peter
ab963c81d2
- people_enrich: a failed TMDB lookup or a dead headshot is skipped, not the end of the run (a dead file is marked and left for a week; three failures in a row end it); portraits wait for the Plex module switch; a no-Plex original keeps its own cache key, so the resize still replaces it; the job entry lives in the plex domain (run_people_enrich) - person-image takes only a headshot-shaped CDN url (no query variants of one file) - every synced row gets Hungarian genres, and a HU genre filter matches the word as picked too; migration 0094 fills the rows no overlay reached - a job run's audit row carries its result as data; audit_clear / demo_reset store their counts - one credit-column list for the prune and the enrichment order; _overlay_pass typed - tests: batch skip + stop, HU bio stored, dead headshots, module switch, the person-image route, the job body, genre filter + facet write + twin fallback, tagline/summary fallbacks, audit data, the reader's alphabet at every remaining collated() call site
414 lines
15 KiB
Python
414 lines
15 KiB
Python
"""E30 S6: the people are made local ahead of time. The people_enrich job fetches linked people's TMDB
|
|
bios (the most-credited first) and caches their portraits resized through Plex; the person page says
|
|
when a bio is still on its way (`enriching`), so it can ask again instead of staying empty.
|
|
DB lane (Postgres); the portrait cache runs in a temp directory.
|
|
"""
|
|
|
|
from datetime import datetime, timezone
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from app import scheduler
|
|
from app.models import PlexItem, PlexLibrary, PlexPerson, User
|
|
from app.plex import imgcache
|
|
from app.plex import people as plex_people
|
|
from app.plex import tmdb as plex_tmdb
|
|
|
|
CDN = plex_people.PERSON_IMG_HOST + "people/"
|
|
DONE = datetime(2024, 1, 1, tzinfo=timezone.utc)
|
|
|
|
|
|
def _movie(db, lib, key, cast):
|
|
db.add(PlexItem(rating_key=key, library_id=lib.id, kind="movie", title=key, cast_names=cast))
|
|
|
|
|
|
def _library(db):
|
|
lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
|
|
db.add(lib)
|
|
db.flush()
|
|
return lib
|
|
|
|
|
|
class _Tmdb:
|
|
"""A TmdbClient stand-in: records the ids asked for, fails on `fail_on`."""
|
|
|
|
def __init__(self, fail_on=()):
|
|
self.asked: list[int] = []
|
|
self.fail_on = set(fail_on)
|
|
|
|
def fetch_person(self, pid):
|
|
self.asked.append(pid)
|
|
if pid in self.fail_on:
|
|
raise plex_tmdb.TmdbError("429")
|
|
return {"biography": f"Bio {pid}."}
|
|
|
|
|
|
def test_the_batch_takes_the_most_credited_linked_people_first(db):
|
|
lib = _library(db)
|
|
_movie(db, lib, "a", ["Often", "Sometimes"])
|
|
_movie(db, lib, "b", ["Often", "Sometimes"])
|
|
_movie(db, lib, "c", ["Often", "Unlinked"])
|
|
db.add_all(
|
|
[
|
|
PlexPerson(name="Sometimes", tmdb_person_id=2),
|
|
PlexPerson(name="Often", tmdb_person_id=1),
|
|
PlexPerson(name="Unlinked"), # no TMDB id: nothing to fetch
|
|
PlexPerson(name="Done", tmdb_person_id=3, tmdb_enriched_at=DONE),
|
|
PlexPerson(name="Rare", tmdb_person_id=4), # credited nowhere: last
|
|
]
|
|
)
|
|
db.commit()
|
|
tmdb = _Tmdb()
|
|
assert plex_tmdb.enrich_people_batch(db, tmdb, 2) == {"enriched": 2} # type: ignore[arg-type]
|
|
assert tmdb.asked == [1, 2]
|
|
db.expire_all()
|
|
often = db.query(PlexPerson).filter_by(name="Often").one()
|
|
assert often.biography == "Bio 1." and often.tmdb_enriched_at is not None
|
|
assert db.query(PlexPerson).filter_by(name="Rare").one().tmdb_enriched_at is None # next run
|
|
|
|
|
|
def test_a_failed_lookup_is_skipped_and_the_rest_still_land(db):
|
|
db.add_all([PlexPerson(name="A", tmdb_person_id=1), PlexPerson(name="B", tmdb_person_id=2)])
|
|
db.add(PlexPerson(name="C", tmdb_person_id=3))
|
|
db.commit()
|
|
tmdb = _Tmdb(fail_on={2})
|
|
assert plex_tmdb.enrich_people_batch(db, tmdb, 10) == {"enriched": 2, "failed": 1} # type: ignore[arg-type]
|
|
assert tmdb.asked == [1, 2, 3] # B refused: skipped, not the end of the batch
|
|
db.expire_all()
|
|
stamped = {p.name: p.tmdb_enriched_at is not None for p in db.query(PlexPerson)}
|
|
assert stamped == {"A": True, "B": False, "C": True} # B is tried again next run
|
|
|
|
|
|
def test_failures_in_a_row_end_the_batch(db):
|
|
db.add_all([PlexPerson(name=f"P{i}", tmdb_person_id=i) for i in range(1, 7)])
|
|
db.commit()
|
|
tmdb = _Tmdb(fail_on={1, 2, 3, 4, 5, 6}) # TMDB is down
|
|
assert plex_tmdb.enrich_people_batch(db, tmdb, 10) == {"enriched": 0, "failed": 3} # type: ignore[arg-type]
|
|
assert tmdb.asked == [1, 2, 3]
|
|
|
|
|
|
def test_the_batch_stores_the_hungarian_biography(db):
|
|
db.add(PlexPerson(name="A", tmdb_person_id=1))
|
|
db.commit()
|
|
|
|
class _WithHu(_Tmdb):
|
|
def fetch_person(self, pid):
|
|
return {
|
|
"biography": "English.",
|
|
"translations": {
|
|
"translations": [{"iso_639_1": "hu", "data": {"biography": "Magyar."}}]
|
|
},
|
|
}
|
|
|
|
assert plex_tmdb.enrich_people_batch(db, _WithHu(), 10) == {"enriched": 1} # type: ignore[arg-type]
|
|
db.expire_all()
|
|
person = db.query(PlexPerson).one()
|
|
assert (person.biography, person.biography_hu) == ("English.", "Magyar.")
|
|
|
|
|
|
class _Plex:
|
|
"""A PlexClient stand-in. `down`: Plex does not answer; `dead`: urls Plex answers with an error."""
|
|
|
|
def __init__(self, down=False, dead=()):
|
|
self.asked: list[tuple[str, int | None]] = []
|
|
self.down = down
|
|
self.dead = set(dead)
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *a):
|
|
return False
|
|
|
|
def image_bytes(self, url, width=None, height=None):
|
|
self.asked.append((url, width))
|
|
if self.down:
|
|
raise plex_people.PlexError("down") from httpx.ConnectError("refused")
|
|
if url in self.dead:
|
|
req = httpx.Request("GET", url)
|
|
status = httpx.HTTPStatusError(
|
|
"404", request=req, response=httpx.Response(404, request=req)
|
|
)
|
|
raise plex_people.PlexError("404") from status
|
|
return b"small", "image/jpeg"
|
|
|
|
|
|
@pytest.fixture
|
|
def cache_dir(tmp_path, monkeypatch):
|
|
monkeypatch.setattr(imgcache, "CACHE_DIR", tmp_path)
|
|
return tmp_path
|
|
|
|
|
|
@pytest.fixture
|
|
def plex_on(monkeypatch):
|
|
"""The Plex module switched on (the job's gate), with `plex` as its client."""
|
|
state = {"enabled": True, "plex": _Plex()}
|
|
monkeypatch.setattr(plex_people.sysconfig, "get_bool", lambda d, k: state["enabled"])
|
|
monkeypatch.setattr(plex_people, "PlexClient", lambda d: state["plex"])
|
|
return state
|
|
|
|
|
|
def _faces(db, n):
|
|
db.add_all(
|
|
[
|
|
PlexPerson(name=f"P{i}", photo_thumb=plex_people.person_thumb_url(CDN + f"{i}.jpg"))
|
|
for i in range(n)
|
|
]
|
|
)
|
|
db.commit()
|
|
|
|
|
|
def test_portraits_are_cached_small_and_replace_the_full_size_original(db, cache_dir, plex_on):
|
|
lib = _library(db)
|
|
_movie(db, lib, "a", ["Often"])
|
|
_movie(db, lib, "b", ["Often", "Cached"])
|
|
db.add_all(
|
|
[
|
|
PlexPerson(name="Often", photo_thumb=plex_people.person_thumb_url(CDN + "often.jpg")),
|
|
PlexPerson(name="Cached", photo_thumb=plex_people.person_thumb_url(CDN + "cached.jpg")),
|
|
PlexPerson(name="Faceless"),
|
|
]
|
|
)
|
|
db.commit()
|
|
small, original = plex_people._portrait_keys(CDN + "often.jpg")
|
|
imgcache.write(original, b"a big original", "image/jpeg") # cached without Plex
|
|
imgcache.write(plex_people._portrait_keys(CDN + "cached.jpg")[0], b"x", "image/jpeg")
|
|
plex = plex_on["plex"]
|
|
|
|
assert plex_people.warm_portraits(db, 10) == {"cached": 1}
|
|
assert plex.asked == [
|
|
(CDN + "often.jpg", plex_people.PORTRAIT_BOX)
|
|
] # resized, the cached one skipped
|
|
assert imgcache.read(small) == (b"small", "image/jpeg")
|
|
assert not imgcache.has(original)
|
|
|
|
|
|
def test_portraits_wait_for_plex(db, cache_dir, plex_on, monkeypatch):
|
|
_faces(db, 1)
|
|
|
|
def not_configured(d):
|
|
raise plex_people.PlexNotConfigured()
|
|
|
|
monkeypatch.setattr(plex_people, "PlexClient", not_configured)
|
|
assert plex_people.warm_portraits(db, 10) == {"cached": 0, "skipped": "disabled"}
|
|
assert list(cache_dir.iterdir()) == [] # no full-size originals behind Plex's back
|
|
|
|
|
|
def test_portraits_wait_for_the_plex_module_to_be_on(db, cache_dir, plex_on):
|
|
_faces(db, 1)
|
|
plex_on["enabled"] = False # switched off, its server still set up
|
|
assert plex_people.warm_portraits(db, 10) == {"cached": 0, "skipped": "disabled"}
|
|
assert plex_on["plex"].asked == []
|
|
|
|
|
|
def test_plex_not_answering_ends_the_portrait_run(db, cache_dir, plex_on):
|
|
_faces(db, 8)
|
|
plex_on["plex"] = _Plex(down=True)
|
|
assert plex_people.warm_portraits(db, 100) == {"cached": 0, "failed": 3}
|
|
assert len(plex_on["plex"].asked) == 3
|
|
assert not list(cache_dir.glob("*.miss")) # Plex was down, the files are not to blame
|
|
|
|
|
|
def test_dead_headshots_are_left_alone_and_the_rest_still_land(db, cache_dir, plex_on):
|
|
_faces(db, 8)
|
|
dead = {CDN + f"{i}.jpg" for i in range(6)} # more dead files than any failure limit
|
|
plex_on["plex"] = _Plex(dead=dead)
|
|
assert plex_people.warm_portraits(db, 100) == {"cached": 2, "failed": 6}
|
|
|
|
plex_on["plex"] = again = _Plex(dead=dead)
|
|
assert plex_people.warm_portraits(db, 100) == {"cached": 0}
|
|
assert again.asked == [] # dead ones marked, live ones cached: nothing to ask for
|
|
|
|
|
|
def test_the_person_image_route(db, cache_dir, monkeypatch):
|
|
from fastapi.testclient import TestClient
|
|
|
|
import app.state as state
|
|
from app.main import app
|
|
from app.routes.plex import playback
|
|
|
|
monkeypatch.setattr(state, "_configured_cache", True)
|
|
monkeypatch.setattr(playback, "_require_session", lambda request: 1)
|
|
client = TestClient(app)
|
|
url = CDN + "face.jpg"
|
|
small, original = plex_people._portrait_keys(url)
|
|
|
|
def get(u):
|
|
return client.get("/api/plex/person-image", params={"u": u})
|
|
|
|
# Only a headshot-shaped url on the CDN host: no query variants of one file, no other host.
|
|
for bad in (url + "?n=1", url + "#x", "https://example.com/people/a.jpg"):
|
|
assert get(bad).status_code == 400, bad
|
|
|
|
# No Plex: the original from the CDN, kept under its own key (the job resizes it later).
|
|
def not_configured(d):
|
|
raise plex_people.PlexNotConfigured()
|
|
|
|
class _Cdn:
|
|
def __init__(self, *a, **k):
|
|
pass
|
|
|
|
def __enter__(self):
|
|
return self
|
|
|
|
def __exit__(self, *a):
|
|
return False
|
|
|
|
def get(self, u):
|
|
return httpx.Response(
|
|
200,
|
|
content=b"original",
|
|
headers={"content-type": "image/jpeg"},
|
|
request=httpx.Request("GET", u),
|
|
)
|
|
|
|
monkeypatch.setattr(playback, "PlexClient", not_configured)
|
|
monkeypatch.setattr(plex_people.httpx, "Client", _Cdn)
|
|
resp = get(url)
|
|
assert (resp.status_code, resp.content) == (200, b"original")
|
|
assert imgcache.has(original) and not imgcache.has(small)
|
|
|
|
# With Plex: resized, and it replaces the original.
|
|
monkeypatch.setattr(playback, "PlexClient", lambda d: _Plex())
|
|
imgcache.drop(original)
|
|
resp = get(url)
|
|
assert (resp.status_code, resp.content) == (200, b"small")
|
|
assert imgcache.has(small)
|
|
assert get(url).content == b"small" # the cache answers now
|
|
|
|
monkeypatch.setattr(playback, "PlexClient", lambda d: _Plex(down=True))
|
|
assert get(CDN + "other.jpg").status_code == 502
|
|
|
|
|
|
def test_the_people_job_runs_its_halves_without_a_tmdb_key(db, cache_dir, plex_on, monkeypatch):
|
|
_faces(db, 1)
|
|
monkeypatch.setattr(plex_tmdb.sysconfig, "get_str", lambda d, k: "")
|
|
assert plex_tmdb.run_people_enrich(db) == {
|
|
"bios": {"skipped": "tmdb_api_key not set"},
|
|
"portraits": {"cached": 1},
|
|
}
|
|
|
|
|
|
def test_a_phase_count_is_a_change_worth_an_audit_row():
|
|
assert scheduler._run_changed({"bios": {"enriched": 3}, "portraits": {"cached": 0}})
|
|
assert scheduler._run_changed({"recent": {"videos_added": 2}, "deep": {}})
|
|
assert not scheduler._run_changed({"bios": {"skipped": "x"}, "portraits": {"cached": 0}})
|
|
|
|
|
|
def test_the_person_page_says_a_bio_is_on_its_way(db, monkeypatch, override_dep):
|
|
from fastapi.testclient import TestClient
|
|
|
|
import app.state as state
|
|
from app.auth import current_user
|
|
from app.db import get_db
|
|
from app.main import app
|
|
from app.routes.plex import people
|
|
|
|
db.add_all(
|
|
[
|
|
PlexPerson(name="Pending", tmdb_person_id=1),
|
|
PlexPerson(name="Known", tmdb_person_id=2, tmdb_enriched_at=DONE, biography="Bio."),
|
|
PlexPerson(name="Nobody"),
|
|
]
|
|
)
|
|
user = User(email="enriching@example.com")
|
|
db.add(user)
|
|
db.commit()
|
|
monkeypatch.setattr(state, "_configured_cache", True)
|
|
override_dep(get_db, db.info["request"])
|
|
override_dep(current_user, lambda: user)
|
|
monkeypatch.setattr(people, "_enrich_person_bg", lambda pid: None)
|
|
key = {"value": "key"}
|
|
monkeypatch.setattr(people.sysconfig, "get_str", lambda d, k: key["value"])
|
|
|
|
def enriching(name):
|
|
resp = TestClient(app).get(f"/api/plex/person/{name}")
|
|
assert resp.status_code == 200, resp.text
|
|
return resp.json()["enriching"]
|
|
|
|
assert enriching("Pending") is True
|
|
assert enriching("Known") is False
|
|
assert enriching("Nobody") is False
|
|
key["value"] = "" # no TMDB key: nothing will ever arrive, so the page must not wait
|
|
assert enriching("Pending") is False
|
|
|
|
|
|
def test_known_for_is_the_most_voted_roles_not_guest_visits():
|
|
payload = {
|
|
"combined_credits": {
|
|
"cast": [
|
|
# Popular this week, but a visit as himself: not what he is known for.
|
|
{
|
|
"id": 1,
|
|
"media_type": "tv",
|
|
"name": "Late Show",
|
|
"character": "Himself - Guest",
|
|
"popularity": 900,
|
|
"vote_count": 50,
|
|
},
|
|
{
|
|
"id": 2,
|
|
"media_type": "tv",
|
|
"name": "Talk Hour",
|
|
"character": "",
|
|
"genre_ids": [10767],
|
|
"popularity": 800,
|
|
"vote_count": 400,
|
|
},
|
|
{
|
|
"id": 3,
|
|
"media_type": "movie",
|
|
"title": "Small Film",
|
|
"character": "Bob",
|
|
"popularity": 90,
|
|
"vote_count": 300,
|
|
},
|
|
{
|
|
"id": 4,
|
|
"media_type": "movie",
|
|
"title": "Big Film",
|
|
"character": "Hero",
|
|
"popularity": 10,
|
|
"vote_count": 9000,
|
|
},
|
|
],
|
|
"crew": [
|
|
{
|
|
"id": 5,
|
|
"media_type": "movie",
|
|
"title": "His Own Film",
|
|
"job": "Director",
|
|
"vote_count": 1000,
|
|
},
|
|
{
|
|
"id": 6,
|
|
"media_type": "movie",
|
|
"title": "Thanked In",
|
|
"job": "Thanks",
|
|
"vote_count": 99999,
|
|
},
|
|
],
|
|
}
|
|
}
|
|
kf = plex_tmdb.parse_person(payload)["known_for"]
|
|
assert [k["title"] for k in kf] == ["Big Film", "His Own Film", "Small Film"]
|
|
|
|
|
|
def test_the_page_shows_at_most_fifteen_known_for_titles(db):
|
|
from app.routes.plex import people
|
|
|
|
lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
|
|
db.add(lib)
|
|
db.flush()
|
|
for i in range(1, 21): # TMDB ids start at 1
|
|
db.add(
|
|
PlexItem(
|
|
rating_key=f"k{i}", library_id=lib.id, kind="movie", title=f"T{i}", guid=f"tmdb:{i}"
|
|
)
|
|
)
|
|
db.commit()
|
|
pool = [{"tmdb_id": i, "media_type": "movie", "title": f"T{i}"} for i in range(1, 21)]
|
|
cards = people._resolve_known_for(db, pool, 0, [lib.id], [], "en")
|
|
assert [c["title"] for c in cards] == [f"T{i}" for i in range(1, 16)]
|