fix(reader): the Takeout import holds up under abuse, races and a run it cannot see

- Uploads: one at a time per user and ten an hour, each refused only after its body arrived;
  the history read an entry at a time (32 MiB cap), a Watch later list capped at YouTube's 5000,
  a user's kept videos at 200k; any unreadable shape is a 422, not a 500.
- Quota: Watch later lookups stop at the backfill reserve and at a per-user daily share; what is
  not asked about waits, known videos still go in, and the shorts job retries the rest.
- Staging and settling share one per-user advisory lock (no deadlock); a run settles only the
  rows it read, so a row staged meanwhile is never called gone.
- A failed run's notice names a translated failure, never the upstream's text.
- The status says when an import is queued; the page watches it to its end even when left, then
  reads the feed, its counts and the playlists again.
- Settings: one live region, the zone kept (unavailable) while a run goes, focus handed back,
  a missed drop kept from the browser, an oversize file refused before it is sent.
- Scheduler and run lists show Takeout runs by the importing user.
This commit is contained in:
2026-10-23 20:48:23 +02:00
parent e0b02a0c14
commit 9f580fd8c8
29 changed files with 1235 additions and 213 deletions
+23 -9
View File
@@ -510,6 +510,15 @@ def detach_user_tag(db: Session, user: User, channel_id: str, tag_id: int) -> No
# --- Google Takeout --------------------------------------------------------------------------
_TAKEOUT_BATCH = 1000
# The advisory-lock namespace of one user's Takeout rows ("TO"), so a key cannot meet another lock's.
_TAKEOUT_LOCK_NS = 0x544F
def lock_takeout(db: Session, user: User) -> None:
"""Hold the user's Takeout rows for the rest of the transaction. An upload's staging and an
import's settling each lock many of the same rows, one statement after another and in no common
order, so without one lock over both the two can deadlock."""
db.execute(select(func.pg_advisory_xact_lock(_TAKEOUT_LOCK_NS, user.id)))
def stage_takeout(
@@ -518,6 +527,7 @@ def stage_takeout(
"""Keep the videos of one Takeout file, `{video id: (time, channel id)}`, for the import job.
A second upload of the same export, or a newer one, adds what is new: a video already kept keeps
the later time, and a row the import has settled keeps its outcome."""
lock_takeout(db, user)
values = [
{"user_id": user.id, "kind": kind, "video_id": vid, "at": at, "channel_id": channel}
for vid, (at, channel) in rows.items()
@@ -551,6 +561,7 @@ def apply_takeout_watched(db: Session, user: User) -> dict[str, int]:
past is not watching it), and a state the user set here wins: watched or hidden, or anything
changed after the Takeout time. The upsert's own condition is that rule, so a state set while
the import runs wins too."""
lock_takeout(db, user)
short: list[int] = []
todo: dict[str, tuple[int, datetime]] = {}
for row_id, video_id, at, is_short in queries.takeout_watched_ready(db, user):
@@ -590,19 +601,22 @@ def apply_takeout_watched(db: Session, user: User) -> dict[str, int]:
return {"watched": len(marked), "kept": len(kept), "shorts": len(short)}
def apply_takeout_watch_later(db: Session, user: User) -> dict[str, int]:
"""Put the videos of the user's YouTube Watch later list into theirs here, oldest first, after
what it already holds. Called once the catalog has fetched what it could: a video still unknown
is one YouTube no longer has."""
waiting = queries.takeout_waiting(db, user, TakeoutKind.WATCH_LATER)
if not waiting:
def apply_takeout_watch_later(
db: Session, user: User, rows: list[tuple[int, str]], asked: set[str]
) -> dict[str, int]:
"""Put the videos of the user's waiting Watch later `rows`, (row id, video id) oldest first, into
their list here, after what it already holds. `asked` is the videos YouTube was just asked for: one
of those the catalog still lacks is gone from YouTube; any other unknown one keeps waiting."""
if not rows:
return {}
known = queries.known_video_ids(db, [vid for _, vid in waiting])
lock_takeout(db, user)
known = queries.known_video_ids(db, [vid for _, vid in rows])
pl = watch_later(db, user)
done: dict[TakeoutOutcome, list[int]] = {o: [] for o in TakeoutOutcome}
for row_id, vid in waiting:
for row_id, vid in rows:
if vid not in known:
done[TakeoutOutcome.MISSING].append(row_id)
if vid in asked:
done[TakeoutOutcome.MISSING].append(row_id)
elif add_item(db, pl, vid, mark_dirty=False):
done[TakeoutOutcome.ADDED].append(row_id)
else: