fix(dictionary): strip Latin romanization debris from Russian translations and sanitize dictionary cache
This commit is contained in:
1 parent
e371cdd4e5
commit
52db766b23
7 files changed
+109
-27
No files matched your search
+4
-9
@@ -240,15 +240,10 @@ def clean_translation(trans: str) -> str:
|
||||
"""Cleans up raw translation strings, removes slash phonetic residues and romanizations."""
|
||||
if not trans:
|
||||
return ""
|
||||
t = re.sub(r"/[^/]+/?", "", trans)
|
||||
parts = [p.strip() for p in re.split(r"[,;]\s*", t) if p.strip()]
|
||||
clean_parts = []
|
||||
for p in parts:
|
||||
if re.search(r"[а-яА-ЯёЁ]", p):
|
||||
clean_p = re.sub(r"[a-zA-ZáéíóúÁÉÍÓÚ]", "", p).strip()
|
||||
if clean_p:
|
||||
clean_parts.append(clean_p)
|
||||
return ", ".join(clean_parts[:3]) if clean_parts else trans.split(",")[0].strip()
|
||||
from app.dictionary import clean_russian_translation
|
||||
cleaned = clean_russian_translation(trans)
|
||||
parts = [p.strip() for p in cleaned.split(",") if p.strip()]
|
||||
return ", ".join(parts[:3]) if parts else trans.split(",")[0].strip()
|
||||
|
||||
|
||||
async def mine_book_questions(
|
||||
|
||||
Reference in new issue
Block a user