from __future__ import annotations

import csv
import subprocess
import sys
from pathlib import Path

REPOSITORY_ROOT = next(
    parent
    for parent in Path(__file__).resolve().parents
    if (parent / "seed" / "generate_seed.py").is_file()
)
SEED_DIRECTORY = REPOSITORY_ROOT / "seed"


def _rows_by_ref(path: Path) -> dict[str, dict[str, str]]:
    with path.open(newline="", encoding="utf-8") as handle:
        rows = list(csv.DictReader(handle))
    assert all(None not in row for row in rows), f"malformed CSV row in {path.name}"
    return {row["public_ref"]: row for row in rows}


def test_generator_reproduces_committed_seed_snapshot_byte_for_byte(tmp_path: Path):
    subprocess.run(
        [
            sys.executable,
            str(SEED_DIRECTORY / "generate_seed.py"),
            "--anchor",
            "2026-08-01",
            "--seed",
            "20260801",
            "--out",
            str(tmp_path),
        ],
        cwd=REPOSITORY_ROOT,
        check=True,
        capture_output=True,
        text=True,
    )

    committed_files = sorted(SEED_DIRECTORY.glob("*.csv"))
    generated_files = sorted(tmp_path.glob("*.csv"))
    assert [path.name for path in generated_files] == [path.name for path in committed_files]
    for committed in committed_files:
        generated = tmp_path / committed.name
        assert generated.read_bytes() == committed.read_bytes(), (
            f"{committed.name} differs from the deterministic generated snapshot"
        )

    bookings = _rows_by_ref(tmp_path / "bookings.csv")
    inspections = _rows_by_ref(tmp_path / "inspections.csv")
    issues = _rows_by_ref(tmp_path / "data_quality_issues.csv")

    assert int(bookings["BK-H-0007"]["end_odometer_km"]) < int(
        bookings["BK-H-0057"]["end_odometer_km"]
    )
    assert int(bookings["BK-H-0010"]["end_odometer_km"]) < int(
        bookings["BK-H-0060"]["end_odometer_km"]
    )
    assert inspections["INSP-0007"]["odometer_km"] == bookings["BK-H-0007"]["end_odometer_km"]
    assert inspections["INSP-0010"]["odometer_km"] == bookings["BK-H-0010"]["end_odometer_km"]
    assert inspections["INSP-0001"]["completed_at"] == bookings["BK-H-0001"]["ends_at"]

    expected_issue_refs = {f"DQ-{index:04d}" for index in range(5, 22)}
    assert expected_issue_refs <= issues.keys()
    assert all(
        issues[public_ref]["evidence"] != "Synthetic deterministic seed issue"
        for public_ref in expected_issue_refs
    )
    assert "INSP-0007" in issues["DQ-0007"]["evidence"]
    assert "INSP-0057" in issues["DQ-0007"]["evidence"]
    assert "INSP-0010" in issues["DQ-0010"]["evidence"]
    assert "INSP-0060" in issues["DQ-0010"]["evidence"]