import json

from fam_edge.oracle_db import OracleDB
from fam_edge.person_service import PersonService


def _service(tmp_path):
    db = OracleDB(str(tmp_path / "oracle.db"))
    svc = PersonService.__new__(PersonService)  # 跳过 __init__（不需要真的建 LLM 适配器）
    svc.db = db
    return svc, db


def _insert_event(db, video_id, appearances):
    db._conn.execute(
        "INSERT INTO events (video_id, ts, description, person_appearances_json) "
        "VALUES (?, ?, ?, ?)",
        (video_id, "2026-08-21 00:00:00", "desc", json.dumps(appearances, ensure_ascii=False)))
    db._conn.commit()


def test_aggregate_features_merges_same_gender_across_videos(tmp_path):
    svc, db = _service(tmp_path)
    _insert_event(db, 1, [{"uid": "人物A", "features": {"gender": "男", "hair": "短发黑色"}}])
    _insert_event(db, 2, [{"uid": "人物A", "features": {"gender": "男", "clothing": "蓝色T恤"}}])
    result = svc._aggregate_features()
    assert set(result.keys()) == {"人物A"}
    assert result["人物A"]["hair"] == "短发黑色"
    assert result["人物A"]["clothing"] == "蓝色T恤"


def test_aggregate_features_splits_gender_conflict_across_videos(tmp_path):
    """核心场景: 复现 "人物A" 在 29 个视频里混了男女两个人的真实 bug——不同视频各自
    独立编号的 uid，字符串相同不代表同一个真人，性别冲突时必须拆成独立分组。"""
    svc, db = _service(tmp_path)
    _insert_event(db, 1, [{"uid": "人物A", "features": {"gender": "男", "clothing": "蓝色Polo衫"}}])
    _insert_event(db, 2, [{"uid": "人物A", "features": {"gender": "女", "clothing": "白色上衣"}}])
    result = svc._aggregate_features()
    assert set(result.keys()) == {"人物A", "人物A#2"}
    assert result["人物A"]["gender"] == "男"
    assert result["人物A#2"]["gender"] == "女"


def test_aggregate_features_unknown_gender_joins_first_group(tmp_path):
    svc, db = _service(tmp_path)
    _insert_event(db, 1, [{"uid": "人物A", "features": {"gender": "男"}}])
    _insert_event(db, 2, [{"uid": "人物A", "features": {"gender": "unknown", "hair": "光头"}}])
    result = svc._aggregate_features()
    assert set(result.keys()) == {"人物A"}
    assert result["人物A"]["gender"] == "男"
    assert result["人物A"]["hair"] == "光头"


def test_aggregate_features_three_way_gender_reuse_creates_three_groups(tmp_path):
    svc, db = _service(tmp_path)
    _insert_event(db, 1, [{"uid": "人物B", "features": {"gender": "男"}}])
    _insert_event(db, 2, [{"uid": "人物B", "features": {"gender": "女"}}])
    _insert_event(db, 3, [{"uid": "人物B", "features": {"gender": "男"}}])  # 应并回第一组
    result = svc._aggregate_features()
    assert set(result.keys()) == {"人物B", "人物B#2"}
    assert result["人物B"]["gender"] == "男"
    assert result["人物B#2"]["gender"] == "女"


def test_aggregate_features_ignores_placeholder_uids(tmp_path):
    svc, db = _service(tmp_path)
    _insert_event(db, 1, [{"uid": "无人", "features": {"gender": "男"}}])
    _insert_event(db, 2, [{"uid": "", "features": {"gender": "男"}}])
    result = svc._aggregate_features()
    assert result == {}