ecd 0.1.1

Fast CLI to detect text file encodings (UTF-8, GBK, Shift_JIS, and 35+ more)
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
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151

//! Supported and planned character encodings for detection.

/// Encodings currently detectable via charset-normalizer-rs (WHATWG / IANA).
pub const SUPPORTED: &[&str] = &[
    // Unicode
    "utf-8",
    "utf-16le",
    "utf-16be",
    // East Asian — multibyte
    "gbk",
    "big5",
    "shift_jis",
    "euc-jp",
    "euc-kr",
    "iso-2022-jp",
    // Cyrillic
    "koi8-r",
    "koi8-u",
    "windows-1251",
    "x-mac-cyrillic",
    // European — ISO 8859
    "iso-8859-2",
    "iso-8859-3",
    "iso-8859-4",
    "iso-8859-5",
    "iso-8859-6",
    "iso-8859-7",
    "iso-8859-8",
    "iso-8859-8-i",
    "iso-8859-10",
    "iso-8859-13",
    "iso-8859-14",
    "iso-8859-15",
    "iso-8859-16",
    // European — Windows
    "windows-1250",
    "windows-1252",
    "windows-1253",
    "windows-1254",
    "windows-1255",
    "windows-1256",
    "windows-1257",
    "windows-1258",
    // Other
    "ibm866",
    "windows-874",
    "macintosh",
    "ascii",
];

/// Encodings not yet supported; may be added in future releases.
pub const PLANNED: &[&str] = &[
    // Legacy encodings outside the WHATWG set used by charset-normalizer-rs
    "tis-620",
    "cp437",
    "cp850",
    "cp932",
    "gb2312",
    "hz-gb-2312",
    "utf-32le",
    "utf-32be",
    "utf-7",
];

/// Group labels for documentation.
pub const GROUPS: &[(&str, &[&str])] = &[
    ("Unicode", &["utf-8", "utf-16le", "utf-16be"]),
    (
        "East Asian",
        &[
            "gbk",
            "big5",
            "shift_jis",
            "euc-jp",
            "euc-kr",
            "iso-2022-jp",
        ],
    ),
    (
        "Cyrillic",
        &["koi8-r", "koi8-u", "windows-1251", "x-mac-cyrillic"],
    ),
    (
        "ISO 8859",
        &[
            "iso-8859-2",
            "iso-8859-3",
            "iso-8859-4",
            "iso-8859-5",
            "iso-8859-6",
            "iso-8859-7",
            "iso-8859-8",
            "iso-8859-8-i",
            "iso-8859-10",
            "iso-8859-13",
            "iso-8859-14",
            "iso-8859-15",
            "iso-8859-16",
        ],
    ),
    (
        "Windows",
        &[
            "windows-1250",
            "windows-1252",
            "windows-1253",
            "windows-1254",
            "windows-1255",
            "windows-1256",
            "windows-1257",
            "windows-1258",
            "windows-874",
        ],
    ),
    ("Other", &["ibm866", "macintosh", "ascii"]),
];

pub fn is_supported(name: &str) -> bool {
    let normalized = name.to_ascii_lowercase();
    SUPPORTED.iter().any(|enc| *enc == normalized)
}

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

    #[test]
    fn groups_cover_all_supported() {
        let mut from_groups: Vec<&str> = GROUPS
            .iter()
            .flat_map(|(_, encs)| encs.iter().copied())
            .collect();
        from_groups.sort_unstable();
        from_groups.dedup();

        let mut supported = SUPPORTED.to_vec();
        supported.sort_unstable();

        assert_eq!(from_groups, supported);
    }

    #[test]
    fn planned_does_not_overlap_supported() {
        for enc in PLANNED {
            assert!(
                !is_supported(enc),
                "planned encoding {enc} is already supported"
            );
        }
    }
}