regexr 0.1.2

A high-performance regex engine built from scratch with JIT compilation and SIMD acceleration
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

//! Unicode script property tests.
//!
//! When the `jit` feature is enabled, these tests use JIT compilation.

use super::regex;

#[test]
fn test_unicode_script_greek() {
    let re = regex(r"\p{Greek}+");
    assert!(re.is_match("αβγ"));
    assert!(re.is_match("ΑΒΓΔ"));
    assert!(!re.is_match("abc"));
    assert!(!re.is_match("中文"));
}

#[test]
fn test_unicode_script_han() {
    let re = regex(r"\p{Han}+");
    assert!(re.is_match("中文"));
    assert!(re.is_match("漢字"));
    assert!(!re.is_match("abc"));
    assert!(!re.is_match("αβγ"));
}

#[test]
fn test_unicode_script_latin() {
    let re = regex(r"\p{Latin}+");
    assert!(re.is_match("abc"));
    assert!(re.is_match("XYZ"));
    assert!(re.is_match("àéîõü"));
    assert!(!re.is_match("αβγ"));
    assert!(!re.is_match("中文"));
}

#[test]
fn test_unicode_script_cyrillic() {
    let re = regex(r"\p{Cyrillic}+");
    assert!(re.is_match("абв"));
    assert!(re.is_match("АБВ"));
    assert!(!re.is_match("abc"));
}

#[test]
fn test_unicode_script_arabic() {
    let re = regex(r"\p{Arabic}+");
    assert!(re.is_match("مرحبا"));
    assert!(!re.is_match("abc"));
}

#[test]
fn test_unicode_script_hiragana() {
    let re = regex(r"\p{Hiragana}+");
    assert!(re.is_match("ひらがな"));
    assert!(!re.is_match("カタカナ"));
    assert!(!re.is_match("abc"));
}

#[test]
fn test_unicode_script_katakana() {
    let re = regex(r"\p{Katakana}+");
    assert!(re.is_match("カタカナ"));
    assert!(!re.is_match("ひらがな"));
    assert!(!re.is_match("abc"));
}

#[test]
fn test_unicode_script_hangul() {
    let re = regex(r"\p{Hangul}+");
    assert!(re.is_match("한글"));
    assert!(!re.is_match("abc"));
    assert!(!re.is_match("中文"));
}

#[test]
fn test_negated_script_property() {
    let re = regex(r"\P{Greek}+");
    assert!(re.is_match("abc"));
    assert!(re.is_match("中文"));
    assert!(re.is_match("123"));
    assert!(!re.is_match("αβγ"));

    let m = re.find("αβγabcδεζ").unwrap();
    assert_eq!(m.as_str(), "abc");
}

#[test]
fn test_combined_script_patterns() {
    let re = regex(r"(?:\p{Han}|\p{Hiragana}|\p{Katakana})+");
    assert!(re.is_match("日本語"));
    assert!(re.is_match("中文"));
    assert!(re.is_match("ひらがな"));
    assert!(re.is_match("カタカナ"));
    assert!(!re.is_match("abc"));
}