# -----------------------------------------------------------------------------
# Lou-Ka — Location court terme
# connectors/hebergia.py : Hébergia (hebergia.ca)
#
# Agence multi-régions (Cantons-de-l'Est, Laurentides, Lanaudière, Charlevoix,
# Centre-du-Québec) — WordPress + moteur Guesty, ~60 chalets.
#
# Méthode :
#   1. LISTE : la page /chalets/ embarque `window.chalets = [...]` (JSON
#      complet : gid Guesty, prix de base/nuit, url, titre, RÉGION, capacité,
#      chambres, lits, lat/lng, vignette). Une seule requête.
#   2. DÉTAIL (cache self.detail, clé = champs stables de la liste) : la page
#      WP fr /chalets/<slug>/ fournit ville (« Austin, Cantons-de-l'Est »),
#      salles de bain (bloc inshort), description, commodités (section
#      « Commodités incluses »), photos (assets.guesty.com) et numéro CITQ
#      (dans le règlement).
#   External_id = gid (id de listing Guesty, stable).
# -----------------------------------------------------------------------------
from __future__ import annotations

import html as _html
import json
import re

from ..schema import StListing
from .base import StConnector

SITE = "https://hebergia.ca"

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


def _text(fragment: str) -> str:
    return _html.unescape(re.sub(r"\s+", " ", _TAG_RE.sub(" ", fragment))).strip()


def _num(v) -> float | None:
    try:
        return float(v) if v not in (None, "") else None
    except (TypeError, ValueError):
        return None


class Hebergia(StConnector):
    source_id = "hebergia"

    # -- liste ----------------------------------------------------------------
    def _list_items(self) -> list[dict]:
        h = self.get(f"{SITE}/chalets/").text
        m = re.search(r"window\.chalets\s*=\s*(\[.*?\]);", h, re.S)
        if not m:
            return []
        try:
            return json.loads(m.group(1))
        except ValueError:
            return []

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

        m = re.search(r'class="sous-titre-localisation">([^<]+)<', h)
        if m:
            loc = _text(m.group(1))
            d["city"] = loc.split(",")[0].strip()

        # bloc « inshort » : 8 voyageurs / 3 chambres / lits / 2 salles de bain
        m = re.search(r"(\d+)\s*salles?\s*de\s*bain", h)
        if m:
            d["bathrooms"] = float(m.group(1))

        # description : paragraphes de l'article avant les accordéons
        m = re.search(r"(?s)<article class=\"hbg-fiche-chalet-content\">"
                      r".*?</h1>(.*?)<h2 class=\"toggler\"", h)
        if m:
            frag = re.sub(r'(?s)<p class="sous-titre-localisation">.*?</p>',
                          " ", m.group(1))
            paras = re.findall(r"(?s)<p[^>]*>(.*?)</p>", frag)
            d["description"] = " ".join(_text(p) for p in paras
                                        if _text(p))[:4000]

        # commodités : section « Commodités incluses » (lignes à puces)
        m = re.search(r'(?s)Commodités incluses</button></h2>\s*'
                      r'<div class="toToggle"[^>]*>(.*?)</div>', h)
        if m:
            amens = []
            for line in re.split(r"<br\s*/?>|</p>", m.group(1)):
                t = _text(line).lstrip("•· ").strip()
                if 2 <= len(t) <= 80 and not t.isupper():
                    amens.append(t)
            d["amenities"] = amens[:60]

        # photos (CDN Guesty, dédupliquées)
        imgs: list[str] = []
        for u in re.findall(r'data-flickity-lazyload-src="'
                            r'(https://assets\.guesty\.com/[^"]+)"', h):
            if u not in imgs:
                imgs.append(u)
        d["images"] = imgs[:20]

        m = re.search(r"CITQ\D{0,12}(\d{6})", h, re.I)
        if m:
            d["citq"] = m.group(1)

        m = re.search(r"animaux non admis|pas d.animaux|no pets", h, re.I)
        if m:
            d["pets"] = "non"
        return d

    # -- contrat ----------------------------------------------------------
    def fetch(self) -> list[StListing]:
        listings: list[StListing] = []
        for it in self._list_items():
            gid = str(it.get("gid") or "").strip()
            url = it.get("url") or ""
            title = _text(str(it.get("title") or ""))
            if not gid or not url or not title or "/en/" in url:
                continue

            key = json.dumps([gid, title, it.get("price"),
                              it.get("accommodates"), it.get("bedrooms"),
                              it.get("beds"), it.get("shortDesc")],
                             ensure_ascii=False)
            try:
                det = self.detail(gid, key, lambda u=url: self._detail(u))
            except Exception:      # une fiche détail cassée ≠ annonce perdue
                det = {}

            price = _num(it.get("price"))
            starting = _num(it.get("startingPrice"))
            if starting and starting > 0:
                price = starting
            desc = det.get("description") or ""
            short = _text(str(it.get("shortDesc") or ""))
            if short and short not in desc:
                desc = f"{short} {desc}".strip()

            listings.append(StListing(
                source=self.source_id,
                external_id=gid,
                url=url,
                title=title,
                property_type="Chalet",
                city=det.get("city") or "",
                region=it.get("region") or "",
                price_night=price,
                price_label=(f"à partir de {price:.0f} $ / nuit"
                             if price else ""),
                capacity=_num(it.get("accommodates")),
                bedrooms=_num(it.get("bedrooms")),
                beds=_num(it.get("beds")),
                bathrooms=det.get("bathrooms"),
                pets=det.get("pets"),
                citq=det.get("citq") or "",
                description=desc[:4000],
                amenities=det.get("amenities") or [],
                details={"guesty_id": gid},
                images=det.get("images")
                       or ([it["thumbnail"]] if it.get("thumbnail") else []),
                lat=_num(it.get("lat")),
                lng=_num(it.get("lng")),
            ))
        return listings