siftlode/backend/app/plex/library.py

"""The Plex browse grid's reads: the unified movies + shows feed, its search, and its facets.

A user's watch state is joined through `userscope`; the feed and its facets share every filter
(`plex.query`), so a facet count is the size of what the grid would show.
"""

from sqlalchemy import Boolean, Integer, String, and_, cast, func, literal, null, or_, select
from sqlalchemy.orm import Session, aliased

from app.collation import collated, sorted_words
from app.models import User
from app.plex import rollup
from app.plex.cards import norm_lang
from app.plex.models import PlexItem, PlexShow, PlexState
from app.plex.query import (
    FIELD_COLUMNS,
    PLAYBACK_CLASSES,
    TS_CONFIG,
    LibraryFilters,
    apply_meta_filters,
    apply_movie_state_filter,
    apply_show_state_filter,
    content_libs,
    field_recheck,
    genres_col,
    meta_filter_conds,
    movie_status_case,
    playable_conds,
    playback_class_expr,
    show_status_case,
    split_csv,
    summary_col,
    title_col,
    vector_col,
    vector_match,
)
from app.userscope import owned_by
from app.utils import to_tsquery_str


def sort_column(u, sort: str, lang: str = "en"):
    """The browse grid's sort key -> orderable column on the union subquery. Module-level (not inline
    in the handler) so a test can pin its vocabulary to `PLEX_SORT_KEYS` — a key the Sort control
    offers but this cannot order would quietly fall back to `added_at` and look like a broken control.
    An unknown key (a stale bookmark, a hand-edited URL) deliberately keeps that fallback. The title sorts
    in the reader's alphabet (`collation`)."""
    return {
        "added": u.c.added_at,
        "title": collated(u.c.title, lang),
        "year": u.c.year,
        "rating": u.c.rating,
        "duration": u.c.duration_s,
        "release": u.c.rel,
        "lastwatched": u.c.last_watched,
    }.get(sort, u.c.added_at)


def library_page(
    db: Session,
    user: User,
    *,
    scope: str,
    q: str | None,
    field: str,
    sort: str,
    sort_dir: str,
    show: str,
    lang: str,
    offset: int,
    limit: int,
    f: LibraryFilters,
) -> tuple[int, list, list]:
    """One page of the unified cross-library browse: (total, rows, episodes). `rows` mixes movies
    and shows (`kind` says which), scoped to movie|show|both, with the shared filters/search/watch
    state (a show's state is the aggregate of its episodes). On a search that also matches episodes
    (and shows are in scope), `episodes` holds the matching ones as (item, state, show) — the
    grouped 'Episodes' section. `lang` is already normalised."""
    p = f.as_dict()
    movie_lib_ids, show_lib_ids = content_libs(db)
    want_movies = scope in ("movie", "both") and bool(movie_lib_ids)
    want_shows = scope in ("show", "both") and bool(show_lib_ids)

    ts = to_tsquery_str(q) if q else None
    tsq = func.to_tsquery(TS_CONFIG, ts) if ts else None
    if field not in FIELD_COLUMNS and field != "all":
        field = "all"
    # `episode` scope targets episode rows only — the movie/show grid stays empty; the recheck for
    # the specific title/people/summary fields is a strict narrowing on top of the GIN prefilter.
    grid_field = field != "episode"
    recheck = field_recheck if tsq is not None and field not in ("all", "episode") else None

    selects = []
    if want_movies and grid_field:
        st = aliased(PlexState)
        m_status = movie_status_case(st)
        mq = (
            select(
                PlexItem.rating_key.label("rk"),
                literal("movie").label("kind"),
                title_col(PlexItem, lang).label("title"),
                PlexItem.year.label("year"),
                PlexItem.rating.label("rating"),
                # Truncated so the card hover-overview costs a few hundred bytes, not the full synopsis.
                func.left(summary_col(PlexItem, lang), 300).label("summary"),
                PlexItem.added_at.label("added_at"),
                PlexItem.originally_available_at.label("rel"),
                PlexItem.duration_s.label("duration_s"),
                PlexItem.playable.label("playable"),
                PlexItem.transcode_hw.label("transcode_hw"),
                cast(null(), Integer).label("season_count"),
                func.coalesce(st.position_seconds, 0).label("position_seconds"),
                m_status.label("status"),
                literal(False).label("resumable"),
                # "last watched" sort key: when the movie was last resumed, else when it was marked
                # watched. NULL for never-touched movies → nullslast sinks them (see the sort dict).
                func.coalesce(st.progress_updated_at, st.watched_at).label("last_watched"),
                (
                    func.ts_rank(vector_col(PlexItem, lang), tsq)
                    if tsq is not None
                    else literal(0.0)
                ).label("rank"),
            )
            .outerjoin(st, and_(st.item_id == PlexItem.id, owned_by(st.user_id, user)))
            .where(PlexItem.kind == "movie", PlexItem.library_id.in_(movie_lib_ids))
        )
        mq = apply_movie_state_filter(mq, st, show)
        mq = apply_meta_filters(mq, PlexItem, p, lang)
        if f.duration_min is not None:
            mq = mq.where(PlexItem.duration_s >= f.duration_min)
        if f.duration_max is not None:
            mq = mq.where(PlexItem.duration_s <= f.duration_max)
        # Playback-class filter (movie-only — a show is an aggregate with no single class).
        mq = mq.where(*playable_conds(split_csv(f.playable)))
        if tsq is not None:
            mq = mq.where(vector_match(PlexItem, lang, tsq))
        if recheck is not None and (narrow := recheck(PlexItem, field, tsq, lang)) is not None:
            mq = mq.where(narrow)
        selects.append(mq)
    if want_shows and grid_field:
        agg = rollup.agg_subquery(db, user.id, include_resumed=True).subquery()
        tot = func.coalesce(agg.c.total, 0)
        wat = func.coalesce(agg.c.watched, 0)
        inp = func.coalesce(agg.c.inprog, 0)
        s_status = show_status_case(tot, wat, inp)
        sq = (
            select(
                PlexShow.rating_key.label("rk"),
                literal("show").label("kind"),
                title_col(PlexShow, lang).label("title"),
                PlexShow.year.label("year"),
                PlexShow.rating.label("rating"),
                func.left(summary_col(PlexShow, lang), 300).label("summary"),
                PlexShow.added_at.label("added_at"),
                PlexShow.originally_available_at.label("rel"),
                cast(null(), Integer).label("duration_s"),
                cast(null(), String).label("playable"),
                cast(null(), Boolean).label("transcode_hw"),
                PlexShow.child_count.label("season_count"),
                literal(0).label("position_seconds"),
                s_status.label("status"),
                # An episode holds a resume point (`ShowState.resumable`, the card's Continue + Restart).
                (inp > 0).label("resumable"),
                # Show leg's "last watched": max(resume/watched time) across the show's episodes (see
                # rollup.agg_subquery include_resumed). NULL for a never-watched show → nullslast.
                agg.c.resumed_at.label("last_watched"),
                (
                    func.ts_rank(vector_col(PlexShow, lang), tsq)
                    if tsq is not None
                    else literal(0.0)
                ).label("rank"),
            )
            .outerjoin(agg, agg.c.show_id == PlexShow.id)
            .where(PlexShow.library_id.in_(show_lib_ids))
        )
        sq = apply_show_state_filter(sq, tot, wat, inp, show)
        sq = apply_meta_filters(sq, PlexShow, p, lang)
        if tsq is not None:
            sq = sq.where(vector_match(PlexShow, lang, tsq))
        if recheck is not None and (narrow := recheck(PlexShow, field, tsq, lang)) is not None:
            sq = sq.where(narrow)
        selects.append(sq)

    total = 0
    rows: list = []
    if selects:
        union = selects[0] if len(selects) == 1 else selects[0].union_all(*selects[1:])
        u = union.subquery()
        total = db.scalar(select(func.count()).select_from(u)) or 0

        if tsq is not None:
            order = [u.c.rank.desc()]
        else:
            col = sort_column(u, sort, lang)
            order = [(col.asc() if sort_dir == "asc" else col.desc()).nullslast()]
        order.append(u.c.rk.desc())
        rows = list(db.execute(select(u).order_by(*order).offset(offset).limit(limit)).all())

    # Episode "grouped result" section: shown for Everywhere (full-vector match, today's behaviour)
    # and for the Episode scope (title-only match, empty item grid). The title/people/summary scopes
    # target the movie/show grid, so they suppress episodes.
    eps: list = []
    if tsq is not None and want_shows and field in ("all", "episode"):
        ep_st = aliased(PlexState)
        # In HU an episode is found by its Hungarian title too (the overlay fills it) — and
        # still by its English one, like `vector_match` does for the grid.
        if field == "episode":
            ep_vec = func.to_tsvector(TS_CONFIG, func.coalesce(PlexItem.title, ""))
            ep_vec_hu = func.to_tsvector(TS_CONFIG, func.coalesce(PlexItem.title_hu, ""))
        else:
            ep_vec, ep_vec_hu = PlexItem.search_vector, PlexItem.search_vector_hu
        hit = ep_vec.op("@@")(tsq)
        if lang == "hu":
            hit = or_(ep_vec_hu.op("@@")(tsq), hit)
            ep_vec = ep_vec_hu
        eps = list(
            db.execute(
                select(PlexItem, ep_st, PlexShow)
                .outerjoin(ep_st, and_(ep_st.item_id == PlexItem.id, owned_by(ep_st.user_id, user)))
                .outerjoin(PlexShow, PlexShow.id == PlexItem.show_id)
                .where(
                    PlexItem.kind == "episode",
                    PlexItem.library_id.in_(show_lib_ids),
                    hit,
                )
                .order_by(func.ts_rank(ep_vec, tsq).desc())
                .limit(24)
            ).all()
        )

    return total, rows, eps


def facets(db: Session, user: User, *, scope: str, show: str, lang: str, f: LibraryFilters) -> dict:
    """Available filter values for the unified library (scope movie|show|both), ADAPTED to the active
    filters (faceted search): each group's values/bounds are computed with all the OTHER active
    filters applied but NOT its own — so selecting a filter narrows what the other groups offer, while
    a multi-select group still lets you add more. Merged across the scope's libraries; duration is
    movie-only. (Search text is not factored in — facets track the sidebar filters.) `lang` is
    normalised here, after the empty answer."""
    empty = {
        "genres": [],
        "content_ratings": [],
        "studios": [],
        "playable": [],
        "year_min": None,
        "year_max": None,
        "rating_max": None,
        "duration_min": None,
        "duration_max": None,
    }
    all_movie_ids, all_show_ids = content_libs(db)
    movie_ids = all_movie_ids if scope in ("movie", "both") else []
    show_ids = all_show_ids if scope in ("show", "both") else []
    if not movie_ids and not show_ids:
        return empty
    lang = norm_lang(lang)
    p = f.as_dict()

    uid = user.id

    # The shows that pass the watch-state scope, asked ONCE. The per-user episode rollup behind it is a
    # full pass over the user's episodes (~10 ms on a prod-sized library), and each of the show groups
    # (genres, ratings, studios, years, rating max) asked it again: half of a filtered facets call.
    # The same filter on the same rows, so the counts do not change
    # (test_plex_facets_grid_parity).
    shows_in_scope: list[int] | None = None
    if show_ids and show in ("watched", "in_progress", "unwatched"):
        agg = rollup.agg_subquery(db, uid).subquery()
        in_scope = select(PlexShow.id).outerjoin(agg, agg.c.show_id == PlexShow.id)
        in_scope = apply_show_state_filter(
            in_scope,
            func.coalesce(agg.c.total, 0),
            func.coalesce(agg.c.watched, 0),
            func.coalesce(agg.c.inprog, 0),
            show,
        )
        shows_in_scope = list(db.scalars(in_scope.where(PlexShow.library_id.in_(show_ids))))

    def wsq(query, model, ids, pp, kind_movie, with_dur):
        """Apply the (self-excluded) metadata filters + library scope + the per-user watch-state to a
        facet aggregation query, so the facets reflect exactly the visible result set."""
        query = query.where(model.library_id.in_(ids), *meta_filter_conds(model, pp, lang))
        if kind_movie:
            query = query.where(model.kind == "movie")
            if with_dur and pp.get("duration_min") is not None:
                query = query.where(model.duration_s >= pp["duration_min"])
            if with_dur and pp.get("duration_max") is not None:
                query = query.where(model.duration_s <= pp["duration_max"])
            # Playback-class filter (movie-only) — applied for the OTHER groups so an active class
            # narrows them; the playable facet itself passes pp with playable=None (self-exclusion).
            query = query.where(*playable_conds(split_csv(pp.get("playable"))))
            # Join watch-state and reuse the grid's exact movie state filter (unified_library) —
            # hidden movies never appear in the grid, so they must not inflate facet counts/bounds either.
            st = aliased(PlexState)
            query = query.outerjoin(st, and_(st.item_id == model.id, owned_by(st.user_id, uid)))
            query = apply_movie_state_filter(query, st, show)
        elif shows_in_scope is not None:
            query = query.where(model.id.in_(shows_in_scope))
        return query

    genre_counts: dict[str, int] = {}
    cr_counts: dict[str, int] = {}
    studio_counts: dict[str, int] = {}
    playable_counts: dict[str, int] = {}
    years: list[int] = []
    ratings: list[float] = []
    durs: list[int] = []

    def per_table(model, ids, kind_movie: bool) -> None:
        if not ids:
            return
        # Genres — in "any"/OR mode, exclude the genre filter itself so each offered genre is a valid
        # OR-addition that only widens (keep adding). In "all"/AND mode, KEEP the filter applied so we
        # offer only genres that CO-OCCUR on the current result set — a non-co-occurring genre would AND
        # the result down to zero, i.e. a dead-end chip. (The already-selected genres still appear, since
        # every matching title carries them, so they stay togglable.)
        genre_pp = p if p.get("genre_mode") == "all" else {**p, "genres": None}
        # Only rows whose `genres` is a JSON array can be unnested. A genre-less item stores JSON
        # `null` (SQLAlchemy's JSONB persists a Python None as JSON null, not SQL NULL), and
        # jsonb_array_elements_text() raises on a scalar ("cannot extract elements from a scalar") —
        # so a single metadata-poor library (e.g. one bare Shows library with no genres) 500'd the
        # whole facets endpoint. Mirror the exact guard people.py already applies to the same columns.
        # In HU the vocabulary comes from the active-language genre column (coalesce(genres_hu, genres)).
        gcol = genres_col(model, lang)
        expanded = (
            wsq(
                select(func.jsonb_array_elements_text(gcol).label("g")),
                model,
                ids,
                genre_pp,
                kind_movie,
                True,
            )
            .where(func.jsonb_typeof(gcol) == "array")
            .subquery()
        )
        for g, c in db.execute(select(expanded.c.g, func.count()).group_by(expanded.c.g)).all():
            genre_counts[g] = genre_counts.get(g, 0) + c
        # Content ratings — exclude its own.
        crq = (
            wsq(
                select(model.content_rating, func.count()),
                model,
                ids,
                {**p, "content_ratings": None},
                kind_movie,
                True,
            )
            .where(model.content_rating.isnot(None))
            .group_by(model.content_rating)
        )
        for cr, c in db.execute(crq).all():
            cr_counts[cr] = cr_counts.get(cr, 0) + c
        # Studios — exclude its own (each offered studio is a valid OR-addition that only widens).
        stq = (
            wsq(
                select(model.studio, func.count()),
                model,
                ids,
                {**p, "studios": None},
                kind_movie,
                True,
            )
            .where(model.studio.isnot(None))
            .group_by(model.studio)
        )
        for s, c in db.execute(stq).all():
            studio_counts[s] = studio_counts.get(s, 0) + c
        # Playback class (movie-only) — exclude its own so each class stays an addable OR option.
        if kind_movie:
            pcls = playback_class_expr()
            pcq = (
                wsq(
                    select(pcls.label("cls"), func.count()),
                    model,
                    ids,
                    {**p, "playable": None},
                    kind_movie,
                    True,
                )
                .where(pcls.isnot(None))
                .group_by(pcls)
            )
            for cls, c in db.execute(pcq).all():
                playable_counts[cls] = playable_counts.get(cls, 0) + c
        # Year bounds — exclude the year filter.
        by = db.execute(
            wsq(
                select(func.min(model.year), func.max(model.year)),
                model,
                ids,
                {**p, "year_min": None, "year_max": None},
                kind_movie,
                True,
            )
        ).one()
        if by[0] is not None:
            years.append(by[0])
        if by[1] is not None:
            years.append(by[1])
        # Rating max — exclude the rating filter. Coalesce(imdb, audience) to match the score the
        # rating filter and the UI badge use (IMDb preferred, audience fallback).
        br = db.scalar(
            wsq(
                select(func.max(func.coalesce(model.imdb_rating, model.rating))),
                model,
                ids,
                {**p, "rating_min": None},
                kind_movie,
                True,
            )
        )
        if br is not None:
            ratings.append(float(br))
        # Duration bounds (movies) — exclude the duration filter.
        if kind_movie:
            bd = db.execute(
                wsq(
                    select(func.min(model.duration_s), func.max(model.duration_s)),
                    model,
                    ids,
                    p,
                    kind_movie,
                    False,
                )
            ).one()
            if bd[0] is not None:
                durs.append(bd[0])
            if bd[1] is not None:
                durs.append(bd[1])

    per_table(PlexItem, movie_ids, True)
    per_table(PlexShow, show_ids, False)
    # Always surface the actively-selected genres (even a zero-match AND combo, where they'd otherwise
    # be absent): the sidebar renders genres solely from this list and hides the whole genre section —
    # chips AND the Any/All toggle — when it's empty, which would trap the user with no per-chip way to
    # undo a zero-result selection. Count 0 is fine (genre chips don't display counts).
    for g in split_csv(f.genres):
        genre_counts.setdefault(g, 0)
    # Same for the actively-selected studios, so a selected studio stays removable even at zero matches.
    for s in split_csv(f.studios):
        studio_counts.setdefault(s, 0)
    # Keep an actively-selected playback class visible even at zero matches (the sidebar hides the whole
    # section when its facet list is empty, which would trap a zero-result selection with no way to undo).
    for c in split_csv(f.playable):
        if c in PLAYBACK_CLASSES:
            playable_counts.setdefault(c, 0)
    # Names in the reader's alphabet: the genres are Hungarian words for a Hungarian reader.
    alpha = {w: i for i, w in enumerate(sorted_words(db, [*genre_counts, *studio_counts], lang))}
    return {
        "genres": [
            {"value": g, "count": c}
            for g, c in sorted(genre_counts.items(), key=lambda kv: alpha[kv[0]])
        ],
        "content_ratings": [
            {"value": cr, "count": c} for cr, c in sorted(cr_counts.items(), key=lambda kv: -kv[1])
        ],
        "studios": [
            {"value": s, "count": c}
            for s, c in sorted(studio_counts.items(), key=lambda kv: (-kv[1], alpha[kv[0]]))
        ],
        # Fixed good→heavy order (not by count), so the class list reads as a severity scale.
        "playable": [
            {"value": c, "count": playable_counts[c]}
            for c in PLAYBACK_CLASSES
            if c in playable_counts
        ],
        "year_min": min(years) if years else None,
        "year_max": max(years) if years else None,
        "rating_max": max(ratings) if ratings else None,
        "duration_min": min(durs) if durs else None,
        "duration_max": max(durs) if durs else None,
    }