"""Retry queue loading from scans.csv (mosaic_download_status=failed)."""

import csv
from pathlib import Path

import pytest

from spruce.orchestrator import load_failed_scans_from_csv
from spruce.settings import SCANS_CSV_FIELDS


def _blank_row(**kwargs: str) -> dict[str, str]:
    row = {k: "" for k in SCANS_CSV_FIELDS}
    row.update(kwargs)
    return row


def _write_scans_csv(path: Path, rows: list[dict[str, str]]) -> None:
    with open(path, "w", newline="", encoding="utf-8") as fh:
        w = csv.DictWriter(fh, fieldnames=SCANS_CSV_FIELDS)
        w.writeheader()
        for r in rows:
            w.writerow({k: r.get(k, "") for k in SCANS_CSV_FIELDS})


def test_load_failed_scans_dedup_keeps_last_row(tmp_path: Path) -> None:
    path = tmp_path / "scans.csv"
    common = {
        "machine": "BW1 [X]",
        "machine_id": "1",
        "scan_id": "100",
        "mosaic_url": "http://x/m.jpg",
        "mosaic_local_path": "",
        "mosaic_on_disk": "False",
    }
    _write_scans_csv(
        path,
        [
            _blank_row(
                **common,
                mosaic_download_status="failed",
                mosaic_error_code="404",
                scan_time="2020-01-01",
            ),
            _blank_row(
                **common,
                mosaic_download_status="failed",
                mosaic_error_code="404",
                scan_time="2020-06-01",
            ),
        ],
    )
    out = load_failed_scans_from_csv(path, "BW1 [X]")
    assert len(out) == 1
    assert out[0]["scan_id"] == 100
    assert out[0]["scan_time"] == "2020-06-01"


def test_load_failed_scans_since_year(tmp_path: Path) -> None:
    path = tmp_path / "scans.csv"
    base = {
        "machine": "M",
        "machine_id": "1",
        "mosaic_url": "",
        "mosaic_local_path": "",
        "mosaic_on_disk": "",
        "mosaic_download_status": "failed",
        "mosaic_error_code": "404",
    }
    _write_scans_csv(
        path,
        [
            _blank_row(**base, scan_id="1", scan_time="2022-12-31"),
            _blank_row(**base, scan_id="2", scan_time="2023-01-01"),
            _blank_row(**base, scan_id="3", scan_time=""),
        ],
    )
    out = load_failed_scans_from_csv(path, "M", since_year="2023")
    ids = {s["scan_id"] for s in out}
    assert ids == {2}


def test_load_failed_scans_error_code(tmp_path: Path) -> None:
    path = tmp_path / "scans.csv"
    base = {
        "machine": "M",
        "machine_id": "1",
        "scan_time": "2024-01-01",
        "mosaic_url": "",
        "mosaic_local_path": "",
        "mosaic_on_disk": "",
        "mosaic_download_status": "failed",
    }
    _write_scans_csv(
        path,
        [
            _blank_row(**base, scan_id="10", mosaic_error_code="404"),
            _blank_row(**base, scan_id="11", mosaic_error_code="200"),
        ],
    )
    out = load_failed_scans_from_csv(path, "M", error_code="200")
    assert [s["scan_id"] for s in out] == [11]


def test_load_failed_scans_excludes_downloaded(tmp_path: Path) -> None:
    path = tmp_path / "scans.csv"
    base = {
        "machine": "M",
        "machine_id": "1",
        "scan_time": "2024-01-01",
        "mosaic_url": "",
        "mosaic_local_path": "",
        "mosaic_on_disk": "True",
    }
    _write_scans_csv(
        path,
        [
            _blank_row(
                **base,
                scan_id="5",
                mosaic_download_status="downloaded",
                mosaic_error_code="",
            ),
            _blank_row(
                **base,
                scan_id="6",
                mosaic_download_status="failed",
                mosaic_error_code="404",
            ),
        ],
    )
    out = load_failed_scans_from_csv(path, "M")
    assert [s["scan_id"] for s in out] == [6]