epub2md/tests/test_merge.py

import re

import yaml

from conftest import PNG, Book, Doc
from epub2md.linkcheck import anchors_in, check_links
from epub2md.merge import main as merge_main

A = ('<h1 id="sec">Kapitel A</h1><p>Siehe <a href="b.xhtml#sec">B</a>, <a href="b.xhtml">Kapitel B</a>, '
     '<a href="#sec">hier</a> und Anmerkung<a epub:type="noteref" href="b.xhtml#n1">1</a>.</p>'
     '<p><img src="img/a.png" alt="Bild"/></p>'
     '<p><a href="b.xhtml"><img src="img/a.png" alt="Bildlink"/></a></p>'
     '<pre>[kein](link.md) id="sec" `code`</pre>')
B = ('<h1 id="sec">Kapitel B</h1><p>Zurück zu <a href="a.xhtml#sec">A</a>, nochmal Anmerkung'
     '<a epub:type="noteref" href="#n1">1</a>.</p>'
     '<aside epub:type="footnote" id="n1"><p>Gemeinsame Anmerkung.</p></aside>')


def book() -> Book:
    return Book(title="Merge-Test", docs=[Doc("a.xhtml", A), Doc("b.xhtml", B)], media={"img/a.png": PNG})


def test_merge_complete_book(convert, tmp_path):
    run = convert(book())
    assert merge_main([str(run.out)]) == 0
    target = run.out / f"{run.report['input']['name'][:-5]}.md"
    text = target.read_text(encoding="utf-8")
    # one book-level frontmatter, no chapter frontmatter
    fm = yaml.safe_load(text.split("---\n")[1])
    assert fm["title"] == "Merge-Test" and fm["author"] == ["Erika Musterfrau"] and fm["lang"] == "de"
    assert text.count("chapter_number") == 0
    # reading order
    assert text.index("# Kapitel A") < text.index("# Kapitel B")
    # links between chapters point into the merged file; colliding id "sec" renamed in chapter B
    assert '<a id="sec"></a>' in text and '<a id="c002-sec"></a>' in text
    assert "[B](#c002-sec)" in text and "[A](#sec)" in text and "[hier](#sec)" in text
    assert "[Kapitel B](#kap-002-kapitel-b)" in text and '<a id="kap-002-kapitel-b"></a>' in text
    # media paths relative to the merged file, also inside image links
    assert "![Bild](media/images/0001-bild.png)" in text
    assert "[![Bildlink](media/images/0001-bild.png)](#kap-002-kapitel-b)" in text
    # code untouched
    assert '[kein](link.md) id="sec" `code`' in text
    # footnote defined in both chapters -> only once in the merged file
    assert text.count("[^fn-001]:") == 1
    assert check_links({target.as_posix(): text}, {p.as_posix() for p in run.out.rglob("*") if p.is_file()}) == []
    prose = re.sub(r"^```.*?^```$", "", text, flags=re.M | re.S)
    ids = re.findall(r'id="([^"]+)"', prose)
    assert len(ids) == len(set(ids))


def test_merge_refuses_overwrite_without_force(convert):
    run = convert(book())
    assert merge_main([str(run.out)]) == 0
    assert merge_main([str(run.out)]) == 1
    assert merge_main([str(run.out), "--force"]) == 0


def test_merge_to_other_location_rewrites_media_paths(convert, tmp_path):
    run = convert(book())
    (tmp_path / "ziel").mkdir()
    target = tmp_path / "ziel" / "buch.md"
    assert merge_main([str(run.out), "-o", str(target), "--toc", "--no-frontmatter"]) == 0
    text = target.read_text(encoding="utf-8")
    assert not text.startswith("---")
    assert f"![Bild](../{run.out.name}/media/images/0001-bild.png)" in text
    assert "1. [Kapitel A](#kap-001-kapitel-a)" in text
    assert "kap-001-kapitel-a" in anchors_in(text)


def test_merge_invalid_directory(tmp_path):
    assert merge_main([str(tmp_path / "gibt-es-nicht")]) == 1
    (tmp_path / "leer").mkdir()
    assert merge_main([str(tmp_path / "leer")]) == 1


def test_merge_shortens_iso_date(convert):
    from epub2md.merge import display_date
    assert display_date("2025-01-13T08:00:00+00:00", "de") == "13.01.2025"
    assert display_date("2025-01-13", "de-DE") == "13.01.2025"
    assert display_date("2025-01-13T08:00:00Z", "en") == "2025-01-13"
    assert display_date("2025", "de") == "2025"  # year only / other formats stay
    assert display_date("Januar 2025", "de") == "Januar 2025"
    run = convert(book())
    assert merge_main([str(run.out)]) == 0
    text = (run.out / f"{run.report['input']['name'][:-5]}.md").read_text(encoding="utf-8")
    assert yaml.safe_load(text.split("---\n")[1])["date"] == "01.01.2024"


def front_book() -> Book:
    docs = [Doc("cover.xhtml", '<div><img src="img/a.png" alt="Cover"/></div>'),
            Doc("titel.xhtml", "<p>Erika Musterfrau</p><p>Vorspann</p><p>Roman</p>"),
            Doc("impressum.xhtml", "<p>© 2024 Testverlag</p><p>Das Werk ist urheberrechtlich geschützt.</p>"),
            Doc("a.xhtml", "<h1>Kapitel A</h1><p>a</p>")]
    return Book(title="Vorspann", docs=docs, nav=[("Kapitel A", "a.xhtml")], media={"img/a.png": PNG})


def test_merge_places_toc_placeholder_after_front_matter(convert):
    run = convert(front_book())
    assert merge_main([str(run.out)]) == 0
    text = (run.out / f"{run.report['input']['name'][:-5]}.md").read_text(encoding="utf-8")
    cover, title, imprint = text.index("![Cover]"), text.index("\nRoman"), text.index("© 2024")
    toc, first = text.index('<div id="epub2md-toc"></div>'), text.index("# Kapitel A")
    assert cover < title < imprint < toc < first
    assert "epub2md-titlepage" not in text  # the book has its own title page


def test_merge_title_placeholder_after_cover_without_own_title_page(convert):
    docs = [Doc("cover.xhtml", '<div><img src="img/a.png" alt="Cover"/></div>'), Doc("a.xhtml", "<h1>Kapitel A</h1><p>a</p>")]
    run = convert(Book(title="Ohne Titelei", docs=docs, nav=[("Kapitel A", "a.xhtml")], media={"img/a.png": PNG}))
    assert merge_main([str(run.out)]) == 0
    text = (run.out / f"{run.report['input']['name'][:-5]}.md").read_text(encoding="utf-8")
    assert text.index("![Cover]") < text.index('<div id="epub2md-titlepage"></div>') \
        < text.index('<div id="epub2md-toc"></div>') < text.index("# Kapitel A")


def test_merge_own_toc_replaces_placeholder(convert):
    run = convert(front_book())
    assert merge_main([str(run.out), "--toc"]) == 0
    text = (run.out / f"{run.report['input']['name'][:-5]}.md").read_text(encoding="utf-8")
    assert "epub2md-toc" not in text and text.index("© 2024") < text.index("## Inhalt") < text.index("# Kapitel A")


def test_merge_front_matter_region_with_gaps(convert):
    """Krooss/Blake-like: short untyped pages between title page and imprint; main matter starts at '1 …'."""
    docs = [Doc("cover.xhtml", '<div><img src="img/a.png" alt="Cover"/></div>'),
            Doc("titel.xhtml", "<p>Erika Musterfrau</p><p>Vorspann</p><p>Roman</p>"),
            Doc("auflage.xhtml", "<h1>Vorspann</h1><p>4. Auflage 2025</p>"),
            Doc("impressum.xhtml", "<p>© 2024 Testverlag</p><p>Das Werk ist urheberrechtlich geschützt.</p>"),
            Doc("brief.xhtml", "<h1>Liebe Leserin, lieber Leser,</h1><p>Viel Spaß.</p>"),
            Doc("k1.xhtml", "<h1>1 Der Einstieg</h1><p>a</p>"), Doc("k2.xhtml", "<h1>Zwischenspiel</h1><p>b</p>")]
    book = Book(title="Vorspann", docs=docs, nav=[("1 Der Einstieg", "k1.xhtml"), ("Zwischenspiel", "k2.xhtml")],
                media={"img/a.png": PNG})
    run = convert(book)
    assert merge_main([str(run.out)]) == 0
    text = (run.out / f"{run.report['input']['name'][:-5]}.md").read_text(encoding="utf-8")
    toc = text.index('<div id="epub2md-toc"></div>')
    assert text.index("© 2024") < text.index("Viel Spaß.") < toc < text.index("# 1 Der Einstieg")
    assert text.count("epub2md-toc") == 1 and "epub2md-titlepage" not in text