1
Fork 0
mirror of https://github.com/thegeneralist01/archivr synced 2026-07-21 18:55:36 +02:00

feat(core+frontend): bare yt:ID resolves to YouTube video

determine_source: yt:ID / youtube:ID with no prefix and exactly 11
chars [A-Za-z0-9_-] → YouTubeVideo via is_youtube_video_id helper.
Reserved prefixes (playlist/, channel/, c/, user/, @) still fire first
so they are unaffected by the fallback.

expand_shorthand_to_url: bare yt:ID expands to watch?v=ID using the
same predicate, consistent with how ytm:ID → music.youtube.com/watch.

isVideoSource (frontend): same 11-char /^[A-Za-z0-9_-]{11}$/ regex so
yt:ID triggers the quality probe and capture-row guards identically to
yt:video/ID.

Tests: test_is_youtube_video_id covers valid IDs (alphanumeric, with _
and -), too-short, too-long, and invalid-char cases using genuinely
invalid fixtures. test_youtube_sources adds bare-ID cases and confirms
reserved prefixes (playlist/, @) are not affected.
This commit is contained in:
TheGeneralist 2026-07-21 14:54:31 +02:00
parent e7104cf29d
commit 916146b4a8
Signed by: thegeneralist01
SSH key fingerprint: SHA256:pp9qddbCNmVNoSjevdvQvM5z0DHN7LTa8qBMbcMq/R4
4 changed files with 49 additions and 9 deletions

View file

@ -211,6 +211,12 @@ fn generate_entry_title(source: Source, meta: &PlatformMetadata) -> String {
Source::Other => "Archived Content".to_string(),
}
}
/// Returns true when `s` is a valid bare YouTube video ID:
/// exactly 11 characters from the set `[A-Za-z0-9_-]`.
fn is_youtube_video_id(s: &str) -> bool {
s.len() == 11 && s.bytes().all(|b| b.is_ascii_alphanumeric() || b == b'_' || b == b'-')
}
fn expand_shorthand_to_url(path: &str, source: &Source) -> String {
// YouTube shorthands: yt:video/ID, yt:playlist/ID, yt:@handle, yt:channel/ID, etc.
@ -238,6 +244,10 @@ fn expand_shorthand_to_url(path: &str, source: &Source) -> String {
if let Some(handle) = after.strip_prefix("@") {
return format!("https://www.youtube.com/@{handle}");
}
// bare yt:ID — validated 11-char video ID
if is_youtube_video_id(after) {
return format!("https://www.youtube.com/watch?v={after}");
}
}
}
@ -328,6 +338,11 @@ fn determine_source(path: &str) -> Source {
{
return Source::YouTubeChannel;
}
// bare yt:ID — exactly 11 chars [A-Za-z0-9_-], no slash/@ prefixes
if is_youtube_video_id(after_scheme) {
return Source::YouTubeVideo;
}
}
// Shorthand scheme: ytm:
@ -2110,6 +2125,15 @@ mod tests {
url: "youtube:@CoreDumpped",
expected: Source::YouTubeChannel,
},
// Bare video ID — exactly 11 chars [A-Za-z0-9_-]
TestCase { url: "yt:dQw4w9WgXcQ", expected: Source::YouTubeVideo },
TestCase { url: "youtube:dQw4w9WgXcQ", expected: Source::YouTubeVideo },
TestCase { url: "yt:a_b-c_d-e_4", expected: Source::YouTubeVideo },
// Non-ID: wrong length (9 chars) → Other
TestCase { url: "yt:not-video", expected: Source::Other },
// Reserved prefixes still route correctly when segment looks like an ID
TestCase { url: "yt:playlist/dQw4w9WgXcQ", expected: Source::YouTubePlaylist },
TestCase { url: "yt:@dQw4w9WgXcQ", expected: Source::YouTubeChannel },
];
for case in &shorthand_cases {
@ -2122,6 +2146,18 @@ mod tests {
}
}
#[test]
fn test_is_youtube_video_id() {
assert!(is_youtube_video_id("dQw4w9WgXcQ"), "canonical ID");
assert!(is_youtube_video_id("a_b-c_d-e_4"), "11-char ID with _ and -");
assert!(!is_youtube_video_id(""), "empty");
assert!(!is_youtube_video_id("short"), "too short");
assert!(!is_youtube_video_id("toolong12345"), "too long (12 chars)");
assert!(!is_youtube_video_id("dQw4w9WgXc!"), "invalid char (! at pos 11)");
assert!(!is_youtube_video_id("not-video"), "9 chars — too short");
assert!(!is_youtube_video_id("dQw4w9WgXC!!"), "12 chars + bad char");
}
#[test]
fn test_youtube_music_sources() {
// --- determine_source ---

View file

@ -4,7 +4,7 @@
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Archivr</title>
<script type="module" crossorigin src="/assets/index-DMYakNuy.js"></script>
<script type="module" crossorigin src="/assets/index-BlDAGZHO.js"></script>
<link rel="stylesheet" crossorigin href="/assets/index-D8ic-z4p.css">
</head>
<body>

View file

@ -14,7 +14,11 @@ function isVideoSource(locator) {
for (const scheme of ['yt:', 'youtube:']) {
if (ll.startsWith(scheme)) {
const after = ll.slice(scheme.length)
return after.startsWith('video/') || after.startsWith('short/') || after.startsWith('shorts/')
if (after.startsWith('video/') || after.startsWith('short/') || after.startsWith('shorts/'))
return true
// bare yt:ID exactly 11 chars [A-Za-z0-9_-], same predicate as is_youtube_video_id in core
if (/^[a-z0-9_-]{11}$/i.test(after)) return true
return false
}
}