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
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151

// 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 std::any::Any;
use std::sync::Arc;

use arrow::array::{ArrayRef, Int32Array, Int64Array, OffsetSizeTrait};
use arrow::datatypes::DataType;

use crate::utils::{make_scalar_function, utf8_to_int_type};
use datafusion_common::cast::as_generic_string_array;
use datafusion_common::utils::datafusion_strsim;
use datafusion_common::{exec_err, Result};
use datafusion_expr::ColumnarValue;
use datafusion_expr::TypeSignature::*;
use datafusion_expr::{ScalarUDFImpl, Signature, Volatility};

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

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

impl LevenshteinFunc {
    pub fn new() -> Self {
        use DataType::*;
        Self {
            signature: Signature::one_of(
                vec![Exact(vec![Utf8, Utf8]), Exact(vec![LargeUtf8, LargeUtf8])],
                Volatility::Immutable,
            ),
        }
    }
}

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

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

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

    fn return_type(&self, arg_types: &[DataType]) -> Result<DataType> {
        utf8_to_int_type(&arg_types[0], "levenshtein")
    }

    fn invoke(&self, args: &[ColumnarValue]) -> Result<ColumnarValue> {
        match args[0].data_type() {
            DataType::Utf8 => make_scalar_function(levenshtein::<i32>, vec![])(args),
            DataType::LargeUtf8 => make_scalar_function(levenshtein::<i64>, vec![])(args),
            other => {
                exec_err!("Unsupported data type {other:?} for function levenshtein")
            }
        }
    }
}

///Returns the Levenshtein distance between the two given strings.
/// LEVENSHTEIN('kitten', 'sitting') = 3
pub fn levenshtein<T: OffsetSizeTrait>(args: &[ArrayRef]) -> Result<ArrayRef> {
    if args.len() != 2 {
        return exec_err!(
            "levenshtein function requires two arguments, got {}",
            args.len()
        );
    }
    let str1_array = as_generic_string_array::<T>(&args[0])?;
    let str2_array = as_generic_string_array::<T>(&args[1])?;
    match args[0].data_type() {
        DataType::Utf8 => {
            let result = str1_array
                .iter()
                .zip(str2_array.iter())
                .map(|(string1, string2)| match (string1, string2) {
                    (Some(string1), Some(string2)) => {
                        Some(datafusion_strsim::levenshtein(string1, string2) as i32)
                    }
                    _ => None,
                })
                .collect::<Int32Array>();
            Ok(Arc::new(result) as ArrayRef)
        }
        DataType::LargeUtf8 => {
            let result = str1_array
                .iter()
                .zip(str2_array.iter())
                .map(|(string1, string2)| match (string1, string2) {
                    (Some(string1), Some(string2)) => {
                        Some(datafusion_strsim::levenshtein(string1, string2) as i64)
                    }
                    _ => None,
                })
                .collect::<Int64Array>();
            Ok(Arc::new(result) as ArrayRef)
        }
        other => {
            exec_err!(
                "levenshtein was called with {other} datatype arguments. It requires Utf8 or LargeUtf8."
            )
        }
    }
}

#[cfg(test)]
mod tests {
    use arrow::array::StringArray;

    use datafusion_common::cast::as_int32_array;

    use super::*;

    #[test]
    fn to_levenshtein() -> Result<()> {
        let string1_array =
            Arc::new(StringArray::from(vec!["123", "abc", "xyz", "kitten"]));
        let string2_array =
            Arc::new(StringArray::from(vec!["321", "def", "zyx", "sitting"]));
        let res = levenshtein::<i32>(&[string1_array, string2_array]).unwrap();
        let result =
            as_int32_array(&res).expect("failed to initialized function levenshtein");
        let expected = Int32Array::from(vec![2, 3, 2, 3]);
        assert_eq!(&expected, result);

        Ok(())
    }
}