fabi/Mangalord
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(crawler): skip sync when empty chapters + prior > 0 (0.36.6)

Browse Source 
The wait_for_selector wait in 0.36.2 narrows the partial-render race
window but doesn't close it: a render that takes longer than
SELECTOR_TIMEOUT (10s) still hands an empty Vec to sync_manga_chapters,
and the soft-drop branch flips every existing chapter to dropped_at.
The next tick recovers but a manga's reader briefly stops working in
between.

Close it at the pipeline level. Between fetch_manga and the upsert/
sync, if the parsed chapter list is empty and the prior live count
for (source_id, source_manga_key) is > 0, treat the fetch as a
transient failure: log, bump mangas_failed, skip upsert + sync + the
seen.insert so a later batch / tick retries. Brand-new mangas with
genuinely zero chapters (prior == 0) pass through unchanged.

New repo helper repo::crawler::live_chapter_count_for_source_manga
joins chapters → chapter_sources → manga_sources with dropped_at IS
NULL — same lockstep as dispatch_target and the enqueue queries.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-30 20:17:42 +02:00
parent 5c04b0532b
commit eaa5afda50
6 changed files with 144 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
backend/Cargo.lock generated
View File

@@ -1470,7 +1470,7 @@ checksum = "c41e0c4fef86961ac6d6f8a82609f55f31b05e4fce149ac5710e439df7619ba4"
[[package]]
name = "mangalord"
version = "0.36.5"
version = "0.36.6"
dependencies = [
"anyhow",
"argon2",

2
backend/Cargo.toml
View File

@@ -1,6 +1,6 @@
[package]
name = "mangalord"
version = "0.36.5"
version = "0.36.6"
edition = "2021"
default-run = "mangalord"

42
backend/src/crawler/pipeline.rs
View File

@@ -215,6 +215,48 @@ pub async fn run_metadata_pass(
}
};
// Partial-render guard: an empty chapter list paired with a
// prior count > 0 is overwhelmingly a chromium snapshot
// taken between the #chapter_table wrapper render and its
// rows render. The wait_for_selector wait in `navigate`
// narrows this window but cannot close it for slow renders
// beyond the selector budget. Treat as a transient failure
// here — skip upsert, skip seen.insert — so the next batch
// (or the next tick) retries. Skipped in `skip_chapters`
// mode because the parser is configured to return an empty
// Vec by design there.
if !skip_chapters && manga.chapters.is_empty() {
match repo::crawler::live_chapter_count_for_source_manga(
db, source_id, &r.source_manga_key,
)
.await
{
Ok(prior) if prior > 0 => {
tracing::warn!(
key = %r.source_manga_key,
url = %r.url,
prior_chapter_count = prior,
"fetch_manga returned empty chapters but prior count > 0; treating as partial-render transient and skipping"
);
stats.mangas_failed += 1;
continue;
}
Ok(_) => {}
Err(e) => {
// DB lookup failed — fail safe: skip rather
// than risk a soft-drop on a manga whose prior
// count we couldn't confirm.
tracing::warn!(
key = %r.source_manga_key,
error = ?e,
"live_chapter_count_for_source_manga failed; skipping cautiously"
);
stats.mangas_failed += 1;
continue;
}
}
}
let upsert = match repo::crawler::upsert_manga_from_source(
db, source_id, &r.url, &manga,
)

38
backend/src/repo/crawler.rs
View File

@@ -458,6 +458,44 @@ pub async fn sync_manga_chapters(
Ok(diff)
}
/// Count the chapters that the source `(source_id, source_manga_key)`
/// is currently known to attach to — i.e. the number of `chapter_sources`
/// rows for the manga identified by the (source_id, source_manga_key)
/// pair, restricted to live (`dropped_at IS NULL`) rows.
///
/// Used by the metadata pass's partial-render guard: if `fetch_manga`
/// returns an empty `chapters` Vec but the source previously surfaced
/// chapters here, that's most likely a chromium snapshot taken between
/// the `#chapter_table` wrapper render and its rows render — the
/// safest move is to skip `sync_manga_chapters` so the soft-drop
/// branch doesn't flip every existing chapter to `dropped_at`.
///
/// Returns `Ok(0)` when the manga is brand-new (no `manga_sources`
/// row yet), which is the legitimate "this manga has no chapters yet"
/// case and must NOT be flagged.
pub async fn live_chapter_count_for_source_manga(
pool: &PgPool,
source_id: &str,
source_manga_key: &str,
) -> sqlx::Result<i64> {
let row: Option<(i64,)> = sqlx::query_as(
"SELECT COUNT(*) \
FROM chapter_sources cs \
JOIN chapters c ON c.id = cs.chapter_id \
JOIN manga_sources ms \
ON ms.manga_id = c.manga_id \
AND ms.source_id = cs.source_id \
WHERE ms.source_id = $1 \
AND ms.source_manga_key = $2 \
AND cs.dropped_at IS NULL",
)
.bind(source_id)
.bind(source_manga_key)
.fetch_optional(pool)
.await?;
Ok(row.map(|(n,)| n).unwrap_or(0))
}
/// Mark a metadata pass as in-flight for `source_id`. Stamps
/// `last_run_completed:<source_id>` in `crawler_state` with
/// `{"completed": false, "at": now}`. A crash, panic, or SIGKILL after

61
backend/tests/crawler_sync.rs
View File

@@ -232,6 +232,67 @@ async fn sync_chapters_adds_new_refreshes_existing_and_drops_vanished(pool: PgPo
assert!(dropped.0.is_some(), "ch2 should be soft-dropped");
}
#[sqlx::test(migrations = "./migrations")]
async fn live_chapter_count_returns_zero_for_unknown_source_key(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
// No manga_sources row yet → unknown key path. Must not error and
// must report zero so the partial-render guard accepts the
// "brand-new manga with no chapters" case as legitimate.
let n = crawler::live_chapter_count_for_source_manga(&pool, "target", "nobody")
.await
.unwrap();
assert_eq!(n, 0);
}
#[sqlx::test(migrations = "./migrations")]
async fn live_chapter_count_only_counts_live_sources(pool: PgPool) {
crawler::ensure_source(&pool, "target", "T", "https://x.example")
.await
.unwrap();
let m = sample_manga("foo", "Foo Manga", "hash-1");
let up = crawler::upsert_manga_from_source(&pool, "target", "https://x.example/foo", &m)
.await
.unwrap();
let chapters = vec![
SourceChapterRef {
source_chapter_key: "1".into(),
number: 1,
title: Some("Ch.1".into()),
url: "https://x.example/foo/1".into(),
},
SourceChapterRef {
source_chapter_key: "2".into(),
number: 2,
title: Some("Ch.2".into()),
url: "https://x.example/foo/2".into(),
},
];
crawler::sync_manga_chapters(&pool, "target", up.manga_id, &chapters)
.await
.unwrap();
assert_eq!(
crawler::live_chapter_count_for_source_manga(&pool, "target", "foo")
.await
.unwrap(),
2
);
// Soft-drop one source row — count drops by one, the row stays.
sqlx::query(
"UPDATE chapter_sources SET dropped_at = NOW() WHERE source_chapter_key = '2'",
)
.execute(&pool)
.await
.unwrap();
assert_eq!(
crawler::live_chapter_count_for_source_manga(&pool, "target", "foo")
.await
.unwrap(),
1
);
}
/// Real-world sources publish multiple chapters at the same number
/// (different uploaders, translator notes, re-releases). After the
/// (manga_id, number) UNIQUE drop in 0013, each `SourceChapterRef`