fix(catalog): a 24/7 stream archive's years-long length is unknown, not summed or sorted by

YouTube reports a 24/7 stream's archive with the years it has run (prod: 122,962,914 s), and one
such video made the Watch later total read 44,073 hours. A length past a day is now no length
(`Video.length_seconds`, LENGTH_MAX_S): the API sends none, the playlist and channel totals
leave it out and count it as `live_without_length` ("+N live" beside the sum), and the duration
filter, sort and Home budget never match it. Migration 0117 moves the duration sort indexes onto
the length expression. An AST test holds who may still read the raw column.

The migration 0110 test now ends its read before the way down: 0117 builds an index
CONCURRENTLY there, which waited for that open transaction forever.
This commit is contained in:
2026-11-07 02:20:03 +01:00
parent 1bf3d6a592
commit 5b846136ad
26 changed files with 446 additions and 39 deletions
+3 -1
View File
@@ -46,11 +46,12 @@ def list_channels(user: User = Depends(current_user), db: Session = Depends(get_
# computed here — the manager table dropped its N/S/L column.)
channel_ids = [c.id for _, c in rows]
agg: dict[str, dict] = {}
for cid, n, last_up, total_dur in queries.aggregates(db, channel_ids):
for cid, n, last_up, total_dur, live in queries.aggregates(db, channel_ids):
agg[cid] = {
"stored": n,
"last_video_at": iso(last_up),
"total_duration_seconds": int(total_dur or 0),
"live_without_length": live,
}
# Channels already in the *global* deep-backfill queue — i.e. at least one user (any
@@ -68,6 +69,7 @@ def list_channels(user: User = Depends(current_user), db: Session = Depends(get_
"stored_videos": (agg.get(ch.id) or {}).get("stored", 0),
"last_video_at": (agg.get(ch.id) or {}).get("last_video_at"),
"total_duration_seconds": (agg.get(ch.id) or {}).get("total_duration_seconds", 0),
"live_without_length": (agg.get(ch.id) or {}).get("live_without_length", 0),
"priority": sub.priority,
"hidden": sub.hidden,
"deep_requested": sub.deep_requested,
+4 -3
View File
@@ -10,6 +10,7 @@ from sqlalchemy.orm.exc import StaleDataError
from app import jobruns, quota, scheduler
from app.catalog import queries as catalog_queries, service as catalog_service
from app.catalog.models import known_length
from app.auth import current_user
from app.db import get_db, release_read_connection
from app.mailtext import lang_for_user
@@ -287,7 +288,7 @@ def get_video_detail(
"channel_title": v.channel.title if v.channel else None,
"published_at": iso(v.published_at),
"view_count": v.view_count,
"duration_seconds": v.duration_seconds,
"duration_seconds": v.length_seconds,
}
# The DB path above is free; the off-catalog YouTube lookup below spends a quota unit.
@@ -315,8 +316,8 @@ def get_video_detail(
"channel_title": snippet.get("channelTitle"),
"published_at": snippet.get("publishedAt"),
"view_count": int(views) if views is not None else None,
"duration_seconds": parse_iso8601_duration(
items[0].get("contentDetails", {}).get("duration")
"duration_seconds": known_length(
parse_iso8601_duration(items[0].get("contentDetails", {}).get("duration"))
),
}
+8 -4
View File
@@ -95,10 +95,13 @@ def _video_or_404(db: Session, video_id: str) -> None:
def _summary(
pl: "Playlist",
count: int,
total_duration: int = 0,
duration: tuple[int, int] = (0, 0),
has_video: bool | None = None,
cover: str | None = None,
) -> dict:
"""`duration` is `queries.durations`'s pair: the known running time, and the live videos it
cannot hold — the "+N live" beside it."""
total_duration, live = duration
out = {
"id": pl.id,
"name": pl.name,
@@ -108,6 +111,7 @@ def _summary(
"dirty": pl.dirty,
"item_count": count,
"total_duration_seconds": total_duration,
"live_without_length": live,
"cover_thumbnail": cover,
# When this list last CHANGED (rename, add/remove/move/reorder) — the rail's
# "recently changed first" sort reads it. See `service.touch` for why it isn't automatic.
@@ -138,7 +142,7 @@ def list_playlists(
_summary(
p,
counts.get(p.id, 0),
durations.get(p.id, 0),
durations.get(p.id, (0, 0)),
(p.id in member) if contains else None,
covers.get(p.id),
)
@@ -363,8 +367,8 @@ def rename_playlist(
raise _refused(400, "name_required")
service.rename_playlist(db, pl, name)
db.commit()
count, total, cover = queries.playlist_totals(db, pl.id)
return _summary(pl, count, total, cover=cover)
count, total, live, cover = queries.playlist_totals(db, pl.id)
return _summary(pl, count, (total, live), cover=cover)
@router.delete("/{playlist_id}")