"""
Mehrstufiges Retrieval für Planungs-Übungssuche (Phase A).

Stufen:
  S1b-0  Gesamte sichtbare Bibliothek (Governance + Hard-Filter, kein Profil-OR-Pool)
  S1b-1  Deterministischer Hybrid-Score auf allen Kandidaten → sortiert
"""
from __future__ import annotations

from typing import Any, Dict, List, Mapping, Optional, Sequence, Set, Tuple

from planning_exercise_profiles import (
    PlanningTargetProfile,
    load_exercise_match_profiles_bulk,
    score_exercise_against_target,
)

_MAX_LIBRARY_ROWS = 8000
_PROFILE_LOAD_BATCH = 400


def _skill_jaccard(a: Set[int], b: Set[int]) -> float:
    if not a or not b:
        return 0.0
    inter = len(a & b)
    union = len(a | b)
    return inter / union if union else 0.0


def _normalize_exercise_kind_filter(exercise_kind_any: Optional[List[str]]) -> List[str]:
    out: List[str] = []
    if not exercise_kind_any:
        return out
    for raw in exercise_kind_any:
        s = str(raw or "").strip().lower()
        if s in ("simple", "combination") and s not in out:
            out.append(s)
    return out


def fetch_all_visible_exercise_rows(
    cur,
    *,
    vis_sql: str,
    vis_params: Sequence[Any],
    query: str,
    exercise_kind_any: Optional[List[str]],
    max_rows: int = _MAX_LIBRARY_ROWS,
) -> List[Dict[str, Any]]:
    """
    S1b-0: Alle sichtbaren Übungen (ohne Profil-/Volltext-Pool-Vorselektion).

    Hard-Filter: Governance, nicht archiviert, optional exercise_kind.
    Volltext-Rank nur als Score-Signal in SELECT, nicht als WHERE-Filter.
    """
    where = [vis_sql, "COALESCE(e.status, '') <> %s"]
    params: List[Any] = []

    if query:
        ft_select = "ts_rank_cd(e.search_vector, plainto_tsquery('german', %s)) AS ft_rank"
        params.append(query)
    else:
        ft_select = "0.0::float AS ft_rank"

    params.extend(vis_params)
    params.append("archived")

    ek_filtered = _normalize_exercise_kind_filter(exercise_kind_any)
    if ek_filtered:
        ph = ",".join(["%s"] * len(ek_filtered))
        where.append(f"(LOWER(TRIM(COALESCE(e.exercise_kind::text,''))) IN ({ph}))")
        params.extend(ek_filtered)

    sql = f"""
        SELECT e.id, e.title, e.summary,
               (
                 SELECT fa.name FROM exercise_focus_areas efa
                 JOIN focus_areas fa ON fa.id = efa.focus_area_id
                 WHERE efa.exercise_id = e.id
                 ORDER BY efa.is_primary DESC NULLS LAST, fa.name ASC
                 LIMIT 1
               ) AS primary_focus_name,
               {ft_select}
        FROM exercises e
        WHERE {' AND '.join(where)}
        ORDER BY e.id ASC
        LIMIT %s
    """
    params.append(int(max_rows))
    cur.execute(sql, params)
    return [dict(r) for r in cur.fetchall()]


def _load_match_profiles_chunked(cur, exercise_ids: Sequence[int], *, batch: int = _PROFILE_LOAD_BATCH):
    ids = sorted({int(x) for x in exercise_ids if int(x) > 0})
    if not ids:
        return {}
    out: Dict[int, Any] = {}
    for i in range(0, len(ids), batch):
        chunk = ids[i : i + batch]
        out.update(load_exercise_match_profiles_bulk(cur, chunk))
    return out


def _load_skill_sets_chunked(cur, exercise_ids: Sequence[int], *, batch: int = _PROFILE_LOAD_BATCH) -> Dict[int, Set[int]]:
    ids = sorted({int(x) for x in exercise_ids if int(x) > 0})
    out: Dict[int, Set[int]] = {eid: set() for eid in ids}
    if not ids:
        return out
    for i in range(0, len(ids), batch):
        chunk = ids[i : i + batch]
        ph = ",".join(["%s"] * len(chunk))
        cur.execute(
            f"SELECT exercise_id, skill_id FROM exercise_skills WHERE exercise_id IN ({ph})",
            chunk,
        )
        for row in cur.fetchall():
            eid = int(row["exercise_id"])
            sid = row.get("skill_id")
            if sid is not None:
                out.setdefault(eid, set()).add(int(sid))
    return out


def rank_visible_library_hits(
    cur,
    rows: Sequence[Dict[str, Any]],
    *,
    query: str,
    intent: str,
    intent_weights: Mapping[str, float],
    target: PlanningTargetProfile,
    pack: Mapping[str, Any],
) -> Tuple[List[Dict[str, Any]], Dict[int, Set[int]]]:
    """S1b-1: Hybrid-Score auf der gesamten sichtbaren Bibliothek."""
    planned_set = set(pack.get("planned_exercise_ids") or [])
    group_recent_set = set(pack.get("group_recent_exercise_ids") or [])
    progression_set = set(pack.get("progression_successor_ids") or [])
    anchor_skills = set(pack.get("anchor_skill_ids") or [])
    anchor_id = pack.get("anchor_exercise_id")
    progression_notes = pack.get("progression_edge_notes") or {}

    last_planned_skills: Set[int] = set()
    planned_ids = pack.get("planned_exercise_ids") or []
    if planned_ids:
        cur.execute(
            "SELECT skill_id FROM exercise_skills WHERE exercise_id = %s",
            (int(planned_ids[-1]),),
        )
        last_planned_skills = {int(r["skill_id"]) for r in cur.fetchall() if r.get("skill_id")}

    cand_rows: List[Dict[str, Any]] = []
    for row in rows:
        eid = int(row["id"])
        if anchor_id and eid == int(anchor_id):
            continue
        cand_rows.append(row)

    cand_ids = [int(r["id"]) for r in cand_rows]
    match_profiles = _load_match_profiles_chunked(cur, cand_ids)
    skills_by_ex = _load_skill_sets_chunked(cur, cand_ids)

    max_ft = 0.0
    scored_items: List[Dict[str, Any]] = []
    for row in cand_rows:
        eid = int(row["id"])
        ft = float(row.get("ft_rank") or 0.0)
        if ft > max_ft:
            max_ft = ft
        scored_items.append(
            {
                "row": row,
                "eid": eid,
                "ft": ft,
                "skills": skills_by_ex.get(eid, set()),
            }
        )

    weights = dict(intent_weights)
    hits: List[Dict[str, Any]] = []
    for item in scored_items:
        eid = item["eid"]
        row = item["row"]
        ft_norm = (item["ft"] / max_ft) if max_ft > 0 else 0.0
        prog_hit = 1.0 if eid in progression_set else 0.0
        skill_sim = _skill_jaccard(anchor_skills, item["skills"]) if anchor_skills else 0.0
        plan_aff = 0.0
        if last_planned_skills and item["skills"]:
            plan_aff = _skill_jaccard(last_planned_skills, item["skills"])
        repeat_unit = 1.0 if eid in planned_set else 0.0
        repeat_group = 1.0 if eid in group_recent_set else 0.0
        profile_score = 0.0
        profile_reasons: List[str] = []
        emp = match_profiles.get(eid)
        if emp:
            profile_score, profile_reasons = score_exercise_against_target(
                emp, target, intent=intent
            )

        score = (
            weights["fulltext"] * ft_norm
            + weights["progression"] * prog_hit
            + weights["skill"] * skill_sim
            + weights["plan"] * plan_aff
            + weights["profile"] * profile_score
            + weights["repeat_unit"] * repeat_unit
            + weights["repeat_group"] * repeat_group
        )

        reasons: List[str] = []
        if query and ft_norm >= 0.35:
            reasons.append("Volltext-Treffer")
        if prog_hit > 0:
            note = progression_notes.get(eid)
            reasons.append(
                f"Nachfolger im Progressionsgraph{f': {note}' if note else ''}"
            )
        if skill_sim >= 0.2 and anchor_id:
            reasons.append("Fähigkeiten passen zur Anker-Übung")
        if plan_aff >= 0.25:
            reasons.append("Schließt an Skills der letzten geplanten Übung an")
        if repeat_unit > 0:
            reasons.append("Bereits in dieser Einheit eingeplant")
        if repeat_group > 0 and repeat_unit <= 0:
            reasons.append("Kürzlich in der Gruppe verwendet")
        for pr in profile_reasons:
            if pr not in reasons:
                reasons.append(pr)

        if score <= 0 and not reasons and not query:
            if prog_hit or skill_sim or plan_aff or profile_score:
                score = 0.05 + prog_hit * 0.3 + skill_sim * 0.2 + profile_score * 0.25

        hits.append(
            {
                "id": eid,
                "title": row.get("title"),
                "summary": row.get("summary"),
                "focus_area": row.get("primary_focus_name"),
                "score": round(max(0.0, min(1.0, score)), 4),
                "reasons": reasons,
            }
        )

    hits.sort(key=lambda h: (-h["score"], h.get("title") or ""))
    return hits, skills_by_ex


def run_multistage_planning_retrieval(
    cur,
    *,
    vis_sql: str,
    vis_params: Sequence[Any],
    query: str,
    exercise_kind_any: Optional[List[str]],
    target: PlanningTargetProfile,
    intent: str,
    intent_weights: Mapping[str, float],
    pack: Mapping[str, Any],
) -> Tuple[List[Dict[str, Any]], Dict[int, Set[int]], bool]:
    """Orchestriert S1b-0 → S1b-1 (Voll-Library-Ranking)."""
    rows = fetch_all_visible_exercise_rows(
        cur,
        vis_sql=vis_sql,
        vis_params=vis_params,
        query=query,
        exercise_kind_any=exercise_kind_any,
    )
    hits, skills_by_ex = rank_visible_library_hits(
        cur,
        rows,
        query=query,
        intent=intent,
        intent_weights=intent_weights,
        target=target,
        pack=pack,
    )
    full_library_ranked = len(rows) > 0
    return hits, skills_by_ex, full_library_ranked


# Legacy-Alias für Tests / externe Imports
fetch_retrieval_candidate_rows = fetch_all_visible_exercise_rows
hybrid_score_planning_hits = rank_visible_library_hits


def profile_preselect_rows(
    cur,
    rows: Sequence[Dict[str, Any]],
    *,
    target: PlanningTargetProfile,
    intent: str,
    progression_successor_ids: Set[int],
    query: str,
    preselect_limit: int = 160,
) -> Tuple[List[Dict[str, Any]], bool]:
    """Deprecated: Phase A rankt die volle Library — keine separate Vorselektion."""
    _ = (cur, target, intent, progression_successor_ids, query, preselect_limit)
    return list(rows), False


__all__ = [
    "fetch_all_visible_exercise_rows",
    "fetch_retrieval_candidate_rows",
    "hybrid_score_planning_hits",
    "profile_preselect_rows",
    "rank_visible_library_hits",
    "run_multistage_planning_retrieval",
]