extractor.py

import fitz  # PyMuPDF
import os

def extract_text(file):
    if not file:
        return ""

    file_ext = os.path.splitext(file.name)[1].lower()

    if file_ext == ".pdf":
        with fitz.open(file.name) as doc:
            return "\n".join([page.get_text() for page in doc])

    elif file_ext == ".txt":
        with open(file.name, "r", encoding="utf-8") as f:
            return f.read()

    else:
        return "Unsupported file type"