app/utils/text_processing.py

import re
from typing import List

def clean_text(text: str) -> str:
    text = re.sub(r'\s+', ' ', text)
    text = text.strip()
    return text

def split_into_sentences(text: str) -> List[str]:
    return [s.strip() for s in re.split(r'[.!?]+', text) if s.strip()]