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/// QueryPairsWriter is used to write query pairs to a url.
68pub struct QueryPairsWriter {
69 base: String,
70 has_query: bool,
71}
72
73impl QueryPairsWriter {
74 /// Create a new QueryPairsWriter with the given base.
75 pub fn new(s: &str) -> Self {
76 // 256 is the average size we observed of a url
77 // in production.
78 //
79 // We eagerly allocate the string to avoid multiple
80 // allocations.
81 let mut base = String::with_capacity(256);
82 base.push_str(s);
83
84 Self {
85 base,
86 has_query: false,
87 }
88 }
89
90 /// Push a new pair of key and value to the url.
91 ///
92 /// The input key and value must already been percent
93 /// encoded correctly.
94 pub fn push(mut self, key: &str, value: &str) -> Self {
95 if self.has_query {
96 self.base.push('&');
97 } else {
98 self.base.push('?');
99 self.has_query = true;
100 }
101
102 // Append the key and value to the base string
103 self.base.push_str(key);
104 if !value.is_empty() {
105 self.base.push('=');
106 self.base.push_str(value);
107 }
108
109 self
110 }
111
112 /// Finish the url and return it.
113 pub fn finish(self) -> String {
114 self.base
115 }
116}
117
118#[cfg(test)]
119mod tests {
120 use super::*;
121
122 #[test]
123 fn test_percent_encode_path() {
124 let cases = vec![
125 (
126 "Reserved Characters",
127 ";,/?:@&=+$",
128 "%3B%2C/%3F%3A%40%26%3D%2B%24",
129 ),
130 ("Unescaped Characters", "-_.!~*'()", "-_.!~*'()"),
131 ("Number Sign", "#", "%23"),
132 (
133 "Alphanumeric Characters + Space",
134 "ABC abc 123",
135 "ABC%20abc%20123",
136 ),
137 (
138 "Unicode",
139 "你好,世界!❤",
140 "%E4%BD%A0%E5%A5%BD%EF%BC%8C%E4%B8%96%E7%95%8C%EF%BC%81%E2%9D%A4",
141 ),
142 ];
143
144 for (name, input, expected) in cases {
145 let actual = percent_encode_path(input);
146
147 assert_eq!(actual, expected, "{name}");
148 }
149 }
150
151 #[test]
152 fn test_percent_decode_path() {
153 let cases = vec![
154 (
155 "Reserved Characters",
156 "%3B%2C/%3F%3A%40%26%3D%2B%24",
157 ";,/?:@&=+$",
158 ),
159 ("Unescaped Characters", "-_.!~*'()", "-_.!~*'()"),
160 ("Number Sign", "%23", "#"),
161 (
162 "Alphanumeric Characters + Space",
163 "ABC%20abc%20123",
164 "ABC abc 123",
165 ),
166 (
167 "Unicode Characters",
168 "%E4%BD%A0%E5%A5%BD%EF%BC%8C%E4%B8%96%E7%95%8C%EF%BC%81%E2%9D%A4",
169 "你好,世界!❤",
170 ),
171 (
172 "Double Encoded Characters",
173 "Double%2520Encoded",
174 "Double%20Encoded",
175 ),
176 (
177 "Not Percent Encoded Characters",
178 "/not percent encoded/path;,/?:@&=+$-",
179 "/not percent encoded/path;,/?:@&=+$-",
180 ),
181 ];
182
183 for (name, input, expected) in cases {
184 let actual = percent_decode_path(input);
185
186 assert_eq!(actual, expected, "{name}");
187 }
188 }
189}