regexr 0.3.2

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
95
96

//! Basic Unicode matching and character class tests.
//!
//! When the `jit` feature is enabled, these tests use JIT compilation.

use super::regex;

// =============================================================================
// Basic Unicode
// =============================================================================

#[test]
fn test_unicode_basic() {
    let re = regex("héllo");
    assert!(re.is_match("héllo world"));
    assert!(!re.is_match("hello world"));
}

// =============================================================================
// Unicode Character Classes (multi-byte UTF-8)
// =============================================================================

#[test]
fn test_unicode_character_class_greek() {
    let re = regex("[α-ω]+");
    assert!(re.is_match("αβγδ"));
    assert!(re.is_match("ωψχ"));
    assert!(!re.is_match("abc"));

    let m = re.find("hello αβγ world").unwrap();
    assert_eq!(m.as_str(), "αβγ");
}

#[test]
fn test_unicode_character_class_mixed() {
    let re = regex("[a-zα-ω]+");
    assert!(re.is_match("hello"));
    assert!(re.is_match("αβγ"));
    assert!(re.is_match("helloαβγ"));

    let m = re.find("123 abcαβγ 456").unwrap();
    assert_eq!(m.as_str(), "abcαβγ");
}

#[test]
fn test_unicode_character_class_cjk() {
    let re = regex("[一-龥]+");
    assert!(re.is_match("中文"));
    assert!(!re.is_match("abc"));
}

#[test]
fn test_unicode_character_class_emoji() {
    let re = regex("[😀-😂]+");
    assert!(re.is_match("😀"));
    assert!(re.is_match("😁"));
    assert!(!re.is_match("abc"));
}

// =============================================================================
// Latin-1 class members inside a concatenation
//
// A standalone single-class pattern like `[é]` takes a different code path
// (`CompiledInner::CodepointClass`) than a class nested inside a
// concatenation, which goes through `HirExpr::Concat`. These tests exercise
// the latter, where a Latin-1 codepoint (U+0080-U+00FF) must be compiled to
// its UTF-8 byte sequence rather than truncated to a single raw byte.
// =============================================================================

#[test]
fn test_latin1_class_in_concat() {
    let re = regex("X[é]Y");
    let m = re.find("XéY").unwrap();
    assert_eq!(m.as_str(), "XéY");
    assert!(!re.is_match("XeY"));
}

#[test]
fn test_latin1_class_plus() {
    let re = regex("[é]+");
    let m = re.find("héllo").unwrap();
    assert_eq!(m.as_str(), "é");
}

#[test]
fn test_latin1_class_in_noncapturing_group() {
    let re = regex("(?:[é])");
    assert!(re.is_match("é"));
    assert!(!re.is_match("e"));
}

#[test]
fn test_latin1_class_range_in_concat() {
    let re = regex("X[à-ÿ]+Y");
    let m = re.find("XàéîöYtail").unwrap();
    assert_eq!(m.as_str(), "XàéîöY");
}