webmail-client/backend/app/sync/folder_names.py

"""Special-use inference from folder names (SPEC §6.3 / §12 M2 fallback).

Used only when the server does not advertise the SPECIAL-USE extension. Matching
is accent- and punctuation-insensitive (so "Wysłane", "Éléments envoyés" and
"Junk E-mail" all resolve), covers the hierarchy leaf under any of the common
IMAP delimiters (``/  \\  .``), and recognises provider prefixes like
``[Gmail]/`` implicitly via the leaf. Names are curated per language rather than
substring-matched, so a folder like "Sent to John" is *not* misfiled as Sent.
"""

from __future__ import annotations

import unicodedata

# Latin letters NFKD doesn't decompose to ASCII; fold them explicitly.
_LATIN_SPECIAL = str.maketrans(
    {"ł": "l", "ø": "o", "đ": "d", "ð": "d", "ß": "ss", "æ": "ae", "œ": "oe", "ı": "i", "þ": "th"}
)


def _compact(name: str) -> str:
    """Fold to a comparable key: lowercase, strip accents/diacritics, drop every
    non-alphanumeric char. "Éléments envoyés" -> "elementsenvoyes"."""
    folded = unicodedata.normalize("NFKD", name.strip().lower()).translate(_LATIN_SPECIAL)
    return "".join(ch for ch in folded if ch.isalnum())


# Localized folder names by special_use. Written readably; compacted at load.
_NAMES: dict[str, list[str]] = {
    "sent": [
        "sent",
        "sent items",
        "sent mail",
        "sent messages",  # English / Outlook / Gmail
        "wysłane",
        "elementy wysłane",
        "wiadomości wysłane",  # Polish
        "gesendet",
        "gesendete objekte",
        "gesendete elemente",  # German
        "envoyés",
        "éléments envoyés",
        "messages envoyés",
        "courrier envoyé",  # French
        "enviados",
        "elementos enviados",
        "correo enviado",  # Spanish
        "inviata",
        "posta inviata",
        "messaggi inviati",  # Italian
        "verzonden",
        "verzonden items",
        "verzonden berichten",  # Dutch
        "enviadas",
        "itens enviados",
        "mensagens enviadas",  # Portuguese
        "отправленные",
        "исходящие",  # Russian
        "skickat",
        "skickade",
        "skickade objekt",  # Swedish
        "sendt",
        "sendte",
        "sendte elementer",  # Norwegian / Danish
        "lähetetyt",  # Finnish
        "odeslané",
        "odeslaná pošta",  # Czech
    ],
    "drafts": [
        "drafts",
        "draft",
        "robocze",
        "kopie robocze",
        "wersje robocze",
        "entwürfe",
        "entwurf",
        "brouillons",
        "borradores",
        "bozze",
        "concepten",
        "rascunhos",
        "черновики",
        "utkast",
        "kladder",  # Danish
        "luonnokset",  # Finnish
        "koncepty",  # Czech
    ],
    "trash": [
        "trash",
        "deleted",
        "deleted items",
        "deleted messages",
        "bin",
        "recycle bin",
        "kosz",
        "papierkorb",
        "gelöschte objekte",
        "gelöschte elemente",
        "corbeille",
        "éléments supprimés",
        "papelera",
        "elementos eliminados",
        "cestino",
        "posta eliminata",
        "prullenbak",
        "verwijderde items",
        "lixeira",
        "lixo",
        "itens excluídos",
        "корзина",
        "удаленные",
        "papperskorg",
        "borttaget",
        "papirkurv",
        "slettet",
        "roskakori",
        "poistetut",
        "koš",  # Czech
    ],
    "junk": [
        "junk",
        "junk email",
        "junk e-mail",
        "spam",
        "bulk mail",
        "bulk",
        "wiadomości-śmieci",
        "niechciane",
        "unerwünscht",
        "werbung",
        "courrier indésirable",
        "indésirables",
        "pourriel",
        "correo no deseado",
        "no deseado",
        "correo basura",
        "posta indesiderata",
        "indesiderata",
        "ongewenst",
        "ongewenste e-mail",
        "lixo eletrônico",
        "спам",
        "нежелательная почта",
        "skräp",
        "skräppost",
        "uønsket",
        "roskaposti",
        "nevyžádaná pošta",
    ],
    "archive": [
        "archive",
        "archives",
        "all mail",
        "archiwum",
        "archiv",
        "archivio",
        "archivo",
        "archief",
        "arquivo",
        "arquivo morto",
        "архив",
        "вся почта",
        "arkiv",
        "arkisto",
    ],
}

_NAME_MAP: dict[str, str] = {
    _compact(name): special for special, names in _NAMES.items() for name in names
}


def infer_special_use(path: str) -> str | None:
    """Infer a special_use value from a mailbox path/name (accent-insensitive)."""
    if path.strip().upper().rstrip("/.") == "INBOX":
        return "inbox"
    # Take the hierarchy leaf under any common IMAP delimiter (/ \ or . for
    # Dovecot/Courier namespaces), then fold for lookup.
    normalized = path
    for delim in ("/", "\\", "."):
        normalized = normalized.replace(delim, "\n")
    segments = [s for s in normalized.split("\n") if s.strip()]
    tail = segments[-1] if segments else path
    return _NAME_MAP.get(_compact(tail)) or _NAME_MAP.get(_compact(path))