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
|
#![warn(clippy::pedantic)]
use std::collections::HashSet;
use std::convert::TryFrom;
// This is the character set containing just numbers.
lazy_static! {
static ref DIGIT: HashSet<char> =
('0'..='9')
.collect();
}
// This is the character set containing just the upper-case
// letters 'A' through 'F', used in upper-case hexadecimal.
lazy_static! {
static ref HEX_UPPER: HashSet<char> =
('A'..='F')
.collect();
}
// This is the character set containing just the lower-case
// letters 'a' through 'f', used in lower-case hexadecimal.
lazy_static! {
static ref HEX_LOWER: HashSet<char> =
('a'..='f')
.collect();
}
// TODO: Learn about using thiserror to define library errors
// [14:05] ABuffSeagull: You should use https://lib.rs/crates/thiserror for the errors
// [14:07] 715209: i also recommend thiserror
#[derive(Debug, Clone, thiserror::Error, PartialEq)]
pub enum Error {
#[error("illegal character")]
IllegalCharacter,
}
pub struct PercentEncodedCharacterDecoder {
decoded_character: u8,
digits_left: usize,
}
impl PercentEncodedCharacterDecoder {
pub fn new() -> Self {
Self{
decoded_character: 0,
digits_left: 2,
}
}
pub fn next(
&mut self,
c: char
) -> Result<Option<u8>, Error> {
self.shift_in_hex_digit(c)?;
self.digits_left -= 1;
if self.digits_left == 0 {
let output = self.decoded_character;
self.reset();
Ok(Some(output))
} else {
Ok(None)
}
}
fn reset(&mut self) {
self.decoded_character = 0;
self.digits_left = 2;
}
fn shift_in_hex_digit(
&mut self,
c: char
) -> Result<(), Error> {
self.decoded_character <<= 4;
if let Some(ci) = c.to_digit(16) {
self.decoded_character += u8::try_from(ci).unwrap();
} else {
self.reset();
return Err(Error::IllegalCharacter);
}
Ok(())
}
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn good_sequences() {
// TODO: consider named tuples instead
//
// [14:07] LeinardoSmith: Looks like there is a macro for named tuples:
// https://docs.rs/named_tuple/0.1.3/named_tuple/
struct TestVector {
sequence: [char; 2],
expected_output: u8,
}
let test_vectors = [
TestVector{sequence: ['4', '1'], expected_output: b'A'},
TestVector{sequence: ['5', 'A'], expected_output: b'Z'},
TestVector{sequence: ['6', 'e'], expected_output: b'n'},
TestVector{sequence: ['e', '1'], expected_output: b'\xe1'},
TestVector{sequence: ['C', 'A'], expected_output: b'\xca'},
];
for test_vector in &test_vectors {
let mut pec = PercentEncodedCharacterDecoder::new();
assert_eq!(
Ok(None),
pec.next(test_vector.sequence[0])
);
assert_eq!(
Ok(Some(test_vector.expected_output)),
pec.next(test_vector.sequence[1])
);
}
}
#[test]
fn bad_sequences() {
let test_vectors = [
'G', 'g', '.', 'z', '-', ' ', 'V',
];
for test_vector in &test_vectors {
let mut pec = PercentEncodedCharacterDecoder::new();
assert!(pec.next(*test_vector).is_err());
}
}
}
|
