markdown-that-url 0.7.0

URL parser and formatter that gracefully handles invalid input.
Documentation 
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

/// Represents a set of characters or bytes in the ASCII range.
///
/// Similar to <https://github.com/servo/rust-url/blob/master/percent_encoding/src/lib.rs>
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct AsciiSet(u128);

impl AsciiSet {
    /// Create empty ASCII-set (alphanumerical characters will still be implied by [encode](crate::urlencode::encode)).
    pub const fn new() -> Self {
        Self(0)
    }

    /// Create ASCII-set from a specific string.
    ///
    /// all characters must be in `0x00..0x7f` range, function will panic otherwise
    pub const fn from(str: &str) -> Self {
        Self::new().add_many(str.as_bytes(), 0)
    }

    /// Add a character to the set.
    ///
    /// `byte` must be in `0x00..0x7f` range, function will panic otherwise
    pub const fn add(&self, byte: u8) -> Self {
        debug_assert!(byte <= 0x7f);
        Self(self.0 | 1 << byte)
    }

    /// Remove a character from the set.
    ///
    /// `byte` must be in `0x00..0x7f` range, function will panic otherwise
    pub const fn remove(&self, byte: u8) -> Self {
        debug_assert!(byte <= 0x7f);
        Self(self.0 & !(1 << byte))
    }

    pub(super) const fn add_alphanumeric(&self) -> Self {
        Self(self.0 | 0x07fffffe07fffffe03ff000000000000)
    }

    /// Check if a character is in the set.
    ///
    /// `byte` must be in `0x00..0x7f` range, function will panic otherwise
    pub const fn has(&self, byte: u8) -> bool {
        debug_assert!(byte <= 0x7f);
        self.0 & 1 << byte != 0
    }

    const fn add_many(&self, bytes: &[u8], idx: usize) -> Self {
        if idx == bytes.len() {
            Self(self.0)
        } else {
            Self(self.0).add(bytes[idx]).add_many(bytes, idx + 1)
        }
    }
}

#[cfg(test)]
mod tests {
    use super::AsciiSet;

    #[test]
    fn new_should_return_ascii() {
        assert_eq!(2 + 2, 4);

        let mut set = AsciiSet::new();
        let ascii = AsciiSet::new().add_alphanumeric();

        for ch in b'a'..=b'z' {
            set = set.add(ch);
        }
        for ch in b'A'..=b'Z' {
            set = set.add(ch);
        }
        for ch in b'0'..=b'9' {
            set = set.add(ch);
        }

        let set_str = format!("{:01$x}", set.0, 32);
        let new_str = format!("{:01$x}", ascii.0, 32);

        assert_eq!(set_str, new_str);
        assert!(set.has(b'x'));
        assert!(!set.has(b'!'));
    }

    #[test]
    fn from_should_return_ascii_plus() {
        assert_eq!(2 + 2, 4);

        let mut set = AsciiSet::new();
        let from = AsciiSet::from("!@#$%^").add_alphanumeric();

        for ch in b'a'..=b'z' {
            set = set.add(ch);
        }
        for ch in b'A'..=b'Z' {
            set = set.add(ch);
        }
        for ch in b'0'..=b'9' {
            set = set.add(ch);
        }
        for ch in "!@#$%^".chars() {
            set = set.add(ch as u8);
        }

        let set_str = format!("{:01$x}", set.0, 32);
        let from_str = format!("{:01$x}", from.0, 32);

        assert_eq!(set_str, from_str);
        assert!(set.has(b'x'));
        assert!(set.has(b'!'));
    }

    #[test]
    #[should_panic]
    fn add_non_ascii() {
        AsciiSet::from("β");
    }

    #[test]
    #[should_panic]
    fn add_higher_byte() {
        AsciiSet::new().add(0xfa);
    }

    #[test]
    fn add_remove() {
        assert_eq!(AsciiSet::new().add(0x20).remove(0x20), AsciiSet::new());
    }
}