"""The benchmark is the project's strongest scientific claim, so its arithmetic is tested."""
import json
import math
import zipfile
from pathlib import Path

import pytest

from rarelens_ml.benchmark import cases, gene_annotations, rank_of, report
from rarelens_ml.hpo import information_content
from rarelens_ml.hpo import phenotype_score as score


def annotations_file(tmp_path: Path, genes: dict[str, list[str]]) -> str:
    path = tmp_path / "gp.tsv"
    path.write_text("".join(f"{g}\t{t}\n" for g, terms in genes.items() for t in terms))
    return str(path)


def phenopacket(gene: str, terms: list[str], excluded: list[str] | None = None) -> dict:
    return {
        "phenotypicFeatures": [{"type": {"id": t}} for t in terms]
        + [{"type": {"id": t}, "excluded": True} for t in (excluded or [])],
        "interpretations": [
            {
                "diagnosis": {
                    "genomicInterpretations": [
                        {"variantInterpretation": {"variationDescriptor": {
                            "geneContext": {"symbol": gene}}}}
                    ]
                }
            }
        ],
    }


def store(tmp_path: Path, packets: dict[str, dict]) -> str:
    path = tmp_path / "pps.zip"
    with zipfile.ZipFile(path, "w") as z:
        for name, packet in packets.items():
            z.writestr(name, json.dumps(packet))
    return str(path)


def test_information_content_makes_a_universal_term_worthless() -> None:
    genes = {"A": {"HP:1", "HP:2"}, "B": {"HP:1"}, "C": {"HP:1"}}
    ic = information_content(genes)
    assert ic["HP:1"] == pytest.approx(0.0)               # every gene has it
    assert ic["HP:2"] == pytest.approx(math.log(3))       # one gene in three


def test_score_is_recall_weighted_by_specificity() -> None:
    ic = {"HP:1": 0.0, "HP:2": 4.0}
    assert score(["HP:1", "HP:2"], {"HP:2"}, ic, 1.0) == pytest.approx(1.0)
    assert score(["HP:1", "HP:2"], {"HP:1"}, ic, 1.0) == pytest.approx(0.0)


def test_rank_separates_optimistic_from_pessimistic_on_ties() -> None:
    """Every gene carrying the same term ties; the report must not hide that."""
    genes = {"RIGHT": {"HP:1"}, "TIED": {"HP:1"}, "WRONG": {"HP:9"}}
    ic = {"HP:1": 1.0, "HP:9": 1.0}
    optimistic, pessimistic, target = rank_of("RIGHT", ["HP:1"], genes, ic, 1.0)
    assert (optimistic, pessimistic) == (1, 2)
    assert target == pytest.approx(1.0)


def test_a_uniquely_matching_gene_ranks_first_either_way() -> None:
    genes = {"RIGHT": {"HP:1", "HP:2"}, "PARTIAL": {"HP:1"}, "WRONG": set()}
    ic = {"HP:1": 1.0, "HP:2": 1.0}
    assert rank_of("RIGHT", ["HP:1", "HP:2"], genes, ic, 1.0)[:2] == (1, 1)


def test_cases_reads_the_causal_gene_and_drops_excluded_terms(tmp_path: Path) -> None:
    """An excluded feature means the authors looked and did not find it."""
    path = store(tmp_path, {
        "a/one.json": phenopacket("TGFBR2", ["HP:1", "HP:2"], excluded=["HP:3"]),
        "a/notes.txt": {},
    })
    assert list(cases(path)) == [("TGFBR2", ["HP:1", "HP:2"])]


def test_cases_skips_packets_without_exactly_one_causal_gene(tmp_path: Path) -> None:
    two = phenopacket("A", ["HP:1"])
    two["interpretations"][0]["diagnosis"]["genomicInterpretations"].append(
        {"variantInterpretation": {"variationDescriptor": {"geneContext": {"symbol": "B"}}}}
    )
    path = store(tmp_path, {"two.json": two, "none.json": phenopacket("C", [])})
    assert list(cases(path)) == []


def test_gene_annotations_reads_the_export(tmp_path: Path) -> None:
    path = annotations_file(tmp_path, {"A": ["HP:1", "HP:2"], "B": ["HP:1"]})
    assert gene_annotations(path) == {"A": {"HP:1", "HP:2"}, "B": {"HP:1"}}


def test_report_states_the_contamination_and_both_bounds() -> None:
    text = report([(1, 2, 1.0), (1, 1, 1.0), (3, 5, 0.5)], n_genes=100)
    assert "optimistic" in text and "pessimistic" in text
    assert "HPO already carries" in text  # the caveat travels with the number