feat(plex): full-library cast backfill via a batched rich re-sync (S1b)
Lazy enrichment only covers viewed titles, so an actor's count/results were partial. Add a background backfill: each plex_sync rich-fetches a bounded batch (60) of not-yet-enriched movies/shows and persists their FULL cast, stamping people_enriched_at so each is fetched once — the whole library is covered over successive runs (migration 0057 adds the marker). Extracted the enrichment into a shared app/plex/people.py (cast_from_meta / enrich_row_people / prune_orphan_people + the person-image host/proxy) so the info-page lazy path and the batch share ONE implementation — no duplication; the info page also stamps the marker so the batch skips it. Verified: an 8-item batch grows those movies' cast_names 3->24 and fills plex_people (32->224); the info-page cast is intact after the _rich_meta refactor. (Plex cast-explore S1b)
This commit is contained in:
@@ -0,0 +1,97 @@
|
||||
"""Shared Plex people helpers: parse cast/crew from rich metadata, persist the full cast onto a movie
|
||||
or show (cast_names + the people_text search blob + the plex_people headshot cache), and prune
|
||||
orphaned people. Used by BOTH the info-page lazy enrichment (routes.plex) and the background rich
|
||||
re-sync (plex.sync), so the two paths never diverge."""
|
||||
|
||||
from urllib.parse import quote
|
||||
|
||||
from sqlalchemy import text
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app.models import PlexPerson
|
||||
|
||||
# Cast/crew photos come from Plex's PUBLIC metadata CDN (no token). We proxy them (host-whitelisted)
|
||||
# so the user's browser makes no third-party request (privacy + self-host CSP friendliness).
|
||||
PERSON_IMG_HOST = "https://metadata-static.plex.tv/"
|
||||
|
||||
|
||||
def person_thumb_url(thumb: str | None) -> str | None:
|
||||
"""Proxied /person-image URL for a Plex CDN headshot, or None when it's missing / off-CDN."""
|
||||
t = str(thumb or "")
|
||||
return f"/api/plex/person-image?u={quote(t, safe='')}" if t.startswith(PERSON_IMG_HOST) else None
|
||||
|
||||
|
||||
def cast_from_meta(meta: dict, limit: int = 24) -> list[dict]:
|
||||
"""[{name, role, thumb}] for the cast (Role tags) in a full Plex metadata dict — thumb is the
|
||||
proxied person-image URL or None. Shared by the info-page response, the lazy enrichment, and the
|
||||
re-sync so the parsing lives in one place."""
|
||||
out: list[dict] = []
|
||||
for role in (meta.get("Role") or [])[:limit]:
|
||||
name = role.get("tag")
|
||||
if not name:
|
||||
continue
|
||||
out.append(
|
||||
{"name": name, "role": role.get("role"), "thumb": person_thumb_url(role.get("thumb"))}
|
||||
)
|
||||
return out
|
||||
|
||||
|
||||
def enrich_row_people(db: Session, row, cast: list[dict]) -> bool:
|
||||
"""Persist the FULLER cast onto the row's `cast_names` + `people_text`, and cache each cast
|
||||
member's headshot in plex_people. The cheap section listing that drives the main sync only carries
|
||||
the top ~3 cast, so this — run whenever a rich fetch happens (info-page view + the rich re-sync) —
|
||||
is what makes the full displayed cast filterable. Returns True if anything was written (the caller
|
||||
commits). Best-effort by contract: never the reason a read 500s."""
|
||||
names = list(dict.fromkeys(c["name"] for c in cast if c.get("name")))[:24]
|
||||
if not names:
|
||||
return False
|
||||
dirty = False
|
||||
# Grow/refresh cast_names only when the rich set adds names the stored (listing top-3) set lacks —
|
||||
# avoid churn and never downgrade a fuller set back to the thin listing.
|
||||
if set(names) - set(row.cast_names or []):
|
||||
row.cast_names = names
|
||||
row.people_text = " ".join(dict.fromkeys(list(row.directors or []) + names)) or None
|
||||
dirty = True
|
||||
# Headshot cache: upsert name -> proxied thumb (a later fetch fills a prior NULL; names without a
|
||||
# whitelisted photo still get a row so a card can show a placeholder).
|
||||
existing = {p.name: p for p in db.query(PlexPerson).filter(PlexPerson.name.in_(names))}
|
||||
for c in cast:
|
||||
nm, th = c.get("name"), c.get("thumb")
|
||||
if not nm:
|
||||
continue
|
||||
p = existing.get(nm)
|
||||
if p is None:
|
||||
p = PlexPerson(name=nm, photo_thumb=th)
|
||||
db.add(p)
|
||||
existing[nm] = p
|
||||
dirty = True
|
||||
elif th and not p.photo_thumb:
|
||||
p.photo_thumb = th
|
||||
dirty = True
|
||||
return dirty
|
||||
|
||||
|
||||
# The person names still referenced by ANY movie/show (cast OR directors). plex_people rows outside
|
||||
# this set are orphans left by a library removal.
|
||||
_REFERENCED_PEOPLE_SQL = """
|
||||
SELECT jsonb_array_elements_text(cast_names) FROM plex_items WHERE jsonb_typeof(cast_names) = 'array'
|
||||
UNION SELECT jsonb_array_elements_text(directors) FROM plex_items WHERE jsonb_typeof(directors) = 'array'
|
||||
UNION SELECT jsonb_array_elements_text(cast_names) FROM plex_shows WHERE jsonb_typeof(cast_names) = 'array'
|
||||
UNION SELECT jsonb_array_elements_text(directors) FROM plex_shows WHERE jsonb_typeof(directors) = 'array'
|
||||
"""
|
||||
|
||||
|
||||
def prune_orphan_people(db: Session) -> int:
|
||||
"""Delete plex_people (headshot cache) rows whose name no longer appears in any movie/show cast or
|
||||
directors — orphaned by a library removal. Returns the number pruned. Commits its own work."""
|
||||
# `WHERE ref IS NOT NULL` matters: a JSON-null array element surfaces as a SQL NULL in the
|
||||
# referenced set, and `name NOT IN (…, NULL)` is NULL (never TRUE) for every row — the classic
|
||||
# NOT IN trap that would silently prune nothing. Filtering NULLs out keeps the delete correct.
|
||||
res = db.execute(
|
||||
text(
|
||||
"DELETE FROM plex_people WHERE name NOT IN "
|
||||
f"(SELECT ref FROM ({_REFERENCED_PEOPLE_SQL}) AS refs(ref) WHERE ref IS NOT NULL)"
|
||||
)
|
||||
)
|
||||
db.commit()
|
||||
return res.rowcount or 0
|
||||
+44
-22
@@ -12,11 +12,11 @@ Cast + intro/credit markers are fetched lazily on the item-detail/player path (P
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
|
||||
from sqlalchemy import text
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from app import sysconfig
|
||||
from app.models import PlexCollection, PlexItem, PlexLibrary, PlexSeason, PlexShow
|
||||
from app.plex import people
|
||||
from app.plex.client import PlexClient, PlexError, PlexNotConfigured
|
||||
|
||||
log = logging.getLogger("siftlode.plex")
|
||||
@@ -130,6 +130,12 @@ def sync(db: Session) -> dict:
|
||||
_sync_shows(db, plex, lib, stats)
|
||||
_sync_collections(db, plex, lib, stats)
|
||||
db.commit()
|
||||
# Rich-fetch a bounded batch of not-yet-enriched titles' FULL cast, so the whole library
|
||||
# becomes filterable over successive runs (the cheap listing above only stored the top ~3).
|
||||
try:
|
||||
stats["people_enriched"] = _enrich_people_batch(db, plex)
|
||||
except Exception as e: # best-effort — never fail the sync over the backfill
|
||||
log.warning("Plex people enrich batch failed: %s", e)
|
||||
except PlexNotConfigured as e:
|
||||
return {"skipped": str(e)}
|
||||
except PlexError as e:
|
||||
@@ -139,37 +145,53 @@ def sync(db: Session) -> dict:
|
||||
# Prune the headshot cache: a reconcile may have removed titles, orphaning people who no longer
|
||||
# appear in ANY item's cast/directors — drop those rows, mirroring how Plex drops orphaned metadata.
|
||||
try:
|
||||
stats["people_pruned"] = prune_orphan_people(db)
|
||||
stats["people_pruned"] = people.prune_orphan_people(db)
|
||||
except Exception as e: # best-effort housekeeping — never fail the sync over it
|
||||
log.warning("Plex people prune failed: %s", e)
|
||||
log.info("Plex sync done: %s", stats)
|
||||
return stats
|
||||
|
||||
|
||||
# The person names still referenced by ANY movie/show (cast OR directors). plex_people rows outside
|
||||
# this set are orphans left by a library removal.
|
||||
_REFERENCED_PEOPLE_SQL = """
|
||||
SELECT jsonb_array_elements_text(cast_names) FROM plex_items WHERE jsonb_typeof(cast_names) = 'array'
|
||||
UNION SELECT jsonb_array_elements_text(directors) FROM plex_items WHERE jsonb_typeof(directors) = 'array'
|
||||
UNION SELECT jsonb_array_elements_text(cast_names) FROM plex_shows WHERE jsonb_typeof(cast_names) = 'array'
|
||||
UNION SELECT jsonb_array_elements_text(directors) FROM plex_shows WHERE jsonb_typeof(directors) = 'array'
|
||||
"""
|
||||
# How many titles to rich-fetch per sync run for the cast backfill — bounds the extra Plex load; the
|
||||
# whole library is covered over successive runs (each fetched item is stamped people_enriched_at once).
|
||||
_ENRICH_BATCH = 60
|
||||
|
||||
|
||||
def prune_orphan_people(db: Session) -> int:
|
||||
"""Delete plex_people (headshot cache) rows whose name no longer appears in any movie/show cast or
|
||||
directors — orphaned by a library removal. Returns the number pruned. Commits its own work."""
|
||||
# `WHERE ref IS NOT NULL` matters: a JSON-null array element would surface as a SQL NULL in the
|
||||
# referenced set, and `name NOT IN (…, NULL)` is NULL (never TRUE) for every row — the classic
|
||||
# NOT IN trap that would silently prune nothing. Filtering NULLs out keeps the delete correct.
|
||||
res = db.execute(
|
||||
text(
|
||||
"DELETE FROM plex_people WHERE name NOT IN "
|
||||
f"(SELECT ref FROM ({_REFERENCED_PEOPLE_SQL}) AS refs(ref) WHERE ref IS NOT NULL)"
|
||||
)
|
||||
def _enrich_people_batch(db: Session, plex: PlexClient, limit: int = _ENRICH_BATCH) -> int:
|
||||
"""Rich-fetch the FULL cast of up to `limit` not-yet-enriched movies/shows and persist it (via the
|
||||
shared enrich_row_people). Oldest-id first, movies before shows. Stamps people_enriched_at only on
|
||||
a SUCCESSFUL fetch, so a transient per-item failure retries next run rather than being lost.
|
||||
Returns how many items were enriched this run."""
|
||||
movies = (
|
||||
db.query(PlexItem)
|
||||
.filter(PlexItem.kind == "movie", PlexItem.people_enriched_at.is_(None))
|
||||
.order_by(PlexItem.id)
|
||||
.limit(limit)
|
||||
.all()
|
||||
)
|
||||
remaining = limit - len(movies)
|
||||
shows = (
|
||||
db.query(PlexShow)
|
||||
.filter(PlexShow.people_enriched_at.is_(None))
|
||||
.order_by(PlexShow.id)
|
||||
.limit(remaining)
|
||||
.all()
|
||||
if remaining > 0
|
||||
else []
|
||||
)
|
||||
now = datetime.now(timezone.utc)
|
||||
n = 0
|
||||
for row in [*movies, *shows]:
|
||||
try:
|
||||
meta = plex.metadata(row.rating_key) or {}
|
||||
except Exception as e:
|
||||
log.debug("Plex people enrich fetch failed for %s: %s", row.rating_key, e)
|
||||
continue # leave people_enriched_at NULL so it's retried on a later run
|
||||
people.enrich_row_people(db, row, people.cast_from_meta(meta))
|
||||
row.people_enriched_at = now
|
||||
n += 1
|
||||
db.commit()
|
||||
return res.rowcount or 0
|
||||
return n
|
||||
|
||||
|
||||
def _upsert_library(db: Session, key: str, title: str, kind: str) -> PlexLibrary:
|
||||
|
||||
Reference in New Issue
Block a user