"""Standardwerte: EPUB-Sprache, Prozesszahl, Titel/Autor aus dem Dateinamen."""

import zipfile

import pymupdf
import pytest

import pdf2md as p
from conftest import needs_pandoc
from test_e2e import run


@pytest.mark.parametrize(
    "ocr_language, expected",
    [("deu", "de"), ("eng", "en"), ("eng+deu", "en"), ("fra", "fr"), ("xyz", "de")],
)
def test_epub_language_follows_ocr_language(ocr_language, expected):
    assert p.epub_language(ocr_language) == expected


@pytest.mark.parametrize("cores, expected", [(None, 1), (1, 1), (4, 2), (24, 8)])
def test_default_jobs(monkeypatch, cores, expected):
    monkeypatch.setattr(p.os, "cpu_count", lambda: cores)
    assert p.default_jobs() == expected


@pytest.mark.parametrize(
    "stem, expected",
    [
        ("Katja_Adler_-_Rolle_rückwärts_DDR", ("Rolle rückwärts DDR", "Katja Adler")),
        ("Zensur_Netzwerk_Deutschland_de-report-de", ("Zensur Netzwerk Deutschland de-report-de", "")),
        ("A_-_B_-_C", ("B - C", "A")),
    ],
)
def test_title_author_from_filename(stem, expected):
    assert p.title_author_from_filename(stem) == expected


@needs_pandoc
def test_epub_without_metadata_uses_filename_and_ocr_language(pdfs, tmp_path):
    doc = pymupdf.open(pdfs["digital"])
    doc.set_metadata({})
    source = tmp_path / "Max_Muster_-_Ein_Buch.pdf"
    doc.save(source)

    run(source, tmp_path / "buch.md", "--epub", "--ocr-language", "eng")
    with zipfile.ZipFile(tmp_path / "buch.epub") as z:
        opf = z.read("EPUB/content.opf").decode()
    assert ">Ein Buch<" in opf
    assert ">Max Muster<" in opf
    assert "<dc:language>en</dc:language>" in opf