#!/usr/bin/env python3
"""
identity.py — provider-agnostic match keys.

The pipeline output and the ground truth may not share one id space: an output
actor can carry only tmdb/jellyfin ids while X-Ray/MovieNet key on IMDb nm-ids.
We represent each actor by the *set* of every key we can derive, and treat two
actors as the same iff their key sets intersect. Namespacing each key by its
provider prevents cross-provider collisions (e.g. an nm-number equalling a
tmdb-number).
"""

from __future__ import annotations

import re
import unicodedata


def norm_name(name: str | None) -> str | None:
    """Lowercased, accent-stripped, punctuation-free name for fuzzy fallback match."""
    if not name:
        return None
    s = unicodedata.normalize("NFKD", name)
    s = "".join(c for c in s if not unicodedata.combining(c))
    s = re.sub(r"[^a-z0-9 ]+", "", s.lower()).strip()
    s = re.sub(r"\s+", " ", s)
    return s or None


def keys_for(imdb_id: str | None = None,
             tmdb_id: str | None = None,
             jellyfin_id: str | None = None,
             name: str | None = None,
             crosswalk=None) -> set[str]:
    """All identity tokens for one actor. Empty strings are ignored.

    If `crosswalk` (a CrosswalkTable) is given and no imdb_id is present, resolve
    tmdb_id → imdb_id through it so a tmdb-only actor still gets an exact `imdb:`
    key — turning the fuzzy name join into an exact id join. See tmdb_imdb_map.py.
    """
    keys: set[str] = set()
    imdb = imdb_id.strip() if (imdb_id and imdb_id.strip()) else None
    if not imdb and crosswalk is not None and tmdb_id:
        imdb = crosswalk.imdb_for(tmdb_id)
    if imdb:
        keys.add(f"imdb:{imdb}")
    if tmdb_id and str(tmdb_id).strip():
        keys.add(f"tmdb:{str(tmdb_id).strip()}")
    if jellyfin_id and jellyfin_id.strip():
        keys.add(f"jf:{jellyfin_id.strip()}")
    nn = norm_name(name)
    if nn:
        keys.add(f"name:{nn}")
    return keys