import json
from pathlib import Path

import pytest
from scripts.score_retrieval_benchmark import score


def _inputs(tmp_path: Path) -> tuple[Path, Path]:
    results = tmp_path / "results.jsonl"
    rows = [
        {
            "kind": "manifest",
            "question_count": 2,
            "questions_sha256": "frozen-hash",
        },
        {
            "kind": "retrieval",
            "question": {"id": "Q01"},
            "seconds": 0.2,
            "is_error": False,
            "returned_node_ids": ["node-a", "other"],
            "response": [{"canonical_revision": "a" * 40}],
        },
        {
            "kind": "retrieval",
            "question": {"id": "Q02"},
            "seconds": 0.4,
            "is_error": False,
            "returned_node_ids": ["node-c"],
            "response": [{"canonical_revision": "a" * 40}],
        },
    ]
    results.write_text("".join(json.dumps(row) + "\n" for row in rows), encoding="utf-8")
    judgments = tmp_path / "judgments.json"
    judgments.write_text(
        json.dumps(
            {
                "method": "independent relevance review",
                "fully_answerable_positive_questions": {
                    "Q01": ["node-a", "node-b"],
                    "Q02": ["node-c"],
                },
            }
        ),
        encoding="utf-8",
    )
    return results, judgments


def test_scores_recall_on_judged_answerable_questions_only(tmp_path: Path) -> None:
    results, judgments = _inputs(tmp_path)

    result = score(results, judgments)

    assert result["question_count"] == 2
    assert result["judged_answerable_questions"] == 2
    assert result["mean_conditional_recall_at_5"] == 0.75
    assert result["conditional_hit_rate"] == 1.0
    assert result["canonical_revision"] == "a" * 40


def test_rejects_missing_judged_questions_and_mixed_canonical_heads(tmp_path: Path) -> None:
    results, judgments = _inputs(tmp_path)
    rows = results.read_text(encoding="utf-8").splitlines()
    missing_results = tmp_path / "missing.jsonl"
    missing_results.write_text("\n".join(rows[:2]) + "\n", encoding="utf-8")
    with pytest.raises(ValueError, match="count does not match"):
        score(missing_results, judgments)

    rows[2] = rows[2].replace("a" * 40, "b" * 40)
    mixed = tmp_path / "mixed.jsonl"
    mixed.write_text("\n".join(rows) + "\n", encoding="utf-8")
    with pytest.raises(ValueError, match="more than one canonical revision"):
        score(mixed, judgments)