Release v0.13: Typography V3 (Safe mode) & Endnote Extraction Fix
This commit is contained in:
@@ -82,11 +82,28 @@ class BackfillEngine:
|
||||
new_tag.string = plain_text
|
||||
|
||||
# Copy attributes
|
||||
# Copy classes and add 'translation'
|
||||
# Copy classes and add 'translation' or 'translation-no-indent'
|
||||
classes = element.get('class', [])
|
||||
if isinstance(classes, str):
|
||||
classes = classes.split()
|
||||
new_tag['class'] = classes + ['translation']
|
||||
|
||||
# Heuristic: Check for Drop Cap / No-Indent indicators
|
||||
# Keywords: 'drop', 'first', 'no-indent', 'noindent'
|
||||
# REMOVED: 'chapter', 'start', 'opener' (too broad, catches titles)
|
||||
special_keywords = ['drop', 'no-indent', 'noindent']
|
||||
|
||||
# 'first' can be risky (e.g. 'first-title').
|
||||
# Be conservative: match 'first' only if combined with 'para' or 'letter' or similar?
|
||||
# For now, let's keep 'first' but be aware.
|
||||
# Actually, user said minimal change. Let's stick to 'drop' and explicit 'no-indent'.
|
||||
# Checking 'calibre1' etc is useless.
|
||||
|
||||
is_special_para = any(k in c.lower() for k in special_keywords for c in classes)
|
||||
|
||||
if is_special_para:
|
||||
new_tag['class'] = classes + ['translation-no-indent']
|
||||
else:
|
||||
new_tag['class'] = classes + ['translation']
|
||||
|
||||
# Copy style
|
||||
style = element.get('style')
|
||||
|
||||
Reference in New Issue
Block a user