parser.py

from __future__ import annotations
from urllib.parse import urlparse


# Normalize raw user text into a clean domain name.
def normalize_domain(raw_value: str) -> str:
    value = raw_value.strip().lower()
    if not value:
        return ""

    if "://" not in value:
        value = f"https://{value}"

    parsed = urlparse(value)
    host = parsed.netloc or parsed.path
    host = host.split("/")[0]
    host = host.split(":")[0]
    if host.startswith("www."):
        host = host[4:]
    return host.strip(".")


# Validate a normalized domain to avoid invalid hosts entries.
def is_valid_domain(domain: str) -> bool:
    if not domain or " " in domain:
        return False
    if "." not in domain:
        return False
    allowed = set("abcdefghijklmnopqrstuvwxyz0123456789-.")
    return all(ch in allowed for ch in domain)