;;; -*- Coding: utf-8 -*-  

;;; HAG (Hausa Grammar)

;;; Author: Berthold Crysmann
;;; 2009

;;; Basic tokenisation

:[ \t]+


; Remove initial marker of ungrammaticality
!^[\*]	


;; pad the full string with trailing and leading whitespace; makes matches for
;; word boundaries a little easier down the road; also, squash multiple spaces
;; and replace tabulators with a space.
;;
!^(.+)$								 \1 
!  +								 
!\t								 

; Split hyphened input tokens

! ([^ ]+[-])([^ ]+)							 \1 \2


; Do away with punctuation for now... 
!([,;?!.()]|``|'')	 


;; >char
;; >diacritics
;; >tone