"""Smoke test for profile_schema mirror (#81 phase A).

The TS registry in services/api/src/profile/registry.ts is the source of truth.
This test checks the names listed here match the registry by reading the TS
file and grepping for `name: '...'`. Crude but cheap, and it catches the
common rename/add-without-mirror failure mode.
"""
from __future__ import annotations
import re
from pathlib import Path

from ml.features.profile_schema import PROFILE_FEATURES, feature_names


REGISTRY_PATH = Path(__file__).resolve().parents[2] / "services" / "api" / "src" / "profile" / "registry.ts"


def _ts_registry_names() -> set[str]:
    text = REGISTRY_PATH.read_text(encoding="utf-8")
    # Each FEATURES entry has `name: 'something_30d',`. Extract every match.
    return set(re.findall(r"name:\s*'([a-zA-Z0-9_]+)'", text))


def test_python_mirror_matches_ts_registry():
    py_names = feature_names()
    ts_names = _ts_registry_names()
    assert py_names == ts_names, (
        f"Profile feature names drifted between TS registry and Python mirror.\n"
        f"  in Python only: {sorted(py_names - ts_names)}\n"
        f"  in TS only:     {sorted(ts_names - py_names)}"
    )


def test_profile_schema_no_duplicates():
    names = [f.name for f in PROFILE_FEATURES]
    assert len(names) == len(set(names)), f"duplicate names: {names}"


def test_profile_schema_dtypes_known():
    for f in PROFILE_FEATURES:
        assert f.dtype in {"numeric", "categorical"}