rays/ipodderx-rs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Keep every enclosure on an item, and view without downloading

Browse Source 
The rss crate keeps at most one enclosure per item and, when a feed ships
several, silently keeps the last -- so a two-file item lost its first
file. enclosures_by_item reads them from the XML in document order,
unescaping attributes so a URL's & survives. The row summarises the
one you would act on and counts the rest; the pane below lists them all.

Non-media enclosures gain a View link opening in a new tab: the
publisher's URL, or the local copy once downloaded. A direct link, not a
proxy, so the daemon does not become a fetch-anything relay.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AdXho5tTkjFLeUXKbEjKBh
This commit is contained in:
Ray Slakinski
2026-09-10 18:01:25 +00:00
parent 6d6b4dd1e4
commit dd9c0881ee
11 changed files with 212 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

134
src/feed.rs
View File

@@ -32,7 +32,7 @@ pub struct Entry {
pub enclosures: Vec<Enclosure>,
}
#[derive(Debug, Default, PartialEq)]
#[derive(Debug, Default, Clone, PartialEq)]
pub struct Enclosure {
pub url: String,
pub mime: Option<String>,
@@ -120,7 +120,7 @@ pub fn opml_title(bytes: &[u8]) -> Option<String> {
/// 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) {
Ok(ch) => Ok(from_rss(ch)),
Ok(ch) => Ok(from_rss(ch, bytes)),
Err(rss_err) => match atom_syndication::Feed::read_from(bytes) {
Ok(feed) => Ok(from_atom(feed)),
Err(atom_err) => Err(anyhow!("not RSS ({rss_err}) and not Atom ({atom_err})")),
@@ -128,7 +128,78 @@ pub fn parse(bytes: &[u8]) -> Result<ParsedFeed> {
}
}
fn from_rss(ch: rss::Channel) -> ParsedFeed {
/// Every `<enclosure>` of every `<item>`, in document order.
///
/// The `rss` crate models an item as having at most one enclosure -- which is what RSS 2.0
/// says -- and when a feed carries several it keeps only the *last*, silently losing the
/// rest. Feeds do ship several, so read them from the XML directly.
fn enclosures_by_item(bytes: &[u8]) -> Vec<Vec<Enclosure>> {
use quick_xml::events::Event;
let mut reader = quick_xml::Reader::from_reader(bytes);
reader.config_mut().trim_text(true);
let mut buf = Vec::new();
let mut out: Vec<Vec<Enclosure>> = Vec::new();
let mut current: Option<Vec<Enclosure>> = None;
let read_enclosure = |e: &quick_xml::events::BytesStart| -> Option<Enclosure> {
let (mut url, mut mime, mut length) = (String::new(), None, None);
for attr in e.attributes().flatten() {
// Values arrive escaped: a feed URL's "&" is "&amp;" in the document.
let val = quick_xml::escape::unescape(&attr.value)
.map(|v| v.trim().to_string())
.unwrap_or_default();
match attr.key.local_name().as_ref() {
"url" => url = val,
"type" => mime = Some(val).filter(|v| !v.is_empty()),
"length" => length = val.parse().ok(),
_ => {}
}
}
(!url.is_empty()).then_some(Enclosure { url, mime, length })
};
loop {
match reader.read_event_into(&mut buf) {
Ok(Event::Start(e)) => match e.name().local_name().as_ref() {
"item" => current = Some(Vec::new()),
"enclosure" => {
if let (Some(list), Some(enc)) = (current.as_mut(), read_enclosure(&e)) {
list.push(enc);
}
}
_ => {}
},
Ok(Event::Empty(e)) => match e.name().local_name().as_ref() {
// <item/> with no children still counts, so the indexes stay aligned.
"item" => out.push(Vec::new()),
"enclosure" => {
if let (Some(list), Some(enc)) = (current.as_mut(), read_enclosure(&e)) {
list.push(enc);
}
}
_ => {}
},
Ok(Event::End(e)) => {
if e.name().local_name().as_ref() == "item"
&& let Some(list) = current.take()
{
out.push(list);
}
}
Ok(Event::Eof) | Err(_) => break,
_ => {}
}
buf.clear();
}
if let Some(list) = current.take() {
out.push(list);
}
out
}
fn from_rss(ch: rss::Channel, bytes: &[u8]) -> ParsedFeed {
let per_item = enclosures_by_item(bytes);
let explicit = ch
.itunes_ext()
.and_then(|it| it.explicit())
@@ -137,17 +208,21 @@ fn from_rss(ch: rss::Channel) -> ParsedFeed {
let entries = ch
.items()
.iter()
.filter_map(|item| {
let enclosures: Vec<Enclosure> = item
.enclosure()
.into_iter()
.map(|e| Enclosure {
url: e.url().trim().to_owned(),
mime: non_empty(Some(e.mime_type())),
length: e.length().parse().ok(),
})
.filter(|e| !e.url.is_empty())
.collect();
.enumerate()
.filter_map(|(idx, item)| {
// Straight from the XML, so an item with several keeps all of them. Falls
// back to the parsed one if the scan and the parser disagree on item count.
let enclosures: Vec<Enclosure> = per_item.get(idx).cloned().unwrap_or_else(|| {
item.enclosure()
.into_iter()
.map(|e| Enclosure {
url: e.url().trim().to_owned(),
mime: non_empty(Some(e.mime_type())),
length: e.length().parse().ok(),
})
.filter(|e| !e.url.is_empty())
.collect()
});
let guid = pick_guid(
item.guid().map(|g| g.value()),
@@ -442,6 +517,36 @@ mod tests {
assert!(!is_opml(include_bytes!("../tests/data/atom.xml")));
}
#[test]
fn an_item_may_carry_several_enclosures() {
// The rss crate keeps only one per item -- the last -- so these come from the XML.
let xml = br#"<?xml version="1.0"?>
<rss version="2.0"><channel><title>M</title><link>https://x</link><description>d</description>
<item><title>Two files</title><guid>m1</guid>
<enclosure url="https://x/a.mp3?v=1&amp;t=2" length="111" type="audio/mpeg"/>
<enclosure url="https://x/b.mp4" length="222" type="video/mp4"/>
</item>
<item><title>One file</title><guid>m2</guid>
<enclosure url="https://x/c.mp3" length="333" type="audio/mpeg"/></item>
<item><title>None</title><guid>m3</guid></item>
</channel></rss>"#;
let f = parse(xml).unwrap();
assert_eq!(f.entries.len(), 3);
let two = &f.entries[0].enclosures;
assert_eq!(two.len(), 2, "both enclosures survive");
assert_eq!(
two[0].url, "https://x/a.mp3?v=1&t=2",
"document order, and the escaped ampersand is decoded"
);
assert_eq!(two[0].length, Some(111));
assert_eq!(two[1].url, "https://x/b.mp4");
assert_eq!(two[1].mime.as_deref(), Some("video/mp4"));
assert_eq!(f.entries[1].enclosures.len(), 1);
assert_eq!(f.entries[2].enclosures.len(), 0, "an item may have none");
}
#[test]
fn durations_parse_from_seconds_or_a_clock() {
assert_eq!(parse_duration("5649"), Some(5649));
@@ -464,3 +569,4 @@ mod tests {
assert_eq!(pick_guid(None, None, None, None), None);
}
}