datafusion_functions/math/
factorial.rs

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
// Licensed to the Apache Software Foundation (ASF) under one
// or more contributor license agreements.  See the NOTICE file
// distributed with this work for additional information
// regarding copyright ownership.  The ASF licenses this file
// to you under the Apache License, Version 2.0 (the
// "License"); you may not use this file except in compliance
// with the License.  You may obtain a copy of the License at
//
//   http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing,
// software distributed under the License is distributed on an
// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
// KIND, either express or implied.  See the License for the
// specific language governing permissions and limitations
// under the License.

use arrow::{
    array::{ArrayRef, Int64Array},
    error::ArrowError,
};
use std::any::Any;
use std::sync::Arc;

use arrow::datatypes::DataType;
use arrow::datatypes::DataType::Int64;

use crate::utils::make_scalar_function;
use datafusion_common::{arrow_datafusion_err, exec_err, DataFusionError, Result};
use datafusion_expr::{ColumnarValue, ScalarUDFImpl, Signature, Volatility};

#[derive(Debug)]
pub struct FactorialFunc {
    signature: Signature,
}

impl Default for FactorialFunc {
    fn default() -> Self {
        FactorialFunc::new()
    }
}

impl FactorialFunc {
    pub fn new() -> Self {
        Self {
            signature: Signature::uniform(1, vec![Int64], Volatility::Immutable),
        }
    }
}

impl ScalarUDFImpl for FactorialFunc {
    fn as_any(&self) -> &dyn Any {
        self
    }

    fn name(&self) -> &str {
        "factorial"
    }

    fn signature(&self) -> &Signature {
        &self.signature
    }

    fn return_type(&self, _arg_types: &[DataType]) -> Result<DataType> {
        Ok(Int64)
    }

    fn invoke(&self, args: &[ColumnarValue]) -> Result<ColumnarValue> {
        make_scalar_function(factorial, vec![])(args)
    }
}

/// Factorial SQL function
fn factorial(args: &[ArrayRef]) -> Result<ArrayRef> {
    match args[0].data_type() {
        DataType::Int64 => {
            let arg = downcast_arg!((&args[0]), "value", Int64Array);
            Ok(arg
                .iter()
                .map(|a| match a {
                    Some(a) => (2..=a)
                        .try_fold(1i64, i64::checked_mul)
                        .ok_or_else(|| {
                            arrow_datafusion_err!(ArrowError::ComputeError(format!(
                                "Overflow happened on FACTORIAL({a})"
                            )))
                        })
                        .map(Some),
                    _ => Ok(None),
                })
                .collect::<Result<Int64Array>>()
                .map(Arc::new)? as ArrayRef)
        }
        other => exec_err!("Unsupported data type {other:?} for function factorial."),
    }
}

#[cfg(test)]
mod test {

    use datafusion_common::cast::as_int64_array;

    use super::*;

    #[test]
    fn test_factorial_i64() {
        let args: Vec<ArrayRef> = vec![
            Arc::new(Int64Array::from(vec![0, 1, 2, 4])), // input
        ];

        let result = factorial(&args).expect("failed to initialize function factorial");
        let ints =
            as_int64_array(&result).expect("failed to initialize function factorial");

        let expected = Int64Array::from(vec![1, 1, 2, 24]);

        assert_eq!(ints, &expected);
    }
}