siftlode/backend/tests/test_plex_detail.py

"""Regression: the info-page rich detail (IMDb score/id, tagline, full cast) is persisted at
rich-fetch time and served from the DB row instead of a live plex.metadata() call.

- `rich_detail`/`apply_rich_detail` are pure — parse + persist the rich-only fields.
- `_enrich_people_batch` (the cast backfill) now also stamps those fields.
- `item_detail` serves a MOVIE's detail from the row (survives a live-Plex outage) while keeping
  markers/streams live; an EPISODE (never enriched) still parses detail from the live meta.
- `show_detail` serves from the row; `related` stays live best-effort.

The endpoint tests use the DB lane (`db` fixture) — skipped when no Postgres is reachable.
"""

from types import SimpleNamespace

from fastapi.testclient import TestClient

import app.routes.plex.detail as detail_routes
import app.state as state
from app.auth import current_user
from app.db import get_db
from app.main import app
from app.models import PlexItem, PlexLibrary, PlexShow, User
from app.plex import detail
from app.plex.sync import _apply_facet_fields, _enrich_people_batch

# A full Plex metadata dict: an explicit IMDb Rating entry (must win over audienceRating), an IMDb Guid,
# a tagline, and a two-person cast (one with a CDN headshot → proxied, one without → thumb None).
RICH_META = {
    "Rating": [
        {"image": "imdb://image.rating.imdb", "value": 8.7},
        {"image": "themoviedb://image.rating", "value": 7.0},
    ],
    "audienceRating": 9.9,  # ignored: the imdb Rating entry is preferred
    "Guid": [{"id": "tmdb://238"}, {"id": "imdb://tt0068646"}],
    "contentRating": "R",
    "Genre": [{"tag": "Crime"}, {"tag": "Drama"}],
    "Director": [{"tag": "Francis Ford Coppola"}],
    "studio": "Paramount",
    "tagline": "An offer you can't refuse.",
    "Role": [
        {
            "tag": "Marlon Brando",
            "role": "Vito Corleone",
            "thumb": "https://metadata-static.plex.tv/b.jpg",
        },
        {"tag": "Al Pacino", "role": "Michael"},
    ],
}


# ---- pure parse/persist --------------------------------------------------------------------------


def test_rich_detail_prefers_imdb_entry_and_builds_link():
    d = detail.rich_detail(RICH_META)
    assert d["imdb_rating"] == 8.7  # the imdb Rating entry, not audienceRating (9.9)
    assert d["imdb_id"] == "tt0068646"
    assert d["imdb_url"] == "https://www.imdb.com/title/tt0068646/"
    assert d["tagline"] == "An offer you can't refuse."
    assert [c["name"] for c in d["cast"]] == ["Marlon Brando", "Al Pacino"]
    assert d["cast"][0]["role"] == "Vito Corleone"
    assert d["cast"][0]["thumb"] and d["cast"][0]["thumb"].startswith("/api/plex/person-image")
    assert d["cast"][1]["thumb"] is None  # no CDN headshot → not proxied


def test_rich_detail_is_imdb_only_no_audience_fallback():
    # Imdb_rating is IMDb-ONLY. With no imdb:// Rating entry it's NULL — the Plex audience score
    # is NOT mislabelled as an IMDb score (it's served separately via the `rating` column).
    d = detail.rich_detail({"audienceRating": 7.25})
    assert d["imdb_rating"] is None
    assert d["imdb_id"] is None and d["imdb_url"] is None


def test_apply_rich_detail_writes_only_rich_fields():
    row = SimpleNamespace(imdb_rating=None, imdb_id=None, tagline=None, full_cast=None)
    detail.apply_rich_detail(row, RICH_META)
    assert row.imdb_rating == 8.7
    assert row.imdb_id == "tt0068646"
    assert row.tagline == "An offer you can't refuse."
    assert [c["name"] for c in row.full_cast] == ["Marlon Brando", "Al Pacino"]


def test_apply_rich_detail_empty_cast_persists_null():
    row = SimpleNamespace(imdb_rating=1.0, imdb_id="x", tagline="t", full_cast=[{"name": "stale"}])
    detail.apply_rich_detail(row, {})  # a poor/empty meta must clear to NULL, not keep stale data
    assert row.full_cast is None
    assert row.imdb_rating is None and row.imdb_id is None and row.tagline is None


# ---- backfill persistence (DB lane) --------------------------------------------------------------


class _StubClient:
    """Stand-in for PlexClient: `_enrich_people_batch` calls plex.metadata(rating_key); item_detail
    uses it as a context manager and passes markers=True. `raise_` simulates a Plex outage."""

    def __init__(self, meta: dict | None = None, raise_: bool = False):
        self._meta = meta or {}
        self._raise = raise_

    def __enter__(self):
        return self

    def __exit__(self, *a):
        return False

    def metadata(self, rating_key, markers=False):
        if self._raise:
            raise RuntimeError("plex unavailable")
        return self._meta


def test_apply_facet_fields_preserves_enriched_cast_names():
    """A full sync must NOT downgrade an already-enriched full cast back to the listing top-20 — since
    sync never clears people_enriched_at, nothing would regrow it and the person-page filter would lose
    the names past the listing cap (regression guard for the enrich gating)."""
    # The cheap listing's top few cast + the (always-present) director.
    thin = {
        "Role": [{"tag": "Al Pacino"}, {"tag": "James Caan"}],
        "Director": [{"tag": "Francis Ford Coppola"}],
    }

    # Not-yet-enriched row: the listing cast IS applied.
    fresh = SimpleNamespace(people_enriched_at=None, directors=None, cast_names=None)
    _apply_facet_fields(fresh, thin)
    assert fresh.cast_names == ["Al Pacino", "James Caan"]

    # Enriched row: the fuller stored cast is KEPT, not overwritten by the thin listing.
    from datetime import datetime, timezone

    enriched = SimpleNamespace(
        people_enriched_at=datetime.now(timezone.utc),
        directors=["Francis Ford Coppola"],
        cast_names=["Marlon Brando", "Al Pacino", "James Caan", "Diane Keaton"],
    )
    _apply_facet_fields(enriched, thin)
    assert enriched.cast_names == ["Marlon Brando", "Al Pacino", "James Caan", "Diane Keaton"]
    # people_text is rebuilt from the (updated) directors + the PRESERVED full cast.
    assert "Diane Keaton" in enriched.people_text and "Francis Ford Coppola" in enriched.people_text


def test_apply_facet_fields_keeps_over_cap_cast_after_a_watermark_reset():
    """The enriched-cast guard must survive a watermark RESET (people_enriched_at nulled, e.g. by a
    migration like 0065). A stored cast LONGER than the listing cap can only be an enriched fuller list,
    so it's kept even though the row now reads as un-enriched — comparing against the cap, not the
    current listing's length, is what makes this robust (regression guard for the review fix)."""
    thin = {"Role": [{"tag": f"Actor {i}"} for i in range(20)]}  # a full 20-name listing
    over_cap = SimpleNamespace(
        people_enriched_at=None,  # watermark was reset
        directors=None,
        cast_names=[f"Enriched {i}" for i in range(22)],  # 22 > the 20 cap => enriched
    )
    _apply_facet_fields(over_cap, thin)
    assert over_cap.cast_names == [f"Enriched {i}" for i in range(22)]  # kept, not downgraded


def test_apply_facet_fields_tracks_a_trimmed_listing_when_unenriched():
    """A listing-sourced cast (at or below the cap, never enriched) must TRACK Plex cast edits in both
    directions. When Plex trims the cast, the shorter fresh listing replaces the stored one — the old
    length-vs-this-listing guard would have wrongly kept the stale longer cast."""
    stored = SimpleNamespace(
        people_enriched_at=None,
        directors=None,
        cast_names=["A", "B", "C", "D", "E"],  # 5, at/below the cap => listing-sourced
    )
    trimmed = {"Role": [{"tag": "A"}, {"tag": "B"}]}  # Plex removed 3 cast members
    _apply_facet_fields(stored, trimmed)
    assert stored.cast_names == ["A", "B"]


def test_enrich_people_batch_persists_detail(db):
    lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
    db.add(lib)
    db.flush()
    mv = PlexItem(rating_key="m1", library_id=lib.id, kind="movie", title="The Godfather")
    db.add(mv)
    db.commit()
    assert mv.people_enriched_at is None and mv.full_cast is None

    n = _enrich_people_batch(db, _StubClient(RICH_META))
    assert n == 1
    db.refresh(mv)
    assert mv.imdb_rating == 8.7
    assert mv.imdb_id == "tt0068646"
    assert mv.tagline == "An offer you can't refuse."
    assert [c["name"] for c in mv.full_cast] == ["Marlon Brando", "Al Pacino"]
    assert mv.cast_names == ["Marlon Brando", "Al Pacino"]  # people enrich still runs alongside
    assert mv.people_enriched_at is not None  # stamped so the backfill skips it next run


# ---- item_detail serving (DB lane) ---------------------------------------------------------------


def _get(db, user, monkeypatch, override_dep, path):
    monkeypatch.setattr(state, "_configured_cache", True)  # pass the request gate
    override_dep(get_db, db.info["request"])
    override_dep(current_user, lambda: user)
    return TestClient(app).get(path)


def _user(db, email):
    u = User(email=email)
    db.add(u)
    db.flush()
    return u


def test_item_detail_movie_serves_from_row_despite_live_outage(db, monkeypatch, override_dep):
    """An enriched movie serves cast/IMDb/tagline from the DB row even when the live Plex call raises —
    only markers/streams (which need the live meta) degrade."""
    lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
    db.add(lib)
    db.flush()
    from datetime import datetime, timezone

    mv = PlexItem(
        rating_key="m1",
        library_id=lib.id,
        kind="movie",
        title="The Godfather",
        genres=["Crime", "Drama"],
        directors=["Francis Ford Coppola"],
        studio="Paramount",
        content_rating="R",
        imdb_rating=8.7,
        imdb_id="tt0068646",
        tagline="An offer you can't refuse.",
        full_cast=[{"name": "Marlon Brando", "role": "Vito Corleone", "thumb": None}],
        people_enriched_at=datetime.now(timezone.utc),
    )
    db.add(mv)
    db.commit()
    user = _user(db, "outage@example.com")
    db.commit()

    monkeypatch.setattr(detail_routes, "PlexClient", lambda db: _StubClient(raise_=True))
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/item/m1")
    assert resp.status_code == 200, resp.text
    body = resp.json()
    assert body["imdb_rating"] == 8.7
    assert body["imdb_id"] == "tt0068646"
    assert body["imdb_url"] == "https://www.imdb.com/title/tt0068646/"
    assert body["tagline"] == "An offer you can't refuse."
    assert [c["name"] for c in body["cast"]] == ["Marlon Brando"]
    assert body["genres"] == ["Crime", "Drama"]
    assert body["markers"] == []  # live fetch failed → markers degrade, but detail survived


def test_item_detail_movie_lazy_fills_when_unenriched(db, monkeypatch, override_dep):
    """A not-yet-enriched movie is filled from the live meta on view (and persisted for next time)."""
    lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
    db.add(lib)
    db.flush()
    mv = PlexItem(rating_key="m1", library_id=lib.id, kind="movie", title="The Godfather")
    db.add(mv)
    db.commit()
    user = _user(db, "lazy@example.com")
    db.commit()

    monkeypatch.setattr(detail_routes, "PlexClient", lambda db: _StubClient(RICH_META))
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/item/m1")
    assert resp.status_code == 200, resp.text
    assert resp.json()["imdb_id"] == "tt0068646"
    db.refresh(mv)
    assert mv.imdb_id == "tt0068646"  # persisted
    assert mv.people_enriched_at is not None
    assert [c["name"] for c in mv.full_cast] == ["Marlon Brando", "Al Pacino"]


def test_item_detail_episode_serves_rich_from_live(db, monkeypatch, override_dep):
    """Episodes are never enriched (not in the grid, no HU overlay), so their detail is parsed from the
    live meta the endpoint fetches for markers/streams."""
    lib = PlexLibrary(plex_key="2", title="Shows", kind="show", enabled=True)
    db.add(lib)
    db.flush()
    show = PlexShow(rating_key="s1", library_id=lib.id, title="A Show")
    db.add(show)
    db.flush()
    ep = PlexItem(
        rating_key="e1", library_id=lib.id, kind="episode", title="Pilot", show_id=show.id
    )
    db.add(ep)
    db.commit()
    user = _user(db, "ep@example.com")
    db.commit()

    monkeypatch.setattr(detail_routes, "PlexClient", lambda db: _StubClient(RICH_META))
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/item/e1")
    assert resp.status_code == 200, resp.text
    body = resp.json()
    assert body["imdb_id"] == "tt0068646"  # from the live meta, not the (NULL) row
    assert [c["name"] for c in body["cast"]] == ["Marlon Brando", "Al Pacino"]
    db.refresh(ep)
    assert ep.full_cast is None  # episodes are not persisted/enriched


def test_show_detail_serves_from_row(db, monkeypatch, override_dep):
    """A show serves cast/IMDb from the DB row; `related` failing (Plex down) must not drop the detail."""
    lib = PlexLibrary(plex_key="2", title="Shows", kind="show", enabled=True)
    db.add(lib)
    db.flush()
    from datetime import datetime, timezone

    show = PlexShow(
        rating_key="s1",
        library_id=lib.id,
        title="A Show",
        genres=["Drama"],
        imdb_rating=9.1,
        imdb_id="tt0903747",
        full_cast=[{"name": "Bryan Cranston", "role": "Walter White", "thumb": None}],
        people_enriched_at=datetime.now(timezone.utc),
    )
    db.add(show)
    db.commit()
    user = _user(db, "show@example.com")
    db.commit()

    # _show_enrichment raises → related degrades to []; the row-served detail must still render.
    def _boom(db_, rk):
        raise RuntimeError("plex unavailable")

    monkeypatch.setattr(detail_routes, "_show_enrichment", _boom)
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/show/s1")
    assert resp.status_code == 200, resp.text
    body = resp.json()["show"]
    assert body["imdb_rating"] == 9.1
    assert body["imdb_id"] == "tt0903747"
    assert body["imdb_url"] == "https://www.imdb.com/title/tt0903747/"
    assert [c["name"] for c in body["cast"]] == ["Bryan Cranston"]
    assert resp.json()["related"] == []


def test_show_detail_lazy_fills_when_unenriched(db, monkeypatch, override_dep):
    """A not-yet-enriched show is filled from the live meta on first view (imdb/full_cast persisted +
    stamped) so subsequent views serve from the row."""
    lib = PlexLibrary(plex_key="2", title="Shows", kind="show", enabled=True)
    db.add(lib)
    db.flush()
    show = PlexShow(rating_key="s1", library_id=lib.id, title="A Show")
    db.add(show)
    db.commit()
    user = _user(db, "showfill@example.com")
    db.commit()

    # _show_enrichment returns (live meta, no related) → the fill branch runs.
    monkeypatch.setattr(detail_routes, "_show_enrichment", lambda db_, rk: (RICH_META, []))
    resp = _get(db, user, monkeypatch, override_dep, "/api/plex/show/s1")
    assert resp.status_code == 200, resp.text
    assert resp.json()["show"]["imdb_id"] == "tt0068646"
    db.refresh(show)
    assert show.imdb_id == "tt0068646"  # persisted for next time
    assert show.people_enriched_at is not None
    assert [c["name"] for c in show.full_cast] == ["Marlon Brando", "Al Pacino"]


def test_item_detail_names_tracks_from_their_language_not_plexs_title(
    db, monkeypatch, override_dep
):
    """Plex titles a track in the Plex SERVER's language ("English (AC3 5.1)", "magyar Forced",
    "中文 (EAC3 Stereo)"), so a Hungarian reader got a mix. The route sends what the client names it
    from instead — the language tag, the forced / SDH flags, the codec tail — keeping Plex's title
    only as the fallback, and no invented English "Audio 2" for a track with neither."""
    lib = PlexLibrary(plex_key="1", title="Movies", kind="movie", enabled=True)
    db.add(lib)
    db.flush()
    db.add(PlexItem(rating_key="m1", library_id=lib.id, kind="movie", title="T"))
    db.commit()
    user = _user(db, "tracks@example.com")
    db.commit()
    streams = [
        {"streamType": 2, "displayTitle": "English (AC3 5.1)", "languageTag": "en-US"},
        {"streamType": 2, "displayTitle": "中文 (EAC3 Stereo)", "languageTag": "zh"},
        {"streamType": 2},
        {
            "streamType": 3,
            "displayTitle": "magyar Forced",
            "languageTag": "hu",
            "forced": True,
            "codec": "srt",
        },
        {
            "streamType": 3,
            "displayTitle": "English SDH",
            "languageTag": "en",
            "hearingImpaired": True,
            "codec": "srt",
        },
    ]
    meta = {**RICH_META, "Media": [{"Part": [{"Stream": streams}]}]}
    monkeypatch.setattr(detail_routes, "PlexClient", lambda db: _StubClient(meta))
    body = _get(db, user, monkeypatch, override_dep, "/api/plex/item/m1").json()

    naming = ("label", "lang_tag", "forced", "hearing_impaired", "detail")
    assert [tuple(a[k] for k in naming) for a in body["audio_streams"]] == [
        ("English (AC3 5.1)", "en-US", False, False, "AC3 5.1"),
        ("中文 (EAC3 Stereo)", "zh", False, False, "EAC3 Stereo"),
        (None, None, False, False, None),
    ]
    assert [tuple(s[k] for k in naming) for s in body["subtitle_streams"]] == [
        ("magyar Forced", "hu", True, False, None),
        ("English SDH", "en", False, True, None),
    ]