dschlueter/epub2md
Watch
1
0
Fork
You've already forked epub2md
 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

fix: Zeilen aus nur - oder = als Text maskieren (QA2-08)

Browse source 
Ein Absatz "---" wurde zur Trennlinie, "===" bzw. "---" nach einem
Zeilenumbruch machte die vorige Zeile zur Setext-Überschrift. Solche
Zeilen erhalten jetzt einen Backslash.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Dieter Schlüter 2026-10-06 00:03:29 +02:00
commit daa99415b5
2 changed files with 12 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

3
epub2md/html_converter.py
View file

@ -116,6 +116,9 @@ def escape_line_starts(text: str) -> str:
token = m.group(2) token = m.group(2)
pos = m.start(2) + (len(token) - 1 if token[0].isdigit() else 0) pos = m.start(2) + (len(token) - 1 if token[0].isdigit() else 0)
line = line[:pos] + "\\" + line[pos:] line = line[:pos] + "\\" + line[pos:]
elif re.fullmatch(r"\s*(-+|=+)\s*", line): # thematic break / setext underline
pos = len(line) - len(line.lstrip())
line = line[:pos] + "\\" + line[pos:]
out.append(line) out.append(line)
return "\n".join(out) return "\n".join(out)

9
tests/test_qa_regressions.py
View file

@ -109,6 +109,15 @@ def test_multiple_blank_lines_inside_code_are_kept(convert):
assert "\n\n\n" not in text.replace(code, "") # outside code blank lines are still normalized assert "\n\n\n" not in text.replace(code, "") # outside code blank lines are still normalized
def test_dash_and_equals_lines_stay_text(convert):
"""QA2-08: a paragraph '---' became a thematic break, '===' after a line break a setext heading."""
body = "<h1>K</h1><p>---</p><p>Zeile<br/>===</p><p>Text<br/>-----</p>"
text = convert(Book(docs=[Doc("c.xhtml", body)])).chapter("001")
assert "\n\\---\n" in text, text
assert "Zeile\\\n\\===" in text, text
assert "Text\\\n\\-----" in text, text
def _simple() -> Book: def _simple() -> Book:
return Book(docs=[Doc("c.xhtml", "<h1>K</h1><p>Text.</p>")]) return Book(docs=[Doc("c.xhtml", "<h1>K</h1><p>Text.</p>")])