ulid/
base32.rs

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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
use core::fmt;

/// Length of a string-encoded Ulid
pub const ULID_LEN: usize = 26;

const ALPHABET: &[u8; 32] = b"0123456789ABCDEFGHJKMNPQRSTVWXYZ";

const NO_VALUE: u8 = 255;
const LOOKUP: [u8; 256] = [
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 255, 255, 255,
    255, 255, 255, 255, 10, 11, 12, 13, 14, 15, 16, 17, 255, 18, 19, 255, 20, 21, 255, 22, 23, 24,
    25, 26, 255, 27, 28, 29, 30, 31, 255, 255, 255, 255, 255, 255, 10, 11, 12, 13, 14, 15, 16, 17,
    255, 18, 19, 255, 20, 21, 255, 22, 23, 24, 25, 26, 255, 27, 28, 29, 30, 31, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
    255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
];

/// Generator code for `LOOKUP`
#[cfg(test)]
#[test]
fn test_lookup_table() {
    let mut lookup = [NO_VALUE; 256];
    for (i, &c) in ALPHABET.iter().enumerate() {
        lookup[c as usize] = i as u8;
        if !(c as char).is_numeric() {
            //lowercase
            lookup[(c + 32) as usize] = i as u8;
        }
    }
    assert_eq!(LOOKUP, lookup);
}

/// An error that can occur when encoding a base32 string
#[derive(Debug, PartialEq, Eq, Hash, Copy, Clone)]
pub enum EncodeError {
    /// The length of the provided buffer is not large enough
    BufferTooSmall,
}

#[cfg(feature = "std")]
impl std::error::Error for EncodeError {}

impl fmt::Display for EncodeError {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
        let text = match *self {
            EncodeError::BufferTooSmall => "buffer too small",
        };
        write!(f, "{}", text)
    }
}

/// Encode a u128 value to a given buffer. The provided buffer should be at least `ULID_LEN` long.
#[deprecated(
    since = "1.2.0",
    note = "Use the infallible `encode_to_array` instead."
)]
pub fn encode_to(mut value: u128, buffer: &mut [u8]) -> Result<usize, EncodeError> {
    // NOTE: This function can't be made const because mut refs aren't allowed for some reason

    if buffer.len() < ULID_LEN {
        return Err(EncodeError::BufferTooSmall);
    }

    for i in 0..ULID_LEN {
        buffer[ULID_LEN - 1 - i] = ALPHABET[(value & 0x1f) as usize];
        value >>= 5;
    }

    Ok(ULID_LEN)
}

/// Encode a u128 value to a given buffer.
pub fn encode_to_array(mut value: u128, buffer: &mut [u8; ULID_LEN]) {
    // NOTE: This function can't be made const because mut refs aren't allowed for some reason

    for i in 0..ULID_LEN {
        buffer[ULID_LEN - 1 - i] = ALPHABET[(value & 0x1f) as usize];
        value >>= 5;
    }
}

#[cfg(feature = "std")]
pub fn encode(value: u128) -> String {
    let mut buffer: [u8; ULID_LEN] = [0; ULID_LEN];

    encode_to_array(value, &mut buffer);

    String::from_utf8(buffer.to_vec()).expect("unexpected failure in base32 encode for ulid")
}

/// An error that can occur when decoding a base32 string
#[derive(Debug, PartialEq, Eq, Hash, Copy, Clone)]
pub enum DecodeError {
    /// The length of the string does not match the expected length
    InvalidLength,
    /// A non-base32 character was found
    InvalidChar,
}

#[cfg(feature = "std")]
impl std::error::Error for DecodeError {}

impl fmt::Display for DecodeError {
    fn fmt(&self, f: &mut fmt::Formatter<'_>) -> Result<(), fmt::Error> {
        let text = match *self {
            DecodeError::InvalidLength => "invalid length",
            DecodeError::InvalidChar => "invalid character",
        };
        write!(f, "{}", text)
    }
}

pub const fn decode(encoded: &str) -> Result<u128, DecodeError> {
    if encoded.len() != ULID_LEN {
        return Err(DecodeError::InvalidLength);
    }

    let mut value: u128 = 0;

    let bytes = encoded.as_bytes();

    // Manual for loop because Range::iter() isn't const
    let mut i = 0;
    while i < ULID_LEN {
        let val = LOOKUP[bytes[i] as usize];
        if val != NO_VALUE {
            value = (value << 5) | val as u128;
        } else {
            return Err(DecodeError::InvalidChar);
        }
        i += 1;
    }

    Ok(value)
}

#[cfg(all(test, feature = "std"))]
mod tests {
    use super::*;

    #[test]
    fn test_valid() {
        let val = 0x41414141414141414141414141414141;
        assert_eq!(decode("21850M2GA1850M2GA1850M2GA1").unwrap(), val);
        assert_eq!(encode(val), "21850M2GA1850M2GA1850M2GA1");

        let val = 0x4d4e385051444a59454234335a413756;
        let enc = "2D9RW50MA499CMAGHM6DD42DTP";
        let lower = enc.to_lowercase();
        assert_eq!(encode(val), enc);
        assert_eq!(decode(enc).unwrap(), val);
        assert_eq!(decode(&lower).unwrap(), val);
    }

    #[test]
    fn test_length() {
        assert_eq!(encode(0xffffffffffffffffffffffffffffffff).len(), ULID_LEN);
        assert_eq!(encode(0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f).len(), ULID_LEN);
        assert_eq!(encode(0x00000000000000000000000000000000).len(), ULID_LEN);

        assert_eq!(decode(""), Err(DecodeError::InvalidLength));
        assert_eq!(
            decode("2D9RW50MA499CMAGHM6DD42DT"),
            Err(DecodeError::InvalidLength)
        );
        assert_eq!(
            decode("2D9RW50MA499CMAGHM6DD42DTPP"),
            Err(DecodeError::InvalidLength)
        );
    }

    #[test]
    fn test_chars() {
        for ref c in encode(0xffffffffffffffffffffffffffffffff).bytes() {
            assert!(ALPHABET.contains(c));
        }
        for ref c in encode(0x0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f0f).bytes() {
            assert!(ALPHABET.contains(c));
        }
        for ref c in encode(0x00000000000000000000000000000000).bytes() {
            assert!(ALPHABET.contains(c));
        }

        assert_eq!(
            decode("2D9RW50[A499CMAGHM6DD42DTP"),
            Err(DecodeError::InvalidChar)
        );
        assert_eq!(
            decode("2D9RW50LA499CMAGHM6DD42DTP"),
            Err(DecodeError::InvalidChar)
        );
        assert_eq!(
            decode("2D9RW50IA499CMAGHM6DD42DTP"),
            Err(DecodeError::InvalidChar)
        );
    }
}