"""Tests für [ocr].timeout → ocrmypdf `tesseract_timeout`.

ocrmypdf wird hier komplett gemockt (per sys.modules), es läuft also nie
wirklich — die Tests laufen auch ohne installiertes ocrmypdf.
"""
from __future__ import annotations

import sys
import tomllib
from pathlib import Path
from types import ModuleType

import pytest

from pdf_ocr_hotfolder.config import OcrConfig
from pdf_ocr_hotfolder.processor import run_ocr


@pytest.fixture
def fake_ocrmypdf(monkeypatch) -> ModuleType:
    """Schiebt ein Dummy-ocrmypdf in sys.modules und merkt sich die kwargs."""
    mod = ModuleType("ocrmypdf")
    mod.calls = []  # type: ignore[attr-defined]

    def ocr(src, dst, **kwargs):
        mod.calls.append({"src": src, "dst": dst, "kwargs": kwargs})  # type: ignore[attr-defined]
        Path(dst).write_bytes(b"%PDF-1.4 ocr\n")

    mod.ocr = ocr  # type: ignore[attr-defined]
    monkeypatch.setitem(sys.modules, "ocrmypdf", mod)
    return mod


def _run(fake, tmp_path: Path, cfg: OcrConfig) -> dict:
    src = tmp_path / "in.pdf"
    src.write_bytes(b"%PDF-1.4\n")
    run_ocr(src, tmp_path / "out.pdf", cfg)
    assert len(fake.calls) == 1
    return fake.calls[0]["kwargs"]


def test_timeout_is_passed_as_tesseract_timeout(fake_ocrmypdf, tmp_path: Path) -> None:
    kwargs = _run(fake_ocrmypdf, tmp_path, OcrConfig(timeout=120))
    assert kwargs["tesseract_timeout"] == 120.0


def test_timeout_zero_means_no_limit(fake_ocrmypdf, tmp_path: Path) -> None:
    """0 = kein Limit → der Key darf NICHT durchgereicht werden.

    ocrmypdf würde tesseract_timeout=0 als 'OCR überspringen' auslegen.
    """
    kwargs = _run(fake_ocrmypdf, tmp_path, OcrConfig(timeout=0))
    assert "tesseract_timeout" not in kwargs


def test_negative_timeout_is_ignored(fake_ocrmypdf, tmp_path: Path) -> None:
    kwargs = _run(fake_ocrmypdf, tmp_path, OcrConfig(timeout=-5))
    assert "tesseract_timeout" not in kwargs


def test_default_timeout_is_passed(fake_ocrmypdf, tmp_path: Path) -> None:
    kwargs = _run(fake_ocrmypdf, tmp_path, OcrConfig())
    assert kwargs["tesseract_timeout"] == 300.0


def test_other_kwargs_still_present(fake_ocrmypdf, tmp_path: Path) -> None:
    """Der neue Key ersetzt nichts Bestehendes."""
    kwargs = _run(fake_ocrmypdf, tmp_path,
                  OcrConfig(languages="deu", jobs=2, pdfa_level=""))
    assert kwargs["language"] == "deu"
    assert kwargs["jobs"] == 2
    assert kwargs["output_type"] == "pdf"
    assert kwargs["skip_text"] is True


def test_config_default_matches_example(tmp_path: Path) -> None:
    """Dataclass-Default und config.example.toml dürfen nicht auseinanderlaufen."""
    cfg_path = Path(__file__).parent.parent / "config.example.toml"
    with cfg_path.open("rb") as f:
        data = tomllib.load(f)
    assert data["ocr"]["timeout"] == OcrConfig().timeout == 300