opendal/raw/http_util/
uri.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
18use crate::*;
19use percent_encoding::percent_decode_str;
20use percent_encoding::utf8_percent_encode;
21use percent_encoding::AsciiSet;
22use percent_encoding::NON_ALPHANUMERIC;
23
24/// Parse http uri invalid error in to opendal::Error.
25pub fn new_http_uri_invalid_error(err: http::uri::InvalidUri) -> Error {
26    Error::new(ErrorKind::Unexpected, "parse http uri").set_source(err)
27}
28
29/// PATH_ENCODE_SET is the encode set for http url path.
30///
31/// This set follows [encodeURIComponent](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/encodeURIComponent) which will encode all non-ASCII characters except `A-Z a-z 0-9 - _ . ! ~ * ' ( )`
32///
33/// There is a special case for `/` in path: we will allow `/` in path as
34/// required by storage services like s3.
35static PATH_ENCODE_SET: AsciiSet = NON_ALPHANUMERIC
36    .remove(b'/')
37    .remove(b'-')
38    .remove(b'_')
39    .remove(b'.')
40    .remove(b'!')
41    .remove(b'~')
42    .remove(b'*')
43    .remove(b'\'')
44    .remove(b'(')
45    .remove(b')');
46
47/// percent_encode_path will do percent encoding for http encode path.
48///
49/// Follows [encodeURIComponent](https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/encodeURIComponent) which will encode all non-ASCII characters except `A-Z a-z 0-9 - _ . ! ~ * ' ( )`
50///
51/// There is a special case for `/` in path: we will allow `/` in path as
52/// required by storage services like s3.
53pub fn percent_encode_path(path: &str) -> String {
54    utf8_percent_encode(path, &PATH_ENCODE_SET).to_string()
55}
56
57/// percent_decode_path will do percent decoding for http decode path.
58///
59/// If the input is not percent encoded or not valid utf8, return the input.
60pub fn percent_decode_path(path: &str) -> String {
61    match percent_decode_str(path).decode_utf8() {
62        Ok(v) => v.to_string(),
63        Err(_) => path.to_string(),
64    }
65}
66
67#[cfg(test)]
68mod tests {
69    use super::*;
70
71    #[test]
72    fn test_percent_encode_path() {
73        let cases = vec![
74            (
75                "Reserved Characters",
76                ";,/?:@&=+$",
77                "%3B%2C/%3F%3A%40%26%3D%2B%24",
78            ),
79            ("Unescaped Characters", "-_.!~*'()", "-_.!~*'()"),
80            ("Number Sign", "#", "%23"),
81            (
82                "Alphanumeric Characters + Space",
83                "ABC abc 123",
84                "ABC%20abc%20123",
85            ),
86            (
87                "Unicode",
88                "你好，世界！❤",
89                "%E4%BD%A0%E5%A5%BD%EF%BC%8C%E4%B8%96%E7%95%8C%EF%BC%81%E2%9D%A4",
90            ),
91        ];
92
93        for (name, input, expected) in cases {
94            let actual = percent_encode_path(input);
95
96            assert_eq!(actual, expected, "{name}");
97        }
98    }
99
100    #[test]
101    fn test_percent_decode_path() {
102        let cases = vec![
103            (
104                "Reserved Characters",
105                "%3B%2C/%3F%3A%40%26%3D%2B%24",
106                ";,/?:@&=+$",
107            ),
108            ("Unescaped Characters", "-_.!~*'()", "-_.!~*'()"),
109            ("Number Sign", "%23", "#"),
110            (
111                "Alphanumeric Characters + Space",
112                "ABC%20abc%20123",
113                "ABC abc 123",
114            ),
115            (
116                "Unicode Characters",
117                "%E4%BD%A0%E5%A5%BD%EF%BC%8C%E4%B8%96%E7%95%8C%EF%BC%81%E2%9D%A4",
118                "你好，世界！❤",
119            ),
120            (
121                "Double Encoded Characters",
122                "Double%2520Encoded",
123                "Double%20Encoded",
124            ),
125            (
126                "Not Percent Encoded Characters",
127                "/not percent encoded/path;,/?:@&=+$-",
128                "/not percent encoded/path;,/?:@&=+$-",
129            ),
130        ];
131
132        for (name, input, expected) in cases {
133            let actual = percent_decode_path(input);
134
135            assert_eq!(actual, expected, "{name}");
136        }
137    }
138}
opendal/raw/http_util/uri.rs

opendal/raw/http_util/
uri.rs
