charset-normalizer-rs 1.0.0

Truly universal encoding detector in pure Rust - port of Python version
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

#![cfg(test)]
use crate::entity::Language;
use lazy_static::lazy_static;
mod cd;
mod detection_base;
mod detection_edge_case;
mod detection_full;
mod detection_large_payload;
mod entity;
mod md;
mod utils;

lazy_static! {
    pub static ref FILES_SAMPLES: Vec<(&'static str, Vec<&'static str>, &'static Language)> = vec![
        (
            "sample-turkish.txt",
            vec!["windows-1254"],
            &Language::Turkish
        ),
        ("sample-chinese.txt", vec!["big5"], &Language::Chinese),
        (
            "sample-french-1.txt",
            vec!["iso-8859-1", "windows-1252"],
            &Language::French
        ),
        (
            "sample-arabic-1.txt",
            vec!["windows-1256"],
            &Language::Arabic
        ),
        ("sample-arabic.txt", vec!["utf-8"], &Language::Arabic),
        (
            "sample-greek.txt",
            vec!["windows-1253", "iso-8859-7"],
            &Language::Greek
        ),
        ("sample-french.txt", vec!["utf-8"], &Language::French),
        ("sample-russian-3.txt", vec!["utf-8"], &Language::Russian),
        (
            "sample-greek-2.txt",
            vec!["windows-1253", "iso-8859-7"],
            &Language::Greek
        ),
        (
            "sample-hebrew-2.txt",
            vec!["windows-1255", "iso-8859-8"],
            &Language::Hebrew
        ),
        (
            "sample-hebrew-3.txt",
            vec!["windows-1255", "iso-8859-8"],
            &Language::Hebrew
        ),
        ("sample-bulgarian.txt", vec!["utf-8"], &Language::Bulgarian),
        ("sample-english.bom.txt", vec!["utf-8"], &Language::English),
        ("sample-spanish.txt", vec!["utf-8"], &Language::Spanish),
        ("sample-korean.txt", vec!["euc-kr"], &Language::Korean),
        ("sample-russian-2.txt", vec!["utf-8"], &Language::Russian),
        (
            "sample-russian.txt",
            vec!["x-mac-cyrillic"],
            &Language::Russian
        ),
        ("sample-polish.txt", vec!["utf-8"], &Language::Polish),
    ];
}