"""Canonical postcode sanitisation for the domain layer.

The legacy postcode_splitter normalises postcodes inline with
``df["postcode"].str.upper().str.replace(" ", "")``. This module promotes
that operation to a pure, reusable function so the same canonical form is
applied wherever a postcode crosses a domain boundary -- including
:class:`domain.addresses.user_address.UserAddress` construction and future
migrations.
"""

from __future__ import annotations


def sanitise_postcode(s: str) -> str:
    """Return the canonical form of a postcode.

    The canonical form is uppercase with all whitespace removed. This matches
    the legacy splitter's ``str.upper().str.replace(" ", "")`` for the
    overwhelmingly common case of space-separated postcodes (e.g. ``"sw1a 1aa"``
    becomes ``"SW1A1AA"``) while also tolerating tabs/newlines that can creep
    in from CSV ingestion.
    """
    return "".join(s.split()).upper()