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
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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241

//! Markup and structured text pattern tests.
//!
//! Patterns for parsing HTML tags, JSON strings, and other structured text formats.
//!
//! When the `jit` feature is enabled, these tests use JIT compilation.

use super::regex;

// =============================================================================
// HTML Tag Patterns
// =============================================================================

/// HTML tag stripping pattern from benchmark
/// Pattern: `<[^>]+>`
#[test]
fn test_html_tag_basic() {
    let re = regex(r"<[^>]+>");

    assert!(re.is_match("<p>"));
    assert!(re.is_match("</p>"));
    assert!(re.is_match("<div class=\"test\">"));
    assert!(re.is_match("<br/>"));
    assert!(re.is_match("<img src=\"image.png\" alt=\"test\">"));

    assert!(!re.is_match("plain text"));
    assert!(!re.is_match("<>")); // Empty tag
}

#[test]
fn test_html_tag_extraction() {
    let re = regex(r"<[^>]+>");

    let html = "<html><head><title>Test</title></head><body><p>Hello</p></body></html>";
    let tags: Vec<_> = re.find_iter(html).map(|m| m.as_str()).collect();

    assert_eq!(tags.len(), 10);
    assert_eq!(tags[0], "<html>");
    assert_eq!(tags[1], "<head>");
    assert_eq!(tags[2], "<title>");
}

#[test]
fn test_html_tag_stripping() {
    let re = regex(r"<[^>]+>");

    let html = "<p>Hello <b>World</b>!</p>";
    let stripped = re.replace_all(html, "");
    assert_eq!(stripped, "Hello World!");
}

#[test]
fn test_html_self_closing_tags() {
    let re = regex(r"<[^>]+>");

    assert!(re.is_match("<br>"));
    assert!(re.is_match("<br/>"));
    assert!(re.is_match("<br />"));
    assert!(re.is_match("<hr>"));
    assert!(re.is_match("<img src=\"x\">"));
}

#[test]
fn test_html_tag_with_attributes() {
    let re = regex(r"<[^>]+>");

    let html = r#"<div id="main" class="container" data-value="123">"#;
    let m = re.find(html).unwrap();
    assert_eq!(m.as_str(), html);
}

// =============================================================================
// JSON String Patterns
// =============================================================================

/// JSON string extraction pattern from benchmark
/// Pattern: `"([^"\\]|\\.)*"`
#[test]
fn test_json_string_basic() {
    let re = regex(r#""([^"\\]|\\.)*""#);

    assert!(re.is_match(r#""hello""#));
    assert!(re.is_match(r#""hello world""#));
    assert!(re.is_match(r#""""#)); // Empty string

    assert!(!re.is_match("hello")); // No quotes
    assert!(!re.is_match(r#""unclosed"#)); // Unclosed
}

#[test]
fn test_json_string_with_escapes() {
    let re = regex(r#""([^"\\]|\\.)*""#);

    // Escaped characters
    assert!(re.is_match(r#""hello\"world""#)); // Escaped quote
    assert!(re.is_match(r#""path\\to\\file""#)); // Escaped backslash
    assert!(re.is_match(r#""line1\nline2""#)); // Escaped newline
    assert!(re.is_match(r#""tab\there""#)); // Escaped tab
}

#[test]
fn test_json_string_extraction() {
    let re = regex(r#""([^"\\]|\\.)*""#);

    let json = r#"{"name": "John", "city": "New York"}"#;
    let strings: Vec<_> = re.find_iter(json).map(|m| m.as_str()).collect();

    assert_eq!(strings.len(), 4);
    assert_eq!(strings[0], r#""name""#);
    assert_eq!(strings[1], r#""John""#);
    assert_eq!(strings[2], r#""city""#);
    assert_eq!(strings[3], r#""New York""#);
}

#[test]
fn test_json_string_in_array() {
    let re = regex(r#""([^"\\]|\\.)*""#);

    let json = r#"["apple", "banana", "cherry"]"#;
    let strings: Vec<_> = re.find_iter(json).map(|m| m.as_str()).collect();

    assert_eq!(strings.len(), 3);
    assert_eq!(strings[0], r#""apple""#);
    assert_eq!(strings[1], r#""banana""#);
    assert_eq!(strings[2], r#""cherry""#);
}

#[test]
fn test_json_string_unicode() {
    let re = regex(r#""([^"\\]|\\.)*""#);

    assert!(re.is_match(r#""hello \u0041""#)); // Unicode escape
    assert!(re.is_match(r#""emoji: 😀""#)); // Direct emoji
    assert!(re.is_match(r#""日本語""#)); // Japanese
}

// =============================================================================
// Backreference Patterns (matching quotes)
// =============================================================================

/// Quote matching pattern with backreference from benchmark
/// Pattern: `(['"])[^'"]*\1`
#[test]
fn test_matching_quotes() {
    let re = regex(r#"(['"])[^'"]*\1"#);

    // Matching quotes
    assert!(re.is_match(r#"'hello'"#));
    assert!(re.is_match(r#""world""#));
    assert!(re.is_match(r#"'test string'"#));
    assert!(re.is_match(r#""another test""#));

    // Mismatched quotes should not match
    assert!(!re.is_match(r#"'hello""#));
    assert!(!re.is_match(r#""world'"#));
}

#[test]
fn test_matching_quotes_extraction() {
    let re = regex(r#"(['"])[^'"]*\1"#);

    let code = r#"let x = 'hello'; let y = "world";"#;
    let strings: Vec<_> = re.find_iter(code).map(|m| m.as_str()).collect();

    assert_eq!(strings.len(), 2);
    assert_eq!(strings[0], "'hello'");
    assert_eq!(strings[1], "\"world\"");
}

#[test]
fn test_matching_quotes_empty() {
    let re = regex(r#"(['"])[^'"]*\1"#);

    assert!(re.is_match(r#"''"#));
    assert!(re.is_match(r#""""#));
}

// =============================================================================
// XML/Markup Patterns
// =============================================================================

#[test]
fn test_xml_comment() {
    let re = regex(r"<!--[^-]*(?:-[^-]+)*-->");

    assert!(re.is_match("<!-- comment -->"));
    assert!(re.is_match("<!---->"));
    // Note: for multiline, a different approach would be needed
}

#[test]
fn test_xml_cdata() {
    let re = regex(r"<!\[CDATA\[.*?\]\]>");

    assert!(re.is_match("<![CDATA[content]]>"));
    assert!(re.is_match("<![CDATA[<html>code</html>]]>"));
}

#[test]
fn test_xml_processing_instruction() {
    let re = regex(r"<\?[^?]+\?>");

    assert!(re.is_match("<?xml version=\"1.0\"?>"));
    assert!(re.is_match("<?php echo 'hello'; ?>"));
}

// =============================================================================
// Markdown Patterns
// =============================================================================

#[test]
fn test_markdown_header() {
    let re = regex(r"^#{1,6}\s+.+$");

    assert!(re.is_match("# Header 1"));
    assert!(re.is_match("## Header 2"));
    assert!(re.is_match("###### Header 6"));

    assert!(!re.is_match("####### Too many"));
    assert!(!re.is_match("#NoSpace"));
}

#[test]
fn test_markdown_link() {
    let re = regex(r"\[([^\]]+)\]\(([^)]+)\)");

    let md = "[Click here](https://example.com)";
    let caps = re.captures(md).unwrap();

    assert_eq!(&caps[1], "Click here");
    assert_eq!(&caps[2], "https://example.com");
}

#[test]
fn test_markdown_code_block() {
    let re = regex(r"```\w*");

    assert!(re.is_match("```"));
    assert!(re.is_match("```python"));
    assert!(re.is_match("```javascript"));
    assert!(re.is_match("```rust"));
}