utils/parser.py

import os
import pdfplumber
from docx import Document

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

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

    elif ext == ".docx":
        doc = Document(file_path)
        return "\n".join([para.text for para in doc.paragraphs])

    elif ext == ".pdf":
        text = ""
        with pdfplumber.open(file_path) as pdf:
            for page in pdf.pages:
                text += page.extract_text() + "\n"
        return text.strip()

    else:
        return "Unsupported file format."