utils.py

import pdfplumber

def extract_text_from_pdf(file_obj):
    text = ""
    with pdfplumber.open(file_obj) as pdf:
        for page in pdf.pages:
            text += page.extract_text() or ""
    return text

def simple_clause_split(text):
    return [clause.strip() for clause in text.split('. ') if clause.strip()]