Patreon creators split into their shows; filters follow settings

A Patreon token pasted into Add feed, or a creator link without
&show=, becomes a folder of that creator's shows, found through
Patreon's web API and kept in step like a subscribed OPML (sync_group,
split out of sync_opml). A creator already read as one feed is split
too: each show takes over the files and read state it held
(Db::adopt). A creator with one show stays a plain feed.

Filter verdicts are judged again every scan, so turning on Allow
explicit brings skipped items back. Add feed has an explicit box.
Feeds in a group follow your settings on the group, as its dialog
said. A new feed no longer takes the id of a removed one at a
different URL and shows its old items. See CHANGELOG.md [Unreleased]
and docs/history.md.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Wi22VSVrkAvqNj61eqHsm9
This commit is contained in:
2026-09-11 18:24:47 +00:00
parent 9269aa99f7
commit 2e416f96cf
8 changed files with 488 additions and 39 deletions

View File

@@ -117,6 +117,103 @@ pub fn opml_title(bytes: &[u8]) -> Option<String> {
.filter(|t| !t.is_empty())
}
/// 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.
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.
pub fn is_patreon_creator(url: &str) -> bool {
matches!(patreon_parts(url), Some((_, None)))
}
/// What was typed into Add feed, as a URL. A bare Patreon token is taken as its creator's
/// feed, since the token alone says whose it is.
pub fn expand_input(input: &str) -> String {
let s = input.trim();
let token = s.len() >= 20 && s.chars().all(|c| c.is_ascii_alphanumeric() || c == '-' || c == '_');
if token { format!("https://www.patreon.com/rss?auth={s}") } else { s.to_owned() }
}
/// 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.
pub fn same_feed(a: &str, b: &str) -> bool {
a == b || 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).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.
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), from Patreon's JSON:API answer.
fn parse_patreon_shows(json: &[u8]) -> Result<(Option<String>, Vec<(String, String)>)> {
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))
}
/// RSS first, then Atom -- the same split the original made on `parsedFeed.version`.
pub fn parse(bytes: &[u8]) -> Result<ParsedFeed> {
match rss::Channel::read_from(bytes) {
@@ -550,6 +647,45 @@ mod tests {
assert!(!is_opml(include_bytes!("../tests/data/atom.xml")));
}
#[test]
fn a_patreon_creator_is_a_list_of_its_shows() {
let tok = "AbCdEfGhIjKlMnOpQrStUvWxYz012_-9";
assert_eq!(expand_input(&format!(" {tok} ")), format!("https://www.patreon.com/rss?auth={tok}"));
assert_eq!(expand_input("https://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());
}
#[test]
fn an_item_may_carry_several_enclosures() {
// The rss crate keeps only one per item -- the last -- so these come from the XML.