utils.py

import PyPDF2
import docx
from pathlib import Path

def load_text(path: str) -> str:
    """
    Load text from TXT, PDF, or DOCX files.
    Returns the extracted text as a string.
    """
    path_obj = Path(path)
    if not path_obj.exists():
        raise FileNotFoundError(f"{path} does not exist.")

    if path_obj.suffix.lower() == ".txt":
        return path_obj.read_text(encoding="utf-8")

    elif path_obj.suffix.lower() == ".pdf":
        text = ""
        with open(path_obj, "rb") as f:
            reader = PyPDF2.PdfReader(f)
            for page in reader.pages:
                page_text = page.extract_text()
                if page_text:
                    text += page_text + "\n"
        return text

    elif path_obj.suffix.lower() == ".docx":
        doc = docx.Document(path_obj)
        return "\n".join([p.text for p in doc.paragraphs])

    else:
        raise ValueError(f"Unsupported file type: {path_obj.suffix}")