# -----------------------------------------------------------------------------
# Lou-Ka — Location court terme
# connectors/domesstcome.py : Dômes St-Côme (domesstcome.com) — 4 dômes
#   géodésiques avec spa privé et vue panoramique à Saint-Côme (Lanaudière).
#
# Méthode : sitemap Wix (index) → dynamic-domes_*-sitemap.xml → 4 URLs
#   /domes/<slug> + lastmod (clé du cache détail). Pages Wix statiques :
#     - <h1> = nom du dôme ; sous-titre « Vue panoramique | Spa privé » ;
#     - « À partir de 370$/nuit » → price_night ;
#     - sections LITS / AUTRES / CUISINE / À L'EXTÉRIEUR / SALLE DE BAIN
#       (texte riche Wix) → amenities ; beds = nb de « Lit … » sous LITS ;
#     - CITQ (6 chiffres) dans le pied de page ;
#     - images : médias wixstatic ~mv2 servis en grand (w ≥ 900) — la galerie
#       Pro Gallery est chargée en JS, seuls les héros sont statiques.
# -----------------------------------------------------------------------------
from __future__ import annotations

import html as _html
import re

from ..schema import StListing
from .base import StConnector

SITE = "https://www.domesstcome.com"
SITEMAP = SITE + "/sitemap.xml"

_SECTIONS = ("LITS", "AUTRES", "CUISINE", "À L'EXTÉRIEUR", "SALLE DE BAIN")

_TAG_RE = re.compile(r"<[^>]+>")


def _lines(fragment: str) -> list[str]:
    """HTML riche Wix → lignes de texte propres (CSS inline filtré)."""
    txt = re.sub(r"\|(?:\s*\|)+", "\n",
                 re.sub(r"\s+", " ", _TAG_RE.sub("|", fragment)))
    out = []
    for x in txt.split("\n"):
        x = _html.unescape(x).strip(" |").strip()
        x = re.sub(r"\s*\|\s*", " | ", x)
        if x and len(x) > 2 and "{" not in x and "--" not in x:
            out.append(x)
    return out


class DomesStCome(StConnector):
    source_id = "domesstcome"
    request_delay = 1.0

    # -- page détail ----------------------------------------------------------
    def _detail(self, url: str) -> dict:
        h = self.get(url).text
        d: dict = {}

        m = re.search(r"(?s)<h1[^>]*>(.*?)</h1>", h)
        if m:
            d["title"] = _html.unescape(
                re.sub(r"\s+", " ", _TAG_RE.sub(" ", m.group(1)))).strip()

        m = re.search(r"À partir de\s*(\d+)\s*\$\s*/\s*nuit", h)
        if m:
            d["price_night"] = float(m.group(1))

        m = re.search(r"CITQ\D{0,25}(\d{6})", h)
        if m:
            d["citq"] = m.group(1)

        # sous-titre (« Vue panoramique | Spa privé ») → description
        i, j = h.find("<h1"), h.find("LITS")
        if 0 <= i < j:
            head = [x for x in _lines(h[i:j])
                    if x != d.get("title") and "À partir de" not in x
                    and "Détails" not in x]
            if head:
                d["description"] = head[0][:500]

        # sections LITS…SALLE DE BAIN → amenities (entêtes exclues)
        i = h.find("LITS")
        j = h.find("Réserver", max(i, 0))
        beds = 0
        amen: list[str] = []
        if 0 <= i < j:
            unescaped_secs = {s for s in _SECTIONS}
            current = ""
            for x in _lines(h[i:j]):
                if x.upper() in unescaped_secs:
                    current = x.upper()
                    continue
                if x in amen or len(x) > 80:
                    continue
                amen.append(x)
                if current == "LITS" and re.match(r"Lit\b", x, re.I):
                    beds += 1
        if amen:
            d["amenities"] = amen
        if beds:
            d["beds"] = float(beds)

        # images : médias wixstatic servis en grand (héros)
        big: dict[str, int] = {}
        for mid, w in re.findall(r"static\.wixstatic\.com/media/"
                                 r"([\w~%.]+)/v1/fill/w_(\d+)", h):
            w = int(w)
            if w >= 900:
                big[mid] = max(big.get(mid, 0), w)
        imgs = [f"https://static.wixstatic.com/media/{mid}"
                for mid in big][:15]
        if imgs:
            d["images"] = imgs
        return d

    # -- contrat --------------------------------------------------------------
    def fetch(self) -> list[StListing]:
        index = self.get(SITEMAP).text
        entries: list[tuple[str, str]] = []
        for sub in re.findall(r"<loc>([^<]+)</loc>", index):
            if "dynamic-domes" not in sub:
                continue
            xml = self.get(sub).text
            entries += re.findall(r"(?s)<url>\s*<loc>([^<]+)</loc>"
                                  r"(?:\s*<lastmod>([^<]*)</lastmod>)?", xml)

        listings: list[StListing] = []
        vus: set[str] = set()
        for url, lastmod in entries:
            m = re.match(r"https://www\.domesstcome\.com/domes/([^/]+)/?$", url)
            if not m:
                continue
            slug = m.group(1)
            if slug in vus:
                continue
            vus.add(slug)

            det = self.detail(slug, lastmod or "v1",
                              lambda u=url: self._detail(u))
            title = det.get("title") or ""
            if not title:
                continue

            price = det.get("price_night")
            listings.append(StListing(
                source=self.source_id,
                external_id=slug,
                url=url,
                title=title,
                property_type="Dôme",
                city="Saint-Côme",
                region="Lanaudière",
                price_night=price,
                price_label=f"À partir de {price:g} $ / nuit" if price else "",
                beds=det.get("beds"),
                citq=det.get("citq") or "",
                description=det.get("description") or "",
                amenities=det.get("amenities") or [],
                details={"domain": "Dômes St-Côme"},
                images=det.get("images") or [],
            ))
        return listings