# Author: Simon-Pierre Boucher
# Contact: contact@spboucher.ai
"""Normalisation pour la résolution d'entités et le regroupement géographique.

- normalize_name : clé canonique d'un nom (accents, ponctuation, suffixes légaux retirés).
- canonical_location : regroupe les variantes ("Montreal"/"Montréal"/"Montréal, QC") en un
  libellé unique, et rattache les grandes villes du Québec à un libellé stable.
- domain : domaine racine d'une URL (pour relier des entités du même site).
"""

from __future__ import annotations

import re
import unicodedata
from urllib.parse import urlparse

_LEGAL = {
    "inc", "ltee", "ltd", "limited", "limitee", "enr", "senc", "sencrl", "srl",
    "corp", "corporation", "cie", "co", "llc", "llp", "sec", "sa", "sas",
}


def strip_accents(s: str) -> str:
    return "".join(c for c in unicodedata.normalize("NFD", s or "") if unicodedata.category(c) != "Mn")


def normalize_name(name: str) -> str:
    """Clé de résolution : minuscules, sans accents/ponctuation ni suffixe légal."""
    s = strip_accents((name or "").lower())
    s = re.sub(r"[^a-z0-9 ]+", " ", s)
    toks = [t for t in s.split() if t and t not in _LEGAL]
    return " ".join(toks).strip()


def domain(url: str | None) -> str:
    if not url:
        return ""
    u = url.strip()
    if "://" not in u:
        u = "http://" + u
    try:
        net = urlparse(u).netloc.lower()
    except Exception:
        return ""
    if net.startswith("www."):
        net = net[4:]
    return net


# Grandes villes / variantes fréquentes -> libellé canonique
_CITY_MAP = {
    "montreal": "Montréal", "mtl": "Montréal", "ville-marie": "Montréal",
    "quebec": "Québec", "quebec city": "Québec", "ville de quebec": "Québec",
    "laval": "Laval", "gatineau": "Gatineau", "hull": "Gatineau",
    "sherbrooke": "Sherbrooke", "trois rivieres": "Trois-Rivières",
    "saguenay": "Saguenay", "chicoutimi": "Saguenay", "jonquiere": "Saguenay",
    "levis": "Lévis", "longueuil": "Longueuil", "terrebonne": "Terrebonne",
    "brossard": "Brossard", "repentigny": "Repentigny", "drummondville": "Drummondville",
    "saint jean sur richelieu": "Saint-Jean-sur-Richelieu", "granby": "Granby",
    "blainville": "Blainville", "saint jerome": "Saint-Jérôme", "mirabel": "Mirabel",
    "rimouski": "Rimouski", "victoriaville": "Victoriaville", "shawinigan": "Shawinigan",
    "rouyn noranda": "Rouyn-Noranda", "sept iles": "Sept-Îles", "val d or": "Val-d'Or",
    "boucherville": "Boucherville", "mascouche": "Mascouche", "salaberry": "Salaberry-de-Valleyfield",
    "chateauguay": "Châteauguay", "saint hyacinthe": "Saint-Hyacinthe", "sorel": "Sorel-Tracy",
    "joliette": "Joliette", "magog": "Magog", "alma": "Alma", "thetford": "Thetford Mines",
}


def canonical_location(text: str | None) -> str:
    """Retourne un libellé de lieu canonique (ville QC connue, sinon 1er segment nettoyé)."""
    if not text:
        return ""
    base = strip_accents(text.lower())
    base = re.sub(r"[^a-z0-9 ]+", " ", base)
    base = re.sub(r"\s+", " ", base).strip()
    for kw, label in _CITY_MAP.items():
        if re.search(rf"\b{re.escape(kw)}\b", base):
            return label
    # sinon : 1er segment avant virgule, sans mentions province/pays
    seg = text.split(",")[0].strip()
    seg = re.sub(r"(?i)\b(qc|québec|quebec|canada)\b", "", seg).strip(" ,-")
    return seg[:60]