datafusion_spark/function/string/
mod.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
18pub mod ascii;
19pub mod base64;
20pub mod char;
21pub mod concat;
22pub mod concat_ws;
23pub mod elt;
24pub mod format_string;
25pub mod ilike;
26pub mod is_valid_utf8;
27pub mod length;
28pub mod like;
29pub mod luhn_check;
30pub mod make_valid_utf8;
31pub mod quote;
32pub mod soundex;
33pub mod space;
34pub mod substring;
35
36use datafusion_expr::ScalarUDF;
37use datafusion_functions::make_udf_function;
38use std::sync::Arc;
39
40make_udf_function!(ascii::SparkAscii, ascii);
41make_udf_function!(base64::SparkBase64, base64);
42make_udf_function!(char::CharFunc, char);
43make_udf_function!(concat::SparkConcat, concat);
44make_udf_function!(concat_ws::SparkConcatWs, concat_ws);
45make_udf_function!(ilike::SparkILike, ilike);
46make_udf_function!(length::SparkLengthFunc, length);
47make_udf_function!(elt::SparkElt, elt);
48make_udf_function!(like::SparkLike, like);
49make_udf_function!(luhn_check::SparkLuhnCheck, luhn_check);
50make_udf_function!(format_string::FormatStringFunc, format_string);
51make_udf_function!(space::SparkSpace, space);
52make_udf_function!(substring::SparkSubstring, substring);
53make_udf_function!(base64::SparkUnBase64, unbase64);
54make_udf_function!(soundex::SparkSoundex, soundex);
55make_udf_function!(make_valid_utf8::SparkMakeValidUtf8, make_valid_utf8);
56make_udf_function!(is_valid_utf8::SparkIsValidUtf8, is_valid_utf8);
57make_udf_function!(quote::SparkQuote, quote);
58
59pub mod expr_fn {
60    use datafusion_functions::export_functions;
61
62    export_functions!((
63        ascii,
64        "Returns the ASCII code point of the first character of string.",
65        arg1
66    ));
67    export_functions!((
68        base64,
69        "Encodes the input binary `bin` into a base64 string.",
70        bin
71    ));
72    export_functions!((
73        char,
74        "Returns the ASCII character having the binary equivalent to col. If col is larger than 256 the result is equivalent to char(col % 256).",
75        arg1
76    ));
77    export_functions!((
78        concat,
79        "Concatenates multiple input strings into a single string. Returns NULL if any input is NULL.",
80        args
81    ));
82    export_functions!((
83        concat_ws,
84        "Concatenates strings with separator. Supports arrays. Null values are skipped.",
85        sep args
86    ));
87    export_functions!((
88        elt,
89        "Returns the n-th input (1-indexed), e.g. returns 2nd input when n is 2. The function returns NULL if the index is 0 or exceeds the length of the array.",
90        select_col arg1 arg2 argn
91    ));
92    export_functions!((
93        ilike,
94        "Returns true if str matches pattern (case insensitive).",
95        str pattern
96    ));
97    export_functions!((
98        length,
99        "Returns the character length of string data or number of bytes of binary data. The length of string data includes the trailing spaces. The length of binary data includes binary zeros.",
100        arg1
101    ));
102    export_functions!((
103        like,
104        "Returns true if str matches pattern (case sensitive).",
105        str pattern
106    ));
107    export_functions!((
108        luhn_check,
109        "Returns whether the input string of digits is valid according to the Luhn algorithm.",
110        arg1
111    ));
112    export_functions!((
113        format_string,
114        "Returns a formatted string from printf-style format strings.",
115        strfmt args
116    ));
117    export_functions!((space, "Returns a string consisting of n spaces.", arg1));
118    export_functions!((
119        substring,
120        "Returns the substring from string `str` starting at position `pos` with length `length.",
121        str pos length
122    ));
123    export_functions!((
124        unbase64,
125        "Decodes the input string `str` from a base64 string into binary data.",
126        str
127    ));
128    export_functions!((soundex, "Returns Soundex code of the string.", str));
129    export_functions!((
130        is_valid_utf8,
131        "Returns true if str is a valid UTF-8 string, otherwise returns false",
132        str
133    ));
134    export_functions!((
135        make_valid_utf8,
136        "Returns the original string if str is a valid UTF-8 string, otherwise returns a new string whose invalid UTF8 byte sequences are replaced using the UNICODE replacement character U+FFFD.",
137        str
138    ));
139    export_functions!((
140        quote,
141        "Returns str enclosed by single quotes and each instance of single quote in it is preceded by a backslash",
142        str
143    ));
144}
145
146pub fn functions() -> Vec<Arc<ScalarUDF>> {
147    vec![
148        ascii(),
149        base64(),
150        char(),
151        concat(),
152        concat_ws(),
153        elt(),
154        ilike(),
155        length(),
156        like(),
157        luhn_check(),
158        format_string(),
159        space(),
160        substring(),
161        unbase64(),
162        soundex(),
163        make_valid_utf8(),
164        is_valid_utf8(),
165        quote(),
166    ]
167}
datafusion_spark/function/string/mod.rs

datafusion_spark/function/string/
mod.rs
