ipx/crates/feed/src/artwork.rs

//! Artwork: on https when its host serves it there, and a site icon where a feed has none.

use crate::{discover, fetch};
use std::collections::HashMap;
use std::time::Duration;

/// Artwork for a feed that has none: the icon its site's page names, or else the site's
/// `/favicon.ico`. None if neither is there.
#[tracing::instrument(skip_all, fields(site = site))]
pub async fn site_icon(client: &reqwest::Client, site: &str) -> Option<String> {
    let timeout = Duration::from_secs(20);
    let resp = client.get(site).timeout(timeout).send().await.ok()?;
    // Relative to where the page ended up, not where it was asked for: a site that redirects
    // to /en/ would otherwise have its icon looked for in the wrong place.
    let base = resp.url().clone();
    // The icon a page names can be gone: antirez.com names /images/favicon.png, a 404, while its
    // /favicon.ico is there. Stored unchecked, it was a broken image that was never looked up again.
    if resp.status().is_success()
        && let Ok(page) = fetch::read_capped(resp).await
        && let Some(href) = page_icon(&page)
        && let Ok(url) = base.join(&href)
        && is_image(client, url.as_str()).await
    {
        return Some(url.into());
    }
    let ico = base.join("/favicon.ico").ok()?;
    is_image(client, ico.as_str()).await.then(|| ico.into())
}

/// How many hosts one scan of a feed asks whether its artwork is on https.
pub(crate) const MAX_ART_HOSTS: usize = 8;

/// Artwork's address on https when its host serves it there, else as it was. The page is https
/// and must not load http; the host is asked once per `known` (one feed's read), and an http
/// address it does not serve on https stays, for /api/art to fetch (#90). Four of the five
/// hosts the catalogue had on http served the same image on https; The Secret Cabal's CDN
/// presents another name's certificate (#110).
pub async fn prefer_https(client: &reqwest::Client, url: &str, known: &mut HashMap<String, bool>) -> String {
    let Some(rest) = url.strip_prefix("http://") else { return url.to_owned() };
    let host = rest.split('/').next().unwrap_or("").to_owned();
    let secure = format!("https://{rest}");
    let ok = match known.get(&host) {
        Some(ok) => *ok,
        // Each new host is a probe of up to 20 s, one after another on the scan, and the feed's
        // author decides how many hosts there are: ports and user names make as many as they like
        // of one server (#339). Real feeds put their artwork on a few.
        None if known.len() >= MAX_ART_HOSTS => false,
        None => {
            let ok = is_image(client, &secure).await;
            known.insert(host, ok);
            ok
        }
    };
    if ok { secure } else { url.to_owned() }
}

/// Whether `url` answers with an image. A site with no favicon often answers 200 with its home
/// page, which is not an icon.
pub async fn is_image(client: &reqwest::Client, url: &str) -> bool {
    let timeout = Duration::from_secs(20);
    let Ok(resp) = client.get(url).timeout(timeout).send().await else { return false };
    resp.status().is_success()
        && resp
            .headers()
            .get(reqwest::header::CONTENT_TYPE)
            .and_then(|v| v.to_str().ok())
            .is_some_and(|t| t.starts_with("image/"))
}

/// The icon a web page names in its `<link>` tags, the larger apple-touch-icon first: a plain
/// `icon` is often 16 pixels, which blurs at the size the list draws artwork.
pub(crate) fn page_icon(bytes: &[u8]) -> Option<String> {
    let text = String::from_utf8_lossy(bytes);
    // ASCII only, so byte offsets in the lowered copy stay valid in the original.
    let lower = text.to_ascii_lowercase();
    let (mut touch, mut icon) = (None, None);
    let mut pos = 0;
    while let Some(at) = lower[pos..].find("<link") {
        let start = pos + at;
        let Some(end) = lower[start..].find('>').map(|e| start + e) else { break };
        pos = end + 1;
        let tag = &text[start..end];
        let Some(rel) = discover::tag_attr(tag, "rel").map(|r| r.to_ascii_lowercase()) else { continue };
        let rels: Vec<&str> = rel.split_whitespace().collect();
        if touch.is_none() && rels.iter().any(|r| r.starts_with("apple-touch-icon")) {
            touch = discover::tag_attr(tag, "href");
        } else if icon.is_none() && rels.contains(&"icon") {
            icon = discover::tag_attr(tag, "href");
        }
    }
    touch.or(icon).filter(|h| !h.is_empty())
}

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

    #[tokio::test]
    async fn artwork_on_more_hosts_than_the_limit_is_not_asked_about() {
        let mut known: std::collections::HashMap<String, bool> =
            (0..MAX_ART_HOSTS).map(|n| (format!("h{n}:80"), false)).collect();
        // No server answers here: were it asked, this would wait on a connection, not return.
        let url = "http://192.0.2.1:9/a.png";
        assert_eq!(prefer_https(&reqwest::Client::new(), url, &mut known).await, url);
        assert_eq!(known.len(), MAX_ART_HOSTS);
    }

    #[test]
    fn page_icon_prefers_the_touch_icon() {
        let page = br#"<head><link rel="stylesheet" href="/a.css">
            <link rel="shortcut icon" href="/fav.ico">
            <LINK REL="apple-touch-icon-precomposed" sizes="180x180" href='/touch.png'></head>"#;
        assert_eq!(page_icon(page).as_deref(), Some("/touch.png"));
        assert_eq!(page_icon(br#"<link rel="icon" href="i.svg">"#).as_deref(), Some("i.svg"));
        assert_eq!(page_icon(br#"<link rel="stylesheet" href="/a.css">"#), None);
    }
}