ggx/tests/test_cli_contract.py

"""CLI 接口契约测试。

**为什么需要**：使用手册（``docs/user-guide.md``）里的命令就是用户看到的接口。
文档与实现脱节是极易发生且很难察觉的问题 —— 实测发现手册记载的
``hdiv sync financial --interleaved`` 在 CLI 中根本没有暴露，
而 ``hdiv ddl verify`` 的输出格式也与手册不符。

本测试把「手册承诺的接口」变成可执行断言：
只要有人删掉一个参数或改掉命令名，测试立刻失败。
"""

from __future__ import annotations

import pandas as pd
import pytest

from hdiv.cli import build_parser


@pytest.fixture(scope="module")
def parser():
    return build_parser()


def _subparsers(p):
    """取子命令表。同时支持两种声明方式：

    - ``add_subparsers()`` → choices 是 dict（sync/universe/...）
    - ``add_argument("action", choices=[...])`` → choices 是 list（ddl/report/strategy）
    """
    for action in p._actions:
        ch = getattr(action, "choices", None)
        if not ch:
            continue
        if isinstance(ch, dict):
            return ch
    raise AssertionError("未找到子命令")


def _action_choices(p) -> set[str]:
    """取位置参数（如 ddl 的 plan/apply/verify）的取值集合。"""
    for action in p._actions:
        ch = getattr(action, "choices", None)
        if isinstance(ch, (list, tuple, set)) and not action.option_strings:
            return set(ch)
    return set()


def _opts(p) -> set[str]:
    out: set[str] = set()
    for a in p._actions:
        out.update(a.option_strings)
    return out


# ---------------------------------------------------------------------------
# 手册记载的顶层命令必须全部存在
# ---------------------------------------------------------------------------

DOCUMENTED_COMMANDS = [
    "ddl", "sync", "audit", "report", "universe",
    "profile", "strategy", "backtest", "sensitivity",
    "web", "site",
]


def test_all_documented_commands_exist(parser) -> None:
    subs = _subparsers(parser)
    missing = [c for c in DOCUMENTED_COMMANDS if c not in subs]
    assert not missing, f"手册记载但 CLI 不存在的命令：{missing}"


def test_no_undocumented_commands(parser) -> None:
    """反向检查：CLI 不应有手册未提及的命令。"""
    subs = set(_subparsers(parser))
    extra = subs - set(DOCUMENTED_COMMANDS)
    assert not extra, f"CLI 存在手册未记载的命令：{sorted(extra)}"


# ---------------------------------------------------------------------------
# 手册记载的动作/参数必须存在
# ---------------------------------------------------------------------------


@pytest.mark.parametrize(
    "cmd,expected",
    [
        ("ddl", {"plan", "apply", "verify"}),
        ("report", {"index", "validate"}),
        ("strategy", {"validate", "register", "list", "diff"}),
        (
            "sync",
            {"dividend", "financial", "index", "price", "trading", "backfill"},
        ),
        ("site", {"normalize", "archive", "build", "status"}),
    ],
)
def test_documented_actions_exist(parser, cmd: str, expected: set[str]) -> None:
    sub = _subparsers(parser)[cmd]
    actual = _action_choices(sub)
    if not actual:  # 用 add_subparsers 声明的命令
        actual = set(_subparsers(sub))
    missing = expected - actual
    assert not missing, f"hdiv {cmd} 缺少手册记载的动作：{sorted(missing)}"


@pytest.mark.parametrize(
    "cmd,flags",
    [
        ("sync", {"--only-missing", "--limit", "--symbols", "--apis",
                  "--interleaved", "--start", "--end", "--no-resume", "--no-weight",
                  "--basic-start", "--basic-end"}),
        ("universe", {"-c", "--config", "--asof", "--no-persist", "--no-html"}),
        ("profile", {"--universe-run", "--symbols", "--asof", "--html-limit"}),
        ("backtest", {"-s", "--strategy", "--mode", "--start", "--end", "--universe-run",
                      "--allow-lookahead-universe"}),
        ("sensitivity", {"-s", "--strategy", "--sweep"}),
        ("strategy", {"-f", "--file", "--other"}),
        ("audit", {"--no-persist", "--no-html"}),
        ("report", {"--dir"}),
        ("web", {"--host", "--port", "--api-only", "--out-dir"}),
    ],
)
def test_documented_flags_exist(parser, cmd: str, flags: set[str]) -> None:
    sub = _subparsers(parser)[cmd]
    have = _opts(sub)
    missing = flags - have
    assert not missing, f"hdiv {cmd} 缺少手册记载的参数：{sorted(missing)}"


def test_sync_interleaved_is_a_real_flag(parser) -> None:
    """回归：手册要求 ``hdiv sync financial --interleaved``，CLI 必须真的支持。"""
    sub = _subparsers(parser)["sync"]
    assert "--interleaved" in _opts(sub)
    # 且必须真的能解析（不只是声明）
    args = parser.parse_args(["sync", "financial", "--interleaved"])
    assert args.interleaved is True
    args2 = parser.parse_args(["sync", "financial"])
    assert args2.interleaved is False


def test_backtest_universe_run_flag(parser) -> None:
    """股票池 ↔ 回测 的关联入口：``--universe-run`` 必须存在且可解析。"""
    args = parser.parse_args(["backtest", "--universe-run", "abc123"])
    assert args.universe_run == "abc123"
    assert args.allow_lookahead_universe is False, "默认不得放行未来函数"
    args2 = parser.parse_args(["backtest"])
    assert args2.universe_run is None


def test_backtest_lookahead_override_flag(parser) -> None:
    """放行未来函数必须是一个显式开关，不能是默认行为。"""
    a = parser.parse_args(
        ["backtest", "--universe-run", "abc123", "--allow-lookahead-universe"]
    )
    assert a.allow_lookahead_universe is True


@pytest.mark.db
def test_frozen_universe_is_used_when_run_id_given() -> None:
    """显式放行时，冻结股票池在各调仓日必须完全相同。"""
    from datetime import date

    from hdiv.backtest.engine import BacktestEngine
    from hdiv.core.config import load_config
    from hdiv.data import db

    db.load_dotenv_once()
    try:
        cfg = load_config("datasource")
        df = db.read_sql(
            "SELECT run_id FROM hd_universe_run WHERE deleted_at IS NULL "
            "ORDER BY created_at DESC LIMIT 1", cfg=cfg,
        )
        if df.empty:
            pytest.skip("没有筛选记录")
        rid = df["run_id"].iloc[0]
    except Exception as exc:
        pytest.skip(f"数据库不可用：{exc}")

    eng = BacktestEngine.from_strategy(
        "config/strategy/high_dividend_v1.yml", universe_run_id=rid,
        allow_lookahead_universe=True,
    )
    assert eng.universe_run_id == rid
    ctx = eng._prepare(eng.repo.trading_days(date(2024, 1, 1), date(2024, 6, 28)),
                       verbose=False)
    sets = list(ctx["universe_by_refresh"].values())
    assert sets, "应产生股票池"
    assert all(x == sets[0] for x in sets), "冻结股票池在各调仓日必须完全相同"


@pytest.mark.db
def test_future_universe_is_rejected_by_default() -> None:
    """回归：股票池 asof 晚于回测起点 = 未来函数，必须默认拒绝。

    早期实现允许用 2025 年选出的股票池跑 2015 起的单次回测，2015-01-06
    就按那份事后名单成交 —— 与 walk-forward 已明确拒绝的做法自相矛盾。
    """
    from datetime import date

    from hdiv.backtest.engine import BacktestEngine
    from hdiv.core.config import load_config
    from hdiv.core.errors import HdivError
    from hdiv.data import db

    db.load_dotenv_once()
    try:
        cfg = load_config("datasource")
        df = db.read_sql(
            "SELECT run_id, asof_date FROM hd_universe_run WHERE deleted_at IS NULL "
            "ORDER BY asof_date DESC LIMIT 1", cfg=cfg,
        )
        if df.empty:
            pytest.skip("没有筛选记录")
        rid = df["run_id"].iloc[0]
        uasof = pd.to_datetime(df["asof_date"].iloc[0]).date()
    except Exception as exc:
        pytest.skip(f"数据库不可用：{exc}")

    eng = BacktestEngine.from_strategy(
        "config/strategy/high_dividend_v1.yml", universe_run_id=rid
    )
    early = date(uasof.year - 5, 1, 1)
    with pytest.raises(HdivError) as ei:
        eng._prepare(eng.repo.trading_days(early, date(uasof.year - 5, 3, 31)), verbose=False)
    msg = str(ei.value)
    assert "晚于回测起点" in msg
    assert "--allow-lookahead-universe" in msg, "错误信息必须给出放行开关"

    # 起点晚于股票池 asof 时是合法的：此时股票池属于「事前信息」
    later = date(uasof.year + 1, 1, 2)
    eng2 = BacktestEngine.from_strategy(
        "config/strategy/high_dividend_v1.yml", universe_run_id=rid
    )
    days = eng2.repo.trading_days(later, date(later.year, 3, 31))
    if len(days) >= 2:
        ctx = eng2._prepare(days, verbose=False)
        assert ctx["universe_by_refresh"], "asof 不晚于起点时应正常使用该股票池"
        assert eng2.lookahead_universe_note is None


def test_backtest_mode_choices(parser) -> None:
    """手册只承诺 single / walkforward 两种模式。"""
    sub = _subparsers(parser)["backtest"]
    for a in sub._actions:
        if "--mode" in a.option_strings:
            assert set(a.choices) == {"single", "walkforward"}
            return
    raise AssertionError("backtest 缺少 --mode 参数")


def test_price_which_choices(parser) -> None:
    sub = _subparsers(parser)["sync"]
    for a in sub._actions:
        if "--which" in a.option_strings:
            assert set(a.choices) == {"daily", "adj_factor", "daily_basic"}
            return
    raise AssertionError("sync 缺少 --which 参数")


# ---------------------------------------------------------------------------
# 手册记载的输出格式
# ---------------------------------------------------------------------------


def test_ddl_verify_output_mentions_table_count() -> None:
    """手册写的是「OK：30 张 hd_* 表结构全部符合 schema 定义」，输出须含数量。"""
    import inspect

    from hdiv import cli
    from hdiv.data.schema import ALL_TABLES

    src = inspect.getsource(cli.cmd_ddl)
    assert "len(ddl.ALL_TABLES)" in src, "ddl verify 输出应包含表的数量"
    assert len(ALL_TABLES) == 30


def test_help_text_is_chinese(parser) -> None:
    """手册面向中文用户，所有命令都应有中文说明。"""
    subs = _subparsers(parser)
    for name in DOCUMENTED_COMMANDS:
        assert subs[name].description, f"hdiv {name} 缺少说明文字"


# ---------------------------------------------------------------------------
# 手册文件本身
# ---------------------------------------------------------------------------


def test_user_guide_exists_and_covers_all_commands() -> None:
    from hdiv.core.paths import project_root

    guide = project_root() / "docs" / "user-guide.md"
    assert guide.is_file(), "缺少使用手册 docs/user-guide.md"
    text = guide.read_text(encoding="utf-8")
    for cmd in DOCUMENTED_COMMANDS:
        assert f"hdiv {cmd}" in text, f"手册未记载命令：hdiv {cmd}"
    # 手册必须如实记录已知限制与部署要求（这两点最容易在文档里被淡化）
    assert "已知限制" in text
    assert "echarts.min.js" in text, "手册必须说明图表库的部署依赖"
    assert "asset_mode" in text, "手册必须说明自包含模式的开关"
    # 前后端分离的部署要点必须在手册里
    assert "/api" in text, "手册必须说明 API 反代"
    assert "nginx" in text, "手册必须给出 nginx 配置指引"


# ---------------------------------------------------------------------------
# 参数组合与错误呈现
# ---------------------------------------------------------------------------


# 只有这三个命令同时具备 --no-persist 与 --html（audit 传内存结果，两者可共存）
@pytest.mark.parametrize("cmd", ["universe", "backtest"])
def test_no_persist_with_html_is_rejected_clearly(cmd: str) -> None:
    """回归：--no-persist 与 --html 互相矛盾，必须给出可操作提示。

    静态报告只从数据库读取（保证数字可追溯到 SQL），未落库的运行渲染不出来。
    早期实现会崩在报告生成器的 ValueError 里，用户看不出是参数冲突。
    """
    import subprocess
    import sys

    r = subprocess.run(
        [sys.executable, "-m", "hdiv", cmd, "--no-persist", "--html"],
        capture_output=True, text=True, env={**__import__("os").environ, "PYTHONPATH": "src"},
    )
    assert r.returncode == 1
    out = r.stdout + r.stderr
    assert "--no-persist 与 --html 不能同时使用" in out, out[:400]
    # 必须是友好提示，而不是 traceback
    assert "Traceback" not in out, "用户可理解的错误不应打印调用栈"


def test_audit_can_combine_no_persist_and_html() -> None:
    """audit 传的是内存结果而非按 run_id 读库，因此两者可以共存。"""
    import inspect

    from hdiv import cli

    src = inspect.getsource(cli.cmd_audit)
    assert "_reject_no_persist_with_html" not in src, \
        "audit 不需拦截该组合（报告用内存 summary 渲染）"


def test_hdiv_error_is_caught_without_traceback() -> None:
    """main() 应优雅处理 HdivError（数据缺失/配置冲突等），不打印调用栈。"""
    import inspect

    from hdiv import cli

    src = inspect.getsource(cli.main)
    assert "except HdivError" in src, "main() 未捕获 HdivError"
    branch = src.split("except HdivError")[1]
    assert "print_exc" not in branch, "HdivError 分支不应打印调用栈"
    assert "return 1" in branch, "应返回非零退出码"


def test_html_flag_exists_on_all_report_producing_commands() -> None:
    """所有会产出报告的命令都应有 --html 开关且默认关闭。"""
    from hdiv.cli import build_parser

    p = build_parser()
    for cmd in ("universe", "profile", "backtest", "audit", "sensitivity"):
        args = p.parse_args([cmd])
        assert getattr(args, "html", None) is False, f"hdiv {cmd} --html 默认应为 False"


def test_walkforward_rejects_universe_run() -> None:
    """回归：--universe-run 与 walk-forward 时序不兼容，必须明确拒绝。

    股票池自带 asof（如 2025-01-21），而 walk-forward 窗口从 2015 年就开始训练；
    把未来时点选出的股票池套到更早的窗口上等于用未来信息选股。
    早期实现没有该参数，于是 --universe-run 被**静默忽略** ——
    用户以为按自己的股票池跑了，实际跑的是逐窗口自筛选。
    """
    import os
    import subprocess
    import sys

    r = subprocess.run(
        [sys.executable, "-m", "hdiv", "backtest",
         "--universe-run", "whatever", "--mode", "walkforward"],
        capture_output=True, text=True,
        env={**os.environ, "PYTHONPATH": "src"},
    )
    assert r.returncode == 1
    out = r.stdout + r.stderr
    assert "不支持 --universe-run" in out, out[:400]
    assert "未来" in out, "应说明原因（未来函数）"
    assert "Traceback" not in out


def test_walkforward_runner_has_no_universe_param() -> None:
    """再确认一层：runner 本身不接受冻结股票池，避免日后被误加回去。"""
    import inspect

    from hdiv.backtest.walk_forward import WalkForwardRunner

    sig = inspect.signature(WalkForwardRunner.__init__)
    assert "universe_run_id" not in sig.parameters, (
        "WalkForwardRunner 不应接受 universe_run_id —— "
        "冻结股票池与 walk-forward 的时序纪律冲突"
    )


def test_no_future_warning_on_selector() -> None:
    """回归：object 列的 fillna 曾触发 pandas Downcasting FutureWarning。

    用 -W error::FutureWarning 跑一遍筛选路径，确保不再产生该警告
    （pandas 未来版本会改变行为，届时结果可能静默变化）。
    """
    import os
    import subprocess
    import sys

    r = subprocess.run(
        [sys.executable, "-W", "error::FutureWarning", "-m", "hdiv",
         "universe", "--asof", "2025-03-21", "--no-persist", "--no-html"],
        capture_output=True, text=True,
        env={**os.environ, "PYTHONPATH": "src"}, timeout=600,
    )
    assert "FutureWarning" not in (r.stdout + r.stderr), \
        f"仍存在 FutureWarning：{(r.stdout + r.stderr)[-400:]}"