"""Tests for the matching engine and provenance logic.

The headline test (PLAN.md §6, Week 3 task 4) verifies connectivity scoring against a known
reference within tolerance; it is marked xfail until the scorer is implemented in Week 3.

The tier-assignment tests run today — they pin the rules from PLAN.md §3 so the most
commercially important design decision can't silently drift.
"""

from __future__ import annotations

import pytest

from src.provenance import ConfidenceTier, assign_tier


class TestAssignTier:
    """Tier rules from PLAN.md §3."""

    def test_measured_large_n_peer_reviewed_multi_source_is_tier_a(self):
        assert (
            assign_tier(
                is_measured=True,
                n_per_group=27,
                peer_reviewed=True,
                single_source=False,
            )
            == ConfidenceTier.A
        )

    def test_inferred_is_always_tier_c(self):
        assert (
            assign_tier(
                is_measured=False,
                n_per_group=1000,
                peer_reviewed=True,
                single_source=False,
            )
            == ConfidenceTier.C
        )

    @pytest.mark.parametrize(
        "kwargs",
        [
            dict(is_measured=True, n_per_group=6, peer_reviewed=True, single_source=False),
            dict(is_measured=True, n_per_group=27, peer_reviewed=False, single_source=False),
            dict(is_measured=True, n_per_group=27, peer_reviewed=True, single_source=True),
            dict(is_measured=True, n_per_group=None, peer_reviewed=True, single_source=False),
        ],
    )
    def test_measured_but_weak_evidence_is_tier_b(self, kwargs):
        assert assign_tier(**kwargs) == ConfidenceTier.B


@pytest.mark.xfail(reason="Connectivity scoring implemented in Week 3 (notebook 04).", strict=True)
def test_connectivity_score_matches_reference():
    """Verify connectivity scoring against a CMap/cmapPy reference within tolerance.

    PLAN.md §6, Week 3 task 4. Replace this body with a known reference example
    (disease up/down sets + drug signature -> expected score) once the scorer exists.
    """
    from src.scoring import connectivity_score

    score = connectivity_score(up_genes=[], down_genes=[], drug_signature=None)  # noqa
    assert score == pytest.approx(0.0, abs=1e-6)