feat: incremental crawl mode with seed-completion gate (0.33.0)

Daemon now auto-detects mode per source: Backfill until the first
full walk records `seed_completed:<source>` in `crawler_state`, then
Incremental (newest-first, stops after N consecutive Unchanged
upserts). `CRAWLER_MODE` overrides to a fixed mode; CLI rejects
`auto` since it has no pre-run DB state.

`Source::discover` returns a lazy `DiscoverWalk` so Incremental can
break out mid-walk without prefetching pages. The drop pass and seed
marker are now gated on a true full walk — fixes a latent soft-drop
of the index tail under partial sweeps.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-28 06:41:26 +02:00
parent 51f42b03e9
commit 45ce0d8f12
11 changed files with 761 additions and 162 deletions

View File

@@ -23,14 +23,34 @@ pub struct MetadataStats {
pub mangas_failed: usize,
}
/// Decide whether the per-ref loop should stop based on the Incremental
/// streak counter. Pulled out as a pure function so the rule is unit-
/// testable without standing up the walker or DB.
pub(crate) fn should_stop(mode: DiscoverMode, consecutive_unchanged: usize) -> bool {
match mode {
DiscoverMode::Backfill => false,
DiscoverMode::Incremental { stop_after_unchanged } => {
consecutive_unchanged >= stop_after_unchanged
}
}
}
/// Runs the discover → fetch → upsert → cover → chapter-list-diff pipeline
/// for the target source. Pure metadata; chapter content is enqueued as
/// separate `SyncChapterContent` jobs by the caller after this returns.
///
/// `limit == 0` means no cap (full backfill). `skip_chapters == true` is
/// the "metadata-only" mode (parser doesn't extract chapters, and
/// `sync_manga_chapters` is skipped — otherwise an empty chapter list
/// would soft-drop existing rows).
/// `limit == 0` means no cap (full sweep up to the source's own bound).
/// `skip_chapters == true` is the "metadata-only" mode (parser doesn't
/// extract chapters, and `sync_manga_chapters` is skipped — otherwise an
/// empty chapter list would soft-drop existing rows).
///
/// `mode` controls the walk:
/// - `Backfill` — oldest-first, no early exit. The only mode that runs
/// the end-of-walk drop pass + writes `seed_completed_at`.
/// - `Incremental { stop_after_unchanged }` — newest-first, breaks out
/// after N consecutive Unchanged upserts. Drop pass is skipped (the
/// tail of the index is never visited, so its `last_seen_at` is
/// stale and using it to soft-drop would be unsafe).
#[allow(clippy::too_many_arguments)]
pub async fn run_metadata_pass(
browser_manager: &BrowserManager,
@@ -41,6 +61,7 @@ pub async fn run_metadata_pass(
start_url: &str,
limit: usize,
skip_chapters: bool,
mode: DiscoverMode,
) -> anyhow::Result<MetadataStats> {
let lease = browser_manager
.acquire()
@@ -74,123 +95,189 @@ pub async fn run_metadata_pass(
let run_started_at = chrono::Utc::now();
let max_refs = (limit > 0).then_some(limit);
tracing::info!(?max_refs, "discovering manga list");
let refs = source
.discover(&ctx, DiscoverMode::Backfill, max_refs)
tracing::info!(?mode, ?max_refs, "starting metadata pass");
let mut walker = source
.discover(&ctx, mode)
.await
.context("discover failed")?;
tracing::info!(count = refs.len(), "discovered manga list");
let mut stats = MetadataStats {
discovered: refs.len(),
..MetadataStats::default()
};
let mut stats = MetadataStats::default();
let mut consecutive_unchanged: usize = 0;
let mut walked_to_completion = false;
let mut hit_limit = false;
let mut hit_incremental_stop = false;
for (i, r) in refs.iter().enumerate() {
tracing::info!(
idx = i + 1,
total = stats.discovered,
key = %r.source_manga_key,
"fetching metadata"
);
let manga = match source.fetch_manga(&ctx, r).await {
Ok(m) => m,
Err(e) => {
tracing::warn!(
key = %r.source_manga_key,
url = %r.url,
error = ?e,
"fetch_manga failed"
);
stats.mangas_failed += 1;
continue;
'outer: loop {
let batch = match walker.next_batch(&ctx).await? {
Some(b) => b,
None => {
walked_to_completion = true;
break;
}
};
let upsert = match repo::crawler::upsert_manga_from_source(db, source_id, &r.url, &manga)
.await
{
Ok(u) => u,
Err(e) => {
tracing::error!(
key = %r.source_manga_key,
error = ?e,
"upsert_manga_from_source failed"
);
stats.mangas_failed += 1;
continue;
for r in batch {
if max_refs.map(|m| stats.discovered >= m).unwrap_or(false) {
hit_limit = true;
tracing::info!(cap = ?max_refs, "max_results reached; halting walk");
break 'outer;
}
};
stats.upserted += 1;
tracing::info!(
key = %manga.source_manga_key,
manga_id = %upsert.manga_id,
status = ?upsert.status,
title = %manga.title,
"manga upserted"
);
// Cover image: download when missing in storage or when metadata
// signaled an update (cover URL is part of metadata_hash, so
// Updated implies the URL may have moved). Failures are non-fatal.
let needs_cover = upsert.cover_image_path.is_none()
|| matches!(upsert.status, repo::crawler::UpsertStatus::Updated);
if needs_cover {
if let Some(cover_url) = manga.cover_url.as_deref() {
match download_and_store_cover(
db,
storage,
http,
rate,
&r.url,
upsert.manga_id,
cover_url,
)
.await
{
Ok(()) => stats.covers_fetched += 1,
Err(e) => tracing::warn!(
manga_id = %upsert.manga_id,
stats.discovered += 1;
tracing::info!(
idx = stats.discovered,
key = %r.source_manga_key,
"fetching metadata"
);
let manga = match source.fetch_manga(&ctx, &r).await {
Ok(m) => m,
Err(e) => {
tracing::warn!(
key = %r.source_manga_key,
url = %r.url,
error = ?e,
"cover download failed"
),
"fetch_manga failed"
);
stats.mangas_failed += 1;
continue;
}
}
}
};
if !skip_chapters {
match repo::crawler::sync_manga_chapters(
db,
source_id,
upsert.manga_id,
&manga.chapters,
let upsert = match repo::crawler::upsert_manga_from_source(
db, source_id, &r.url, &manga,
)
.await
{
Ok(diff) => tracing::info!(
manga_id = %upsert.manga_id,
new = diff.new,
refreshed = diff.refreshed,
dropped = diff.dropped,
"chapters synced"
),
Err(e) => tracing::warn!(
manga_id = %upsert.manga_id,
error = ?e,
"chapter sync failed"
),
Ok(u) => u,
Err(e) => {
tracing::error!(
key = %r.source_manga_key,
error = ?e,
"upsert_manga_from_source failed"
);
stats.mangas_failed += 1;
continue;
}
};
stats.upserted += 1;
tracing::info!(
key = %manga.source_manga_key,
manga_id = %upsert.manga_id,
status = ?upsert.status,
title = %manga.title,
"manga upserted"
);
// Cover image: download when missing in storage or when metadata
// signaled an update (cover URL is part of metadata_hash, so
// Updated implies the URL may have moved). Failures are non-fatal.
let needs_cover = upsert.cover_image_path.is_none()
|| matches!(upsert.status, repo::crawler::UpsertStatus::Updated);
if needs_cover {
if let Some(cover_url) = manga.cover_url.as_deref() {
match download_and_store_cover(
db,
storage,
http,
rate,
&r.url,
upsert.manga_id,
cover_url,
)
.await
{
Ok(()) => stats.covers_fetched += 1,
Err(e) => tracing::warn!(
manga_id = %upsert.manga_id,
error = ?e,
"cover download failed"
),
}
}
}
if !skip_chapters {
match repo::crawler::sync_manga_chapters(
db,
source_id,
upsert.manga_id,
&manga.chapters,
)
.await
{
Ok(diff) => tracing::info!(
manga_id = %upsert.manga_id,
new = diff.new,
refreshed = diff.refreshed,
dropped = diff.dropped,
"chapters synced"
),
Err(e) => tracing::warn!(
manga_id = %upsert.manga_id,
error = ?e,
"chapter sync failed"
),
}
}
// Incremental stop: count consecutive Unchanged upserts and
// bail once the threshold is reached. New/Updated resets the
// streak so a fresh entry mid-batch doesn't accidentally trip
// the cutoff.
match upsert.status {
repo::crawler::UpsertStatus::Unchanged => {
consecutive_unchanged += 1;
}
repo::crawler::UpsertStatus::New | repo::crawler::UpsertStatus::Updated => {
consecutive_unchanged = 0;
}
}
if should_stop(mode, consecutive_unchanged) {
hit_incremental_stop = true;
tracing::info!(
consecutive_unchanged,
"incremental stop threshold reached; halting walk"
);
break 'outer;
}
}
}
if limit == 0 {
// Drop pass: only when the walk truly covered everything the source
// surfaces. `last_seen_at` on un-visited rows is stale, so running
// the drop on a partial walk would soft-drop the tail of the index.
let full_walk = walked_to_completion && !hit_limit && !hit_incremental_stop;
let backfill_complete = full_walk && matches!(mode, DiscoverMode::Backfill);
if full_walk {
match repo::crawler::mark_dropped_mangas(db, source_id, run_started_at).await {
Ok(n) => tracing::info!(dropped = n, "marked unseen manga as dropped"),
Err(e) => tracing::warn!(error = ?e, "drop-pass failed"),
}
} else {
tracing::info!(limit, "partial sync — skipping drop pass");
tracing::info!(
?mode,
hit_limit,
hit_incremental_stop,
"partial sync — skipping drop pass"
);
}
if backfill_complete {
if let Err(e) = repo::crawler::mark_seed_completed(db, source_id, run_started_at).await {
tracing::warn!(error = ?e, "mark_seed_completed failed");
} else {
tracing::info!(source_id, "seed marked complete");
}
}
tracing::info!(
?mode,
discovered = stats.discovered,
upserted = stats.upserted,
covers_fetched = stats.covers_fetched,
mangas_failed = stats.mangas_failed,
walked_to_completion,
hit_limit,
hit_incremental_stop,
"metadata pass complete"
);
drop(lease);
Ok(stats)
@@ -345,3 +432,36 @@ fn origin_of(url: &str) -> Option<String> {
let host = rest.split('/').next()?;
Some(format!("{scheme}://{host}"))
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn backfill_never_stops_regardless_of_streak() {
assert!(!should_stop(DiscoverMode::Backfill, 0));
assert!(!should_stop(DiscoverMode::Backfill, 100));
assert!(!should_stop(DiscoverMode::Backfill, usize::MAX));
}
#[test]
fn incremental_stops_when_streak_meets_threshold() {
let mode = DiscoverMode::Incremental {
stop_after_unchanged: 3,
};
assert!(!should_stop(mode, 0));
assert!(!should_stop(mode, 2));
assert!(should_stop(mode, 3), "stops at exactly the threshold");
assert!(should_stop(mode, 100), "stops at anything past threshold");
}
#[test]
fn incremental_with_zero_threshold_stops_immediately() {
// A nonsensical config (no Unchanged needed to stop) shouldn't
// panic — it just means the very first ref triggers the bail.
let mode = DiscoverMode::Incremental {
stop_after_unchanged: 0,
};
assert!(should_stop(mode, 0));
}
}