siftlode/backend/app/plex/query.py

"""Plex library query-shaping: the full-text field-scope rechecks and the sidebar metadata
filters that /library and /facets share. Extracted from routes/plex/browse.py so the query
builder has one home (and so the HU-overlay column selection lands here, not in the router).
Pure query fragments — every function returns SQLAlchemy expressions or a params dict."""

from dataclasses import dataclass
from datetime import datetime, timedelta, timezone

from sqlalchemy import and_, case, func, or_, select, type_coerce
from sqlalchemy.dialects.postgresql import JSONB

TS_CONFIG = "public.unaccent_simple"

# --- Language-aware column pickers (E5 S6) ----------------------------------
#
# The HU-overlay twin (E5 S5) stores Hungarian metadata in `*_hu` columns on the SAME EN row. When
# the app language is `hu` we serve those, falling back to the EN column where a row has no HU twin.
# Two flavours of picker, on purpose:
#   * DISPLAY / FILTER (`title_col`/`genres_col`): `coalesce(*_hu, *)` — an EN fallback so a row with
#     no HU metadata still shows (and filters on) its English value. (The detail endpoints serve the
#     HU summary directly off the loaded row, so no `summary_col` SQL helper is needed.)
#   * SEARCH (`vector_col` + `field_recheck`): the raw `*_hu` column coalesced to '' — MIRRORING the
#     generated `search_vector_hu` definition (which uses `coalesce(title_hu, '')`, NOT an EN
#     fallback), so the field recheck stays a strict subset of the GIN vector prefilter (the S2
#     invariant). `people_text` is language-neutral and shared by both vectors.


def title_col(model, lang: str):
    return func.coalesce(model.title_hu, model.title) if lang == "hu" else model.title


def summary_col(model, lang: str):
    """DISPLAY summary, HU-coalesced (EN fallback) — the card hover-overview + info page read this."""
    return func.coalesce(model.summary_hu, model.summary) if lang == "hu" else model.summary


def genres_col(model, lang: str):
    # type_coerce so the JSONB comparator (`.contains` / `@>`, GIN-backed) survives the coalesce.
    if lang == "hu":
        return type_coerce(func.coalesce(model.genres_hu, model.genres), JSONB)
    return model.genres


def top_art_keys(
    db, model, lib_ids: list[int], key_col, keys: list[str], *, per: int = 4, extra_conds=()
) -> dict[str, list[str]]:
    """For each value in `keys` (a member of the JSONB array `key_col` — e.g. a genre value or a
    collection rating_key), the rating_keys of its top `per` items (best-rated, then most-recent) as
    {key: [rating_key, …]}. ONE windowed query: unnest the array, rank within each key, take the top.
    The caller renders posters from /api/plex/image/{rating_key}, so only the keys are returned."""
    if not lib_ids or not keys:
        return {}
    k = func.jsonb_array_elements_text(key_col).label("k")
    expanded = (
        select(model.rating_key.label("rk"), model.rating.label("r"), model.added_at.label("a"), k)
        .where(model.library_id.in_(lib_ids), func.jsonb_typeof(key_col) == "array", *extra_conds)
        .subquery()
    )
    ranked = select(
        expanded.c.rk,
        expanded.c.k,
        func.row_number()
        .over(
            partition_by=expanded.c.k,
            order_by=(expanded.c.r.desc().nullslast(), expanded.c.a.desc().nullslast()),
        )
        .label("rn"),
    ).subquery()
    out: dict[str, list[str]] = {}
    for rk, key in db.execute(
        select(ranked.c.rk, ranked.c.k)
        .where(ranked.c.k.in_(keys), ranked.c.rn <= per)
        .order_by(ranked.c.k, ranked.c.rn)
    ).all():
        out.setdefault(key, []).append(rk)
    return out


def vector_col(model, lang: str):
    # RANKING vector. In HU we rank by the Hungarian vector; a row matched only via its English vector
    # (see `vector_match`) gets rank 0 and sorts last, which is the intended HU-first ordering.
    return model.search_vector_hu if lang == "hu" else model.search_vector


def vector_match(model, lang: str, tsq):
    """The full-text WHERE clause. In HU, match EITHER vector so a row with no HU twin stays findable
    by its English title (search_vector_hu has no title tokens for such a row); EN matches only the EN
    vector. Ranking still uses `vector_col` (the HU vector in HU mode)."""
    if lang == "hu":
        return or_(
            model.search_vector_hu.op("@@")(tsq), model.search_vector.op("@@")(tsq)
        )
    return model.search_vector.op("@@")(tsq)


# Field-scoped search: the scope-pill in the header search box narrows a full-text query to ONE
# facet of the row. `all` uses the GIN-indexed weighted `search_vector` untouched (byte-identical to
# the pre-scope behaviour); a specific field keeps that GIN prefilter AND re-checks a per-column
# tsvector, so the scoped hits are always a strict subset of Everywhere. The per-field expressions
# mirror the `search_vector` Computed definition (same `TS_CONFIG`, same `left(summary, 1000)`
# truncation) so scoping never surfaces a match the vector itself wouldn't. `episode` is handled
# separately in the query body (it targets episode rows, not the movie/show grid).
FIELD_COLUMNS = ("title", "people", "summary", "episode")


def _title_tsv(col):
    return func.to_tsvector(TS_CONFIG, func.coalesce(col, ""))


def _summary_tsv(col):
    return func.to_tsvector(TS_CONFIG, func.left(func.coalesce(col, ""), 1000))


def field_recheck(model, field: str, tsq, lang: str = "en"):
    """A per-field `to_tsvector(...) @@ tsq` clause for a non-`all`, non-`episode` scope, or None.
    Each per-field tsvector mirrors the generated `search_vector[_hu]` definition (same TS_CONFIG,
    same `left(summary, 1000)`). In HU, title/summary re-check BOTH the HU and EN columns so a scoped
    hit stays a strict subset of `vector_match`'s HU union; `people` is language-neutral."""
    hu = lang == "hu"
    if field == "title":
        cols = [model.title_hu, model.title] if hu else [model.title]
        return or_(*[_title_tsv(c).op("@@")(tsq) for c in cols])
    if field == "people":
        return func.to_tsvector(TS_CONFIG, func.coalesce(model.people_text, "")).op("@@")(tsq)
    if field == "summary":
        cols = [model.summary_hu, model.summary] if hu else [model.summary]
        return or_(*[_summary_tsv(c).op("@@")(tsq) for c in cols])
    return None


def split_csv(v: str | None) -> list[str]:
    return [s.strip() for s in v.split(",") if s.strip()] if v else []


_ADDED_WINDOWS = {"24h": 1, "1w": 7, "1m": 30, "6m": 182, "1y": 365}


def added_cutoff(within: str | None) -> datetime | None:
    days = _ADDED_WINDOWS.get(within or "")
    return datetime.now(timezone.utc) - timedelta(days=days) if days else None


def meta_filter_conds(model, p: dict, lang: str = "en") -> list:
    """The shared metadata-filter conditions (identical column names on plex_items + plex_shows) for
    `p` (the request's filter params). Duration is movie-only, handled by the caller. Returned as a
    list so faceted search can apply all-but-one group. DRY for browse, unified, and /facets.
    Genre chips are language-specific strings, so they filter the active-language genre column."""
    conds: list = []
    gsel = split_csv(p.get("genres"))
    if gsel:
        gcol = genres_col(model, lang)
        gc = [gcol.contains([g]) for g in gsel]
        conds.append(and_(*gc) if p.get("genre_mode") == "all" else or_(*gc))
    crs = split_csv(p.get("content_ratings"))
    if crs:
        conds.append(model.content_rating.in_(crs))
    if p.get("year_min") is not None:
        conds.append(model.year >= p["year_min"])
    if p.get("year_max") is not None:
        conds.append(model.year <= p["year_max"])
    if p.get("rating_min") is not None:
        # Filter by the SAME score the UI shows on the badge (IMDb preferred, audience fallback), so a
        # ratingMin picked from a displayed IMDb score narrows the right column instead of the raw
        # audience `rating`. Both are 0–10, so coalesce is scale-consistent.
        conds.append(func.coalesce(model.imdb_rating, model.rating) >= p["rating_min"])
    cutoff = added_cutoff(p.get("added_within"))
    if cutoff is not None:
        conds.append(model.added_at >= cutoff)
    for d in split_csv(p.get("directors")):  # AND
        conds.append(model.directors.contains([d]))
    alist = split_csv(p.get("actors"))
    if alist:  # AND (all) or OR (any) — default OR, mirroring genre_mode
        ac = [model.cast_names.contains([a]) for a in alist]
        conds.append(and_(*ac) if p.get("actor_mode") == "all" else or_(*ac))
    stds = split_csv(p.get("studios"))
    if stds:  # OR
        conds.append(model.studio.in_(stds))
    for kw in split_csv(p.get("keywords")):  # AND — TMDB keyword chips from the detail page (E5 S5)
        conds.append(model.keywords.contains([kw]))
    csel = split_csv(p.get("collections"))
    if csel:  # OR (any) or AND (all) — a title can belong to several collections, mirroring genre_mode
        cc = [model.collection_keys.contains([c]) for c in csel]
        conds.append(and_(*cc) if p.get("collection_mode") == "all" else or_(*cc))
    return conds


def apply_meta_filters(q, model, p: dict, lang: str = "en"):
    conds = meta_filter_conds(model, p, lang)
    return q.where(*conds) if conds else q


@dataclass
class LibraryFilters:
    """The shared sidebar filter query-params for /library + /facets, declared once and injected via
    ``Depends()``. `as_dict()` yields the `p` dict the query builders read; `duration_*` is included
    for /facets' wsq but ignored by `meta_filter_conds` (both callers apply duration separately)."""

    genres: str | None = None
    genre_mode: str = "any"
    content_ratings: str | None = None
    year_min: int | None = None
    year_max: int | None = None
    rating_min: float | None = None
    duration_min: int | None = None
    duration_max: int | None = None
    added_within: str | None = None
    directors: str | None = None
    actors: str | None = None
    actor_mode: str = (
        "any"  # how multiple actors combine: any (OR, default) | all (AND)
    )
    studios: str | None = None
    keywords: str | None = None  # TMDB keyword chips (E5 S5), CSV; language-neutral
    collections: str | None = None  # CSV of collection rating_keys
    collection_mode: str = "any"  # how multiple collections combine: any (OR, default) | all (AND)

    def as_dict(self) -> dict:
        return {
            "genres": self.genres,
            "genre_mode": self.genre_mode,
            "content_ratings": self.content_ratings,
            "year_min": self.year_min,
            "year_max": self.year_max,
            "rating_min": self.rating_min,
            "duration_min": self.duration_min,
            "duration_max": self.duration_max,
            "added_within": self.added_within,
            "directors": self.directors,
            "actors": self.actors,
            "actor_mode": self.actor_mode,
            "studios": self.studios,
            "keywords": self.keywords,
            "collections": self.collections,
            "collection_mode": self.collection_mode,
        }


def like_escape(s: str) -> str:
    return s.replace("\\", "\\\\").replace("%", "\\%").replace("_", "\\_")


# --- Watch-state scope (shared by the /library grid AND the /facets aggregation) ---------------
#
# The `show` scope (all | watched | in_progress | unwatched) filters the browse result by per-user
# watch state. The SAME predicate has to be applied in two places — `unified_library` (the grid) and
# `facets.wsq` (so the facet counts reflect exactly the visible set) — and they MUST stay identical:
# a hidden movie kept out of the grid must not inflate the facets either. These helpers are the one
# home for that predicate so the two call sites can't drift (E3 S1; pinned by test_plex_facets_grid_
# parity). Callers pass the already-joined state expressions, so this module stays model-agnostic:
#   * movies — `st` is an aliased PlexState outer-joined on (item_id, user_id).
#   * shows  — `tot`/`wat`/`inp` are the coalesced totals from `rollup.agg_subquery`.


def movie_status_case(st):
    """The per-movie status label (new | in_progress | watched) from its PlexState alias `st`."""
    return case(
        (st.status == "watched", "watched"),
        (
            and_(st.position_seconds > 0, or_(st.status.is_(None), st.status != "watched")),
            "in_progress",
        ),
        else_="new",
    )


def show_status_case(tot, wat, inp):
    """The per-show status label rolled up from its episodes' totals (total/watched/in-progress)."""
    return case(
        (and_(tot > 0, wat >= tot), "watched"),
        (or_(wat > 0, inp > 0), "in_progress"),
        else_="new",
    )


def apply_movie_state_filter(query, st, show: str):
    """Restrict a movie query to the `show` scope via its PlexState alias `st`. The default (`all`)
    excludes hidden movies — the exclusion that must match between grid and facets."""
    if show == "watched":
        return query.where(st.status == "watched")
    if show == "in_progress":
        return query.where(
            st.position_seconds > 0, or_(st.status.is_(None), st.status != "watched")
        )
    if show == "unwatched":
        return query.where(or_(st.status.is_(None), st.status.notin_(["watched", "hidden"])))
    return query.where(or_(st.status.is_(None), st.status != "hidden"))


def apply_show_state_filter(query, tot, wat, inp, show: str):
    """Restrict a show query to the `show` scope via its rollup totals. `all` is a no-op (shows have
    no hidden concept); the caller only joins the rollup for the three non-`all` scopes."""
    if show == "watched":
        return query.where(tot > 0, wat >= tot)
    if show == "in_progress":
        return query.where(or_(wat > 0, inp > 0), wat < tot)
    if show == "unwatched":
        return query.where(wat == 0, inp == 0)
    return query