ipx/crates/feed/src/patreon.rs

//! Patreon: a creator's feed, its shows, and when two Patreon addresses are the same feed.

use crate::fetch;
use anyhow::{Context, Result, anyhow};

/// The token and show of a Patreon feed link, or None for any other URL.
///
/// Patreon gives each patron one token per creator. With no show it stands for the creator,
/// whose feed carries every show at once.
pub(crate) fn patreon_parts(url: &str) -> Option<(String, Option<String>)> {
    let u = url::Url::parse(url).ok()?;
    if !matches!(u.host_str()?, "patreon.com" | "www.patreon.com") || !u.path().starts_with("/rss") {
        return None;
    }
    let param = |name: &str| u.query_pairs().find(|(k, _)| k == name).map(|(_, v)| v.into_owned());
    Some((param("auth")?, param("show")))
}

/// A Patreon link naming a creator but no show.
#[must_use]
pub fn is_patreon_creator(url: &str) -> bool {
    matches!(patreon_parts(url), Some((_, None)))
}

/// Whether two URLs are the same feed. One Patreon show has several spellings -- by the
/// creator's name, by number, or with no creator at all -- and the token and show are what
/// identify it.
#[must_use]
pub fn same_feed(a: &str, b: &str) -> bool {
    // Parsing both is the slow part, and only Patreon's addresses can differ and still match.
    a == b
        || (a.contains("patreon.com")
            && b.contains("patreon.com")
            && patreon_parts(a).is_some_and(|p| Some(p) == patreon_parts(b)))
}

/// A Patreon creator's name and shows, each show as (title, feed URL).
///
/// ponytail: Patreon's own web API, undocumented, asked without signing in. If it changes,
/// finding shows stops and the show feeds already found keep working. The documented API
/// needs an OAuth client per install and does not list shows.
pub async fn patreon_shows(client: &reqwest::Client, url: &str) -> Result<(Option<String>, Vec<(String, String)>)> {
    // The creator feed names its campaign by number in its self link, a few hundred bytes in.
    // The whole feed runs to megabytes and Patreon ignores Range, so read until it turns up.
    let mut resp = client.get(url).timeout(fetch::FEED_TIMEOUT).send().await.context("connecting")?;
    if !resp.status().is_success() {
        return Err(anyhow!("Patreon refused the feed: HTTP {}", resp.status()));
    }
    let mut head = Vec::new();
    while patreon_campaign(&head).is_none() && head.len() < 64 * 1024 {
        let Some(chunk) = resp.chunk().await.context("reading the feed")? else { break };
        head.extend_from_slice(&chunk);
    }
    let campaign = patreon_campaign(&head).ok_or_else(|| anyhow!("the Patreon feed does not say whose it is"))?;

    let api = format!(
        "https://www.patreon.com/api/campaigns/{campaign}\
         ?include=shows&fields%5Bcampaign%5D=name&fields%5Bcollection%5D=title"
    );
    let resp = client.get(api).send().await.context("asking Patreon for the shows")?;
    if !resp.status().is_success() {
        return Err(anyhow!("Patreon would not list the shows: HTTP {}", resp.status()));
    }
    let (name, shows) = parse_patreon_shows(&resp.bytes().await.context("reading the shows")?)?;
    Ok((name, shows.into_iter().map(|(id, title)| (title, format!("{url}&show={id}"))).collect()))
}

/// The campaign number in the start of a Patreon feed.
pub(crate) fn patreon_campaign(head: &[u8]) -> Option<String> {
    let text = String::from_utf8_lossy(head);
    text.match_indices("patreon.com/rss/").find_map(|(i, m)| {
        let id: String = text[i + m.len()..].chars().take_while(char::is_ascii_digit).collect();
        (!id.is_empty()).then_some(id)
    })
}

/// A campaign's name, and its shows as (id, title).
pub(crate) type PatreonShows = (Option<String>, Vec<(String, String)>);

/// A campaign's name and its shows as (id, title), from Patreon's JSON:API answer.
pub(crate) fn parse_patreon_shows(json: &[u8]) -> Result<PatreonShows> {
    let v: serde_json::Value = serde_json::from_slice(json).context("Patreon's answer is not JSON")?;
    // Missing is not the same as none. Read as no shows, the creator feed would be scanned as
    // a plain feed, claim every show's files, and leave the shows empty once the list returned.
    let ids = v["data"]["relationships"]["shows"]["data"]
        .as_array()
        .ok_or_else(|| anyhow!("Patreon's answer does not list the shows"))?;
    let title = |id: &str| -> Option<String> {
        let show = v["included"].as_array()?.iter().find(|x| x["type"] == "collection" && x["id"] == id)?;
        show["attributes"]["title"].as_str().map(|t| t.trim().to_owned())
    };
    let shows = ids
        .iter()
        .filter_map(|s| s["id"].as_str())
        .map(|id| (id.to_owned(), title(id).unwrap_or_else(|| format!("Show {id}"))))
        .collect();
    Ok((v["data"]["attributes"]["name"].as_str().map(str::to_owned), shows))
}

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

    #[test]
    fn a_patreon_creator_is_a_list_of_its_shows() {
        let tok = "AbCdEfGhIjKlMnOpQrStUvWxYz012_-9";
        assert_eq!(discover::expand_input(&format!(" {tok} ")), format!("https://www.patreon.com/rss?auth={tok}"));
        assert_eq!(discover::expand_input("https://example.com/rss"), "https://example.com/rss");
        assert_eq!(discover::expand_input("http://example.com/rss"), "http://example.com/rss");
        assert_eq!(discover::expand_input(" cnn.com "), "https://cnn.com");
        assert_eq!(discover::expand_input("example.com/feed.xml"), "https://example.com/feed.xml");
        assert_eq!(discover::expand_input("//example.com/rss"), "https://example.com/rss");

        assert!(is_patreon_creator(&format!("https://www.patreon.com/rss/glasscannon?auth={tok}")));
        assert!(is_patreon_creator(&format!("https://www.patreon.com/rss?auth={tok}")));
        assert!(!is_patreon_creator(&format!("https://www.patreon.com/rss/x?auth={tok}&show=1")), "one show is a feed");
        assert!(!is_patreon_creator(&format!("https://example.com/rss?auth={tok}")));

        // The show you already have by name is the one a bare token would add by number.
        assert!(same_feed(
            &format!("https://www.patreon.com/rss/glasscannon?auth={tok}&show=2073588"),
            &format!("https://www.patreon.com/rss?auth={tok}&show=2073588"),
        ));
        assert!(!same_feed(
            &format!("https://www.patreon.com/rss?auth={tok}&show=1"),
            &format!("https://www.patreon.com/rss?auth={tok}&show=2"),
        ));

        // The self link carries the campaign by number, whichever spelling was asked for.
        let head = br#"<rss><channel><link>https://www.patreon.com/glasscannon</link>
            <atom:link href="https://www.patreon.com/rss/369921?auth=t" rel="self"/>"#;
        assert_eq!(patreon_campaign(head).as_deref(), Some("369921"));
        assert_eq!(patreon_campaign(b"<rss><channel><title>T"), None);

        let json = br#"{"data":{"id":"369921","type":"campaign","attributes":{"name":"The Glass Cannon Network"},
            "relationships":{"shows":{"data":[{"id":"2073588","type":"collection"},{"id":"2073636","type":"collection"}]}}},
            "included":[{"id":"2073588","type":"collection","attributes":{"title":"Get in the Trunk "}},
                        {"id":"2073636","type":"collection","attributes":{"title":"Shadowdark"}}]}"#;
        let (name, shows) = parse_patreon_shows(json).unwrap();
        assert_eq!(name.as_deref(), Some("The Glass Cannon Network"));
        assert_eq!(shows, [("2073588".into(), "Get in the Trunk".into()), ("2073636".into(), "Shadowdark".into())]);

        // An answer that stops naming the shows is an error, never "this creator has none".
        assert!(parse_patreon_shows(br#"{"data":{"attributes":{"name":"X"}}}"#).is_err());
    }
}