eml-codec 0.1.2

Email enCOder DECoder in Rust. Support Internet Message Format and MIME (RFC 822, 5322, 2045, 2046, 2047, 2048, 2049).
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
133
134

use crate::text::ascii;
use crate::text::whitespace::cfws;
use nom::{
    bytes::complete::{tag, take_while1},
    character::is_alphanumeric,
    combinator::{opt, recognize},
    multi::many0,
    sequence::{delimited, pair},
    IResult,
};

pub fn is_vchar(c: u8) -> bool {
    (ascii::EXCLAMATION..=ascii::TILDE).contains(&c)
}

/// MIME Token allowed characters
///
/// forbidden: ()<>@,;:\"/[]?=
fn is_mime_atom_text(c: u8) -> bool {
    is_alphanumeric(c)
        || c == ascii::EXCLAMATION
        || c == ascii::NUM
        || c == ascii::DOLLAR
        || c == ascii::PERCENT
        || c == ascii::AMPERSAND
        || c == ascii::SQUOTE
        || c == ascii::ASTERISK
        || c == ascii::PLUS
        || c == ascii::MINUS
        || c == ascii::PERIOD
        || c == ascii::CARRET
        || c == ascii::UNDERSCORE
        || c == ascii::GRAVE
        || c == ascii::LEFT_CURLY
        || c == ascii::PIPE
        || c == ascii::RIGHT_CURLY
        || c == ascii::TILDE
}

/// MIME Token
///
/// `[CFWS] 1*token_text [CFWS]`
pub fn mime_atom(input: &[u8]) -> IResult<&[u8], &[u8]> {
    delimited(opt(cfws), take_while1(is_mime_atom_text), opt(cfws))(input)
}

/// Atom allowed characters
///
/// authorized: !#$%&'*+-/=?^_`{|}~
fn is_atext(c: u8) -> bool {
    is_alphanumeric(c)
        || c == ascii::EXCLAMATION
        || c == ascii::NUM
        || c == ascii::DOLLAR
        || c == ascii::PERCENT
        || c == ascii::AMPERSAND
        || c == ascii::SQUOTE
        || c == ascii::ASTERISK
        || c == ascii::PLUS
        || c == ascii::MINUS
        || c == ascii::SLASH
        || c == ascii::EQ
        || c == ascii::QUESTION
        || c == ascii::CARRET
        || c == ascii::UNDERSCORE
        || c == ascii::GRAVE
        || c == ascii::LEFT_CURLY
        || c == ascii::PIPE
        || c == ascii::RIGHT_CURLY
        || c == ascii::TILDE
}

/// Atom
///
/// `[CFWS] 1*atext [CFWS]`
pub fn atom(input: &[u8]) -> IResult<&[u8], &[u8]> {
    delimited(opt(cfws), take_while1(is_atext), opt(cfws))(input)
}

/// dot-atom-text
///
/// `1*atext *("." 1*atext)`
pub fn dot_atom_text(input: &[u8]) -> IResult<&[u8], &[u8]> {
    recognize(pair(
        take_while1(is_atext),
        many0(pair(tag("."), take_while1(is_atext))),
    ))(input)
}

/// dot-atom
///
/// `[CFWS] dot-atom-text [CFWS]`
#[allow(dead_code)]
pub fn dot_atom(input: &[u8]) -> IResult<&[u8], &[u8]> {
    delimited(opt(cfws), dot_atom_text, opt(cfws))(input)
}

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

    #[test]
    fn test_atext() {
        assert!(is_atext(b'='));
        assert!(is_atext(b'5'));
        assert!(is_atext(b'Q'));
        assert!(!is_atext(b' '));
        //assert!(is_atext('É')); // support utf8
    }

    #[test]
    fn test_atom() {
        assert_eq!(
            atom(b"(skip)  imf_codec (hidden) aerogramme"),
            Ok((&b"aerogramme"[..], &b"imf_codec"[..]))
        );
    }

    #[test]
    fn test_dot_atom_text() {
        assert_eq!(
            dot_atom_text(b"quentin.dufour.io abcdef"),
            Ok((&b" abcdef"[..], &b"quentin.dufour.io"[..]))
        );
    }

    #[test]
    fn test_dot_atom() {
        assert_eq!(
            dot_atom(b"   (skip) quentin.dufour.io abcdef"),
            Ok((&b"abcdef"[..], &b"quentin.dufour.io"[..]))
        );
    }
}