAN).unwrap();
49
50        let index = match index {
51            ColumnIndexMetaData::BOOLEAN(index) => index,
52            _ => panic!("expected boolean column index"),
53        };
54
55        // should be false, true
56        assert!(!index.is_null_page(0));
57        assert!(index.is_null_page(1));
58        assert!(!index.min_value(0).unwrap()); // min is false
59        assert!(index.max_value(0).unwrap()); // max is true
60        assert!(index.min_value(1).is_none());
61        assert!(index.max_value(1).is_none());
62    }
63
64    #[test]
65    pub fn read_boolean_list_alternative_encoding() {
66        // Boolean collection type encoded as 0x02, as allowed by the spec.
67        // Values encoded as 1 (true) or 0 (false) as before the thrift documentation change on 2024-12-13.
68        let bytes = vec![
69            0x19, 0x22, 0, 1, 0x19, 0x28, 1, 0, 0, 0x19, 0x28, 1, 1, 0, 0x15, 0, 0,
70        ];
71        let index = decode_column_index(&bytes, Type::BOOLEAN).unwrap();
72
73        let index = match index {
74            ColumnIndexMetaData::BOOLEAN(index) => index,
75            _ => panic!("expected boolean column index"),
76        };
77
78        // should be false, true
79        assert!(!index.is_null_page(0));
80        assert!(index.is_null_page(1));
81        assert!(!index.min_value(0).unwrap()); // min is false
82        assert!(index.max_value(0).unwrap()); // max is true
83        assert!(index.min_value(1).is_none());
84        assert!(index.max_value(1).is_none());
85    }
86}
parquet/thrift.rs

parquet/
thrift.rs
