bulletty 0.2.2

a pretty TUI feed reader (RSS+ATOM) that stores articles locally as Markdown files
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

use std::borrow::Cow;

use tl::{Bytes, Node};
use url::Url;

pub fn is_html(content: &str) -> bool {
    let trimmed = content.trim_start();
    trimmed.starts_with("<!DOCTYPE html")
        || trimmed.starts_with("<html")
        || trimmed.starts_with("<HTML")
}

pub fn extract_embedded_feed_urls(
    html: &str,
    url: &Url,
    maximum_feeds: usize,
) -> color_eyre::Result<Vec<String>> {
    let dom = tl::parse(html, tl::ParserOptions::default())?;
    let parser = dom.parser();

    let links = dom
        .query_selector("link[rel='alternate']")
        .into_iter()
        .flatten()
        .filter_map(|node_handle| {
            node_handle
                .get(parser)
                .and_then(Node::as_tag)
                .filter(|tag| get_attribute(tag, "type").is_some_and(is_feed))
                .and_then(|tag| get_attribute(tag, "href"))
                .and_then(|href| join(url, &href))
        })
        .take(maximum_feeds)
        .collect();

    Ok(links)
}

fn get_attribute<'a>(tag: &'a tl::HTMLTag<'_>, attribute: &'a str) -> Option<Cow<'a, str>> {
    tag.attributes()
        .get(attribute)
        .flatten()
        .map(Bytes::as_utf8_str)
}

fn is_feed(link_type: Cow<'_, str>) -> bool {
    let link_type = link_type.to_lowercase();
    link_type.contains("atom") || link_type.contains("rss")
}

fn join(url: &Url, href: &str) -> Option<String> {
    url.join(href).map(String::from).ok()
}

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

    #[test]
    fn extract_absolute_url() {
        let html = r#"<!DOCTYPE html>
<html>
<head>
<title>My Blog</title>
<link rel="alternate" type="application/rss+xml" href="https://example.com/feed.rss" />
</head>
<body>
<h1>Welcome</h1>
</body>
</html>"#;

        let feeds =
            extract_embedded_feed_urls(html, &Url::parse("https://example.com/").unwrap(), 10)
                .unwrap();
        assert_eq!(feeds, vec!["https://example.com/feed.rss"]);
    }

    #[test]
    fn extract_relative_url() {
        let html = r#"<!DOCTYPE html>
<html>
<head>
<title>My Blog</title>
<link rel="alternate" type="application/atom+xml" href="/feed.atom" />
</head>
<body>
<h1>Welcome</h1>
</body>
</html>"#;

        let feeds =
            extract_embedded_feed_urls(html, &Url::parse("https://example.com/blog/").unwrap(), 10)
                .unwrap();
        assert_eq!(feeds, vec!["https://example.com/feed.atom"]);
    }

    #[test]
    fn extract_mixed_feed_urls() {
        let html = r#"<!DOCTYPE html>
<html>
<head>
<title>Multi-feed Site</title>
<link rel="alternate" type="application/rss+xml" href="https://example.com/rss" />
<link rel="alternate" type="application/atom+xml" href="https://example.com/atom" />
</head>
<body>
<h1>Welcome</h1>
</body>
</html>"#;

        let feeds =
            extract_embedded_feed_urls(html, &Url::parse("https://example.com/").unwrap(), 10)
                .unwrap();
        assert_eq!(
            feeds,
            vec!["https://example.com/rss", "https://example.com/atom"]
        );
    }

    #[test]
    fn extract_limited_urls() {
        let html = r#"<!DOCTYPE html>
<html>
<head>
<title>Multi-feed Site</title>
<link rel="alternate" type="application/rss+xml" href="https://example.com/rss1" />
<link rel="alternate" type="application/rss+xml" href="https://example.com/rss2" />
<link rel="alternate" type="application/rss+xml" href="https://example.com/rss3" />
</head>
<body>
<h1>Welcome</h1>
</body>
</html>"#;

        let feeds =
            extract_embedded_feed_urls(html, &Url::parse("https://example.com/").unwrap(), 2)
                .unwrap();
        assert_eq!(
            feeds,
            vec!["https://example.com/rss1", "https://example.com/rss2"]
        );
    }

    #[test]
    fn extract_no_urls() {
        let html = r#"<!DOCTYPE html>
<html>
<head>
<title>No Feed Site</title>
</head>
<body>
<h1>Welcome</h1>
</body>
</html>"#;

        let feeds =
            extract_embedded_feed_urls(html, &Url::parse("https://example.com/").unwrap(), 10)
                .unwrap();
        assert!(feeds.is_empty());
    }

    #[test]
    fn html_doctype_is_html() {
        assert!(is_html("<!DOCTYPE html><html></html>"));
    }

    #[test]
    fn html_doctype_with_leading_whitespace_is_html() {
        assert!(is_html("  \n  <!DOCTYPE html><html></html>"));
    }

    #[test]
    fn html_tag_is_html() {
        assert!(is_html("<html><head></head></html>"));
    }

    #[test]
    fn rss_is_not_html() {
        assert!(!is_html("<?xml version=\"1.0\"?><rss></rss>"));
    }

    #[test]
    fn atom_is_not_html() {
        assert!(!is_html("<?xml version=\"1.0\"?><feed></feed>"));
    }
}