import json
from pathlib import Path

from scripts.evaluate_yolo_checkpoint_matrix import (
    dataset_overlap_evidence,
    training_sample_independence_evidence,
    write_blocked_manifest,
)


def test_dataset_overlap_evidence_marks_repeated_validation_rows(
    tmp_path: Path,
) -> None:
    dataset_yaml = tmp_path / "dataset.yaml"
    dataset_yaml.write_text("path: .\nval: images/val\n", encoding="utf-8")
    (tmp_path / "yolo_tile_dataset_summary.json").write_text(
        json.dumps({"tile_size": 512, "stride": 256}), encoding="utf-8"
    )

    evidence = dataset_overlap_evidence(dataset_yaml)

    assert evidence["status"] == "overlapping"
    assert evidence["overlap_pixels"] == 256
    assert evidence["validation_tiles_non_overlapping"] is False
    assert evidence["statistical_independence_established"] is False


def test_dataset_overlap_evidence_is_explicit_when_summary_missing(
    tmp_path: Path,
) -> None:
    evidence = dataset_overlap_evidence(tmp_path / "dataset.yaml")

    assert evidence["status"] == "unavailable"
    assert evidence["validation_tiles_non_overlapping"] is None
    assert evidence["statistical_independence_established"] is False


def test_nonoverlap_does_not_overclaim_statistical_independence(
    tmp_path: Path,
) -> None:
    dataset_yaml = tmp_path / "dataset.yaml"
    dataset_yaml.write_text("path: .\nval: images/val\n", encoding="utf-8")
    (tmp_path / "yolo_tile_dataset_summary.json").write_text(
        json.dumps({"tile_size": 512, "stride": 512}), encoding="utf-8"
    )

    evidence = dataset_overlap_evidence(dataset_yaml)

    assert evidence["validation_tiles_non_overlapping"] is True
    assert evidence["statistical_independence_established"] is False
    assert "not established" in evidence["interpretation"]


def _write_summary(path: Path, rows: list[tuple[str, str]]) -> None:
    path.write_text(
        json.dumps(
            {
                "tile_size": 512,
                "stride": 512,
                "tiles": [
                    {"sample_slug": sample_slug, "split": split}
                    for sample_slug, split in rows
                ],
            }
        ),
        encoding="utf-8",
    )


def test_training_sample_independence_detects_overlap_for_each_corpus(
    tmp_path: Path,
) -> None:
    evaluation = tmp_path / "evaluation"
    evaluation.mkdir()
    dataset_yaml = evaluation / "dataset.yaml"
    dataset_yaml.write_text("path: .\nval: images/val\n", encoding="utf-8")
    _write_summary(
        evaluation / "yolo_tile_dataset_summary.json",
        [("turnhout", "val"), ("postel_bos", "val")],
    )
    active = tmp_path / "active.json"
    challenger = tmp_path / "challenger.json"
    _write_summary(active, [("postel_bos", "train"), ("mol", "train")])
    _write_summary(
        challenger, [("postel_bos", "train"), ("dessel", "train")]
    )

    evidence = training_sample_independence_evidence(
        dataset_yaml, [active, challenger]
    )

    assert evidence["status"] == "overlap"
    assert evidence["overlapping_evaluation_samples"] == ["postel_bos"]
    assert evidence["independent_for_all_supplied_training_corpora"] is False
    assert [
        row["overlapping_evaluation_samples"] for row in evidence["training_corpora"]
    ] == [["postel_bos"], ["postel_bos"]]


def test_training_sample_independence_accepts_disjoint_samples(tmp_path: Path) -> None:
    evaluation = tmp_path / "evaluation"
    evaluation.mkdir()
    dataset_yaml = evaluation / "dataset.yaml"
    dataset_yaml.write_text("path: .\nval: images/val\n", encoding="utf-8")
    _write_summary(
        evaluation / "yolo_tile_dataset_summary.json", [("turnhout", "val")]
    )
    training = tmp_path / "training.json"
    _write_summary(training, [("mol", "train")])

    evidence = training_sample_independence_evidence(dataset_yaml, [training])

    assert evidence["status"] == "independent"
    assert evidence["overlapping_evaluation_samples"] == []
    assert evidence["independent_for_all_supplied_training_corpora"] is True


def test_training_sample_independence_is_unavailable_without_training_corpus(
    tmp_path: Path,
) -> None:
    evaluation = tmp_path / "evaluation"
    evaluation.mkdir()
    dataset_yaml = evaluation / "dataset.yaml"
    dataset_yaml.write_text("path: .\nval: images/val\n", encoding="utf-8")
    _write_summary(
        evaluation / "yolo_tile_dataset_summary.json", [("turnhout", "val")]
    )

    evidence = training_sample_independence_evidence(dataset_yaml, [])

    assert evidence["status"] == "unavailable"
    assert evidence["overlapping_evaluation_samples"] == []
    assert evidence["independent_for_all_supplied_training_corpora"] is False


def test_blocked_manifest_records_that_models_and_gpu_were_not_used(
    tmp_path: Path,
) -> None:
    dataset_yaml = tmp_path / "dataset.yaml"
    dataset_yaml.write_text("path: .\nval: images/val\n", encoding="utf-8")
    output = tmp_path / "evidence" / "matrix.json"

    write_blocked_manifest(
        output,
        dataset_yaml,
        {
            "status": "overlap",
            "independent_for_all_supplied_training_corpora": False,
        },
    )

    payload = json.loads(output.read_text(encoding="utf-8"))
    assert payload["status"] == "blocked_training_sample_overlap"
    assert payload["model_loading_attempted"] is False
    assert payload["gpu_inference_attempted"] is False