xdid-core 0.7.0

Core types for DID methods to implement.
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
131
132

#[derive(Copy, Clone, PartialEq, Eq)]
pub enum Segment {
    /// segment
    Base,
    /// segment-nz
    Nz,
    // segment-nz-nc
    NzNc,
}

/// Whether the string conforms to a given [Segment], following [RFC 3986](https://www.rfc-editor.org/rfc/rfc3986#section-3.3).
pub fn is_segment(value: &str, segment: Segment) -> bool {
    if (segment == Segment::Nz || segment == Segment::NzNc) && value.is_empty() {
        return false;
    }

    let mut processing_pct_encoded = false;
    let mut pct_encoded_char = 0usize;

    for c in value.chars() {
        // pct-encoded = "%" HEXDIG HEXDIG
        if processing_pct_encoded {
            if pct_encoded_char == 2 {
                pct_encoded_char = 0;
                processing_pct_encoded = false;
            } else {
                pct_encoded_char += 1;

                if c.is_ascii_hexdigit() {
                    continue;
                }
                return false;
            }
        }

        if c == '%' {
            processing_pct_encoded = true;
            continue;
        }

        if is_unreserved(c) {
            continue;
        }

        if is_sub_delim(c) {
            continue;
        }

        // pchar = unreserved / pct-encoded / sub-delims / ":" / "@"
        // segment       = *pchar
        // segment-nz    = 1*pchar
        // segment-nz-nc = 1*( unreserved / pct-encoded / sub-delims / "@" )
        //            ; non-zero-length segment without any colon ":"
        if c == '@' {
            continue;
        }

        match segment {
            Segment::Base | Segment::Nz => {
                if c == ':' {
                    continue;
                }
            }
            Segment::NzNc => {}
        }

        return false;
    }

    true
}

/// unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~"
fn is_unreserved(c: char) -> bool {
    c.is_alphanumeric() || c == '-' || c == '.' || c == '_' || c == '~'
}

/// sub-delims = "!" / "$" / "&" / "'" / "(" / ")" / "*" / "+" / "," / ";" / "="
const fn is_sub_delim(c: char) -> bool {
    c == '!'
        || c == '$'
        || c == '&'
        || c == '\''
        || c == '('
        || c == ')'
        || c == '*'
        || c == '+'
        || c == ','
        || c == ';'
        || c == '='
}

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

    #[test]
    fn test_segment_length() {
        assert!(is_segment("", Segment::Base));
        assert!(!is_segment("", Segment::Nz));
        assert!(!is_segment("", Segment::NzNc));
    }

    #[test]
    fn test_segment_alphanumeric() {
        assert!(is_segment(
            "abcdefghijklmnopqrstuvwxyz0123456789",
            Segment::Base
        ));
    }

    #[test]
    fn test_segment_symbols() {
        assert!(is_segment("!$&'()*+,;=@", Segment::Base));
        assert!(is_segment("!$&'()*+,;=@", Segment::Nz));
        assert!(is_segment("!$&'()*+,;=@", Segment::NzNc));
    }

    #[test]
    fn test_segment_colon() {
        assert!(is_segment(":", Segment::Base));
        assert!(is_segment(":", Segment::Nz));
        assert!(!is_segment(":", Segment::NzNc));
    }

    #[test]
    fn test_segment_pct_encode() {
        assert!(is_segment("%30%f9a", Segment::Base));
        assert!(!is_segment("%3%f9a", Segment::Base));
        assert!(!is_segment("%%f9a", Segment::Base));
    }
}