
    
Bj                        d Z ddlmZ ddlZddlZddlZddlmZ  ej                  e	      Z
 ej                  d      ZddlmZ d
dZddZdd	Zy)u  Shared helpers for canonicalising WhatsApp sender identity.

WhatsApp's bridge can surface the same human under two different JID shapes
within a single conversation:

- LID form: ``999999999999999@lid``
- Phone form: ``15551234567@s.whatsapp.net``

Both the authorisation path (:mod:`gateway.run`) and the session-key path
(:mod:`gateway.session`) need to collapse these aliases to a single stable
identity. This module is the single source of truth for that resolution so
the two paths can never drift apart.

Public helpers:

- :func:`normalize_whatsapp_identifier` — strip JID/LID/device/plus syntax
  down to the bare numeric identifier.
- :func:`canonical_whatsapp_identifier` — walk the bridge's
  ``lid-mapping-*.json`` files and return a stable canonical identity
  across phone/LID variants.
- :func:`expand_whatsapp_aliases` — return the full alias set for an
  identifier. Used by authorisation code that needs to match any known
  form of a sender against an allow-list.

Plugins that need per-sender behaviour on WhatsApp (role-based routing,
per-contact authorisation, policy gating in a gateway hook) should use
``canonical_whatsapp_identifier`` so their bookkeeping lines up with
Hermes' own session keys.
    )annotationsN)Setz^[A-Za-z0-9@.+\-]+$)get_hermes_homec                    t        | xs d      j                         j                  ddd      j                  dd      d   j                  dd      d   S )aN  Strip WhatsApp JID/LID syntax down to its stable numeric identifier.

    Accepts any of the identifier shapes the WhatsApp bridge may emit:
    ``"60123456789@s.whatsapp.net"``, ``"60123456789:47@s.whatsapp.net"``,
    ``"60123456789@lid"``, or a bare ``"+601****6789"`` / ``"60123456789"``.
    Returns just the numeric identifier (``"60123456789"``) suitable for
    equality comparisons.

    Useful for plugins that want to match sender IDs against
    user-supplied config (phone numbers in ``config.yaml``) without
    worrying about which variant the bridge happens to deliver.
     +   :r   @)strstripreplacesplit)values    >/home/ubuntu/.hermes/hermes-agent/gateway/whatsapp_identity.pynormalize_whatsapp_identifierr   0   sP     	EKR		b!		sAq	 
sAq		    c                F   t        |       }|s
t               S t               dz  dz  }t               }|g}|r|j                  d      }|r||v rt        j                  |      s0|j                  |       dD ]f  }|d| | dz  }|j                         s	 t        t        j                  |j                  d                  }|sQ||vsV|j                  |       h |r|S # t        t        j                  f$ r!}	t        j                  d	||	       Y d
}	~	d
}	~	ww xY w)a  Resolve WhatsApp phone/LID aliases via bridge session mapping files.

    Returns the set of all identifiers transitively reachable through the
    bridge's ``$HERMES_HOME/whatsapp/session/lid-mapping-*.json`` files,
    starting from ``identifier``. The result always includes the
    normalized input itself, so callers can safely ``in`` check against
    the return value without a separate fallback branch.

    Returns an empty set if ``identifier`` normalizes to empty.
    whatsappsessionr   )r   _reversezlid-mapping-z.jsonzutf-8)encodingz(whatsapp_identity: failed to read %s: %sN)r   setr   pop_SAFE_IDENTIFIER_REmatchaddexistsjsonloads	read_textOSErrorJSONDecodeErrorloggerdebugappend)

identifier
normalizedsession_dirresolvedqueuecurrentsuffixmapping_pathmappedexcs
             r   expand_whatsapp_aliasesr1   F   s(    /z:Ju!#j09<KHLE
))A,'X- #((1W& 	%F&<y)NNL&&(6JJ|55w5GH &0V$	%! < O T112 GWZ[s   .C&&D ?DD c                P    t        |       }|syt        |      }t        |d       S )u  Return a stable WhatsApp sender identity across phone-JID/LID variants.

    WhatsApp may surface the same person under either a phone-format JID
    (``60123456789@s.whatsapp.net``) or a LID (``1234567890@lid``). This
    applies to a DM ``chat_id`` *and* to the ``participant_id`` of a
    member inside a group chat — both represent a user identity, and the
    bridge may flip between the two for the same human.

    This helper reads the bridge's ``whatsapp/session/lid-mapping-*.json``
    files, walks the mapping transitively, and picks the shortest
    (numeric-preferred) alias as the canonical identity.
    :func:`gateway.session.build_session_key` uses this for both WhatsApp
    DM chat_ids and WhatsApp group participant_ids, so callers get the
    same session-key identity Hermes itself uses.

    Plugins that need per-sender behaviour (role-based routing,
    authorisation, per-contact policy) should use this so their
    bookkeeping lines up with Hermes' session bookkeeping even when
    the bridge reshuffles aliases.

    Returns an empty string if ``identifier`` normalizes to empty. If no
    mapping files exist yet (fresh bridge install), returns the
    normalized input unchanged.
    r   c                    t        |       | fS )N)len)	candidates    r   <lambda>z/canonical_whatsapp_identifier.<locals>.<lambda>   s    s9~y.I r   )key)r   r1   min)r'   r(   aliasess      r   canonical_whatsapp_identifierr:   z   s.    2 /z:J
 &j1GwIJJr   )r   r   returnr   )r'   r   r;   zSet[str])r'   r   r;   r   )__doc__
__future__r   r   loggingretypingr   	getLogger__name__r$   compiler   hermes_constantsr   r   r1   r:    r   r   <module>rF      sU   < #   	 			8	$
 !bjj!78  ,,1h!Kr   