sxurl 1.1.0

Fixed-length, sliceable URL identifier system for efficient database storage and querying
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
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324

//! Tests for URL normalization, validation, and component extraction.

use sxurl::*;

#[test]
fn test_url_normalization_basic() {
    let test_cases = vec![
        ("HTTPS://EXAMPLE.COM/", "https://example.com/"),
        ("HTTP://DOCS.RS/PATH", "http://docs.rs/PATH"),
        ("https://Example.Org/Test", "https://example.org/Test"),
        ("FTP://FILES.EXAMPLE.COM/", "ftp://files.example.com/"),
    ];

    for (input, expected) in test_cases {
        let result = normalize_url(input).unwrap();
        assert_eq!(result.as_str(), expected, "Normalization failed for: {}", input);
    }
}

#[test]
fn test_url_normalization_idna() {
    // Test IDNA normalization for international domains
    let test_cases = vec![
        "https://café.com/",
        "https://москва.рф/",
        "https://日本.jp/",
    ];

    for url in test_cases {
        let result = normalize_url(url);
        assert!(result.is_ok(), "IDNA normalization should work for: {}", url);

        let normalized = result.unwrap();
        assert!(normalized.host_str().unwrap().is_ascii(), "Host should be ASCII after IDNA: {}", url);
    }
}

#[test]
fn test_scheme_validation() {
    // Valid schemes
    let valid_schemes = vec![
        "https://example.com/",
        "http://example.com/",
        "ftp://example.com/",
    ];

    for url in valid_schemes {
        let result = normalize_url(url);
        assert!(result.is_ok(), "Should accept valid scheme: {}", url);
    }

    // Invalid schemes
    let invalid_schemes = vec![
        "ws://example.com/",
        "file:///path",
        "mailto:test@example.com",
        "data:text/plain,hello",
        "javascript:alert('test')",
    ];

    for url in invalid_schemes {
        let result = normalize_url(url);
        assert!(result.is_err(), "Should reject invalid scheme: {}", url);
    }
}

#[test]
fn test_component_extraction() {
    let test_cases = vec![
        (
            "https://docs.rs/",
            UrlComponents {
                scheme: "https".to_string(),
                tld: "rs".to_string(),
                domain: "docs".to_string(),
                subdomain: "".to_string(),
                port: 443,
                path: "/".to_string(),
                query: "".to_string(),
                fragment: "".to_string(),
            }
        ),
        (
            "http://api.example.com:8080/search?q=test#results",
            UrlComponents {
                scheme: "http".to_string(),
                tld: "com".to_string(),
                domain: "example".to_string(),
                subdomain: "api".to_string(),
                port: 8080,
                path: "/search".to_string(),
                query: "q=test".to_string(),
                fragment: "results".to_string(),
            }
        ),
    ];

    for (url, expected) in test_cases {
        let normalized = normalize_url(url).unwrap();
        let components = extract_url_components(&normalized).unwrap();

        assert_eq!(components.scheme, expected.scheme, "Scheme mismatch for: {}", url);
        assert_eq!(components.tld, expected.tld, "TLD mismatch for: {}", url);
        assert_eq!(components.domain, expected.domain, "Domain mismatch for: {}", url);
        assert_eq!(components.subdomain, expected.subdomain, "Subdomain mismatch for: {}", url);
        assert_eq!(components.port, expected.port, "Port mismatch for: {}", url);
        assert_eq!(components.path, expected.path, "Path mismatch for: {}", url);
        assert_eq!(components.query, expected.query, "Query mismatch for: {}", url);
        assert_eq!(components.fragment, expected.fragment, "Fragment mismatch for: {}", url);
    }
}

#[test]
fn test_default_ports() {
    let test_cases = vec![
        ("https://example.com/", 443),
        ("http://example.com/", 80),
        ("ftp://example.com/", 21),
        ("https://example.com:443/", 443),  // Explicit default
        ("https://example.com:8443/", 8443), // Non-default
    ];

    for (url, expected_port) in test_cases {
        let normalized = normalize_url(url).unwrap();
        let components = extract_url_components(&normalized).unwrap();
        assert_eq!(components.port, expected_port, "Port mismatch for: {}", url);
    }
}

#[test]
fn test_path_preservation() {
    // Test that paths are preserved exactly (no normalization)
    let test_cases = vec![
        ("https://example.com/path", "/path"),
        ("https://example.com/path/", "/path/"),
        ("https://example.com/path%20with%20spaces", "/path%20with%20spaces"),
        ("https://example.com/path?query", "/path"),
        ("https://example.com/", "/"),
        ("https://example.com", "/"),
    ];

    for (url, expected_path) in test_cases {
        let normalized = normalize_url(url).unwrap();
        let components = extract_url_components(&normalized).unwrap();
        assert_eq!(components.path, expected_path, "Path mismatch for: {}", url);
    }
}

#[test]
fn test_query_preservation() {
    // Test that query parameters are preserved exactly
    let test_cases = vec![
        ("https://example.com/?q=test", "q=test"),
        ("https://example.com/?q=test&lang=en", "q=test&lang=en"),
        ("https://example.com/?q=hello%20world", "q=hello%20world"),
        ("https://example.com/", ""),
        ("https://example.com/?", ""),
    ];

    for (url, expected_query) in test_cases {
        let normalized = normalize_url(url).unwrap();
        let components = extract_url_components(&normalized).unwrap();
        assert_eq!(components.query, expected_query, "Query mismatch for: {}", url);
    }
}

#[test]
fn test_fragment_preservation() {
    // Test that fragments are preserved exactly
    let test_cases = vec![
        ("https://example.com/#section", "section"),
        ("https://example.com/#section%20one", "section%20one"),
        ("https://example.com/", ""),
        ("https://example.com/#", ""),
    ];

    for (url, expected_fragment) in test_cases {
        let normalized = normalize_url(url).unwrap();
        let components = extract_url_components(&normalized).unwrap();
        assert_eq!(components.fragment, expected_fragment, "Fragment mismatch for: {}", url);
    }
}

#[test]
fn test_invalid_urls() {
    let invalid_urls = vec![
        "not-a-url",
        "://example.com",
        "https://",
        "https:///path",
        "",
    ];

    for url in invalid_urls {
        let result = normalize_url(url);
        assert!(result.is_err(), "Should reject invalid URL: {}", url);
    }
}

#[test]
fn test_ip_address_rejection() {
    // SXURL spec only supports DNS names, not IP addresses
    let ip_urls = vec![
        "https://192.168.1.1/",
        "http://127.0.0.1:8080/",
        "https://[::1]/",
        "https://[2001:db8::1]/",
    ];

    for url in ip_urls {
        let result = normalize_url(url);
        // Note: This depends on implementation - the spec says DNS names only
        // but url crate might parse IP addresses successfully
        if result.is_ok() {
            let components_result = extract_url_components(&result.unwrap());
            // PSL extraction should fail for IP addresses
            assert!(components_result.is_err(), "Should reject IP address: {}", url);
        }
    }
}

#[test]
fn test_host_validation() {
    // Test that host validation works correctly
    let valid_hosts = vec![
        "example.com",
        "sub.example.com",
        "a.b.c.example.com",
        "test-domain.org",
        "123example.com",
    ];

    for host in valid_hosts {
        let url = format!("https://{}/", host);
        let result = normalize_url(&url);
        assert!(result.is_ok(), "Should accept valid host: {}", host);
    }

    // Invalid hosts (these might not all be caught by url crate, but PSL should handle them)
    let invalid_hosts = vec![
        "-example.com",      // starts with hyphen
        "example-.com",      // ends with hyphen
        ".example.com",      // starts with dot
        "example..com",      // double dot
        "ex ample.com",      // space
    ];

    for host in invalid_hosts {
        let url = format!("https://{}/", host);
        let result = normalize_url(&url);
        // Some invalid hosts might be accepted by url crate but rejected later
        if result.is_ok() {
            let components_result = extract_url_components(&result.unwrap());
            // Either normalization or component extraction should fail
            assert!(components_result.is_err(), "Should reject invalid host: {}", host);
        }
    }
}

#[test]
fn test_case_insensitive_normalization() {
    // Test that scheme and host are normalized to lowercase
    let test_cases = vec![
        ("HTTPS://EXAMPLE.COM/Path", "https", "example.com"),
        ("HTTP://DOCS.RS/", "http", "docs.rs"),
        ("FTP://Files.Example.ORG/", "ftp", "files.example.org"),
    ];

    for (url, expected_scheme, expected_host) in test_cases {
        let normalized = normalize_url(url).unwrap();
        assert_eq!(normalized.scheme(), expected_scheme);
        assert_eq!(normalized.host_str().unwrap(), expected_host);
    }
}

#[test]
fn test_url_components_new() {
    // Test the UrlComponents::new constructor
    let components = UrlComponents::new(
        "https".to_string(),
        "com".to_string(),
        "example".to_string(),
        "api".to_string(),
        8443,
        "/search".to_string(),
        "q=test".to_string(),
        "results".to_string(),
    );

    assert_eq!(components.scheme, "https");
    assert_eq!(components.tld, "com");
    assert_eq!(components.domain, "example");
    assert_eq!(components.subdomain, "api");
    assert_eq!(components.port, 8443);
    assert_eq!(components.path, "/search");
    assert_eq!(components.query, "q=test");
    assert_eq!(components.fragment, "results");
}

#[test]
fn test_complex_real_world_urls() {
    // Test some complex real-world URLs
    let complex_urls = vec![
        "https://docs.rs/serde/1.0.136/serde/de/trait.Deserialize.html",
        "https://github.com/rust-lang/rust/blob/master/library/std/src/lib.rs",
        "https://crates.io/search?q=async&sort=downloads",
        "https://play.rust-lang.org/?version=stable&mode=debug&edition=2021",
        "https://www.rust-lang.org/learn/get-started#installing-rust",
    ];

    for url in complex_urls {
        let normalized = normalize_url(url).unwrap();
        let components = extract_url_components(&normalized).unwrap();

        // Basic sanity checks
        assert!(!components.scheme.is_empty());
        assert!(!components.tld.is_empty());
        assert!(!components.domain.is_empty());
        assert!(!components.path.is_empty());

        println!("Processed: {} -> TLD:{} Domain:{} Sub:{}",
                url, components.tld, components.domain, components.subdomain);
    }
}