"""回归测试:锁定 P0 三项「静默失效」缺陷不再复发。

这些用例不依赖数据库 —— 它们用静态分析检查代码结构,
因为三个 P0 的本质都是「集成方式错误」,在 mock 掉 slice_fn /
provider 的单元测试里永远照不出来(这正是它们当初漏网的原因)。

- P0-1/P0-2: 查询 Match 的函数必须 eager-load 切片会访问的关系
- P0-3: bzzoiro 写 source_event_id 时用的 raw 必须与 nm 配对
"""
from __future__ import annotations

import re
from pathlib import Path

SRC = Path(__file__).resolve().parent.parent / "src"

# 切片函数会读取的关系属性 → 查询时必须 eager-load
MATCH_RELATIONS = ("stats", "home_team", "away_team", "league")


def _read(rel: str) -> str:
    return (SRC / rel).read_text(encoding="utf-8")


class TestEagerLoadCoverage:
    """P0-1 / P0-2: 凡是 select(Match) 且后续访问关系的函数,必须有 eager-load。"""

    def test_context_builder_getters_eager_load(self):
        """_get_form / _get_h2h / _get_home_away 必须预加载关系。

        models.py 已声明 lazy="selectin" 兜底,但这里同时检查显式
        selectinload —— 显式声明是查询意图的固化,也被 P0 修复所依赖。
        """
        src = _read("llm/context_builder.py")
        for fn in ("_get_form", "_get_h2h", "_get_home_away"):
            # 截取函数体
            m = re.search(rf"async def {fn}\(.*?(?=\nasync def |\n# =|\Z)", src, re.S)
            assert m, f"{fn} 未找到"
            body = m.group(0)
            assert "selectinload" in body, (
                f"{fn} 查询 Match 但未 eager-load 关系 —— "
                "this would raise MissingGreenlet in async SQLAlchemy (P0-2)"
            )

    def test_backtest_candidates_eager_load(self):
        """回测取历史比赛必须 eager-load(否则 session 关闭后访问关系必炸)。"""
        src = _read("llm/backtest.py")
        assert "selectinload" in src, "backtest 未 eager-load 关系 (P0-1)"

    def test_relationship_default_is_selectin(self):
        """models.py 中 Match 的高频关系应声明 lazy='selectin' 作为兜底。"""
        src = _read("db/models.py")
        # 找到 Match 类定义段
        m = re.search(r"class Match\(Base\):.*?(?=\nclass )", src, re.S)
        assert m, "Match 类未找到"
        body = m.group(0)
        for rel in MATCH_RELATIONS:
            # 关系声明可能跨多行(stats/home_team/away_team 都是),因此按
            # 「从 `rel: Mapped` 到下一个 `xxx: Mapped` 之前」整段匹配。
            m_rel = re.search(
                rf"^\s*{rel}: Mapped.*?(?=^\s*\w+: Mapped|\Z)", body, re.M | re.S
            )
            assert m_rel, f"Match.{rel} 未找到"
            assert 'lazy="selectin"' in m_rel.group(0), (
                f"Match.{rel} 未声明 lazy='selectin' —— 兜底缺失 (P0-2)"
            )


class TestBzzoiroLineage:
    """P0-3: source_event_id 必须取配对的 raw,不能是循环残留变量。"""

    def test_normalized_matches_carries_raw(self):
        src = _read("data/bzzoiro.py")
        # 规范化结果必须与原始 event 成对保存
        assert "normalized_matches.append((nm, raw))" in src, (
            "normalized_matches 未携带 (nm, raw) 元组 —— raw 变量泄漏会回归 (P0-3)"
        )
        # 内层消费循环必须解包成对变量
        assert re.search(r"for nm, raw in normalized_matches", src), (
            "消费循环未解包 (nm, raw) —— 血缘字段会取到错误 event (P0-3)"
        )

    def test_no_orphan_raw_use(self):
        """source_event_id 所在行必须在解包循环内(用缩进 + 上下文粗判)。"""
        src = _read("data/bzzoiro.py")
        lines = src.splitlines()
        # 找到 "for nm, raw in normalized_matches" 所在行号
        start = next(
            (i for i, ln in enumerate(lines) if "for nm, raw in normalized_matches" in ln),
            None,
        )
        assert start is not None
        # 该循环之后、下一个同/更低缩进的顶层语句之前的范围
        seg = "\n".join(lines[start:])
        uses = [ln for ln in seg.splitlines() if "source_event_id" in ln]
        assert uses, "未找到 source_event_id 赋值"
        assert all("raw.get(" in ln for ln in uses), (
            "source_event_id 未使用配对的 raw (P0-3)"
        )