;;; tai-tham.el --- support for Tai Tham -*- coding: utf-8 -*-

;; Copyright (C) 2008, 2009, 2010, 2011
;;   National Institute of Advanced Industrial Science and Technology (AIST)
;;   Registration Number H13PRO009

;; Keywords: multilingual, Tai Tham, i18n

;; This file is part of GNU Emacs.

;; GNU Emacs is free software: you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
;; the Free Software Foundation, either version 3 of the License, or
;; (at your option) any later version.

;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
;; GNU General Public License for more details.

;; You should have received a copy of the GNU General Public License
;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.

;;; Code:

;; (set-language-info-alist
;;  "Northern Thai" '((charset unicode)
;; 		   (coding-system utf-8)
;;		   (coding-priority utf-8)
;;		   (sample-text .
;;		     "Northern Thai (ᨣᩣᩴᨾᩮᩬᩥᨦ / ᨽᩣᩈᩣᩃ᩶ᩣ᩠ᨶᨶᩣ)	ᩈ᩠ᩅᩢᩔ᩠ᨯᩦᨣᩕᩢ᩠ᨸ")
;;		   (documentation . t)))

;; To load:
;; (load-file "~/tham/tai-tham.el") tai-tham-composable-pattern
;; 

(defvar tai-tham-composable-pattern
  (let ((table
	 ;; C is letters, independent vowels, digits, punctuation and symbols.
	 '(("C" . "[\u1A20-\u1A54\u1A80-\u1A89\u1A90-\u1A99\u1AA0-\u1AAD]")
	   ("M" . "[\u1A55-\u1A57\u1A59-\u1A5E\u1A61-\u1A7C\u1A7F]"); Mark
	   ("H" . "\u1A60") ; sakot
           ("S" . "[\u1A75-\u1A7C]") ; Marks commuting with sakot
	   ("N" . "\u1A58"))) ; mai kang lai
;; The definition of a sequence of interacting Tai Tham characters is
;; surprisingly complicated.  The basic syllable structure should just be:
;;
;;                           C(M|HC)*
;;
;; There are three complications:
;;
;; 1. Emacs uses a backtracking regular expression engine, but it only
;;    backtracks if the characters accepted so far don't only match the regular
;;    expression.  Thus if M includes sakot, CHC will be parsed as CH and then
;;    C - there is no cause to backtrack!  On the other hand, missing consonants
;;    should not disrupt display - the glyph for sakot will normally alert the
;;    user that text entry is incomplete.
;;
;; 2. Some characters can be swapped round with sakot without changing the
;;    signification of the sequence of characters.  The regular expression
;;    works with strings of characters rather than traces of fully decomposed
;;    characters subject to Unicode's canonical equivalence.
;;
;; 3. Which syllable mai kang lai belongs to depends on the font.  Again, if
;;    M included mai kang lai, CNC would be parsed as CN and C.  The word
;;    ᨴᩘ᩠ᩃᩣ᩠ᨿ has mai kang lai in the middle of an orthographic syllable.
;	(basic_syllable "C\\(N*\\(M\\|HS*C?\\)\\)*")
	(basic_syllable "C\\(N*\\(M\\|HS*C\\)\\)*")
        (regexp "X\\(N\\(X\\)?\\)*H?")) ; X is basic syllable
    (let ((case-fold-search nil))
      (setq regexp (replace-regexp-in-string "X" basic_syllable regexp t t))
      (dolist (elt table)
	(setq regexp (replace-regexp-in-string (car elt) (cdr elt)
					       regexp t t))))
    regexp))

; Failed attempt to get proper composition for incomplete word ᨴᩘ᩠ᩃᩣ᩠.
;(let ((elt (list (vector tai-tham-composable-pattern 3 'font-shape-gstring)
;		 (vector tai-tham-composable-pattern 2 'font-shape-gstring)
;		 (vector tai-tham-composable-pattern 1 'font-shape-gstring)
;		 (vector tai-tham-composable-pattern 0 'font-shape-gstring)
;		 (vector "." 0 'font-shape-gstring)
;		 )))
;  (set-char-table-range composition-function-table '(#x1A20 . #x1AAD) elt))

(let ((elt (list (vector tai-tham-composable-pattern 0 'font-shape-gstring)
		 (vector "." 0 'font-shape-gstring)
		 )))
  (set-char-table-range composition-function-table '(#x1A20 . #x1AAD) elt))