hashiverse-lib 1.0.7-rc2

Core protocol library for Hashiverse — your open-source decentralized X/Twitter replacement.
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

//! # Open Graph / link-preview extraction
//!
//! Parses the `<head>` of an HTML page and extracts the fields needed to render a link
//! preview card in a post: title, description, image, and canonical URL.
//!
//! Open Graph (`og:title`, `og:description`, `og:image`, `og:url`) is preferred; the
//! extractor falls back to the page's `<title>` element and `<meta name="description">`
//! when OG isn't present. The [`UrlPreviewData`] struct is what callers hand up to the
//! protocol layer — servers fetch the target URL under an RPC budget gated by
//! `POW_MINIMUM_PER_URL_FETCH` and return this struct back to the client so the preview
//! card can render without every client individually fetching (and thus leaking its IP to)
//! the target site.

use scraper::{Html, Selector};

pub struct UrlPreviewData {
    pub title: String,
    pub description: String,
    pub image_url: String,
    pub canonical_url: String,
}

pub fn extract_url_preview(html: &str) -> UrlPreviewData {
    let document = Html::parse_document(html);

    let title = first_non_empty([
        select_meta_content(&document, "meta[property='og:title']"),
        select_meta_content(&document, "meta[name='twitter:title']"),
        select_title(&document),
    ])
    .unwrap_or_default();

    let description = first_non_empty([
        select_meta_content(&document, "meta[property='og:description']"),
        select_meta_content(&document, "meta[name='twitter:description']"),
        select_meta_content(&document, "meta[name='description']"),
    ])
    .unwrap_or_default();

    let image_url = first_non_empty([
        select_meta_content(&document, "meta[property='og:image']"),
        select_meta_content(&document, "meta[name='twitter:image']"),
        select_meta_content(&document, "meta[name='twitter:image:src']"),
    ])
    .unwrap_or_default();

    let canonical_url = first_non_empty([
        select_meta_content(&document, "meta[property='og:url']"),
        select_link_href(&document, "link[rel='canonical']"),
    ])
    .unwrap_or_default();

    UrlPreviewData {
        title,
        description,
        image_url,
        canonical_url,
    }
}

fn select_meta_content(document: &Html, selector_str: &str) -> Option<String> {
    let selector = Selector::parse(selector_str).ok()?;
    document.select(&selector).next()?.value().attr("content").map(|s| s.to_string())
}

fn select_link_href(document: &Html, selector_str: &str) -> Option<String> {
    let selector = Selector::parse(selector_str).ok()?;
    document.select(&selector).next()?.value().attr("href").map(|s| s.to_string())
}

fn select_title(document: &Html) -> Option<String> {
    let selector = Selector::parse("title").ok()?;
    Some(document.select(&selector).next()?.text().collect::<String>())
}

// A present-but-empty `content=""` should fall through, not short-circuit.
fn first_non_empty<I: IntoIterator<Item = Option<String>>>(candidates: I) -> Option<String> {
    candidates.into_iter().flatten().find(|s| !s.is_empty())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_extract_url_preview_with_og_tags() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <meta property="og:title" content="OG Title" />
                <meta property="og:description" content="OG Description" />
                <meta property="og:image" content="https://example.com/og.png" />
                <meta property="og:url" content="https://example.com/canonical" />
                <title>Page Title</title>
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.title, "OG Title");
        assert_eq!(data.description, "OG Description");
        assert_eq!(data.image_url, "https://example.com/og.png");
        assert_eq!(data.canonical_url, "https://example.com/canonical");
    }

    #[test]
    fn test_extract_url_preview_fallback_to_title_and_meta_description() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <title>Fallback Title</title>
                <meta name="description" content="Fallback Description" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.title, "Fallback Title");
        assert_eq!(data.description, "Fallback Description");
        assert_eq!(data.image_url, "");
        assert_eq!(data.canonical_url, "");
    }

    #[test]
    fn test_extract_url_preview_empty_html() {
        let data = extract_url_preview("");
        assert_eq!(data.title, "");
        assert_eq!(data.description, "");
        assert_eq!(data.image_url, "");
        assert_eq!(data.canonical_url, "");
    }

    #[cfg(not(target_arch = "wasm32"))]
    mod bolero_fuzz {
        use super::*;

        #[test]
        fn fuzz_extract_url_preview() {
            bolero::check!().for_each(|data: &[u8]| {
                if let Ok(html) = std::str::from_utf8(data) {
                    let _ = extract_url_preview(html);
                }
            });
        }
    }

    #[test]
    fn test_extract_url_preview_og_overrides_title() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <title>Page Title</title>
                <meta property="og:title" content="OG Title" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.title, "OG Title");
    }

    #[test]
    fn test_twitter_title_used_when_og_missing() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <title>HTML Title</title>
                <meta name="twitter:title" content="Twitter Title" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.title, "Twitter Title");
    }

    #[test]
    fn test_twitter_description_used_when_og_missing() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <meta name="twitter:description" content="Twitter Description" />
                <meta name="description" content="Plain Description" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.description, "Twitter Description");
    }

    #[test]
    fn test_twitter_image_used_when_og_missing() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <meta name="twitter:image" content="https://example.com/twitter.png" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.image_url, "https://example.com/twitter.png");
    }

    #[test]
    fn test_twitter_image_src_fallback() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <meta name="twitter:image:src" content="https://example.com/twitter-src.png" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.image_url, "https://example.com/twitter-src.png");
    }

    #[test]
    fn test_canonical_link_used_when_og_url_missing() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <link rel="canonical" href="https://example.com/canonical-from-link" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.canonical_url, "https://example.com/canonical-from-link");
    }

    #[test]
    fn test_empty_content_falls_through() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <meta property="og:title" content="" />
                <title>Real Title</title>
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.title, "Real Title");
    }

    #[test]
    fn test_og_still_wins_over_twitter() {
        let html = r#"
            <!DOCTYPE html>
            <html>
            <head>
                <meta property="og:title" content="OG Title" />
                <meta name="twitter:title" content="Twitter Title" />
                <meta property="og:description" content="OG Description" />
                <meta name="twitter:description" content="Twitter Description" />
                <meta property="og:image" content="https://example.com/og.png" />
                <meta name="twitter:image" content="https://example.com/twitter.png" />
                <meta property="og:url" content="https://example.com/og-canonical" />
                <link rel="canonical" href="https://example.com/link-canonical" />
            </head>
            <body></body>
            </html>
        "#;

        let data = extract_url_preview(html);
        assert_eq!(data.title, "OG Title");
        assert_eq!(data.description, "OG Description");
        assert_eq!(data.image_url, "https://example.com/og.png");
        assert_eq!(data.canonical_url, "https://example.com/og-canonical");
    }
}