feat: epub2md_merge.py – Gesamtdatei aus einer epub2md-Ausgabe

Fügt die Kapiteldateien in Lesereihenfolge (manifest.json) zu einer
Markdown-Datei mit dem Original-EPUB-Namen (.md) zusammen. Dabei werden:
- Links zwischen Kapiteln zu Sprunglinks in der Gesamtdatei,
- kollidierende Anker pro Kapitel umbenannt,
- Medienpfade relativ zum Ziel umgeschrieben,
- doppelte Fußnotendefinitionen entfernt,
- Code nie verändert.
Optionen -o, --toc, --no-frontmatter und --force; abschließender
Linkcheck.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

tests/test_merge.py

@@ -0,0 +1,73 @@
+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](#002-kapitel-b)" in text and '<a id="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)](#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](#001-kapitel-a)" in text
+    assert "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