Mercurial > hg > xemacs-beta
view lisp/mule/lao-util.el @ 814:a634e3b7acc8
[xemacs-hg @ 2002-04-14 12:41:59 by ben]
latest changes
TODO.ben-mule-21-5: Update.
make-docfile.c: Add basic support for handling ISO 2022 doc strings -- we parse
the basic charset designation sequences so we know whether we're
in ASCII and have to pay attention to end quotes and such.
Reformat code according to coding standards.
abbrev.el: Add `global-abbrev-mode', which turns on or off abbrev-mode in all
buffers. Added `defining-abbrev-turns-on-abbrev-mode' -- if
non-nil, defining an abbrev through an interactive function will
automatically turn on abbrev-mode, either globally or locally
depending on the command. This is the "what you'd expect"
behavior.
indent.el: general function for indenting a balanced expression in a
mode-correct way. Works similar to indent-region in that a mode
can specify a specific command to do the whole operation; if not,
figure out the region using forward-sexp and indent each line
using indent-according-to-mode.
keydefs.el: Removed.
Modify M-C-backslash to do indent-region-or-balanced-expression.
Make S-Tab just insert a TAB char, like it's meant to do.
make-docfile.el: Now that we're using the call-process-in-lisp, we need to load
an extra file win32-native.el because we're running a bare temacs.
menubar-items.el: Totally redo the Cmds menu so that most used commands appear
directly on the menu and less used commands appear in submenus.
The old way may have been very pretty, but rather impractical.
process.el: Under Windows, don't ever use old-call-process-internal, even
in batch mode. We can do processes in batch mode.
subr.el: Someone recoded truncate-string-to-width, saying "the FSF version
is too complicated and does lots of hard-to-understand stuff" but
the resulting recoded version was *totally* wrong! it
misunderstood the basic point of this function, which is work in
*columns* not chars. i dumped ours and copied the version from
FSF 21.1. Also added truncate-string-with-continuation-dots,
since this idiom is used often.
config.inc.samp, xemacs.mak: Separate out debug and optimize flags.
Remove all vestiges of USE_MINIMAL_TAGBITS,
USE_INDEXED_LRECORD_IMPLEMENTATION, and GUNG_HO, since those
ifdefs have long been removed.
Make error-checking support actually work.
Some rearrangement of config.inc.samp to make it more logical.
Remove callproc.c and ntproc.c from xemacs.mak, no longer used.
Make pdump the default.
lisp.h: Add support for strong type-checking of Bytecount, Bytebpos,
Charcount, Charbpos, and others, by making them classes,
overloading the operators to provide integer-like operation and
carefully controlling what operations are allowed. Not currently
enabled in C++ builds because there are still a number of compile
errors, and it won't really work till we merge in my "8-bit-Mule"
workspace, in which I make use of the new types Charxpos,
Bytexpos, Memxpos, representing a "position" either in a buffer or
a string. (This is especially important in the extent code.)
abbrev.c, alloc.c, eval.c, buffer.c, buffer.h, editfns.c, fns.c, text.h: Warning fixes, some of them related to new C++ strict type
checking of Bytecount, Charbpos, etc.
dired.c: Caught an actual error due to strong type checking -- char len
being passed when should be byte len.
alloc.c, backtrace.h, bytecode.c, bytecode.h, eval.c, sysdep.c: Further optimize Ffuncall:
-- process arg list at compiled-function creation time, converting
into an array for extra-quick access at funcall time.
-- rewrite funcall_compiled_function to use it, and inline this
function.
-- change the order of check for magic stuff in
SPECBIND_FAST_UNSAFE to be faster.
-- move the check for need to garbage collect into the allocation
code, so only a single flag needs to be checked in funcall.
buffer.c, symbols.c: add debug funs to check on mule optimization info in buffers and
strings.
eval.c, emacs.c, text.c, regex.c, scrollbar-msw.c, search.c: Fix evil crashes due to eistrings not properly reinitialized under
pdump. Redo a bit some of the init routines; convert some
complex_vars_of() into simple vars_of(), because they didn't need
complex processing.
callproc.c, emacs.c, event-stream.c, nt.c, process.c, process.h, sysdep.c, sysdep.h, syssignal.h, syswindows.h, ntproc.c: Delete. Hallelujah, praise the Lord, there is no god
but Allah!!!
fix so that processes can be invoked in bare temacs -- thereby
eliminating any need for callproc.c. (currently only eliminated
under NT.) remove all crufty and unnecessary old process code in
ntproc.c and elsewhere. move non-callproc-specific stuff (mostly
environment) into process.c, so callproc.c can be left out under
NT.
console-tty.c, doc.c, file-coding.c, file-coding.h, lstream.c, lstream.h: fix doc string handling so it works with Japanese, etc docs.
change handling of "character mode" so callers don't have to
manually set it (quite error-prone).
event-msw.c: spacing fixes.
lread.c: eliminate unused crufty vintage-19 "FSF defun hack" code.
lrecord.h: improve pdump description docs.
buffer.c, ntheap.c, unexnt.c, win32.c, emacs.c: Mule-ize some unexec and startup code. It was pseudo-Mule-ized
before by simply always calling the ...A versions of functions,
but that won't cut it -- eventually we want to be able to run
properly even if XEmacs has been installed in a Japanese
directory. (The current problem is the timing of the loading of
the Unicode tables; this will eventually be fixed.) Go through and
fix various other places where the code was not Mule-clean.
Provide a function mswindows_get_module_file_name() to get our own
name without resort to PATH_MAX and such. Add a big comment in
main() about the problem with Unicode table load timing that I
just alluded to.
emacs.c: When error-checking is enabled (interpreted as "user is developing
XEmacs"), don't ask user to "pause to read messages" when a fatal
error has occurred, because it will wedge if we are in an inner
modal loop (typically when a menu is popped up) and make us unable
to get a useful stack trace in the debugger.
text.c: Correct update_entirely_ascii_p_flag to actually work.
lisp.h, symsinit.h: declarations for above changes.
author | ben |
---|---|
date | Sun, 14 Apr 2002 12:43:31 +0000 |
parents | 2923009caf47 |
children | 72d64d886449 |
line wrap: on
line source
;;; lao-util.el --- utilities for Lao -*- coding: iso-2022-7bit; -*- ;; Copyright (C) 1997 Electrotechnical Laboratory, JAPAN. ;; Licensed to the Free Software Foundation. ;; Keywords: multilingual, Lao ;; 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/lao-util.el). ;;; Commentary: ;;; Code: ;; Setting information of Thai characters. (defconst lao-category-table (make-category-table)) (define-category ?c "Lao consonant" lao-category-table) (define-category ?s "Lao semi-vowel" lao-category-table) (define-category ?v "Lao upper/lower vowel" lao-category-table) (define-category ?t "Lao tone" lao-category-table) (let ((l '((?(1!(B consonant "LETTER KOR KAI'" "CHICKEN") (?(1"(B consonant "LETTER KHOR KHAI'" "EGG") (?(1#(B invalid nil) (?(1$(B consonant "LETTER QHOR QHWARGN" "BUFFALO") (?(1%(B invalid nil) (? invalid nil) (?(1'(B consonant "LETTER NGOR NGUU" "SNAKE") (?(1((B consonant "LETTER JOR JUA" "BUDDHIST NOVICE") (?(1)(B invalid nil) (?(1*(B consonant "LETTER XOR X\"ARNG" "ELEPHANT") (?(1+(B invalid nil) (?(1,(B invalid nil) (?(1-(B consonant "LETTER YOR YUNG" "MOSQUITO") (?(1.(B invalid nil) (?(1.(B invalid nil) (?(1.(B invalid nil) (?(1.(B invalid nil) (?(1.(B invalid nil) (?(1.(B invalid nil) (?(14(B consonant "LETTER DOR DANG" "NOSE") (?(15(B consonant "LETTER TOR TAR" "EYE") (?(16(B consonant "LETTER THOR THUNG" "TO ASK,QUESTION") (?(17(B consonant "LETTER DHOR DHARM" "FLAG") (?(18(B invalid nil) (?(19(B consonant "LETTER NOR NOK" "BIRD") (?(1:(B consonant "LETTER BOR BED" "FISHHOOK") (?(1;(B consonant "LETTER POR PAR" "FISH") (?(1<(B consonant "LETTER HPOR HPER\"" "BEE") (?(1=(B consonant "LETTER FHOR FHAR" "WALL") (?(1>(B consonant "LETTER PHOR PHUU" "MOUNTAIN") (?(1?(B consonant "LETTER FOR FAI" "FIRE") (?(1@(B invalid nil) (?(1A(B consonant "LETTER MOR MAR\"" "HORSE") (?(1B(B consonant "LETTER GNOR GNAR" "MEDICINE") (?(1C(B consonant "LETTER ROR ROD" "CAR") (?(1D(B invalid nil) (?(1E(B consonant "LETTER LOR LIING" "MONKEY") (?(1F(B invalid nil) (?(1G(B consonant "LETTER WOR WII" "HAND FAN") (?(1H(B invalid nil) (?(1I(B invalid nil) (?(1J(B consonant "LETTER SOR SEA" "TIGER") (?(1K(B consonant "LETTER HHOR HHAI" "JAR") (?(1L(B invalid nil) (?(1M(B consonant "LETTER OR OOW" "TAKE") (?(1N(B consonant "LETTER HOR HEA" "BOAT") (?(1O(B special "ELLIPSIS") (?(1P(B vowel-base "VOWEL SIGN SARA A") (?(1Q(B vowel-upper "VOWEL SIGN MAI KAN") (?(1R(B vowel-base "VOWEL SIGN SARA AR") (?(1S(B vowel-base "VOWEL SIGN SARA AM") (?(1T(B vowel-upper "VOWEL SIGN SARA I") (?(1U(B vowel-upper "VOWEL SIGN SARA II") (?(1V(B vowel-upper "VOWEL SIGN SARA EU") (?(1W(B vowel-upper "VOWEL SIGN SARA UR") (?(1X(B vowel-lower "VOWEL SIGN SARA U") (?(1Y(B vowel-lower "VOWEL SIGN SARA UU") (?(1Z(B invalid nil) (?(1[(B vowel-upper "VOWEL SIGN MAI KONG") (?(1\(B semivowel-lower "SEMIVOWEL SIGN LO") (?(1](B vowel-base "SEMIVOWEL SIGN SARA IA") (?(1^(B invalid nil) (?(1_(B invalid nil) (?(1`(B vowel-base "VOWEL SIGN SARA EE") (?(1a(B vowel-base "VOWEL SIGN SARA AA") (?(1b(B vowel-base "VOWEL SIGN SARA OO") (?(1c(B vowel-base "VOWEL SIGN SARA EI MAI MUAN\"") (?(1d(B vowel-base "VOWEL SIGN SARA AI MAI MAY") (?(1e(B invalid nil) (?(1f(B special "KO LA (REPETITION)") (?(1g(B invalid nil) (?(1h(B tone "TONE MAI EK") (?(1i(B tone "TONE MAI THO") (?(1j(B tone "TONE MAI TI") (?(1k(B tone "TONE MAI JADTAWAR") (?(1l(B tone "CANCELLATION MARK") (?(1m(B vowel-upper "VOWEL SIGN SARA OR") (?(1n(B invalid nil) (?(1o(B invalid nil) (?(1p(B special "DIGIT ZERO") (?(1q(B special "DIGIT ONE") (?(1r(B special "DIGIT TWO") (?(1s(B special "DIGIT THREE") (?(1t(B special "DIGIT FOUR") (?(1u(B special "DIGIT FIVE") (?(1v(B special "DIGIT SIX") (?(1w(B special "DIGIT SEVEN") (?(1x(B special "DIGIT EIGHT") (?(1y(B special "DIGIT NINE") (?(1z(B invalid nil) (?(1{(B invalid nil) (?(1|(B consonant "LETTER NHOR NHUU" "MOUSE") (?(1}(B consonant "LETTER MHOR MHAR" "DOG") (?(1~(B invalid nil) )) elm) (while l (setq elm (car l) l (cdr l)) (let ((char (car elm)) (ptype (nth 1 elm))) (cond ((eq ptype 'consonant) (modify-category-entry char ?c lao-category-table)) ((memq ptype '(vowel-upper vowel-lower)) (modify-category-entry char ?v lao-category-table)) ((eq ptype 'semivowel-lower) (modify-category-entry char ?s lao-category-table)) ((eq ptype 'tone) (modify-category-entry char ?t lao-category-table))) (put-char-code-property char 'phonetic-type ptype) (put-char-code-property char 'name (nth 2 elm)) (put-char-code-property char 'meaning (nth 3 elm))))) ;; The general composing rules are as follows: ;; ;; T ;; V T V T ;; CV -> C, CT -> C, CVT -> C, Cv -> C, CvT -> C ;; v v ;; T ;; V T V T ;; CsV -> C, CsT -> C, CsVT -> C, Csv -> C, CvT -> C ;; s s s s s ;; v v ;; where C: consonant, V: vowel upper, v: vowel lower, ;; T: tone mark, s: semivowel lower (defvar lao-composition-pattern "\\cc\\(\\ct\\|\\cv\\ct?\\|\\cs\\(\\ct\\|\\cv\\ct?\\)?\\)" "Regular expression matching a Lao composite sequence.") ;;;###autoload (defun lao-compose-string (str) (with-category-table lao-category-table (let ((idx 0)) (while (setq idx (string-match lao-composition-pattern str idx)) (compose-string str idx (match-end 0)) (setq idx (match-end 0)))) str)) ;;; LRT: Lao <-> Roman Transcription ;; Upper vowels and tone-marks are put on the letter. ;; Semi-vowel-sign-lo and lower vowels are put under the letter. (defconst lao-transcription-consonant-alist (sort '(;; single consonants ("k" . "(1!(B") ("kh" . "(1"(B") ("qh" . "(1$(B") ("ng" . "(1'(B") ("j" . "(1((B") ("s" . "(1J(B") ("x" . "(1*(B") ("y" . "(1-(B") ("d" . "(14(B") ("t" . "(15(B") ("th" . "(16(B") ("dh" . "(17(B") ("n" . "(19(B") ("b" . "(1:(B") ("p" . "(1;(B") ("hp" . "(1<(B") ("fh" . "(1=(B") ("ph" . "(1>(B") ("f" . "(1?(B") ("m" . "(1A(B") ("gn" . "(1B(B") ("l" . "(1E(B") ("r" . "(1C(B") ("v" . "(1G(B") ("w" . "(1G(B") ("hh" . "(1K(B") ("O" . "(1M(B") ("h" . "(1N(B") ("nh" . "(1|(B") ("mh" . "(1}(B") ("lh" . ["(1K\(B"]) ;; double consonants ("ngh" . ["(1K'(B"]) ("yh" . ["(1K](B"]) ("wh" . ["(1KG(B"]) ("hl" . ["(1KE(B"]) ("hy" . ["(1K-(B"]) ("hn" . ["(1K9(B"]) ("hm" . ["(1KA(B"]) ) (function (lambda (x y) (> (length (car x)) (length (car y))))))) (defconst lao-transcription-semi-vowel-alist '(("r" . "(1\(B"))) (defconst lao-transcription-vowel-alist (sort '(("a" . "(1P(B") ("ar" . "(1R(B") ("i" . "(1T(B") ("ii" . "(1U(B") ("eu" . "(1V(B") ("ur" . "(1W(B") ("u" . "(1X(B") ("uu" . "(1Y(B") ("e" . ["(1`P(B"]) ("ee" . "(1`(B") ("ae" . ["(1aP(B"]) ("aa" . "(1a(B") ("o" . ["(1bP(B"]) ("oo" . "(1b(B") ("oe" . ["(1`RP(B"]) ("or" . "(1m(B") ("er" . ["(1`T(B"]) ("ir" . ["(1`U(B"]) ("ua" . ["(1[GP(B"]) ("uaa" . ["(1[G(B"]) ("ie" . ["(1`Q]P(B"]) ("ia" . ["(1`Q](B"]) ("ea" . ["(1`VM(B"]) ("eaa" . ["(1`WM(B"]) ("ai" . "(1d(B") ("ei" . "(1c(B") ("ao" . ["(1`[R(B"]) ("aM" . "(1S(B")) (function (lambda (x y) (> (length (car x)) (length (car y))))))) ;; Maa-sakod is put at the tail. (defconst lao-transcription-maa-sakod-alist '(("k" . "(1!(B") ("g" . "(1'(B") ("y" . "(1-(B") ("d" . "(14(B") ("n" . "(19(B") ("b" . "(1:(B") ("m" . "(1A(B") ("v" . "(1G(B") ("w" . "(1G(B") )) (defconst lao-transcription-tone-alist '(("'" . "(1h(B") ("\"" . "(1i(B") ("^" . "(1j(B") ("+" . "(1k(B") ("~" . "(1l(B"))) (defconst lao-transcription-punctuation-alist '(("\\0" . "(1p(B") ("\\1" . "(1q(B") ("\\2" . "(1r(B") ("\\3" . "(1s(B") ("\\4" . "(1t(B") ("\\5" . "(1u(B") ("\\6" . "(1v(B") ("\\7" . "(1w(B") ("\\8" . "(1x(B") ("\\9" . "(1y(B") ("\\\\" . "(1f(B") ("\\$" . "(1O(B"))) (defconst lao-transcription-pattern (concat "\\(" (mapconcat 'car lao-transcription-consonant-alist "\\|") "\\)\\(" (mapconcat 'car lao-transcription-semi-vowel-alist "\\|") "\\)?\\(\\(" (mapconcat 'car lao-transcription-vowel-alist "\\|") "\\)\\(" (mapconcat 'car lao-transcription-maa-sakod-alist "\\|") "\\)?\\(" (mapconcat (lambda (x) (regexp-quote (car x))) lao-transcription-tone-alist "\\|") "\\)?\\)?\\|" (mapconcat (lambda (x) (regexp-quote (car x))) lao-transcription-punctuation-alist "\\|") ) "Regexp of Roman transcription pattern for one Lao syllable.") (defconst lao-transcription-pattern (concat "\\(" (regexp-opt (mapcar 'car lao-transcription-consonant-alist)) "\\)\\(" (regexp-opt (mapcar 'car lao-transcription-semi-vowel-alist)) "\\)?\\(\\(" (regexp-opt (mapcar 'car lao-transcription-vowel-alist)) "\\)\\(" (regexp-opt (mapcar 'car lao-transcription-maa-sakod-alist)) "\\)?\\(" (regexp-opt (mapcar 'car lao-transcription-tone-alist)) "\\)?\\)?\\|" (regexp-opt (mapcar 'car lao-transcription-punctuation-alist)) ) "Regexp of Roman transcription pattern for one Lao syllable.") (defconst lao-vowel-reordering-rule '(("(1P(B" (0 ?(1P(B) (0 ?(1Q(B)) ("(1R(B" (0 ?(1R(B)) ("(1T(B" (0 ?(1U(B)) ("(1U(B" (0 ?(1U(B)) ("(1V(B" (0 ?(1V(B)) ("(1W(B" (0 ?(1W(B)) ("(1X(B" (0 ?(1X(B)) ("(1Y(B" (0 ?(1Y(B)) ("(1`P(B" (?(1`(B 0 ?(1P(B) (?(1`(B 0 ?(1Q(B)) ("(1`(B" (?(1`(B 0)) ("(1aP(B" (?(1a(B 0 ?(1P(B) (?(1a(B 0 ?(1Q(B)) ("(1a(B" (?(1a(B 0)) ("(1bP(B" (?(1b(B 0 ?(1P(B) (0 ?(1[(B) (?(1-(B ?(1b(B 0 ?(1Q(B) (?(1G(B ?(1b(B 0 ?(1Q(B)) ("(1b(B" (?(1b(B 0)) ("(1`RP(B" (?(1`(B 0 ?(1R(B ?(1P(B) (0 ?(1Q(B ?(1M(B)) ("(1m(B" (0 ?(1m(B) (0 ?(1M(B)) ("(1`T(B" (?(1`(B 0 ?(1T(B)) ("(1`U(B" (?(1`(B 0 ?(1U(B)) ("(1[GP(B" (0 ?(1[(B ?(1G(B ?(1P(B) (0 ?(1Q(B ?(1G(B)) ("(1[G(B" (0 ?(1[(B ?(1G(B) (0 ?(1G(B)) ("(1`Q]P(B" (?(1`(B 0 ?(1Q(B ?(1](B ?(1P(B) (0 ?(1Q(B ?(1](B)) ("(1`Q](B" (?(1`(B 0 ?(1Q(B ?(1](B) (0 ?(1](B)) ("(1`VM(B" (?(1`(B 0 ?(1V(B ?(1M(B)) ("(1`WM(B" (?(1`(B 0 ?(1W(B ?(1M(B)) ("(1d(B" (?(1d(B 0)) ("(1c(B" (?(1c(B 0)) ("(1`[R(B" (?(1`(B 0 ?(1[(B ?(1R(B)) ("(1S(B" (0 ?(1S(B))) "Alist of Lao vowel string vs the corresponding re-ordering rule. Each element has this form: (VOWEL NO-MAA-SAKOD-RULE WITH-MAA-SAKOD-RULE (MAA-SAKOD-0 RULE-0) ...) VOWEL is a vowel string (e.g. \"(1`Q]P(B\"). NO-MAA-SAKOD-RULE is a rule to re-order and modify VOWEL following a consonant. It is a list vowel characters or 0. The element 0 indicate the place to embed a consonant. Optional WITH-MAA-SAKOD-RULE is a rule to re-order and modify VOWEL follwoing a consonant and preceding a maa-sakod character. If it is nil, NO-MAA-SAKOD-RULE is used. The maa-sakod character is alwasy appended at the tail. For instance, rule `(\"(1`WM(B\" (?(1`(B t ?(1W(B ?(1M(B))' tells that this vowel string following a consonant `(1!(B' should be re-ordered as \"(1`!WM(B\". Optional (MAA-SAKOD-n RULE-n) are rules specially applied to maa-sakod character MAA-SAKOD-n.") ;;;###autoload (defun lao-transcribe-single-roman-syllable-to-lao (from to &optional str) "Transcribe a Romanized Lao syllable in the region FROM and TO to Lao string. Only the first syllable is transcribed. The value has the form: (START END LAO-STRING), where START and END are the beggining and end positions of the Roman Lao syllable, LAO-STRING is the Lao character transcription of it. Optional 3rd arg STR, if non-nil, is a string to search for Roman Lao syllable. In that case, FROM and TO are indexes to STR." (if str (if (setq from (string-match lao-transcription-pattern str from)) (progn (if (>= from to) (setq from nil) (setq to (match-end 0))))) (save-excursion (goto-char from) (if (setq to (re-search-forward lao-transcription-pattern to t)) (setq from (match-beginning 0)) (setq from nil)))) (if from (let* ((consonant (match-string 1 str)) (semivowel (match-string 3 str)) (vowel (match-string 5 str)) (maa-sakod (match-string 8 str)) (tone (match-string 9 str)) lao-consonant lao-semivowel lao-vowel lao-maa-sakod lao-tone clen cidx) (setq to (match-end 0)) (if (not consonant) (setq str (cdr (assoc (match-string 0 str) lao-transcription-punctuation-alist))) (setq lao-consonant (cdr (assoc consonant lao-transcription-consonant-alist))) (if (vectorp lao-consonant) (setq lao-consonant (aref lao-consonant 0))) (setq clen (length lao-consonant)) (if semivowel ;; Include semivowel in STR. (setq lao-semivowel (cdr (assoc semivowel lao-transcription-semi-vowel-alist)) str (if (= clen 1) (concat lao-consonant lao-semivowel) (concat (substring lao-consonant 0 1) lao-semivowel (substring lao-consonant 1)))) (setq str lao-consonant)) (if vowel (let (rule) (setq lao-vowel (cdr (assoc vowel lao-transcription-vowel-alist))) (if (vectorp lao-vowel) (setq lao-vowel (aref lao-vowel 0))) (setq rule (assoc lao-vowel lao-vowel-reordering-rule)) (if (null maa-sakod) (setq rule (nth 1 rule)) (setq lao-maa-sakod (cdr (assoc maa-sakod lao-transcription-maa-sakod-alist)) rule (or (cdr (assq (aref lao-maa-sakod 0) (nthcdr 2 rule))) (nth 2 rule) (nth 1 rule)))) (or rule (error "Lao vowel %S has no re-ordering rule" lao-vowel)) (setq lao-consonant str str "") (while rule (if (= (car rule) 0) (setq str (concat str lao-consonant) cidx (length str)) (setq str (concat str (list (car rule))))) (setq rule (cdr rule))) (or cidx (error "Lao vowel %S has malformed re-ordering rule" vowel)) ;; Set CIDX to after upper or lower vowel if any. (let ((len (length str))) (while (and (< cidx len) (memq (get-char-code-property (aref str cidx) 'phonetic-type) '(vowel-lower vowel-upper))) (setq cidx (1+ cidx)))) (if lao-maa-sakod (setq str (concat str lao-maa-sakod))) (if tone (setq lao-tone (cdr (assoc tone lao-transcription-tone-alist)) str (concat (substring str 0 cidx) lao-tone (substring str cidx))))))) (list from to (lao-compose-string str))))) ;;;###autoload (defun lao-transcribe-roman-to-lao-string (str) "Transcribe Romanized Lao string STR to Lao character string." (let ((from 0) (to (length str)) (lao-str "") val) (while (setq val (lao-transcribe-single-roman-syllable-to-lao from to str)) (let ((start (car val)) (end (nth 1 val)) (lao (nth 2 val))) (if (> start from) (setq lao-str (concat lao-str (substring str from start) lao)) (setq lao-str (concat lao-str lao))) (setq from end))) (if (< from to) (concat lao-str (substring str from to)) lao-str))) ;;;###autoload (defun lao-composition-function (from to pattern &optional string) "Compose Lao text in the region FROM and TO. The text matches the regular expression PATTERN. Optional 4th argument STRING, if non-nil, is a string containing text to compose. The return value is number of composed characters." (if (< (1+ from) to) (prog1 (- to from) (if string (compose-string string from to) (compose-region from to)) (- to from)))) ;;;###autoload (defun lao-compose-region (from to) (interactive "r") (save-restriction (narrow-to-region from to) (goto-char (point-min)) (with-category-table lao-category-table (while (re-search-forward lao-composition-pattern nil t) (compose-region (match-beginning 0) (point)))))) ;; (provide 'lao-util) ;;; lao-util.el ends here