Mercurial > hg > xemacs-beta

view lisp/mule/tibetan.el @ 5157:1fae11d56ad2

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
redo memory-usage mechanism, add way of dynamically initializing Lisp objects -------------------- ChangeLog entries follow: -------------------- lisp/ChangeLog addition: 2010-03-18 Ben Wing <ben@xemacs.org> * diagnose.el (show-memory-usage): Rewrite to take into account API changes in memory-usage functions. src/ChangeLog addition: 2010-03-18 Ben Wing <ben@xemacs.org> * alloc.c: * alloc.c (disksave_object_finalization_1): * alloc.c (lisp_object_storage_size): * alloc.c (listu): * alloc.c (listn): * alloc.c (Fobject_memory_usage_stats): * alloc.c (compute_memusage_stats_length): * alloc.c (Fobject_memory_usage): * alloc.c (Ftotal_object_memory_usage): * alloc.c (malloced_storage_size): * alloc.c (common_init_alloc_early): * alloc.c (reinit_alloc_objects_early): * alloc.c (reinit_alloc_early): * alloc.c (init_alloc_once_early): * alloc.c (syms_of_alloc): * alloc.c (reinit_vars_of_alloc): * buffer.c: * buffer.c (struct buffer_stats): * buffer.c (compute_buffer_text_usage): * buffer.c (compute_buffer_usage): * buffer.c (buffer_memory_usage): * buffer.c (buffer_objects_create): * buffer.c (syms_of_buffer): * buffer.c (vars_of_buffer): * console-impl.h (struct console_methods): * dynarr.c (Dynarr_memory_usage): * emacs.c (main_1): * events.c (clear_event_resource): * extents.c: * extents.c (compute_buffer_extent_usage): * extents.c (extent_objects_create): * extents.h: * faces.c: * faces.c (compute_face_cachel_usage): * faces.c (face_objects_create): * faces.h: * general-slots.h: * glyphs.c: * glyphs.c (compute_glyph_cachel_usage): * glyphs.c (glyph_objects_create): * glyphs.h: * lisp.h: * lisp.h (struct usage_stats): * lrecord.h: * lrecord.h (enum lrecord_type): * lrecord.h (struct lrecord_implementation): * lrecord.h (MC_ALLOC_CALL_FINALIZER_FOR_DISKSAVE): * lrecord.h (DEFINE_DUMPABLE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_FROB_BLOCK_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_INTERNAL_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_SIZABLE_INTERNAL_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_FROB_BLOCK_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_FROB_BLOCK_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_INTERNAL_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_SIZABLE_INTERNAL_LISP_OBJECT): * lrecord.h (MAKE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_MODULE_LISP_OBJECT): * lrecord.h (DEFINE_DUMPABLE_MODULE_SIZABLE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_MODULE_LISP_OBJECT): * lrecord.h (DEFINE_NODUMP_MODULE_SIZABLE_LISP_OBJECT): * lrecord.h (MAKE_MODULE_LISP_OBJECT): * lrecord.h (INIT_LISP_OBJECT): * lrecord.h (INIT_MODULE_LISP_OBJECT): * lrecord.h (UNDEF_LISP_OBJECT): * lrecord.h (UNDEF_MODULE_LISP_OBJECT): * lrecord.h (DECLARE_LISP_OBJECT): * lrecord.h (DECLARE_MODULE_API_LISP_OBJECT): * lrecord.h (DECLARE_MODULE_LISP_OBJECT): * lstream.c: * lstream.c (syms_of_lstream): * lstream.c (vars_of_lstream): * marker.c: * marker.c (compute_buffer_marker_usage): * mc-alloc.c (mc_alloced_storage_size): * mc-alloc.h: * mule-charset.c: * mule-charset.c (struct charset_stats): * mule-charset.c (compute_charset_usage): * mule-charset.c (charset_memory_usage): * mule-charset.c (mule_charset_objects_create): * mule-charset.c (syms_of_mule_charset): * mule-charset.c (vars_of_mule_charset): * redisplay.c: * redisplay.c (compute_rune_dynarr_usage): * redisplay.c (compute_display_block_dynarr_usage): * redisplay.c (compute_glyph_block_dynarr_usage): * redisplay.c (compute_display_line_dynarr_usage): * redisplay.c (compute_line_start_cache_dynarr_usage): * redisplay.h: * scrollbar-gtk.c (gtk_compute_scrollbar_instance_usage): * scrollbar-msw.c (mswindows_compute_scrollbar_instance_usage): * scrollbar-x.c (x_compute_scrollbar_instance_usage): * scrollbar.c (compute_scrollbar_instance_usage): * scrollbar.h: * symbols.c: * symbols.c (reinit_symbol_objects_early): * symbols.c (init_symbols_once_early): * symbols.c (reinit_symbols_early): * symbols.c (defsymbol_massage_name_1): * symsinit.h: * ui-gtk.c: * ui-gtk.c (emacs_gtk_object_getprop): * ui-gtk.c (emacs_gtk_object_putprop): * ui-gtk.c (ui_gtk_objects_create): * unicode.c (compute_from_unicode_table_size_1): * unicode.c (compute_to_unicode_table_size_1): * unicode.c (compute_from_unicode_table_size): * unicode.c (compute_to_unicode_table_size): * window.c: * window.c (struct window_stats): * window.c (compute_window_mirror_usage): * window.c (compute_window_usage): * window.c (window_memory_usage): * window.c (window_objects_create): * window.c (syms_of_window): * window.c (vars_of_window): * window.h: Redo memory-usage mechanism, make it general; add way of dynamically initializing Lisp object types -- OBJECT_HAS_METHOD(), similar to CONSOLE_HAS_METHOD(). (1) Create OBJECT_HAS_METHOD(), OBJECT_HAS_PROPERTY() etc. for specifying that a Lisp object type has a particular method or property. Call such methods with OBJECT_METH, MAYBE_OBJECT_METH, OBJECT_METH_OR_GIVEN; retrieve properties with OBJECT_PROPERTY. Methods that formerly required a DEFINE_*GENERAL_LISP_OBJECT() to specify them (getprop, putprop, remprop, plist, disksave) now instead use the dynamic-method mechanism. The main benefit of this is that new methods or properties can be added without requiring that the declaration statements of all existing methods be modified. We have to make the `struct lrecord_implementation' non-const, but I don't think this should have any effect on speed -- the only possible method that's really speed-critical is the mark method, and we already extract those out into a separate (non-const) array for increased cache locality. Object methods need to be reinitialized after pdump, so we put them in separate functions such as face_objects_create(), extent_objects_create() and call them appropriately from emacs.c The only current object property (`memusage_stats_list') that objects can specify is a Lisp object and gets staticpro()ed so it only needs to be set during dump time, but because it references symbols that might not exist in a syms_of_() function, we initialize it in vars_of_(). There is also an object property (`num_extra_memusage_stats') that is automatically initialized based on `memusage_stats_list'; we do that in reinit_vars_of_alloc(), which is called after all vars_of_() functions are called. `disksaver' method was renamed `disksave' to correspond with the name normally given to the function (e.g. disksave_lstream()). (2) Generalize the memory-usage mechanism in `buffer-memory-usage', `window-memory-usage', `charset-memory-usage' into an object-type- specific mechanism called by a single function `object-memory-usage'. (Former function `object-memory-usage' renamed to `total-object-memory-usage'). Generalize the mechanism of different "slices" so that we can have different "classes" of memory described and different "slices" onto each class; `t' separates classes, `nil' separates slices. Currently we have three classes defined: the memory of an object itself, non-Lisp-object memory associated with the object (e.g. arrays or dynarrs stored as fields in the object), and Lisp-object memory associated with the object (other internal Lisp objects stored in the object). This isn't completely finished yet and we might need to further separate the "other internal Lisp objects" class into two classes. The memory-usage mechanism uses a `struct usage_stats' (renamed from `struct overhead_stats') to describe a malloc-view onto a set of allocated memory (listing how much was requested and various types of overhead) and a more general `struct generic_usage_stats' (with a `struct usage_stats' in it) to hold all statistics about object memory. `struct generic_usage_stats' contains an array of 32 Bytecounts, which are statistics of unspecified semantics. The intention is that individual types declare a corresponding struct (e.g. `struct window_stats') with the same structure but with specific fields in place of the array, corresponding to specific statistics. The number of such statistics is an object property computed from the list of tags (Lisp symbols describing the statistics) stored in `memusage_stats_list'. The idea here is to allow particular object types to customize the number and semantics of the statistics where completely avoiding consing. This doesn't matter so much yet, but the intention is to have the memory usage of all objects computed at the end of GC, at the same time as other statistics are currently computed. The values for all statistics for a single type would be added up to compute aggregate values for all objects of a specific type. To make this efficient, we can't allow any memory allocation at all. (3) Create some additional functions for creating lists that specify the elements directly as args rather than indirectly through an array: listn() (number of args given), listu() (list terminated by Qunbound). (4) Delete a bit of remaining unused C window_config stuff, also unused lrecord_type_popup_data.
author Ben Wing <ben@xemacs.org>
date Thu, 18 Mar 2010 10:50:06 -0500
parents 949ac151a10d
children 308d34e9f07d
line wrap: on
line source

;;; tibetan.el --- support for Tibetan language -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN.
;; Copyright (C) 2002 Ben Wing.
;; Licensed to the Free Software Foundation.

;; Keywords: multilingual, Tibetan

;; This file is part of XEmacs.

;; XEmacs 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 2, or (at your option)
;; any later version.

;; XEmacs 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 XEmacs; see the file COPYING.  If not, write to the Free
;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
;; 02111-1307, USA.

;;; Synched up with: Emacs 21.1 (language/tibetan.el).

;; Author: Toru TOMABECHI, <Toru.Tomabechi@orient.unil.ch>

;; Created: Feb. 17. 1997

;; History:
;; 1997.03.13 Modification for special signs and punctuations. 

;;; Commentary:

;;; Code:

;;; Tibetan Character set.
;;; \x2130 -- \x234a is a subset of Unicode v.2 \x0f00 - \x0fb9
;;; with a slight modification. And there are some subjoined
;;; consonants which are not specified in Unicode.
;;; I hope I can add missing characters later.
;;;
;;;     00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
;;;2120 // $(7!!(B $(7!"(B $(7!#(B $(7!$(B $(7!%(B $(7!&(B $(7!'(B $(7!((B $(7!)(B $(7!*(B $(7!+(B $(7!,(B $(7!-(B $(7!.(B $(7!/(B ; obsolete glyphs (2123-5)
;;;2130 $(7!0(B $(7!1(B $(7!2(B $(7!3(B $(7!4(B $(7!5(B $(7!6(B $(7!7(B $(7!8(B $(7!9(B $(7!:(B $(7!;(B $(7!<(B $(7!=(B $(7!>(B $(7!?(B ; Punctuations,
;;;2140 $(7!@(B $(7!A(B $(7!B(B $(7!C(B $(7!D(B $(7!E(B $(7!F(B $(7!G(B $(7!H(B $(7!I(B $(7!J(B $(7!K(B $(7!L(B $(7!M(B $(7!N(B $(7!O(B ; Digits and
;;;2150 $(7!P(B $(7!Q(B $(7!R(B $(7!S(B $(7!T(B $(7!U(B $(7!V(B $(7!W(B $(7!X(B $(7!Y(B $(7!Z(B $(7![(B $(7!\(B $(7!](B $(7!^(B $(7!_(B ; Special signs.
;;;2160 $(7!`(B $(7!a(B $(7!b(B $(7!c(B $(7!d(B $(7!e(B $(7!f(B $(7!g(B $(7!h(B $(7!i(B $(7!j(B $(7!k(B $(7!l(B $(7!m(B $(7!n(B $(7!o(B ;
;;;2170 $(7!p(B $(7!q(B $(7!r(B $(7!s(B $(7!t(B $(7!u(B $(7!v(B $(7!w(B $(7!x(B $(7!y(B $(7!z(B $(7!{(B $(7!|(B $(7!}(B $(7!~(B // ;
;;;
;;;     00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
;;;2220 // $(7"!(B $(7""(B $(7"#(B $(7"$(B $(7"%(B $(7"&(B $(7"'(B $(7"((B $(7")(B $(7"*(B $(7"+(B $(7",(B $(7"-(B $(7".(B $(7"/(B ; Base consonants
;;;2230 $(7"0(B $(7"1(B $(7"2(B $(7"3(B $(7"4(B $(7"5(B $(7"6(B $(7"7(B $(7"8(B $(7"9(B $(7":(B $(7";(B $(7"<(B $(7"=(B $(7">(B $(7"?(B ; and
;;;2240 $(7"@(B $(7"A(B $(7"B(B $(7"C(B $(7"D(B $(7"E(B $(7"F(B $(7"G(B $(7"H(B $(7"I(B $(7"J(B $(7"K(B $(7"L(B $(7"M(B $(7"N(B $(7"O(B ; Vowel signs.
;;;2250 $(7"P(B $(7"Q(B $(7"R(B $(7"S(B $(7"T(B $(7"U(B $(7"V(B $(7"W(B $(7"X(B $(7"Y(B $(7"Z(B $(7"[(B $(7"\(B $(7"](B $(7"^(B $(7"_(B ; (\x2251 = vowel a)
;;;2260 $(7"`(B $(7"a(B $(7"b(B $(7"c(B $(7"d(B $(7"e(B $(7"f(B $(7"g(B $(7"h(B $(7"i(B $(7"j(B $(7"k(B $(7"l(B $(7"m(B $(7"n(B $(7"o(B ; Long vowels and
;;;2270 $(7"p(B $(7"q(B $(7"r(B $(7"s(B $(7"t(B $(7"u(B $(7"v(B $(7"w(B $(7"x(B $(7"y(B $(7"z(B $(7"{(B $(7"|(B $(7"}(B $(7"~(B // ; vocalic r, l ARE
;;;                                                     ; atomically
;;;                                                     ; encoded. 
;;;     00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
;;;2320 // $(7#!(B $(7#"(B $(7##(B $(7#$(B $(7#%(B $(7#&(B $(7#'(B $(7#((B $(7#)(B $(7#*(B $(7#+(B $(7#,(B $(7#-(B $(7#.(B $(7#/(B ; Subjoined consonants
;;;2330 $(7#0(B $(7#1(B $(7#2(B $(7#3(B $(7#4(B $(7#5(B $(7#6(B $(7#7(B $(7#8(B $(7#9(B $(7#:(B $(7#;(B $(7#<(B $(7#=(B $(7#>(B $(7#?(B ;
;;;2340 $(7#@(B $(7#A(B $(7#B(B $(7#C(B $(7#D(B $(7#E(B $(7#F(B $(7#G(B $(7#H(B $(7#I(B $(7#J(B $(7#K(B $(7#L(B $(7#M(B $(7#N(B $(7#O(B ;
;;;2350 $(7#P(B $(7#Q(B $(7#R(B $(7#S(B $(7#T(B $(7#U(B $(7#V(B $(7#W(B $(7#X(B $(7#Y(B $(7#Z(B $(7#[(B $(7#\(B $(7#](B $(7#^(B $(7#_(B ; Hereafter, the chars
;;;2360 $(7#`(B $(7#a(B $(7#b(B $(7#c(B $(7#d(B $(7#e(B $(7#f(B $(7#g(B $(7#h(B $(7#i(B $(7#j(B $(7#k(B $(7#l(B $(7#m(B $(7#n(B $(7#o(B ; are not specified
;;;2370 $(7#p(B $(7#q(B $(7#r(B $(7#s(B $(7#t(B $(7#u(B $(7#v(B $(7#w(B $(7#x(B $(7#y(B $(7#z(B $(7#{(B $(7#|(B $(7#}(B $(7#~(B // ; in Unicode.
;;;
;;;     00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F
;;;2420 // $(7$!(B $(7$"(B $(7$#(B $(7$$(B $(7$%(B $(7$&(B $(7$'(B $(7$((B $(7$)(B $(7$*(B $(7$+(B $(7$,(B $(7$-(B $(7$.(B $(7$/(B ; Precomposed
;;;2430 $(7$0(B $(7$1(B $(7$2(B $(7$3(B $(7$4(B $(7$5(B $(7$6(B $(7$7(B $(7$8(B $(7$9(B $(7$:(B $(7$;(B $(7$<(B $(7$=(B $(7$>(B $(7$?(B ; consonants for
;;;2440 $(7$@(B $(7$A(B $(7$B(B $(7$C(B $(7$D(B $(7$E(B $(7$F(B $(7$G(B $(7$H(B $(7$I(B $(7$J(B $(7$K(B $(7$L(B $(7$M(B $(7$N(B $(7$O(B ; ordinary Tibetan.
;;;2450 $(7$P(B $(7$Q(B $(7$R(B $(7$S(B $(7$T(B $(7$U(B $(7$V(B $(7$W(B $(7$X(B $(7$Y(B $(7$Z(B $(7$[(B $(7$\(B $(7$](B $(7$^(B $(7$_(B ; They are decomposed
;;;2460 $(7$`(B $(7$a(B $(7$b(B $(7$c(B $(7$d(B $(7$e(B $(7$f(B $(7$g(B $(7$h(B $(7$i(B $(7$j(B $(7$k(B $(7$l(B $(7$m(B $(7$n(B $(7$o(B ; into base and 
;;;2470 $(7$p(B $(7$q(B $(7$r(B $(7$s(B $(7$t(B $(7$u(B $(7$v(B $(7$w(B $(7$x(B $(7$y(B $(7$z(B $(7${(B $(7$|(B $(7$}(B $(7$~(B // ; subjoined consonants
;;;                                                     ; when written on a
;;;     00 01 02 03 04 05 06 07 08 09 0A 0B 0C 0D 0E 0F ; file in Tibetan
;;;2520 // $(7%!(B $(7%"(B $(7%#(B $(7%$(B $(7%%(B $(7%&(B $(7%'(B $(7%((B $(7%)(B $(7%*(B $(7%+(B $(7%,(B $(7%-(B $(7%.(B $(7%/(B ; coding system.
;;;2530 $(7%0(B $(7%1(B $(7%2(B $(7%3(B $(7%4(B $(7%5(B $(7%6(B $(7%7(B $(7%8(B $(7%9(B $(7%:(B $(7%;(B $(7%<(B $(7%=(B $(7%>(B $(7%?(B ;
;;;2540 $(7%@(B $(7%A(B $(7%B(B $(7%C(B $(7%D(B $(7%E(B $(7%F(B $(7%G(B $(7%H(B $(7%I(B $(7%J(B $(7%K(B $(7%L(B $(7%M(B $(7%N(B $(7%O(B ;
;;;2550 $(7%P(B $(7%Q(B $(7%R(B $(7%S(B $(7%T(B $(7%U(B $(7%V(B $(7%W(B $(7%X(B $(7%Y(B $(7%Z(B $(7%[(B $(7%\(B $(7%](B $(7%^(B $(7%_(B ;
;;;2560 $(7%`(B $(7%a(B $(7%b(B $(7%c(B $(7%d(B $(7%e(B $(7%f(B $(7%g(B $(7%h(B $(7%i(B $(7%j(B $(7%k(B $(7%l(B $(7%m(B $(7%n(B $(7%o(B ;
;;;2570 $(7%p(B $(7%q(B $(7%r(B $(7%s(B $(7%t(B $(7%u(B $(7%v(B $(7%w(B $(7%x(B $(7%y(B $(7%z(B $(7%{(B $(7%|(B $(7%}(B $(7%~(B // ;
;;;

(make-charset 'tibetan-1-column "Tibetan 1 column glyph"
	      '(dimension
		2
		registries ["MuleTibetan-1"]
		chars 94
		columns 1
		direction l2r
		final ?8
		graphic 0
		short-name "Tibetan 1-col"
		long-name "Tibetan 1 column"
		))

;; Tibetan script.
(make-charset 'tibetan "Tibetan characters"
	      '(dimension
		2
		registries ["MuleTibetan-2"]
		chars 94
		columns 2
		direction l2r
		final ?7
		graphic 0
		short-name "Tibetan 2-col"
		long-name "Tibetan 2 column"
		))

; (make-coding-system
;  'tibetan-iso-8bit 2 ?Q
;  "8-bit encoding for ASCII (MSB=0) and TIBETAN (MSB=1)"
;  '(ascii tibetan nil nil
;    nil nil)
;  '((safe-charsets ascii tibetan)
;    (post-read-conversion . tibetan-post-read-conversion)
;    (pre-write-conversion . tibetan-pre-write-conversion)))

(make-coding-system
 'tibetan-iso-8bit 'iso2022 "Tibetan/8-bit"
 '(charset-g0 ascii
   charset-g1 tibetan
   mnemonic "Tibetan"
   safe-charsets (ascii tibetan)
   post-read-conversion tibetan-post-read-conversion
   pre-write-conversion tibetan-pre-write-conversion
   documentation "8-bit encoding for ASCII (MSB=0) and TIBETAN (MSB=1)"))

(define-coding-system-alias 'tibetan 'tibetan-iso-8bit)

(set-language-info-alist
 "Tibetan" '((charset tibetan tibetan-1-column)
	     (coding-system tibetan-iso-8bit)
	     (coding-priority iso-2022-7bit tibetan-iso-8bit)
             ;; Not available in packages. 
	     ;; (input-method . "tibetan-wylie")
	     (features tibet-util)
	     (documentation . t)
	     (sample-text 
	      . (tibetan-compose-string
		 (copy-sequence
"Tibetan (4$(7"7r'"]0"7"]14"20"21!;4%P0"G#!"Q14"20"21!;(B) $(7!4!5!5!>4"70"714$P0"!#C"Q1!;4"Er'"S0"E"S14"G0"G1!;4"70"714"2r'"[0"2"[1!;4"Dr'"[0"D"[14"#0"#14"G0"G1!>4"Ir'"]r'"_0"I"]"_1!;4"90"9"Q1!;4"/r'"S0"/"S1!;4"50"5"Q14#2x!#9r'"[0"2#9"[1!;4"Hx!"Rx!"Ur'"c0"H"A"U"c1!>(B")))))


;; `$(7"A(B' is included in the pattern for subjoined consonants because we
;; treat it specially in tibetan-add-components.
;; modified by Tomabechi 1999/12/10
;; modified by Tomabechi 2000/06/08
;;          To allow infinite addition of vowels/modifiers
;;          as specified in Unicode v.3
;; $(7"A(B is removed from the class of subjoined. Tomabechi 2000/06/08
;; (for Unicode support)
(defconst tibetan-composable-pattern
  "[$(7"!(B-$(7"J"K(B][$(7#!(B-$(7#J#K#L#M(B]*[$(7"Q"R"S(B-$(7"^"a"b"e(B]*[$(7"_"c"d"g(B-$(7"l!I!e!g(B]*"
  "Regexp matching a composable sequence of Tibetan characters.")

;; Register a function to compose Tibetan characters.
(put-char-table 'tibetan
		(list (cons tibetan-composable-pattern
			    'tibetan-composition-function))
		composition-function-table)

;;;
;;; Definitions of conversion data.
;;;


;;; alists for tibetan char <-> transcription conversion
;;; longer transcription should come first
(defconst tibetan-consonant-transcription-alist
  '(("tsh" . "$(7";(B")
    ("dzh" . "$(7"=(B")
    ("kSH" . "$(7"J(B")
    ("kh" . "$(7""(B")
    ("gh" . "$(7"$(B")
    ("ng" . "$(7"%(B")
    ("ch" . "$(7"'(B")
    ("ny" . "$(7"*(B")
    ("TH" . "$(7",(B")
    ("DH" . "$(7".(B")
    ("th" . "$(7"1(B")
    ("dh" . "$(7"3(B")
    ("ph" . "$(7"6(B")
    ("bh" . "$(7"8(B")
    ("ts" . "$(7":(B")
    ("dz" . "$(7"<(B")
    ("zh" . "$(7"?(B")
    ("sh" . "$(7"E(B")
    ("SH" . "$(7"F(B")
    ("k" . "$(7"!(B")
    ("g" . "$(7"#(B")
    ("c" . "$(7"&(B")
    ("j" . "$(7"((B")
    ("T" . "$(7"+(B")
    ("D" . "$(7"-(B")
    ("N" . "$(7"/(B")
    ("t" . "$(7"0(B")
    ("d" . "$(7"2(B")
    ("n" . "$(7"4(B")
    ("p" . "$(7"5(B")
    ("b" . "$(7"7(B")
    ("m" . "$(7"9(B")
    ("w" . "$(7">(B")
    ("z" . "$(7"@(B")
    ("'" . "$(7"A(B")
    ("y" . "$(7"B(B")
    ("r" . "$(7"C(B")
    ("l" . "$(7"D(B")
    ("s" . "$(7"G(B")
    ("h" . "$(7"H(B")
    ("H" . "$(7"H(B")
    ("A" . "$(7"I(B")
    ;; Added by Tomabechi 1999/12/10
    ("R" . "$(7"K(B") ;; fixed form RA
    ))


(defconst tibetan-vowel-transcription-alist
  '(
    ;; Composite Vowels
    ;; Added by Tomabechi 2000/06/08
    ("frr" . "$(7"X(B")
    ("fll" . "$(7"Z(B")
    ("fa" . "$(7"R(B")
    ("fi" . "$(7"T(B")
    ("fu" . "$(7"V(B")
    ("fr" . "$(7"W(B")
    ("fl" . "$(7"Y(B")
    ("fI" . "$(7"b(B")
    ;; Normal Vowels
    ("ai" . "$(7"\(B")
    ("au" . "$(7"^(B")
    ("ee" . "$(7"\(B")
    ("oo" . "$(7"^(B")
    ("a" . "$(7"Q(B")			; invisible vowel sign (\x2251)
    ("i" . "$(7"S(B")
    ("u" . "$(7"U(B")
    ("e" . "$(7"[(B")
    ("o" . "$(7"](B")
    ("E" . "$(7"\(B")
    ("O" . "$(7"^(B")
    ("I" . "$(7"a(B")
    ("," . "$(7"e(B")			; idem.
    ))

(defconst tibetan-modifier-transcription-alist
  '(("M" . "$(7"_(B")
    ("~" . "$(7"c(B")
    ("`" . "$(7"d(B")
    ("x" . "$(7"i(B")
    ("X" . "$(7"j(B")
    ("v" . "$(7"g(B")
    ("V" . "$(7"h(B")
    ("q" . "$(7"k(B")
    ("Q" . "$(7"l(B")
    ("_/" . "$(7!I(B")
    ("_o" . "$(7!g(B")
    ("_O" . "$(7!e(B")))

(defconst tibetan-precomposed-transcription-alist
  '(("phyw" . "$(7$G(B")
    ("tshw" . "$(7$)(B")
    ("rtsw" . "$(7%.(B")
    ("khw" . "$(7$"(B")
    ("nyw" . "$(7$%(B")
    ("tsw" . "$(7$((B")
    ("zhw" . "$(7$*(B")
    ("shw" . "$(7$.(B")
    ("khy" . "$(7$A(B")
    ("phy" . "$(7$D(B")
    ("khr" . "$(7$Q(B")
    ("thr" . "$(7$T(B")
    ("phr" . "$(7$W(B")
    ("shr" . "$(7$Z(B")
    ("dzr" . "$(7$^(B")
    ("grw" . "$(7$_(B")
    ("rng" . "$(7%#(B")
    ("rny" . "$(7%%(B")
    ("rts" . "$(7%+(B")
    ("rdz" . "$(7%,(B")
    ("rgw" . "$(7%-(B")
    ("rky" . "$(7%0(B")
    ("rgy" . "$(7%1(B")
    ("rmy" . "$(7%2(B")
    ("lng" . "$(7%B(B")
    ("sng" . "$(7%R(B")
    ("sny" . "$(7%S(B")
    ("sts" . "$(7%Z(B")
    ("sky" . "$(7%`(B")
    ("sgy" . "$(7%a(B")
    ("spy" . "$(7%b(B")
    ("sby" . "$(7%c(B")
    ("smy" . "$(7%d(B")
    ("skr" . "$(7%p(B")
    ("sgr" . "$(7%q(B")
    ("snr" . "$(7%r(B")
    ("spr" . "$(7%s(B")
    ("sbr" . "$(7%t(B")
    ("smr" . "$(7%u(B")
    ("kw" . "$(7$!(B")
    ("gw" . "$(7$#(B")
    ("cw" . "$(7$$(B")
    ("tw" . "$(7$&(B")
    ("dw" . "$(7$'(B")
    ("zw" . "$(7$+(B")
    ("rw" . "$(7$,(B")
    ("lw" . "$(7$-(B")
    ("sw" . "$(7$/(B")
    ("hw" . "$(7$0(B")
    ("ky" . "$(7$@(B")
    ("gy" . "$(7$B(B")
    ("py" . "$(7$C(B")
    ("by" . "$(7$E(B")
    ("my" . "$(7$F(B")
    ("kr" . "$(7$P(B")
    ("gr" . "$(7$R(B")
    ("tr" . "$(7$S(B")
    ("dr" . "$(7$U(B")
    ("pr" . "$(7$V(B")
    ("brk" . "$(7"7%!(B")
    ("brg" . "$(7"7%"(B")
    ("brng" . "$(7"7%#(B")
    ("brj" . "$(7"7%$(B")
    ("brny" . "$(7"7%%(B")
    ("brt" .  "$(7"7%&(B")
    ("brd" . "$(7"7%'(B")
    ("brn" . "$(7"7%((B")
    ("brts" . "$(7"7%+(B")
    ("brdz" . "$(7"7%,(B")
    ("brl" . "$(7"7$d(B")
    ("br" . "$(7$X(B")
    ("mr" . "$(7$Y(B")
    ("sr" . "$(7$[(B")
    ("hr" . "$(7$\(B")
    ("jr" . "$(7$](B")
    ("kl" . "$(7$`(B")
    ("gl" . "$(7$a(B")
    ("blt" . "$(7"7%E(B")
    ("bld" . "$(7"7%F(B")
    ("bl" . "$(7$b(B")
    ("zl" . "$(7$c(B")
    ("rl" . "$(7$d(B")
    ("sl" . "$(7$e(B")
    ("rk" . "$(7%!(B")
    ("rg" . "$(7%"(B")
    ("rj" . "$(7%$(B")
    ("rt" . "$(7%&(B")
    ("rd" . "$(7%'(B")
    ("rn" . "$(7%((B")
    ("rb" . "$(7%)(B")
    ("rm" . "$(7%*(B")
    ("lk" . "$(7%@(B")
    ("lg" . "$(7%A(B")
    ("lc" . "$(7%C(B")
    ("lj" . "$(7%D(B")
    ("lt" . "$(7%E(B")
    ("ld" . "$(7%F(B")
    ("ln" . "$(7!!(B")			; dummy \x2121
    ("lp" . "$(7%G(B")
    ("lb" . "$(7%H(B")
    ("lh" . "$(7%I(B")
    ("sk" . "$(7%P(B")
    ("sg" . "$(7%Q(B")
    ("st" . "$(7%T(B")
    ("sd" . "$(7%U(B")
    ("sn" . "$(7%V(B")
    ("sp" . "$(7%W(B")
    ("sb" . "$(7%X(B")
    ("sm" . "$(7%Y(B"))
  )


(defconst tibetan-subjoined-transcription-alist
  (sort '(("+k"  . "$(7#!(B")
	  ("+kh" . "$(7#"(B")
	  ("+g"  . "$(7##(B")
	  ("+gh" . "$(7#$(B")
	  ("+ng" . "$(7#%(B")
	  ("+c"  . "$(7#&(B")
	  ("+ch" . "$(7#'(B")
	  ("+j"  . "$(7#((B")
	  ("+ny"  . "$(7#*(B")
	  ("+T"  . "$(7#+(B")
	  ("+TH" . "$(7#,(B")
	  ("+D"  . "$(7#-(B")
	  ("+DH" . "$(7#.(B")
	  ("+N"  . "$(7#/(B")
	  ("+t"  . "$(7#0(B")
	  ("+th" . "$(7#1(B")
	  ("+d"  . "$(7#2(B")
	  ("+dh" . "$(7#3(B")
	  ("+n"  . "$(7#4(B")
	  ("+p"  . "$(7#5(B")
	  ("+ph" . "$(7#6(B")
	  ("+b"  . "$(7#7(B")
	  ("+bh" . "$(7#8(B")
	  ("+m"  . "$(7#9(B")
	  ("+ts" . "$(7#:(B")
	  ("+tsh" . "$(7#;(B")
	  ("+dz" . "$(7#<(B")
	  ("+dzh" . "$(7#=(B")
	  ("+w"  . "$(7#>(B")
	  ("+zh" . "$(7#?(B")
	  ("+z"  . "$(7#@(B")
	  ("+'"  . "$(7#A(B")
	  ("+y"  . "$(7#B(B")
	  ("+r"  . "$(7#C(B")
	  ("+l"  . "$(7#D(B")
	  ("+sh" . "$(7#E(B")
	  ("+SH" . "$(7#F(B")
	  ("+s"  . "$(7#G(B")
	  ("+h"  . "$(7#H(B")
	  ("+A"  . "$(7#I(B")
	  ("+kSH" . "$(7#J(B")
	  ;; Added by Tomabechi 1999/12/10
	  ("+W" . "$(7#K(B") ;; fixed form subscribed WA
	  ("+Y" . "$(7#L(B") ;; fixed form subscribed YA
	  ("+R" . "$(7#M(B") ;; fixed form subscribed RA
	  )
	(lambda (x y) (> (length (car x)) (length (car y))))))

;;;
;;; alist for Tibetan base consonant <-> subjoined consonant conversion.
;;;
(defconst tibetan-base-to-subjoined-alist
  '(("$(7"!(B" . "$(7#!(B")
    ("$(7""(B" . "$(7#"(B")
    ("$(7"#(B" . "$(7##(B")
    ("$(7"$(B" . "$(7#$(B")
    ("$(7"%(B" . "$(7#%(B")
    ("$(7"&(B" . "$(7#&(B")
    ("$(7"'(B" . "$(7#'(B")
    ("$(7"((B" . "$(7#((B")
    ("$(7"*(B" . "$(7#*(B")
    ("$(7"+(B" . "$(7#+(B")
    ("$(7",(B" . "$(7#,(B")
    ("$(7"-(B" . "$(7#-(B")
    ("$(7".(B" . "$(7#.(B")
    ("$(7"/(B" . "$(7#/(B")
    ("$(7"0(B" . "$(7#0(B")
    ("$(7"1(B" . "$(7#1(B")
    ("$(7"2(B" . "$(7#2(B")
    ("$(7"3(B" . "$(7#3(B")
    ("$(7"4(B" . "$(7#4(B")
    ("$(7"5(B" . "$(7#5(B")
    ("$(7"6(B" . "$(7#6(B")
    ("$(7"7(B" . "$(7#7(B")
    ("$(7"8(B" . "$(7#8(B")
    ("$(7"9(B" . "$(7#9(B")
    ("$(7":(B" . "$(7#:(B")
    ("$(7";(B" . "$(7#;(B")
    ("$(7"<(B" . "$(7#<(B")
    ("$(7"=(B" . "$(7#=(B")
    ("$(7">(B" . "$(7#>(B")
    ("$(7"?(B" . "$(7#?(B")
    ("$(7"@(B" . "$(7#@(B")
    ("$(7"A(B" . "$(7#A(B")
    ("$(7"B(B" . "$(7#B(B")
    ("$(7"C(B" . "$(7#C(B")
    ("$(7"D(B" . "$(7#D(B")
    ("$(7"E(B" . "$(7#E(B")
    ("$(7"F(B" . "$(7#F(B")
    ("$(7"G(B" . "$(7#G(B")
    ("$(7"H(B" . "$(7#H(B")
    ("$(7"I(B" . "$(7#I(B")
    ("$(7"J(B" . "$(7#J(B")
    ;; Added by Tomabechi 1999/12/10
    ("$(7"K(B" . "$(7#M(B") ;; Fixed form RA (224B->234D)
    ))

;;; alist for Tibetan composite vowels (long i, vocalic r, etc.)
;;; New varialble. created by Tomabechi 2000/06/08
(defconst tibetan-composite-vowel-alist
  '(;; LONG A
    ;; ("$(7"R(B" . ((bc . tc) ?$(7"R(B))
    ;; LONG I
    ("$(7"T(B" . (?$(7"R(B (tc . bc) ?$(7"S(B))
    ;; LONG U
    ("$(7"V(B" . (?$(7"R(B (bc . tc) ?$(7"U(B))
    ;; VOCALIC R
    ("$(7"W(B" . (?$(7#C(B (tc . bc) ?$(7"a(B))
    ;; LONG VOCALIC R
    ("$(7"X(B" . (?$(7#C(B (bc . tc) ?$(7"R(B (tc . bc) ?$(7"a(B))
    ;; VOCALIC L
    ("$(7"Y(B" . (?$(7#D(B (tc . bc) ?$(7"a(B))
    ;;$(7!;(BLONG VOCALIC L
    ("$(7"Z(B" . (?$(7#D(B (bc . tc) ?$(7"R(B (tc . bc) ?$(7"a(B))
    ;; LONG REVERSE I
    ("$(7"b(B" . (?$(7"R(B (tc . bc) ?$(7"a(B))
    ))



;;;
;;; alist for Tibetan consonantic components <-> precomposed glyph conversion.
;;; (includes some punctuation conversion rules)
;;;
(defconst tibetan-precomposition-rule-alist
  `(("$(7"6#B#>(B" . "$(7$G(B")
    ("$(7"##C#>(B" . "$(7$_(B")
    ("$(7";#>(B" . "$(7$)(B")
    ("$(7"C#:#>(B" . "$(7%.(B")
    ("$(7"C###>(B" . "$(7%-(B")
    ("$(7"C#!#B(B" . "$(7%0(B")
    ("$(7"C###B(B" . "$(7%1(B")
    ("$(7"C#9#B(B" . "$(7%2(B")
    ("$(7"G#!#B(B" . "$(7%`(B")
    ("$(7"G###B(B" . "$(7%a(B")
    ("$(7"G#5#B(B" . "$(7%b(B")
    ("$(7"G#7#B(B" . "$(7%c(B")
    ("$(7"G#9#B(B" . "$(7%d(B")
    ("$(7"G#!#C(B" . "$(7%p(B")
    ("$(7"G###C(B" . "$(7%q(B")
    ("$(7"G#4#C(B" . "$(7%r(B")
    ("$(7"G#5#C(B" . "$(7%s(B")
    ("$(7"G#7#C(B" . "$(7%t(B")
    ("$(7"G#9#C(B" . "$(7%u(B")
    ("$(7""#>(B" . "$(7$"(B")
    ("$(7"*#>(B" . "$(7$%(B")
    ("$(7":#>(B" . "$(7$((B")
    ("$(7"?#>(B" . "$(7$*(B")
    ("$(7"E#>(B" . "$(7$.(B")
    ("$(7""#B(B" . "$(7$A(B")
    ("$(7"6#B(B" . "$(7$D(B")
    ("$(7""#C(B" . "$(7$Q(B")
    ("$(7"1#C(B" . "$(7$T(B")
    ("$(7"6#C(B" . "$(7$W(B")
    ("$(7"E#C(B" . "$(7$Z(B")
    ("$(7"<#C(B" . "$(7$^(B")
    ("$(7"C#%(B" . "$(7%#(B")
    ("$(7"C#*(B" . "$(7%%(B")
    ("$(7"C#:(B" . "$(7%+(B")
    ("$(7"C#<(B" . "$(7%,(B")
    ("$(7"D#%(B" . "$(7%B(B")
    ("$(7"G#%(B" . "$(7%R(B")
    ("$(7"G#*(B" . "$(7%S(B")
    ("$(7"G#:(B" . "$(7%Z(B")
    ("$(7"!#>(B" . "$(7$!(B")
    ("$(7"##>(B" . "$(7$#(B")
    ("$(7"&#>(B" . "$(7$$(B")
    ("$(7"0#>(B" . "$(7$&(B")
    ("$(7"2#>(B" . "$(7$'(B")
    ("$(7"@#>(B" . "$(7$+(B")
    ("$(7"C#>(B" . "$(7$,(B")
    ("$(7"D#>(B" . "$(7$-(B")
    ("$(7"G#>(B" . "$(7$/(B")
    ("$(7"H#>(B" . "$(7$0(B")
    ("$(7"!#B(B" . "$(7$@(B")
    ("$(7"##B(B" . "$(7$B(B")
    ("$(7"5#B(B" . "$(7$C(B")
    ("$(7"7#B(B" . "$(7$E(B")
    ("$(7"9#B(B" . "$(7$F(B")
    ("$(7"!#C(B" . "$(7$P(B")
    ("$(7"##C(B" . "$(7$R(B")
    ("$(7"0#C(B" . "$(7$S(B")
    ("$(7"2#C(B" . "$(7$U(B")
    ("$(7"5#C(B" . "$(7$V(B")
    ("$(7"7#C(B" . "$(7$X(B")
    ("$(7"9#C(B" . "$(7$Y(B")
    ("$(7"G#C(B" . "$(7$[(B")
    ("$(7"H#C(B" . "$(7$\(B")
    ("$(7"(#C(B" . "$(7$](B")
    ("$(7"!#D(B" . "$(7$`(B")
    ("$(7"##D(B" . "$(7$a(B")
    ("$(7"7#D(B" . "$(7$b(B")
    ("$(7"@#D(B" . "$(7$c(B")
    ("$(7"C#D(B" . "$(7$d(B")
    ("$(7"G#D(B" . "$(7$e(B")
    ("$(7"C#!(B" . "$(7%!(B")
    ("$(7"C##(B" . "$(7%"(B")
    ("$(7"C#((B" . "$(7%$(B")
    ("$(7"C#0(B" . "$(7%&(B")
    ("$(7"C#2(B" . "$(7%'(B")
    ("$(7"C#4(B" . "$(7%((B")
    ("$(7"C#7(B" . "$(7%)(B")
    ("$(7"C#9(B" . "$(7%*(B")
    ("$(7"D#!(B" . "$(7%@(B")
    ("$(7"D##(B" . "$(7%A(B")
    ("$(7"D#4(B" . "$(7!!(B") ; dummy 0x2121 added 2000/06/08 for transition l -> lng
    ("$(7"D#&(B" . "$(7%C(B")
    ("$(7"D#((B" . "$(7%D(B")
    ("$(7"D#0(B" . "$(7%E(B")
    ("$(7"D#2(B" . "$(7%F(B")
    ("$(7"D#5(B" . "$(7%G(B")
    ("$(7"D#7(B" . "$(7%H(B")
    ("$(7"D#H(B" . "$(7%I(B")
    ("$(7"G#!(B" . "$(7%P(B")
    ("$(7"G##(B" . "$(7%Q(B")
    ("$(7"G#0(B" . "$(7%T(B")
    ("$(7"G#2(B" . "$(7%U(B")
    ("$(7"G#4(B" . "$(7%V(B")
    ("$(7"G#5(B" . "$(7%W(B")
    ("$(7"G#7(B" . "$(7%X(B")
    ("$(7"G#9(B" . "$(7%Y(B")))

(defconst tibetan-obsolete-glyphs
  `(("$(7!=(B" . "$(8!=(B")			; 2 col <-> 1 col
    ("$(7!?(B" . "$(8!?(B")
    ("$(7!@(B" . "$(8!@(B")
    ("$(7!A(B" . "$(8!A(B")
    ("$(7"`(B" . "$(8"`(B")
    ("$(7!;(B" . "$(8!;(B")
    ("$(7!D(B" . "$(8!D(B")
    ;; Yes these are dirty. But ...
    ("$(7!>(B $(7!>(B" . ,(compose-string "$(7!>(B $(7!>(B" 0 3 [?$(7!>(B (Br . Bl) ?  (Br . Bl) ?$(7!>(B]))
    ("$(7!4!5!5(B" . ,(compose-string
		  "$(7#R#S#S#S(B" 0 4
		  [?$(7#R(B (Br . Bl) ?$(7#S(B (Br . Bl) ?$(7#S(B (Br . Bl) ?$(7#S(B]))
    ("$(7!4!5(B" . ,(compose-string "$(7#R#S#S(B" 0 3 [?$(7#R(B (Br . Bl) ?$(7#S(B (Br . Bl) ?$(7#S(B]))
    ("$(7!6(B" . ,(compose-string "$(7#R#S!I(B" 0 3 [?$(7#R(B (Br . Bl) ?$(7#S(B (br . tr) ?$(7!I(B]))
    ("$(7!4(B"   . ,(compose-string "$(7#R#S(B" 0 2 [?$(7#R(B (Br . Bl) ?$(7#S(B]))))

(defconst tibetan-regexp
  (let ((l (list tibetan-precomposed-transcription-alist
		 tibetan-consonant-transcription-alist
		 tibetan-vowel-transcription-alist
		 tibetan-modifier-transcription-alist
		 tibetan-subjoined-transcription-alist))
	(separator "\\|")
	tail pattern)
    (while l
      (setq tail (car l) l (cdr l))
      (while tail
	(setq pattern (cons separator (cons (car (car tail)) pattern))
	      tail (cdr tail))))
    (apply 'concat (nreverse (cdr pattern))))
  "Regexp matching a Tibetan transcription of a composable Tibetan sequence.
The result of matching is to be used for indexing alists at conversion
from a roman transcription to the corresponding Tibetan character.")

(defvar tibetan-precomposed-regexp
  (let ((l tibetan-precomposed-transcription-alist)
	temp)
    (setq temp "^\\(")
    (setq temp
	  (concat temp (car (car l))))
    (setq l (cdr l))
    (while l
      (setq temp
	    (concat temp "\\|" (car (car l))))
      (setq l (cdr l)))
    (concat temp "\\)"))
  "Regexp string to match a romanized Tibetan complex consonant.
The result of matching is to be used for indexing alists when the input key
from an input method is converted to the corresponding precomposed glyph.")

(defvar tibetan-precomposition-rule-regexp
  (let ((l tibetan-precomposition-rule-alist)
	temp)
    (setq temp "\\(")
    (setq temp (concat temp (car (car l))))
    (setq l (cdr l))
    (while l
      (setq temp (concat temp "\\|" (car (car l))))
      (setq l (cdr l)))
    (concat temp "\\)"))
  "Regexp string to match a sequence of Tibetan consonantic components, i.e.,
one base consonant and one or more subjoined consonants.
The result of matching is to be used for indexing alist when the component
sequence is converted to the corresponding precomposed glyph.
This also matches some punctuation characters which need conversion.")

(defvar tibetan-decomposed nil)
(defvar tibetan-decomposed-temp nil)

(provide 'tibetan)

;;; tibetan.el ends here