"""Utility functions for the Hotel Search App."""

import re
from urllib.parse import urlparse

BLOCKED_DOMAINS = {
    "expedia.com", "booking.com", "hotels.com", "trivago.com",
    "kayak.com", "priceline.com", "orbitz.com", "travelocity.com",
    "agoda.com", "trip.com", "hotwire.com", "cheaptickets.com",
    "tripadvisor.com", "google.com", "bing.com", "momondo.com",
    "skyscanner.com", "makemytrip.com", "goibibo.com", "yatra.com",
    "cleartrip.com", "lonelyplanet.com", "hostelworld.com",
    "hotels.ng", "hrs.com", "destinia.com",
    "travelzoo.com", "smartertravel.com", "travelpod.com",
    "wotif.com", "lastminute.com", "opodo.com", "edreams.com",
    "loveholidays.com", "secretescapes.com", "hotelscombined.com",
    "travelsupermarket.com", "skyscanner.net", "cheapoair.com",
    "onetravel.com", "getaroom.com", "snaptravel.com",
}


def is_travel_agency(url: str) -> bool:
    """Return True if the URL belongs to a known travel agency or aggregator."""
    try:
        parsed = urlparse(url)
        domain = parsed.netloc.lower().replace("www.", "")
        for blocked in BLOCKED_DOMAINS:
            if blocked in domain:
                return True
        return False
    except Exception:
        return False


def extract_direct_hotel_url(urls: list[str]) -> str | None:
    """From a list of URLs, return the first one that is NOT a travel agency."""
    for url in urls:
        if url and not is_travel_agency(url):
            return url
    return None


def extract_price_from_text(text: str) -> float | None:
    """Try to extract a dollar price from a text string."""
    patterns = [
        r"\$\s?(\d{1,5}(?:\.\d{2})?)",
        r"(\d{1,5})\s*(?:dollars|usd|per night|/night|a night)",
    ]
    for pattern in patterns:
        match = re.search(pattern, text, re.IGNORECASE)
        if match:
            try:
                return float(match.group(1))
            except ValueError:
                continue
    return None


def clean_snippet(text: str) -> str:
    """Clean up a search result snippet."""
    if not text:
        return ""
    text = re.sub(r"<[^>]+>", "", text)
    text = re.sub(r"\s+", " ", text).strip()
    return text