"""QlibEngine 数据管线测试：落盘格式、D.features 读回、端到端回测（合成数据、临时 qlib 目录）。"""

from __future__ import annotations

from datetime import date
from pathlib import Path

import numpy as np
import pandas as pd
import pytest
from app.domain.entities.research import ResearchSpec, UniverseSpec
from app.quant.qlib_adapter.dataset import load_close_panel
from app.quant.qlib_adapter.engine import QlibEngine
from app.quant.qlib_adapter.provider import build_qlib_dataset

from conftest_quant import synthetic_daily


def _daily5(n: int = 220) -> pd.DataFrame:
    drifts = {
        "600519.SH": 0.004,
        "600036.SH": 0.002,
        "601318.SH": 0.001,
        "000001.SZ": -0.001,
        "600030.SH": -0.003,
    }
    return synthetic_daily(drifts, n=n)


def _spec(**kw) -> ResearchSpec:
    base = dict(
        type="backtest",
        universe=UniverseSpec(exclude_st=False, min_listing_days=0),
        factors=[{"name": "momentum_60", "weight": 1.0}],
        selection={"top_n": 2},
        rebalance="monthly",
        period=(date(2024, 5, 1), date(2024, 8, 31)),
    )
    base.update(kw)
    return ResearchSpec.model_validate(base)


class TestProviderFormat:
    def test_bin_has_start_index_header(self, tmp_path: Path) -> None:
        daily = synthetic_daily({"600519.SH": 0.003, "600036.SH": -0.001}, n=200)
        uri = build_qlib_dataset(daily, tmp_path)

        cal = (uri / "calendars" / "day.txt").read_text().strip().splitlines()
        assert len(cal) == 200
        inst_line = (uri / "instruments" / "all.txt").read_text().strip().splitlines()[0]
        assert inst_line.count("\t") == 2  # 3 列，无 TYPE 列

        # 落盘目录用小写 instrument；bin 首 4 字节 = 起始日历下标
        raw = (uri / "features" / "600519.sh" / "close.day.bin").read_bytes()
        assert np.frombuffer(raw[:4], dtype="<f")[0] == pytest.approx(0.0)
        assert len(raw) // 4 - 1 == 200  # 数据长度 = 日历交易日数

    def test_bin_with_late_listing(self, tmp_path: Path) -> None:
        daily = synthetic_daily({"600000.SH": 0.002, "600001.SH": 0.001}, n=120)
        days = daily["trade_date"].unique()
        merged = pd.concat(
            [
                daily[daily["symbol"] == "600000.SH"],
                daily[(daily["symbol"] == "600001.SH") & (daily["trade_date"] >= days[50])],
            ]
        )
        uri = build_qlib_dataset(merged, tmp_path)
        raw = (uri / "features" / "600001.sh" / "close.day.bin").read_bytes()
        assert np.frombuffer(raw[:4], dtype="<f")[0] == pytest.approx(50.0)


class TestQlibDatasetRead:
    def test_load_close_panel_roundtrip(self, tmp_path: Path) -> None:
        daily = synthetic_daily({"600519.SH": 0.003, "600036.SH": -0.001}, n=120)
        uri = build_qlib_dataset(daily, tmp_path)
        panel = load_close_panel(
            uri, ["600519.SH", "600036.SH"], date(2024, 2, 1), date(2024, 5, 31)
        )
        assert len(panel) > 0
        assert set(panel.columns) == {"600519.SH", "600036.SH"}

        src = daily[daily["symbol"] == "600519.SH"].set_index("trade_date")["close"]
        src.index = pd.to_datetime(src.index)
        target = panel["600519.SH"]
        overlap = src.index.intersection(target.index)
        assert len(overlap) > 10
        rel = (target.loc[overlap] / src.loc[overlap].astype(float) - 1).abs().max()
        assert rel < 1e-3  # qlib 存储为 float32，允许微小舍入


class TestQlibEngine:
    def test_backtest_via_qlib_pipeline(self, tmp_path: Path) -> None:
        daily = _daily5()
        result = QlibEngine(qlib_dir=tmp_path).run_backtest(daily, _spec())

        assert result.summary.total_return_pct > 0  # 强趋势下动量择股盈利
        assert len(result.equity_curve) > 50
        assert any("QlibEngine v1" in u for u in result.unimplemented)
        assert result.config_snapshot["factors"][0]["name"] == "momentum_60"
        assert (tmp_path / "features").is_dir()  # 数据确实落盘到 qlib 目录

    def test_factor_test_shared_path(self, tmp_path: Path) -> None:
        daily = _daily5()
        spec = _spec()
        spec.type = "factor_test"
        report = QlibEngine(qlib_dir=tmp_path).run_factor_test(daily, spec)
        assert report.factor_name == "momentum_60"
        assert report.sample_days > 5
        assert report.ic_mean > 0  # 5 只强趋势股票的截面动量 IC 为正