"""Scoring kandydat ↔ kandydat dla pipeline'u dedup."""
from __future__ import annotations

import uuid
from collections.abc import Iterable

from sqlalchemy import select
from sqlalchemy.orm import Session

from app.models.scene import Scene, SceneFingerprint, ScenePerformer
from app.normalize.scenes import NormalizedScene
from app.resolve.scoring import (
    ScoreBreakdown,
    composite_score,
    date_proximity,
    duration_proximity,
    performer_set_similarity,
    phash_similarity,
    title_similarity,
)


def score_candidate(
    session: Session,
    *,
    candidate: Scene,
    norm: NormalizedScene,
    resolved_performer_ids: Iterable[uuid.UUID],
    studio_id: uuid.UUID | None,
    aggregator_mode: bool = False,
) -> ScoreBreakdown:
    """Liczy ScoreBreakdown dla pary (kandydat z DB, znormalizowana scena z importu).

    `aggregator_mode=True` dla scen pochodzących z tube/agregatora (np. pornapp): studio
    nie jest informatywne (tube agreguje wiele studiów), performers stają się głównym
    sygnałem — patrz `composite_score` szczegóły.
    """

    fp = _best_phash_similarity(session, candidate.id, norm.fingerprints)
    title = title_similarity(candidate.title_normalized, norm.title_normalized)
    cand_perfs = _candidate_performer_ids(session, candidate.id)
    perf = performer_set_similarity(cand_perfs, list(resolved_performer_ids)) if (cand_perfs or list(resolved_performer_ids)) else None
    date_score = date_proximity(candidate.release_date, norm.release_date)
    duration_score = duration_proximity(candidate.duration_sec, norm.duration_sec)

    studio_match: bool | None
    if studio_id is None or candidate.studio_id is None:
        studio_match = None  # nieinformatywne
    else:
        studio_match = candidate.studio_id == studio_id

    composite, reasons = composite_score(
        fp=fp,
        title=title,
        performers=perf,
        date_score=date_score if (candidate.release_date and norm.release_date) else None,
        duration_score=duration_score,
        studio_match=studio_match,
        aggregator_mode=aggregator_mode,
    )

    breakdown = ScoreBreakdown(
        fp=fp,
        title=title,
        performers=perf,
        date=date_score,
        duration=duration_score,
        studio_match=studio_match,
        composite=composite,
        reasons=reasons,
    )
    return breakdown


def _best_phash_similarity(
    session: Session,
    scene_id: uuid.UUID,
    incoming_fingerprints: list[tuple[str, str]],
) -> float | None:
    """Najlepsza similarity między phashami sceny w DB a incoming."""
    incoming = [v for kind, v in incoming_fingerprints if kind == "phash"]
    if not incoming:
        return None
    existing = (
        session.execute(
            select(SceneFingerprint.value).where(
                SceneFingerprint.scene_id == scene_id,
                SceneFingerprint.kind == "phash",
            )
        )
        .scalars()
        .all()
    )
    if not existing:
        return None
    best = 0.0
    for left in incoming:
        for right in existing:
            if len(left) != len(right):
                continue
            try:
                sim = phash_similarity(left, right)
            except ValueError:
                continue
            if sim > best:
                best = sim
    return best


def _candidate_performer_ids(session: Session, scene_id: uuid.UUID) -> list[uuid.UUID]:
    return list(
        session.execute(
            select(ScenePerformer.performer_id).where(ScenePerformer.scene_id == scene_id)
        )
        .scalars()
        .all()
    )