utils/file_loader.py

import os
import PyPDF2
from docx import Document

SUPPORTED_ERROR = "❌ Supported formats: .txt, .pdf, .docx"

def extract_text(file_path: str) -> str:
    ext = os.path.splitext(file_path)[1].lower()

    try:
        if ext == ".txt":
            with open(file_path, "r", encoding="utf-8") as f:
                return f.read().strip()

        if ext == ".pdf":
            text = ""
            with open(file_path, "rb") as f:
                reader = PyPDF2.PdfReader(f)
                for page in reader.pages:
                    text += (page.extract_text() or "") + "\n"
            return text.strip()

        if ext == ".docx":
            doc = Document(file_path)
            return "\n".join(
                p.text for p in doc.paragraphs if p.text.strip()
            ).strip()

        return SUPPORTED_ERROR

    except Exception as e:
        return f"❌ Error reading file: {str(e)}"