Mercurial > emacs
diff lisp/international/characters.el @ 89483:2f877ed80fa6
*** empty log message ***
| author | Kenichi Handa <handa@m17n.org> |
|---|---|
| date | Mon, 08 Sep 2003 12:53:41 +0000 |
| parents | 375f2633d815 f040012c16bb |
| children | 1ad3832f1d1d |
line wrap: on
line diff
--- a/lisp/international/characters.el Mon Sep 08 11:56:09 2003 +0000 +++ b/lisp/international/characters.el Mon Sep 08 12:53:41 2003 +0000 @@ -1,8 +1,11 @@ ;;; characters.el --- set syntax and category for multibyte characters ;; Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN. -;; Licensed to the Free Software Foundation. +;; Licensed to the Free Software Foundation. ;; Copyright (C) 2001, 2002 Free Software Foundation, Inc. +;; Copyright (C) 2003 +;; National Institute of Advanced Industrial Science and Technology (AIST) +;; Registration Number H13PRO009 ;; Keywords: multibyte character, character set, syntax, category @@ -25,12 +28,6 @@ ;;; Commentary: -;; This file contains multibyte characters. Save this file always in -;; the coding system `iso-2022-7bit'. - -;; This file does not define the syntax for Latin-N character sets; -;; those are defined by the files latin-N.el. - ;;; Code: ;;; Predefined categories. @@ -98,11 +95,156 @@ ;; ASCII -(let ((ch 32)) - (while (< ch 127) ; All ASCII characters have - (modify-category-entry ch ?a) ; the category `a' (ASCII) - (modify-category-entry ch ?l) ; and `l' (Latin). - (setq ch (1+ ch)))) +;; All ASCII characters have the category `a' (ASCII) and `l' (Latin). +(modify-category-entry '(32 . 127) ?a) +(modify-category-entry '(32 . 127) ?l) + +;; Deal with the CJK charsets first. Since the syntax of blocks is +;; defined per charset, and the charsets may contain e.g. Latin +;; characters, we end up with the wrong syntax definitions if we're +;; not careful. + +;; Chinese characters (Unicode) +(modify-category-entry '(#x3400 . #x9FAF) ?C) +(modify-category-entry '(#x3400 . #x9FAF) ?c) +(modify-category-entry '(#x3400 . #x9FAF) ?|) +(modify-category-entry '(#xF900 . #xFAFF) ?C) +(modify-category-entry '(#xF900 . #xFAFF) ?c) +(modify-category-entry '(#xF900 . #xFAFF) ?|) + +;; Chinese character set (GB2312) + +(map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2121 #x217E) +(map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2221 #x227E) +(map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2921 #x297E) + +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?c) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?|) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2330 #x2339) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2341 #x235A) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2361 #x237A) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?H #x2421 #x247E) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?K #x2521 #x257E) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?G #x2621 #x267E) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?Y #x2721 #x277E) +(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?C #x3021 #x7E7E) + +;; Chinese character set (BIG5) + +(map-charset-chars #'modify-category-entry 'big5 ?c) +(map-charset-chars #'modify-category-entry 'big5 ?C #xA259 #xA25F) +(map-charset-chars #'modify-category-entry 'big5 ?C #xA440 #xC67E) +(map-charset-chars #'modify-category-entry 'big5 ?C #xC940 #xF9DF) +(map-charset-chars #'modify-category-entry 'big5 ?|) + + +;; Chinese character set (CNS11643) + +(dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3 + chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6 + chinese-cns11643-7)) + (map-charset-chars #'modify-category-entry c ?c) + (if (eq c 'chinese-cns11643-1) + (map-charset-chars #'modify-category-entry c ?C #x4421 #x7E7E) + (map-charset-chars #'modify-category-entry c ?C)) + (map-charset-chars #'modify-category-entry c ?|)) + +;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213) + +(map-charset-chars #'modify-category-entry 'katakana-jisx0201 ?k) + +(map-charset-chars #'modify-category-entry 'latin-jisx0201 ?r) + +(dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212 + japanese-jisx0213-1 japanese-jisx0213-2)) + (map-charset-chars #'modify-category-entry l ?j) + (if (eq l 'japanese-jisx0213-1) + (map-charset-chars #'modify-category-entry l ?\| #x2E21 #x7E7F) + (map-charset-chars #'modify-category-entry l ?\|))) + +;; Unicode equivalents of JISX0201-kana +(let ((range '(#xff61 . #xff9f))) + (modify-category-entry range ?k) + (modify-category-entry range ?j) + (modify-category-entry range ?\|)) + +;; Katakana block +(let ((range '(#x30a0 . #x30ff))) + ;; ?K is double width, ?k isn't specified + (modify-category-entry range ?K) + (modify-category-entry range ?\|)) + +;; Hiragana block +(let ((range '(#x3040 . #x309d))) + ;; ?H is actually defined to be double width + ;;(modify-category-entry range ?H) + ;;(modify-category-entry range ?\|) + ) + +;; JISX0208 +(map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2121 #x227E) +(map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2821 #x287E) +(let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇))) + (dolist (elt chars) + (modify-syntax-entry (car chars) "w"))) + +(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?A #x2321 #x237E) +(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?H #x2421 #x247E) +(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?K #x2521 #x257E) +(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?G #x2621 #x267E) +(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?Y #x2721 #x277E) +(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?C #x3021 #x7E7E) +(modify-category-entry ?ー ?K) +(let ((chars '(?゛ ?゜))) + (while chars + (modify-category-entry (car chars) ?K) + (modify-category-entry (car chars) ?H) + (setq chars (cdr chars)))) +(let ((chars '(?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇))) + (while chars + (modify-category-entry (car chars) ?C) + (setq chars (cdr chars)))) + +;; JISX0212 + +(map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E) + +;; JISX0201-Kana + +(let ((chars '(?｡ ?､ ?･))) + (while chars + (modify-syntax-entry (car chars) ".") + (setq chars (cdr chars)))) + +(modify-syntax-entry ?\｢ "(｣") +(modify-syntax-entry ?\｣ "(｢") + +;; Korean character set (KSC5601) + +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?h) + +(map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2121 #x227E) +(map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2621 #x277E) +(map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2830 #x287E) +(map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2930 #x297E) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2330 #x2339) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2341 #x235A) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2361 #x237A) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?G #x2521 #x257E) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?H #x2A21 #x2A7E) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?K #x2B21 #x2B7E) +(map-charset-chars #'modify-category-entry 'korean-ksc5601 ?Y #x2C21 #x2C7E) + +;; These are in more than one charset. +(let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛" + "︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄" + "（）［］｛｝")) + open close) + (dotimes (i (/ (length parens) 2)) + (setq open (aref parens (* i 2)) + close (aref parens (1+ (* i 2)))) + (modify-syntax-entry open (format "(%c" close)) + (modify-syntax-entry close (format ")%c" open)))) ;; Arabic character set @@ -111,606 +253,52 @@ arabic-1-column arabic-2-column))) (while charsets -;; (modify-syntax-entry (make-char (car charsets)) "w") - (modify-category-entry (make-char (car charsets)) ?b) + (map-charset-chars #'modify-category-entry (car charsets) ?b) (setq charsets (cdr charsets)))) -(let ((ch #x600)) - (while (<= ch #x6ff) - (modify-category-entry (decode-char 'ucs ch) ?b) - (setq ch (1+ ch))) - (setq ch #xfb50) - (while (<= ch #xfdff) - (modify-category-entry (decode-char 'ucs ch) ?b) - (setq ch (1+ ch))) - (setq ch #xfe70) - (while (<= ch #xfefe) - (modify-category-entry (decode-char 'ucs ch) ?b) - (setq ch (1+ ch)))) - -;; Chinese character set (GB2312) - -;; (modify-syntax-entry (make-char 'chinese-gb2312) "w") -(modify-syntax-entry (make-char 'chinese-gb2312 33) "_") -(modify-syntax-entry (make-char 'chinese-gb2312 34) "_") -(modify-syntax-entry (make-char 'chinese-gb2312 41) "_") -(modify-syntax-entry ?\$A!2(B "($A!3(B") -(modify-syntax-entry ?\$A!4(B "($A!5(B") -(modify-syntax-entry ?\$A!6(B "($A!7(B") -(modify-syntax-entry ?\$A!8(B "($A!9(B") -(modify-syntax-entry ?\$A!:(B "($A!;(B") -(modify-syntax-entry ?\$A!<(B "($A!=(B") -(modify-syntax-entry ?\$A!>(B "($A!?(B") -(modify-syntax-entry ?\$A#((B "($A#)(B") -(modify-syntax-entry ?\$A#{(B "($A#}(B") -(modify-syntax-entry ?\$A#[(B "($A#](B") -(modify-syntax-entry ?\$A!3(B ")$A!2(B") -(modify-syntax-entry ?\$A!5(B ")$A!4(B") -(modify-syntax-entry ?\$A!7(B ")$A!6(B") -(modify-syntax-entry ?\$A!9(B ")$A!8(B") -(modify-syntax-entry ?\$A!;(B ")$A!:(B") -(modify-syntax-entry ?\$A!=(B ")$A!<(B") -(modify-syntax-entry ?\$A!?(B ")$A!>(B") -(modify-syntax-entry ?\$A#)(B ")$A#((B") -(modify-syntax-entry ?\$A#}(B ")$A#{(B") -(modify-syntax-entry ?\$A#](B ")$A#[(B") -;; Unicode equivalents of above -(modify-syntax-entry ?\$,2=T(B "($,2=U(B") -(modify-syntax-entry ?\$,2=H(B "($,2=I(B") -(modify-syntax-entry ?\$,2=J(B "($,2=K(B") -(modify-syntax-entry ?\$,2=L(B "($,2=M(B") -(modify-syntax-entry ?\$,2=N(B "($,2=O(B") -(modify-syntax-entry ?\$,2=V(B "($,2=W(B") -(modify-syntax-entry ?\$,2=P(B "($,2=Q(B") -(modify-syntax-entry ?\$,2=U(B ")$,2=T(B") -(modify-syntax-entry ?\$,2=I(B ")$,2=H(B") -(modify-syntax-entry ?\$,2=K(B ")$,2=J(B") -(modify-syntax-entry ?\$,2=M(B ")$,2=L(B") -(modify-syntax-entry ?\$,2=O(B ")$,2=N(B") -(modify-syntax-entry ?\$,2=W(B ")$,2=V(B") -(modify-syntax-entry ?\$,2=Q(B ")$,2=P(B") - -(let ((chars "$A#,!"!##.!$#;#:#?#!!C!-!'#|#_!.!/!0!1#"!e#`!d(B")) - (dotimes (i (length chars)) - (modify-syntax-entry (aref chars i) "."))) - -(modify-category-entry (make-char 'chinese-gb2312) ?c) -(modify-category-entry (make-char 'chinese-gb2312) ?\|) -(modify-category-entry (make-char 'chinese-gb2312 35) ?A) -(modify-category-entry (make-char 'chinese-gb2312 36) ?H) -(modify-category-entry (make-char 'chinese-gb2312 37) ?K) -(modify-category-entry (make-char 'chinese-gb2312 38) ?G) -(modify-category-entry (make-char 'chinese-gb2312 39) ?Y) -(let ((row 48)) - (while (< row 127) - (modify-category-entry (make-char 'chinese-gb2312 row) ?C) - (setq row (1+ row)))) - -;; Chinese character set (BIG5) - - - -(let ((from (decode-big5-char #xA141)) - (to (decode-big5-char #xA15D))) - (while (< from to) - (modify-syntax-entry from ".") - (setq from (1+ from)))) -(let ((from (decode-big5-char #xA1A5)) - (to (decode-big5-char #xA1AD))) - (while (< from to) - (modify-syntax-entry from ".") - (setq from (1+ from)))) -(let ((from (decode-big5-char #xA1AD)) - (to (decode-big5-char #xA2AF))) - (while (< from to) - (modify-syntax-entry from "_") - (setq from (1+ from)))) - -(let ((parens "$(0!>!?!@!A!B!C!D!E!F!G!H!I!J!K!L!M!N!O!P!Q!R!S!T!U!V!W!X!Y!Z![!\!]!^!_!`!a!b!c(B") - open close) - (dotimes (i (/ (length parens) 2)) - (setq open (aref parens (* i 2)) - close (aref parens (1+ (* i 2)))) - (modify-syntax-entry open (format "(%c" close)) - (modify-syntax-entry close (format ")%c" open)))) - -(let ((generic-big5-1-char (make-char 'chinese-big5-1)) - (generic-big5-2-char (make-char 'chinese-big5-2))) -;; (modify-syntax-entry generic-big5-1-char "w") -;; (modify-syntax-entry generic-big5-2-char "w") - - (modify-category-entry generic-big5-1-char ?c) - (modify-category-entry generic-big5-2-char ?c) - - (modify-category-entry generic-big5-1-char ?C) - (modify-category-entry generic-big5-2-char ?C) - - (modify-category-entry generic-big5-1-char ?\|) - (modify-category-entry generic-big5-2-char ?\|)) - - -;; Chinese character set (CNS11643) - -(let ((cns-list '(chinese-cns11643-1 - chinese-cns11643-2 - chinese-cns11643-3 - chinese-cns11643-4 - chinese-cns11643-5 - chinese-cns11643-6 - chinese-cns11643-7)) - generic-char) - (while cns-list - (setq generic-char (make-char (car cns-list))) -;; (modify-syntax-entry generic-char "w") - (modify-category-entry generic-char ?c) - (modify-category-entry generic-char ?C) - (modify-category-entry generic-char ?|) - (setq cns-list (cdr cns-list)))) +(modify-category-entry '(#x600 . #x6ff) ?b) +(modify-category-entry '(#xfb50 . #xfdff) ?b) +(modify-category-entry '(#xfe70 . #xfefe) ?b) ;; Cyrillic character set (ISO-8859-5) -(modify-category-entry (make-char 'cyrillic-iso8859-5) ?y) - -(modify-syntax-entry (make-char 'cyrillic-iso8859-5 160) " ") -(modify-syntax-entry ?,L-(B ".") -(modify-syntax-entry ?,Lp(B ".") -(modify-syntax-entry ?,L}(B ".") -(let ((tbl (standard-case-table))) - (set-case-syntax-pair ?,L!(B ?,Lq(B tbl) - (set-case-syntax-pair ?,L"(B ?,Lr(B tbl) - (set-case-syntax-pair ?,L#(B ?,Ls(B tbl) - (set-case-syntax-pair ?,L$(B ?,Lt(B tbl) - (set-case-syntax-pair ?,L%(B ?,Lu(B tbl) - (set-case-syntax-pair ?,L&(B ?,Lv(B tbl) - (set-case-syntax-pair ?,L'(B ?,Lw(B tbl) - (set-case-syntax-pair ?,L((B ?,Lx(B tbl) - (set-case-syntax-pair ?,L)(B ?,Ly(B tbl) - (set-case-syntax-pair ?,L*(B ?,Lz(B tbl) - (set-case-syntax-pair ?,L+(B ?,L{(B tbl) - (set-case-syntax-pair ?,L,(B ?,L|(B tbl) - (set-case-syntax-pair ?,L.(B ?,L~(B tbl) - (set-case-syntax-pair ?,L/(B ?,L(B tbl) - (set-case-syntax-pair ?,L0(B ?,LP(B tbl) - (set-case-syntax-pair ?,L1(B ?,LQ(B tbl) - (set-case-syntax-pair ?,L2(B ?,LR(B tbl) - (set-case-syntax-pair ?,L3(B ?,LS(B tbl) - (set-case-syntax-pair ?,L4(B ?,LT(B tbl) - (set-case-syntax-pair ?,L5(B ?,LU(B tbl) - (set-case-syntax-pair ?,L6(B ?,LV(B tbl) - (set-case-syntax-pair ?,L7(B ?,LW(B tbl) - (set-case-syntax-pair ?,L8(B ?,LX(B tbl) - (set-case-syntax-pair ?,L9(B ?,LY(B tbl) - (set-case-syntax-pair ?,L:(B ?,LZ(B tbl) - (set-case-syntax-pair ?,L;(B ?,L[(B tbl) - (set-case-syntax-pair ?,L<(B ?,L\(B tbl) - (set-case-syntax-pair ?,L=(B ?,L](B tbl) - (set-case-syntax-pair ?,L>(B ?,L^(B tbl) - (set-case-syntax-pair ?,L?(B ?,L_(B tbl) - (set-case-syntax-pair ?,L@(B ?,L`(B tbl) - (set-case-syntax-pair ?,LA(B ?,La(B tbl) - (set-case-syntax-pair ?,LB(B ?,Lb(B tbl) - (set-case-syntax-pair ?,LC(B ?,Lc(B tbl) - (set-case-syntax-pair ?,LD(B ?,Ld(B tbl) - (set-case-syntax-pair ?,LE(B ?,Le(B tbl) - (set-case-syntax-pair ?,LF(B ?,Lf(B tbl) - (set-case-syntax-pair ?,LG(B ?,Lg(B tbl) - (set-case-syntax-pair ?,LH(B ?,Lh(B tbl) - (set-case-syntax-pair ?,LI(B ?,Li(B tbl) - (set-case-syntax-pair ?,LJ(B ?,Lj(B tbl) - (set-case-syntax-pair ?,LK(B ?,Lk(B tbl) - (set-case-syntax-pair ?,LL(B ?,Ll(B tbl) - (set-case-syntax-pair ?,LM(B ?,Lm(B tbl) - (set-case-syntax-pair ?,LN(B ?,Ln(B tbl) - (set-case-syntax-pair ?,LO(B ?,Lo(B tbl) - (set-case-syntax-pair ?$,1(!(B ?$,1(q(B tbl) - (set-case-syntax-pair ?$,1("(B ?$,1(r(B tbl) - (set-case-syntax-pair ?$,1(#(B ?$,1(s(B tbl) - (set-case-syntax-pair ?$,1($(B ?$,1(t(B tbl) - (set-case-syntax-pair ?$,1(%(B ?$,1(u(B tbl) - (set-case-syntax-pair ?$,1(&(B ?$,1(v(B tbl) - (set-case-syntax-pair ?$,1('(B ?$,1(w(B tbl) - (set-case-syntax-pair ?$,1(((B ?$,1(x(B tbl) - (set-case-syntax-pair ?$,1()(B ?$,1(y(B tbl) - (set-case-syntax-pair ?$,1(*(B ?$,1(z(B tbl) - (set-case-syntax-pair ?$,1(+(B ?$,1({(B tbl) - (set-case-syntax-pair ?$,1(,(B ?$,1(|(B tbl) - (set-case-syntax-pair ?$,1(.(B ?$,1(~(B tbl) - (set-case-syntax-pair ?$,1(/(B ?$,1((B tbl) - (set-case-syntax-pair ?$,1(0(B ?$,1(P(B tbl) - (set-case-syntax-pair ?$,1(1(B ?$,1(Q(B tbl) - (set-case-syntax-pair ?$,1(2(B ?$,1(R(B tbl) - (set-case-syntax-pair ?$,1(3(B ?$,1(S(B tbl) - (set-case-syntax-pair ?$,1(4(B ?$,1(T(B tbl) - (set-case-syntax-pair ?$,1(5(B ?$,1(U(B tbl) - (set-case-syntax-pair ?$,1(6(B ?$,1(V(B tbl) - (set-case-syntax-pair ?$,1(7(B ?$,1(W(B tbl) - (set-case-syntax-pair ?$,1(8(B ?$,1(X(B tbl) - (set-case-syntax-pair ?$,1(9(B ?$,1(Y(B tbl) - (set-case-syntax-pair ?$,1(:(B ?$,1(Z(B tbl) - (set-case-syntax-pair ?$,1(;(B ?$,1([(B tbl) - (set-case-syntax-pair ?$,1(<(B ?$,1(\(B tbl) - (set-case-syntax-pair ?$,1(=(B ?$,1(](B tbl) - (set-case-syntax-pair ?$,1(>(B ?$,1(^(B tbl) - (set-case-syntax-pair ?$,1(?(B ?$,1(_(B tbl) - (set-case-syntax-pair ?$,1(@(B ?$,1(`(B tbl) - (set-case-syntax-pair ?$,1(A(B ?$,1(a(B tbl) - (set-case-syntax-pair ?$,1(B(B ?$,1(b(B tbl) - (set-case-syntax-pair ?$,1(C(B ?$,1(c(B tbl) - (set-case-syntax-pair ?$,1(D(B ?$,1(d(B tbl) - (set-case-syntax-pair ?$,1(E(B ?$,1(e(B tbl) - (set-case-syntax-pair ?$,1(F(B ?$,1(f(B tbl) - (set-case-syntax-pair ?$,1(G(B ?$,1(g(B tbl) - (set-case-syntax-pair ?$,1(H(B ?$,1(h(B tbl) - (set-case-syntax-pair ?$,1(I(B ?$,1(i(B tbl) - (set-case-syntax-pair ?$,1(J(B ?$,1(j(B tbl) - (set-case-syntax-pair ?$,1(K(B ?$,1(k(B tbl) - (set-case-syntax-pair ?$,1(L(B ?$,1(l(B tbl) - (set-case-syntax-pair ?$,1(M(B ?$,1(m(B tbl) - (set-case-syntax-pair ?$,1(N(B ?$,1(n(B tbl) - (set-case-syntax-pair ?$,1(O(B ?$,1(o(B tbl)) - -;; Devanagari character set - -;;; Commented out since the categories appear not to be used anywhere -;;; and word syntax is the default. -;; (let ((deflist '(;; chars syntax category -;; ("$(5!!!"!#(B" "w" ?7) ; vowel-modifying diacritical mark -;; ; chandrabindu, anuswar, visarga -;; ("$(5!$(B-$(5!2(B" "w" ?1) ; independent vowel -;; ("$(5!3(B-$(5!X(B" "w" ?0) ; consonant -;; ("$(5!Z(B-$(5!g(B" "w" ?8) ; matra -;; ("$(5!q(B-$(5!z(B" "w" ?6) ; digit -;; ;; Unicode equivalents -;; ("$,15A5B5C(B" "w" ?7) ; vowel-modifying diacritical mark -;; ; chandrabindu, anuswar, visarga -;; ("$,15E(B-$,15M(B" "w" ?1) ; independent vowel -;; ("$,15U(B-$,15y(B" "w" ?0) ; consonant -;; ("$,15~(B-$,16)(B" "w" ?8) ; matra -;; ("$,16F(B-$,16O(B" "w" ?6) ; digit -;; )) -;; elm chars len syntax category to ch i) -;; (while deflist -;; (setq elm (car deflist)) -;; (setq chars (car elm) -;; len (length chars) -;; syntax (nth 1 elm) -;; category (nth 2 elm) -;; i 0) -;; (while (< i len) -;; (if (= (aref chars i) ?-) -;; (setq i (1+ i) -;; to (aref chars i)) -;; (setq ch (aref chars i) -;; to ch)) -;; (while (<= ch to) -;; (modify-syntax-entry ch syntax) -;; (modify-category-entry ch category) -;; (setq ch (1+ ch))) -;; (setq i (1+ i))) -;; (setq deflist (cdr deflist)))) +(modify-syntax-entry ?№ ".") ;; Ethiopic character set -(modify-category-entry (make-char 'ethiopic) ?e) -;; (modify-syntax-entry (make-char 'ethiopic) "w") -(dotimes (i (1+ (- #x137c #x1200))) - (modify-category-entry (decode-char 'ucs (+ #x1200 i)) ?e)) -(let ((chars '(?$(3$h(B ?$(3$i(B ?$(3$j(B ?$(3$k(B ?$(3$l(B ?$(3$m(B ?$(3$n(B ?$(3$o(B ?$(3%i(B ?$(3%t(B ?$(3%u(B ?$(3%v(B ?$(3%w(B ?$(3%x(B - ;; Unicode equivalents of the above: - ?$,1Q!(B ?$,1Q"(B ?$,1Q#(B ?$,1Q$(B ?$,1Q%(B ?$,1Q&(B ?$,1Q'(B ?$,1Q((B ?$,3op(B ?$,3o{(B ?$,3o|(B ?$,3o}(B ?$,3o~(B ?$,3o(B))) +(modify-category-entry '(#x1200 . #x137b) ?e) +(let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨ ? ? ? ? ? ?))) (while chars (modify-syntax-entry (car chars) ".") (setq chars (cdr chars)))) - -;; Greek character set (ISO-8859-7) - -(modify-category-entry (make-char 'greek-iso8859-7) ?g) -(let ((c #x370)) - (while (<= c #x3ff) - (modify-category-entry (decode-char 'ucs c) ?g) - (setq c (1+ c)))) - -;; (let ((c 182)) -;; (while (< c 255) -;; (modify-syntax-entry (make-char 'greek-iso8859-7 c) "w") -;; (setq c (1+ c)))) -;; (modify-syntax-entry (make-char 'greek-iso8859-7 160) "w") ; NBSP -(modify-syntax-entry ?,F7(B ".") -(modify-syntax-entry ?,F;(B ".") -(modify-syntax-entry ?,F=(B ".") -(let ((tbl (standard-case-table))) - ;; Fixme: non-letter syntax copied from latin-1, but that's dubious - ;; in several cases. - (set-case-syntax ?,F!(B "." tbl) - (set-case-syntax ?,F"(B "." tbl) - (set-case-syntax ?,F&(B "." tbl) - (set-case-syntax ?,F&(B "_" tbl) - (set-case-syntax ?,F'(B "." tbl) - (set-case-syntax ?,F)(B "_" tbl) - (set-case-syntax ?,F+(B "." tbl) - (set-case-syntax ?,F,(B "_" tbl) - (set-case-syntax ?,F-(B "_" tbl) - (set-case-syntax ?,F/(B "." tbl) - (set-case-syntax ?,F0(B "_" tbl) - (set-case-syntax ?,F1(B "_" tbl) -;; (set-case-syntax ?,F7(B "_" tbl) -;; (set-case-syntax ?,F=(B "_" tbl) - (set-case-syntax-pair ?,FA(B ?,Fa(B tbl) - (set-case-syntax-pair ?,FB(B ?,Fb(B tbl) - (set-case-syntax-pair ?,FC(B ?,Fc(B tbl) - (set-case-syntax-pair ?,FD(B ?,Fd(B tbl) - (set-case-syntax-pair ?,FE(B ?,Fe(B tbl) - (set-case-syntax-pair ?,FF(B ?,Ff(B tbl) - (set-case-syntax-pair ?,FG(B ?,Fg(B tbl) - (set-case-syntax-pair ?,FH(B ?,Fh(B tbl) - (set-case-syntax-pair ?,FI(B ?,Fi(B tbl) - (set-case-syntax-pair ?,FJ(B ?,Fj(B tbl) - (set-case-syntax-pair ?,FK(B ?,Fk(B tbl) - (set-case-syntax-pair ?,FL(B ?,Fl(B tbl) - (set-case-syntax-pair ?,FM(B ?,Fm(B tbl) - (set-case-syntax-pair ?,FN(B ?,Fn(B tbl) - (set-case-syntax-pair ?,FO(B ?,Fo(B tbl) - (set-case-syntax-pair ?,FP(B ?,Fp(B tbl) - (set-case-syntax-pair ?,FQ(B ?,Fq(B tbl) - (set-case-syntax-pair ?,FS(B ?,Fs(B tbl) - (set-case-syntax-pair ?,FT(B ?,Ft(B tbl) - (set-case-syntax-pair ?,FU(B ?,Fu(B tbl) - (set-case-syntax-pair ?,FV(B ?,Fv(B tbl) - (set-case-syntax-pair ?,FW(B ?,Fw(B tbl) - (set-case-syntax-pair ?,FX(B ?,Fx(B tbl) - (set-case-syntax-pair ?,FY(B ?,Fy(B tbl) - (set-case-syntax-pair ?,FZ(B ?,Fz(B tbl) - (set-case-syntax-pair ?,F[(B ?,F{(B tbl) - (set-case-syntax-pair ?,F?(B ?,F~(B tbl) - (set-case-syntax-pair ?,F>(B ?,F}(B tbl) - (set-case-syntax-pair ?,F<(B ?,F|(B tbl) - (set-case-syntax-pair ?,F6(B ?,F\(B tbl) - (set-case-syntax-pair ?,F8(B ?,F](B tbl) - (set-case-syntax-pair ?,F9(B ?,F^(B tbl) - (set-case-syntax-pair ?,F:(B ?,F_(B tbl) - ;; Unicode equivalents - (set-case-syntax-pair ?$,1&q(B ?$,1'1(B tbl) - (set-case-syntax-pair ?$,1&r(B ?$,1'2(B tbl) - (set-case-syntax-pair ?$,1&s(B ?$,1'3(B tbl) - (set-case-syntax-pair ?$,1&t(B ?$,1'4(B tbl) - (set-case-syntax-pair ?$,1&u(B ?$,1'5(B tbl) - (set-case-syntax-pair ?$,1&v(B ?$,1'6(B tbl) - (set-case-syntax-pair ?$,1&w(B ?$,1'7(B tbl) - (set-case-syntax-pair ?$,1&x(B ?$,1'8(B tbl) - (set-case-syntax-pair ?$,1&y(B ?$,1'9(B tbl) - (set-case-syntax-pair ?$,1&z(B ?$,1':(B tbl) - (set-case-syntax-pair ?$,1&{(B ?$,1';(B tbl) - (set-case-syntax-pair ?$,1&|(B ?$,1'<(B tbl) - (set-case-syntax-pair ?$,1&}(B ?$,1'=(B tbl) - (set-case-syntax-pair ?$,1&~(B ?$,1'>(B tbl) - (set-case-syntax-pair ?$,1&(B ?$,1'?(B tbl) - (set-case-syntax-pair ?$,1' (B ?$,1'@(B tbl) - (set-case-syntax-pair ?$,1'!(B ?$,1'A(B tbl) - (set-case-syntax-pair ?$,1'#(B ?$,1'C(B tbl) - (set-case-syntax-pair ?$,1'$(B ?$,1'D(B tbl) - (set-case-syntax-pair ?$,1'%(B ?$,1'E(B tbl) - (set-case-syntax-pair ?$,1'&(B ?$,1'F(B tbl) - (set-case-syntax-pair ?$,1''(B ?$,1'G(B tbl) - (set-case-syntax-pair ?$,1'((B ?$,1'H(B tbl) - (set-case-syntax-pair ?$,1')(B ?$,1'I(B tbl) - (set-case-syntax-pair ?$,1'*(B ?$,1'J(B tbl) - (set-case-syntax-pair ?$,1'+(B ?$,1'K(B tbl) - (set-case-syntax-pair ?$,1&o(B ?$,1'N(B tbl) - (set-case-syntax-pair ?$,1&n(B ?$,1'M(B tbl) - (set-case-syntax-pair ?$,1&l(B ?$,1'L(B tbl) - (set-case-syntax-pair ?$,1&f(B ?$,1',(B tbl) - (set-case-syntax-pair ?$,1&h(B ?$,1'-(B tbl) - (set-case-syntax-pair ?$,1&i(B ?$,1'.(B tbl) - (set-case-syntax-pair ?$,1&j(B ?$,1'/(B tbl)) +(map-charset-chars #'modify-category-entry 'ethiopic ?e) ;; Hebrew character set (ISO-8859-8) -(modify-category-entry (make-char 'hebrew-iso8859-8) ?w) -(let ((c #x591)) - (while (<= c #x5f4) - (modify-category-entry (decode-char 'ucs c) ?w) - (setq c (1+ c)))) - -(modify-syntax-entry (make-char 'hebrew-iso8859-8 208) ".") ; PASEQ -(modify-syntax-entry (make-char 'hebrew-iso8859-8 211) ".") ; SOF PASUQ -(modify-syntax-entry (decode-char 'ucs #x5be) ".") ; MAQAF -(modify-syntax-entry (decode-char 'ucs #x5c0) ".") ; PASEQ -(modify-syntax-entry (decode-char 'ucs #x5c3) ".") ; SOF PASUQ -(modify-syntax-entry (decode-char 'ucs #x5f3) ".") ; GERESH -(modify-syntax-entry (decode-char 'ucs #x5f4) ".") ; GERSHAYIM - -;; (let ((c 224)) -;; (while (< c 251) -;; (modify-syntax-entry (make-char 'hebrew-iso8859-8 c) "w") -;; (setq c (1+ c)))) -;; (modify-syntax-entry (make-char 'hebrew-iso8859-8 160) "w") ; NBSP +(modify-syntax-entry #x5be ".") ; MAQAF +(modify-syntax-entry #x5c0 ".") ; PASEQ +(modify-syntax-entry #x5c3 ".") ; SOF PASUQ +(modify-syntax-entry #x5f3 ".") ; GERESH +(modify-syntax-entry #x5f4 ".") ; GERSHAYIM ;; Indian character set (IS 13194 and other Emacs original Indian charsets) -(modify-category-entry (make-char 'indian-is13194) ?i) -(modify-category-entry (make-char 'indian-2-column) ?I) -(modify-category-entry (make-char 'indian-glyph) ?I) -;; Unicode Devanagari block -(let ((c #x901)) - (while (<= c #x970) - (modify-category-entry (decode-char 'ucs c) ?i) - (setq c (1+ c)))) - -(let ((l '(;; RANGE CATEGORY MEANINGS - (#x01 #x03 ?7) ; vowel modifier - (#x05 #x14 ?1) ; base vowel - (#x15 #x39 ?0) ; consonants - (#x3e #x4d ?8) ; vowel modifier - (#x51 #x54 ?4) ; stress/tone mark - (#x58 #x5f ?0) ; consonants - (#x60 #x61 ?1) ; base vowel - (#x62 #x63 ?8) ; vowel modifier - (#x66 #x6f ?6) ; digits - ))) - (dolist (elt1 '(#x900 #x980 #xa00 #xa80 #xb00 #xb80 #xc00 #xc80 #xd00)) - (dolist (elt2 l) - (let* ((from (car elt2)) - (counts (1+ (- (nth 1 elt2) from))) - (category (nth 2 elt2))) - (dotimes (i counts) - (modify-category-entry (decode-char 'ucs (+ elt1 from i)) - category)))))) - -;; Japanese character set (JISX0201-kana, JISX0201-roman, JISX0208, JISX0212) - -(modify-category-entry (make-char 'katakana-jisx0201) ?k) -(modify-category-entry (make-char 'katakana-jisx0201) ?j) -(modify-category-entry (make-char 'latin-jisx0201) ?r) -(modify-category-entry (make-char 'japanese-jisx0208) ?j) -(modify-category-entry (make-char 'japanese-jisx0212) ?j) -(modify-category-entry (make-char 'katakana-jisx0201) ?\|) -(modify-category-entry (make-char 'japanese-jisx0208) ?\|) -(modify-category-entry (make-char 'japanese-jisx0212) ?\|) - -;; Unicode equivalents of JISX0201-kana -(let ((c #xff61)) - (while (<= c #xff9f) - (modify-category-entry (decode-char 'ucs c) ?k) - (modify-category-entry (decode-char 'ucs c) ?j) - (modify-category-entry (decode-char 'ucs c) ?\|) - (setq c (1+ c)))) - -;; Katakana block -(let ((c #x30a0)) - (while (<= c #x30ff) - ;; ?K is double width, ?k isn't specified - (modify-category-entry (decode-char 'ucs c) ?k) - (modify-category-entry (decode-char 'ucs c) ?j) - (modify-category-entry (decode-char 'ucs c) ?\|) - (setq c (1+ c)))) - -;; Hiragana block -(let ((c #x3040)) - (while (<= c #x309f) - ;; ?H is actually defined to be double width - (modify-category-entry (decode-char 'ucs c) ?H) - ;;(modify-category-entry (decode-char 'ucs c) ?j) - (modify-category-entry (decode-char 'ucs c) ?\|) - (setq c (1+ c)))) - -;; JISX0208 -;; (modify-syntax-entry (make-char 'japanese-jisx0208) "w") -(modify-syntax-entry (make-char 'japanese-jisx0208 33) "_") -(modify-syntax-entry (make-char 'japanese-jisx0208 34) "_") -(modify-syntax-entry (make-char 'japanese-jisx0208 40) "_") -(let ((chars '(?$B!<(B ?$B!+(B ?$B!,(B ?$B!3(B ?$B!4(B ?$B!5(B ?$B!6(B ?$B!7(B ?$B!8(B ?$B!9(B ?$B!:(B ?$B!;(B))) - (while chars - (modify-syntax-entry (car chars) "w") - (setq chars (cdr chars)))) -(modify-syntax-entry ?\$B!J(B "($B!K(B") -(modify-syntax-entry ?\$B!N(B "($B!O(B") -(modify-syntax-entry ?\$B!P(B "($B!Q(B") -(modify-syntax-entry ?\$B!V(B "($B!W(B") -(modify-syntax-entry ?\$B!X(B "($B!Y(B") -(modify-syntax-entry ?\$B!K(B ")$B!J(B") -(modify-syntax-entry ?\$B!O(B ")$B!N(B") -(modify-syntax-entry ?\$B!Q(B ")$B!P(B") -(modify-syntax-entry ?\$B!W(B ")$B!V(B") -(modify-syntax-entry ?\$B!Y(B ")$B!X(B") - -(modify-category-entry (make-char 'japanese-jisx0208 35) ?A) -(modify-category-entry (make-char 'japanese-jisx0208 36) ?H) -(modify-category-entry (make-char 'japanese-jisx0208 37) ?K) -(modify-category-entry (make-char 'japanese-jisx0208 38) ?G) -(modify-category-entry (make-char 'japanese-jisx0208 39) ?Y) -(let ((row 48)) - (while (< row 127) - (modify-category-entry (make-char 'japanese-jisx0208 row) ?C) - (setq row (1+ row)))) -(modify-category-entry ?$B!<(B ?K) -(let ((chars '(?$B!+(B ?$B!,(B))) - (while chars - (modify-category-entry (car chars) ?K) - (modify-category-entry (car chars) ?H) - (setq chars (cdr chars)))) -(let ((chars '(?$B!3(B ?$B!4(B ?$B!5(B ?$B!6(B ?$B!7(B ?$B!8(B ?$B!9(B ?$B!:(B ?$B!;(B))) - (while chars - (modify-category-entry (car chars) ?C) - (setq chars (cdr chars)))) - -;; JISX0212 -;; (modify-syntax-entry (make-char 'japanese-jisx0212) "w") -(modify-syntax-entry (make-char 'japanese-jisx0212 33) "_") -(modify-syntax-entry (make-char 'japanese-jisx0212 34) "_") -(modify-syntax-entry (make-char 'japanese-jisx0212 35) "_") - -(modify-category-entry (make-char 'japanese-jisx0212 ) ?C) - -;; JISX0201-Kana -;; (modify-syntax-entry (make-char 'katakana-jisx0201) "w") -(let ((chars '(?(I!(B ?(I$(B ?(I%(B - ;; Unicode: - ?$,3sa(B ?$,3sd(B ?$,3se(B))) - (while chars - (modify-syntax-entry (car chars) ".") - (setq chars (cdr chars)))) - -(modify-syntax-entry ?\(I"(B "((I#(B") -(modify-syntax-entry ?\(I#(B "((I"(B") - -;; Korean character set (KSC5601) - -;; (modify-syntax-entry (make-char 'korean-ksc5601) "w") -(modify-syntax-entry (make-char 'korean-ksc5601 33) "_") -(modify-syntax-entry (make-char 'korean-ksc5601 34) "_") -(modify-syntax-entry (make-char 'korean-ksc5601 38) "_") -(modify-syntax-entry (make-char 'korean-ksc5601 39) "_") -(modify-syntax-entry (make-char 'korean-ksc5601 40) "_") -(modify-syntax-entry (make-char 'korean-ksc5601 41) "_") - -(modify-category-entry (make-char 'korean-ksc5601) ?h) -(modify-category-entry (make-char 'korean-ksc5601 35) ?A) -(modify-category-entry (make-char 'korean-ksc5601 37) ?G) -(modify-category-entry (make-char 'korean-ksc5601 42) ?H) -(modify-category-entry (make-char 'korean-ksc5601 43) ?K) -(modify-category-entry (make-char 'korean-ksc5601 44) ?Y) - -;; Latin character set (latin-1,2,3,4,5,8,9) - -(modify-category-entry (make-char 'latin-iso8859-1) ?l) -(modify-category-entry (make-char 'latin-iso8859-2) ?l) -(modify-category-entry (make-char 'latin-iso8859-3) ?l) -(modify-category-entry (make-char 'latin-iso8859-4) ?l) -(modify-category-entry (make-char 'latin-iso8859-9) ?l) -(modify-category-entry (make-char 'latin-iso8859-14) ?l) -(modify-category-entry (make-char 'latin-iso8859-15) ?l) - -(modify-category-entry (make-char 'latin-iso8859-1 160) ?\ ) -(modify-category-entry (make-char 'latin-iso8859-2 160) ?\ ) -(modify-category-entry (make-char 'latin-iso8859-3 160) ?\ ) -(modify-category-entry (make-char 'latin-iso8859-4 160) ?\ ) -(modify-category-entry (make-char 'latin-iso8859-9 160) ?\ ) -(modify-category-entry (make-char 'latin-iso8859-14 160) ?\ ) -(modify-category-entry (make-char 'latin-iso8859-15 160) ?\ ) +(modify-category-entry '(#x901 . #x970) ?i) +(map-charset-chars #'modify-category-entry 'indian-is13194 ?i) +(map-charset-chars #'modify-category-entry 'indian-2-column ?i) ;; Lao character set -(modify-category-entry (make-char 'lao) ?o) -(dotimes (i (1+ (- #xeff #xe80))) - (modify-category-entry (decode-char 'ucs (+ i #xe80)) ?o)) +(modify-category-entry '(#xe80 . #xeff) ?o) +(map-charset-chars #'modify-category-entry 'lao ?o) -(let ((deflist '(;; chars syntax category - ("(1!(B-(1N(B" "w" ?0) ; consonant - ("(1PRS]`(B-(1d(B" "w" ?1) ; vowel base - ("(1QT(B-(1W[m(B" "w" ?2) ; vowel upper - ("(1XY(B" "w" ?3) ; vowel lower - ("(1h(B-(1l(B" "w" ?4) ; tone mark - ("(1\(B" "w" ?9) ; semivowel lower - ("(1p(B-(1y(B" "w" ?6) ; digit - ("(1Of(B" "_" ?5) ; symbol - ;; Unicode equivalents - ("$,1D!(B-$,1DN(B" "w" ?0) ; consonant - ("$,1DPDRDSD]D`(B-$,1Dd(B" "w" ?1) ; vowel base - ("$,1DQDT(B-$,1DWD[Dm(B" "w" ?2) ; vowel upper - ("$,1DXDY(B" "w" ?3) ; vowel lower - ("$,1Dh(B-$,1Dk(B" "w" ?4) ; tone mark - ("$,1D\D](B" "w" ?9) ; semivowel lower - ("$,1Dp(B-$,1Dy(B" "w" ?6) ; digit - ("$,1DODf(B" "_" ?5) ; symbol +(let ((deflist '(("ກ-ຮ" "w" ?0) ; consonant + ("ະາຳຽເ-ໄ" "w" ?1) ; vowel base + ("ັິ-ືົໍ" "w" ?2) ; vowel upper + ("ຸູ" "w" ?3) ; vowel lower + ("່-໋" "w" ?4) ; tone mark + ("ຼຽ" "w" ?9) ; semivowel lower + ("໐-໙" "w" ?6) ; digit + ("ຯໆ" "_" ?5) ; symbol )) elm chars len syntax category to ch i) (while deflist @@ -736,26 +324,17 @@ ;; Thai character set (TIS620) -(modify-category-entry (make-char 'thai-tis620) ?t) -(dotimes (i (1+ (- #xe7f #xe00))) - (modify-category-entry (decode-char 'ucs (+ i #xe00)) ?t)) +(modify-category-entry '(#xe00 . #xe7f) ?t) +(map-charset-chars #'modify-category-entry 'thai-tis620 ?t) (let ((deflist '(;; chars syntax category - (",T!(B-,TCEG(B-,TN(B" "w" ?0) ; consonant - (",TDFPRS`(B-,Te(B" "w" ?1) ; vowel base - (",TQT(B-,TWgn(B" "w" ?2) ; vowel upper - (",TX(B-,TZ(B" "w" ?3) ; vowel lower - (",Th(B-,Tm(B" "w" ?4) ; tone mark - (",Tp(B-,Ty(B" "w" ?6) ; digit - (",TOf_oz{(B" "_" ?5) ; symbol - ;; Unicode equivalents - ("$,1Ba(B-$,1C#C%C'(B-$,1C.(B" "w" ?0) ; consonant - ("$,1C$C&C0C2C3C@(B-$,1CE(B" "w" ?1) ; vowel base - ("$,1C1C4(B-$,1C7CGCN(B" "w" ?2) ; vowel upper - ("$,1C8(B-$,1C:(B" "w" ?3) ; vowel lower - ("$,1CH(B-$,1CM(B" "w" ?4) ; tone mark - ("$,1CP(B-$,1CY(B" "w" ?6) ; digit - ("$,1C/CFC?COCZC[(B" "_" ?5) ; symbol + ("ก-รลว-ฮ" "w" ?0) ; consonant + ("ฤฦะาำเ-ๅ" "w" ?1) ; vowel base + ("ัิ-ื็๎" "w" ?2) ; vowel upper + ("ุ-ฺ" "w" ?3) ; vowel lower + ("่-ํ" "w" ?4) ; tone mark + ("๐-๙" "w" ?6) ; digit + ("ฯๆ฿๏๚๛" "_" ?5) ; symbol )) elm chars len syntax category to ch i) (while deflist @@ -781,38 +360,26 @@ ;; Tibetan character set -(modify-category-entry (make-char 'tibetan) ?q) -(modify-category-entry (make-char 'tibetan-1-column) ?q) -(dotimes (i (1+ (- #xfff #xf00))) - (modify-category-entry (decode-char 'ucs (+ i #xf00)) ?q)) +(modify-category-entry '(#xf00 . #xfff) ?q) +(map-charset-chars #'modify-category-entry 'tibetan ?q) +(map-charset-chars #'modify-category-entry 'tibetan-1-column ?q) (let ((deflist '(;; chars syntax category - ("4$(7"!0"!1(B-4$(7"J0"J14"K0"K1(B" "w" ?0) ; consonant - ("$(7#!(B-$(7#J#K#L#M!"!#(B" "w" ?0) ; - ("$(7$!(B-$(7$e(B" "w" ?0) ; - ("$(7%!(B-$(7%u(B" "w" ?0) ; - ("$(7"S"["\"]"^"a(B" "w" ?2) ; upper vowel - ("$(7"_"c"d"g"h"i"j"k"l(B" "w" ?2) ; upper modifier - ("$(7!I"Q"R"U"e!e!g(B" "w" ?3) ; lowel vowel/modifier - ("$(7!P(B-$(7!Y!Z(B-$(7!c(B" "w" ?6) ; digit - ("$(7!;!=(B-$(7!B!D"`(B" "." ?|) ; line-break char - ("$(8!;!=!?!@!A!D"`(B" "." ?|) ; - ("$(7!8!;!=(B-$(7!B!D"`!m!d(B" "." ?>) ; prohibition - ("$(8!;!=!?!@!A!D"`(B" "." ?>) ; - ("$(7!0(B-$(7!:!l#R#S"f(B" "." ?<) ; prohibition - ("$(7!C!E(B-$(7!H!J(B-$(7!O!f!h(B-$(7!k!n!o#O#P(B-$(7#`(B" "." ?q) ; others - - ;; Unicode version (not complete) - ("$,1F (B-$,1FIFJ(B" "w" ?0) ; consonant - ("$,1Fp(B-$,1G9G:G;G<(B" "w" ?0) ; - ("$,1FRFZF[F\F]F`(B" "w" ?2) ; upper vowel - ("$,1F^FbFcFfFgFhFiFjFk(B" "w" ?2) ; upper modifier - ("$,1EYFPFQFTFdEuEw(B" "w" ?3) ; lowel vowel/modifier - ("$,1E`(B-$,1EiEj(B-$,1Es(B" "w" ?6) ; digit - ("$,1EKEM(B-$,1ERETF_(B" "." ?|) ; line-break char - ("$,1EHEKEM(B-$,1ERETF_E}Et(B" "." ?>) ; prohibition - ("$,1E@(B-$,1EJE|GAGBFe(B" "." ?<) ; prohibition - ("$,1ESEU(B-$,1EXEZ(B-$,1E_EvEx(B-$,1E{E~EG>G?(B-$,1GO(B" "." ?q) ; others + ("ཀ-ཀྵཪ" "w" ?0) ; consonant + ("ྐ-ྐྵྺྻྼ" "w" ?0) ; + ("-" "w" ?0) ; + ("-" "w" ?0) ; + ("ིེཻོཽྀ" "w" ?2) ; upper vowel + ("ཾྂྃ྆྇ྈྉྊྋ" "w" ?2) ; upper modifier + ("྄ཱུ༙༵༷" "w" ?3) ; lowel vowel/modifier + ("" "w" ?3) ; invisible vowel a + ("༠-༩༪-༳" "w" ?6) ; digit + ("་།-༒༔ཿ" "." ?|) ; line-break char + ("་།༏༐༑༔ཿ" "." ?|) ; + ("༈་།-༒༔ཿ༽༴" "." ?>) ; prohibition + ("་།༏༐༑༔ཿ" "." ?>) ; + ("ༀ-༊༼࿁࿂྅" "." ?<) ; prohibition + ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q) ; others )) elm chars len syntax category to ch i) (while deflist @@ -838,324 +405,348 @@ ;; Vietnamese character set -(let ((lower (make-char 'vietnamese-viscii-lower)) - (upper (make-char 'vietnamese-viscii-upper))) -;; (modify-syntax-entry lower "w") -;; (modify-syntax-entry upper "w") - (modify-category-entry lower ?v) - (modify-category-entry upper ?v) - (modify-category-entry lower ?l) ; To make a word with - (modify-category-entry upper ?l) ; latin characters. - ) +;; To make a word with Latin characters +(map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?l) +(map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?v) + +(map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?l) +(map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?v) (let ((tbl (standard-case-table)) (i 32)) (while (< i 128) - (set-case-syntax-pair (make-char 'vietnamese-viscii-upper i) - (make-char 'vietnamese-viscii-lower i) - tbl) + (let* ((char (decode-char 'vietnamese-viscii-upper i)) + (charl (decode-char 'vietnamese-viscii-lower i)) + (uc (encode-char char 'ucs)) + (lc (encode-char charl 'ucs))) + (set-case-syntax-pair char (decode-char 'vietnamese-viscii-lower i) + tbl) + (if uc (modify-category-entry uc ?v)) + (if lc (modify-category-entry lc ?v))) (setq i (1+ i)))) -;; Unicode (mule-unicode-0100-24ff) + +;; Latin + +(modify-category-entry '(#x80 . #x024F) ?l) (let ((tbl (standard-case-table)) c) ;; In some languages, U+0049 LATIN CAPITAL LETTER I and U+0131 LATIN ;; SMALL LETTER DOTLESS I make a case pair, and so do U+0130 LATIN ;; CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN SMALL LETTER I. -;; Thus we have to check language-environment to handle casing -;; correctly. Currently only I<->i is available. +;; See the Turkish language environment. + + ;; Latin-1 + + ;; Fixme: Some of the non-word syntaxes here perhaps should be + ;; reviewed. (Note that the following all implicitly have word + ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.) There should be a well-defined way of + ;; relating Unicode categories to Emacs syntax codes. + (set-case-syntax ? " " tbl) ; dubious + (set-case-syntax ?¡ "." tbl) + (set-case-syntax ?¦ "_" tbl) + (set-case-syntax ?§ "." tbl) + (set-case-syntax ?© "_" tbl) + (set-case-syntax-delims 171 187 tbl) ; « » + (set-case-syntax ?¬ "_" tbl) + (set-case-syntax ? "_" tbl) + (set-case-syntax ?® "_" tbl) + (set-case-syntax ?° "_" tbl) + (set-case-syntax ?± "_" tbl) + (set-case-syntax ?µ "_" tbl) + (set-case-syntax ?· "_" tbl) + (set-case-syntax ?¼ "_" tbl) + (set-case-syntax ?½ "_" tbl) + (set-case-syntax ?¾ "_" tbl) + (set-case-syntax ?¿ "." tbl) + (let ((c 192)) + (while (<= c 222) + (set-case-syntax-pair c (+ c 32) tbl) + (setq c (1+ c)))) + (set-case-syntax ?× "_" tbl) + (set-case-syntax ?ß "w" tbl) + (set-case-syntax ?÷ "_" tbl) + ;; See below for ÿ. ;; Latin Extended-A, Latin Extended-B (setq c #x0100) (while (<= c #x0233) - (modify-category-entry (decode-char 'ucs c) ?l) (and (or (<= c #x012e) (and (>= c #x014a) (<= c #x0177))) (zerop (% c 2)) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl)) + (set-case-syntax-pair c (1+ c) tbl)) (and (>= c #x013a) (<= c #x0148) (zerop (% c 2)) - (set-case-syntax-pair - (decode-char 'ucs (1- c)) (decode-char 'ucs c) tbl)) + (set-case-syntax-pair (1- c) c tbl)) (setq c (1+ c))) - (set-case-syntax-pair ?$,1 R(B ?$,1 S(B tbl) - (set-case-syntax-pair ?$,1 T(B ?$,1 U(B tbl) - (set-case-syntax-pair ?$,1 V(B ?$,1 W(B tbl) -;;; (set-case-syntax-pair ?$,1!8(B ?,A(B tbl) ; these two have different length! - (set-case-syntax-pair ?$,1!9(B ?$,1!:(B tbl) - (set-case-syntax-pair ?$,1!;(B ?$,1!<(B tbl) - (set-case-syntax-pair ?$,1!=(B ?$,1!>(B tbl) + (set-case-syntax-pair ?IJ ?ij tbl) + (set-case-syntax-pair ?Ĵ ?ĵ tbl) + (set-case-syntax-pair ?Ķ ?ķ tbl) + (set-case-syntax-pair ?Ÿ ?ÿ tbl) + (set-case-syntax-pair ?Ź ?ź tbl) + (set-case-syntax-pair ?Ż ?ż tbl) + (set-case-syntax-pair ?Ž ?ž tbl) ;; Latin Extended-B - (set-case-syntax-pair ?$,1!A(B ?$,1#S(B tbl) - (set-case-syntax-pair ?$,1!B(B ?$,1!C(B tbl) - (set-case-syntax-pair ?$,1!D(B ?$,1!E(B tbl) - (set-case-syntax-pair ?$,1!F(B ?$,1#T(B tbl) - (set-case-syntax-pair ?$,1!G(B ?$,1!H(B tbl) - (set-case-syntax-pair ?$,1!I(B ?$,1#V(B tbl) - (set-case-syntax-pair ?$,1!J(B ?$,1#W(B tbl) - (set-case-syntax-pair ?$,1!K(B ?$,1!L(B tbl) - (set-case-syntax-pair ?$,1!N(B ?$,1"=(B tbl) - (set-case-syntax-pair ?$,1!O(B ?$,1#Y(B tbl) - (set-case-syntax-pair ?$,1!P(B ?$,1#[(B tbl) - (set-case-syntax-pair ?$,1!Q(B ?$,1!R(B tbl) - (set-case-syntax-pair ?$,1!S(B ?$,1#`(B tbl) - (set-case-syntax-pair ?$,1!T(B ?$,1#c(B tbl) - (set-case-syntax-pair ?$,1!V(B ?$,1#i(B tbl) - (set-case-syntax-pair ?$,1!W(B ?$,1#h(B tbl) - (set-case-syntax-pair ?$,1!X(B ?$,1!Y(B tbl) - (set-case-syntax-pair ?$,1!\(B ?$,1#o(B tbl) - (set-case-syntax-pair ?$,1!](B ?$,1#r(B tbl) - (set-case-syntax-pair ?$,1!_(B ?$,1#u(B tbl) - (set-case-syntax-pair ?$,1!`(B ?$,1!a(B tbl) - (set-case-syntax-pair ?$,1!b(B ?$,1!c(B tbl) - (set-case-syntax-pair ?$,1!d(B ?$,1!e(B tbl) - (set-case-syntax-pair ?$,1!f(B ?$,1$ (B tbl) - (set-case-syntax-pair ?$,1!g(B ?$,1!h(B tbl) - (set-case-syntax-pair ?$,1!i(B ?$,1$#(B tbl) - (set-case-syntax-pair ?$,1!l(B ?$,1!m(B tbl) - (set-case-syntax-pair ?$,1!n(B ?$,1$((B tbl) - (set-case-syntax-pair ?$,1!o(B ?$,1!p(B tbl) - (set-case-syntax-pair ?$,1!q(B ?$,1$*(B tbl) - (set-case-syntax-pair ?$,1!r(B ?$,1$+(B tbl) - (set-case-syntax-pair ?$,1!s(B ?$,1!t(B tbl) - (set-case-syntax-pair ?$,1!u(B ?$,1!v(B tbl) - (set-case-syntax-pair ?$,1!w(B ?$,1$2(B tbl) - (set-case-syntax-pair ?$,1!x(B ?$,1!y(B tbl) - (set-case-syntax-pair ?$,1!|(B ?$,1!}(B tbl) - (set-case-syntax-pair ?$,1"$(B ?$,1"&(B tbl) - (set-case-syntax-pair ?$,1"%(B ?$,1"&(B tbl) - (set-case-syntax-pair ?$,1"'(B ?$,1")(B tbl) - (set-case-syntax-pair ?$,1"((B ?$,1")(B tbl) - (set-case-syntax-pair ?$,1"*(B ?$,1",(B tbl) - (set-case-syntax-pair ?$,1"+(B ?$,1",(B tbl) - (set-case-syntax-pair ?$,1"-(B ?$,1".(B tbl) - (set-case-syntax-pair ?$,1"/(B ?$,1"0(B tbl) - (set-case-syntax-pair ?$,1"1(B ?$,1"2(B tbl) - (set-case-syntax-pair ?$,1"3(B ?$,1"4(B tbl) - (set-case-syntax-pair ?$,1"5(B ?$,1"6(B tbl) - (set-case-syntax-pair ?$,1"7(B ?$,1"8(B tbl) - (set-case-syntax-pair ?$,1"9(B ?$,1":(B tbl) - (set-case-syntax-pair ?$,1";(B ?$,1"<(B tbl) - (set-case-syntax-pair ?$,1">(B ?$,1"?(B tbl) - (set-case-syntax-pair ?$,1"@(B ?$,1"A(B tbl) - (set-case-syntax-pair ?$,1"B(B ?$,1"C(B tbl) - (set-case-syntax-pair ?$,1"D(B ?$,1"E(B tbl) - (set-case-syntax-pair ?$,1"F(B ?$,1"G(B tbl) - (set-case-syntax-pair ?$,1"H(B ?$,1"I(B tbl) - (set-case-syntax-pair ?$,1"J(B ?$,1"K(B tbl) - (set-case-syntax-pair ?$,1"L(B ?$,1"M(B tbl) - (set-case-syntax-pair ?$,1"N(B ?$,1"O(B tbl) + (set-case-syntax-pair ?Ɓ ?ɓ tbl) + (set-case-syntax-pair ?Ƃ ?ƃ tbl) + (set-case-syntax-pair ?Ƅ ?ƅ tbl) + (set-case-syntax-pair ?Ɔ ?ɔ tbl) + (set-case-syntax-pair ?Ƈ ?ƈ tbl) + (set-case-syntax-pair ?Ɖ ?ɖ tbl) + (set-case-syntax-pair ?Ɗ ?ɗ tbl) + (set-case-syntax-pair ?Ƌ ?ƌ tbl) + (set-case-syntax-pair ?Ǝ ?ǝ tbl) + (set-case-syntax-pair ?Ə ?ə tbl) + (set-case-syntax-pair ?Ɛ ?ɛ tbl) + (set-case-syntax-pair ?Ƒ ?ƒ tbl) + (set-case-syntax-pair ?Ɠ ?ɠ tbl) + (set-case-syntax-pair ?Ɣ ?ɣ tbl) + (set-case-syntax-pair ?Ɩ ?ɩ tbl) + (set-case-syntax-pair ?Ɨ ?ɨ tbl) + (set-case-syntax-pair ?Ƙ ?ƙ tbl) + (set-case-syntax-pair ?Ɯ ?ɯ tbl) + (set-case-syntax-pair ?Ɲ ?ɲ tbl) + (set-case-syntax-pair ?Ɵ ?ɵ tbl) + (set-case-syntax-pair ?Ơ ?ơ tbl) + (set-case-syntax-pair ?Ƣ ?ƣ tbl) + (set-case-syntax-pair ?Ƥ ?ƥ tbl) + (set-case-syntax-pair ?Ʀ ?ʀ tbl) + (set-case-syntax-pair ?Ƨ ?ƨ tbl) + (set-case-syntax-pair ?Ʃ ?ʃ tbl) + (set-case-syntax-pair ?Ƭ ?ƭ tbl) + (set-case-syntax-pair ?Ʈ ?ʈ tbl) + (set-case-syntax-pair ?Ư ?ư tbl) + (set-case-syntax-pair ?Ʊ ?ʊ tbl) + (set-case-syntax-pair ?Ʋ ?ʋ tbl) + (set-case-syntax-pair ?Ƴ ?ƴ tbl) + (set-case-syntax-pair ?Ƶ ?ƶ tbl) + (set-case-syntax-pair ?Ʒ ?ʒ tbl) + (set-case-syntax-pair ?Ƹ ?ƹ tbl) + (set-case-syntax-pair ?Ƽ ?ƽ tbl) + (set-case-syntax-pair ?DŽ ?dž tbl) + (set-case-syntax-pair ?Dž ?dž tbl) + (set-case-syntax-pair ?LJ ?lj tbl) + (set-case-syntax-pair ?Lj ?lj tbl) + (set-case-syntax-pair ?NJ ?nj tbl) + (set-case-syntax-pair ?Nj ?nj tbl) + (set-case-syntax-pair ?Ǎ ?ǎ tbl) + (set-case-syntax-pair ?Ǐ ?ǐ tbl) + (set-case-syntax-pair ?Ǒ ?ǒ tbl) + (set-case-syntax-pair ?Ǔ ?ǔ tbl) + (set-case-syntax-pair ?Ǖ ?ǖ tbl) + (set-case-syntax-pair ?Ǘ ?ǘ tbl) + (set-case-syntax-pair ?Ǚ ?ǚ tbl) + (set-case-syntax-pair ?Ǜ ?ǜ tbl) + (set-case-syntax-pair ?Ǟ ?ǟ tbl) + (set-case-syntax-pair ?Ǡ ?ǡ tbl) + (set-case-syntax-pair ?Ǣ ?ǣ tbl) + (set-case-syntax-pair ?Ǥ ?ǥ tbl) + (set-case-syntax-pair ?Ǧ ?ǧ tbl) + (set-case-syntax-pair ?Ǩ ?ǩ tbl) + (set-case-syntax-pair ?Ǫ ?ǫ tbl) + (set-case-syntax-pair ?Ǭ ?ǭ tbl) + (set-case-syntax-pair ?Ǯ ?ǯ tbl) ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON - (set-case-syntax-pair ?$,1"Q(B ?$,1"S(B tbl) - (set-case-syntax-pair ?$,1"R(B ?$,1"S(B tbl) - (set-case-syntax-pair ?$,1"T(B ?$,1"U(B tbl) - (set-case-syntax-pair ?$,1"V(B ?$,1!U(B tbl) - (set-case-syntax-pair ?$,1"W(B ?$,1!(B tbl) - (set-case-syntax-pair ?$,1"X(B ?$,1"Y(B tbl) - (set-case-syntax-pair ?$,1"Z(B ?$,1"[(B tbl) - (set-case-syntax-pair ?$,1"\(B ?$,1"](B tbl) - (set-case-syntax-pair ?$,1"^(B ?$,1"_(B tbl) - (set-case-syntax-pair ?$,1"`(B ?$,1"a(B tbl) - (set-case-syntax-pair ?$,1"b(B ?$,1"c(B tbl) - (set-case-syntax-pair ?$,1"d(B ?$,1"e(B tbl) - (set-case-syntax-pair ?$,1"f(B ?$,1"g(B tbl) - (set-case-syntax-pair ?$,1"h(B ?$,1"i(B tbl) - (set-case-syntax-pair ?$,1"j(B ?$,1"k(B tbl) - (set-case-syntax-pair ?$,1"l(B ?$,1"m(B tbl) - (set-case-syntax-pair ?$,1"n(B ?$,1"o(B tbl) - (set-case-syntax-pair ?$,1"p(B ?$,1"q(B tbl) - (set-case-syntax-pair ?$,1"r(B ?$,1"s(B tbl) - (set-case-syntax-pair ?$,1"t(B ?$,1"u(B tbl) - (set-case-syntax-pair ?$,1"v(B ?$,1"w(B tbl) - (set-case-syntax-pair ?$,1"x(B ?$,1"y(B tbl) - (set-case-syntax-pair ?$,1"z(B ?$,1"{(B tbl) - (set-case-syntax-pair ?$,1"|(B ?$,1"}(B tbl) - (set-case-syntax-pair ?$,1"~(B ?$,1"(B tbl) - (set-case-syntax-pair ?$,1#"(B ?$,1##(B tbl) - (set-case-syntax-pair ?$,1#$(B ?$,1#%(B tbl) - (set-case-syntax-pair ?$,1#&(B ?$,1#'(B tbl) - (set-case-syntax-pair ?$,1#((B ?$,1#)(B tbl) - (set-case-syntax-pair ?$,1#*(B ?$,1#+(B tbl) - (set-case-syntax-pair ?$,1#,(B ?$,1#-(B tbl) - (set-case-syntax-pair ?$,1#.(B ?$,1#/(B tbl) - (set-case-syntax-pair ?$,1#0(B ?$,1#1(B tbl) - (set-case-syntax-pair ?$,1#2(B ?$,1#3(B tbl) + (set-case-syntax-pair ?DZ ?dz tbl) + (set-case-syntax-pair ?Dz ?dz tbl) + (set-case-syntax-pair ?Ǵ ?ǵ tbl) + (set-case-syntax-pair ?Ƕ ?ƕ tbl) + (set-case-syntax-pair ?Ƿ ?ƿ tbl) + (set-case-syntax-pair ?Ǹ ?ǹ tbl) + (set-case-syntax-pair ?Ǻ ?ǻ tbl) + (set-case-syntax-pair ?Ǽ ?ǽ tbl) + (set-case-syntax-pair ?Ǿ ?ǿ tbl) + (set-case-syntax-pair ?Ȁ ?ȁ tbl) + (set-case-syntax-pair ?Ȃ ?ȃ tbl) + (set-case-syntax-pair ?Ȅ ?ȅ tbl) + (set-case-syntax-pair ?Ȇ ?ȇ tbl) + (set-case-syntax-pair ?Ȉ ?ȉ tbl) + (set-case-syntax-pair ?Ȋ ?ȋ tbl) + (set-case-syntax-pair ?Ȍ ?ȍ tbl) + (set-case-syntax-pair ?Ȏ ?ȏ tbl) + (set-case-syntax-pair ?Ȑ ?ȑ tbl) + (set-case-syntax-pair ?Ȓ ?ȓ tbl) + (set-case-syntax-pair ?Ȕ ?ȕ tbl) + (set-case-syntax-pair ?Ȗ ?ȗ tbl) + (set-case-syntax-pair ?Ș ?ș tbl) + (set-case-syntax-pair ?Ț ?ț tbl) + (set-case-syntax-pair ?Ȝ ?ȝ tbl) + (set-case-syntax-pair ?Ȟ ?ȟ tbl) + (set-case-syntax-pair ?Ȣ ?ȣ tbl) + (set-case-syntax-pair ?Ȥ ?ȥ tbl) + (set-case-syntax-pair ?Ȧ ?ȧ tbl) + (set-case-syntax-pair ?Ȩ ?ȩ tbl) + (set-case-syntax-pair ?Ȫ ?ȫ tbl) + (set-case-syntax-pair ?Ȭ ?ȭ tbl) + (set-case-syntax-pair ?Ȯ ?ȯ tbl) + (set-case-syntax-pair ?Ȱ ?ȱ tbl) + (set-case-syntax-pair ?Ȳ ?ȳ tbl) ;; Latin Extended Additional + (modify-category-entry '(#x1e00 . #x1ef9) ?l) (setq c #x1e00) (while (<= c #x1ef9) - (modify-category-entry (decode-char 'ucs c) ?l) (and (zerop (% c 2)) (or (<= c #x1e94) (>= c #x1ea0)) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl)) + (set-case-syntax-pair c (1+ c) tbl)) (setq c (1+ c))) ;; Greek + (modify-category-entry '(#x0370 . #x03ff) ?g) (setq c #x0370) (while (<= c #x03ff) - (modify-category-entry (decode-char 'ucs c) ?g) (if (or (and (>= c #x0391) (<= c #x03a1)) (and (>= c #x03a3) (<= c #x03ab))) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (+ c 32)) tbl)) + (set-case-syntax-pair c (+ c 32) tbl)) (and (>= c #x03da) (<= c #x03ee) (zerop (% c 2)) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl)) + (set-case-syntax-pair c (1+ c) tbl)) (setq c (1+ c))) - (set-case-syntax-pair ?$,1&f(B ?$,1',(B tbl) - (set-case-syntax-pair ?$,1&h(B ?$,1'-(B tbl) - (set-case-syntax-pair ?$,1&i(B ?$,1'.(B tbl) - (set-case-syntax-pair ?$,1&j(B ?$,1'/(B tbl) - (set-case-syntax-pair ?$,1&l(B ?$,1'L(B tbl) - (set-case-syntax-pair ?$,1&n(B ?$,1'M(B tbl) - (set-case-syntax-pair ?$,1&o(B ?$,1'N(B tbl) + (set-case-syntax-pair ?Ά ?ά tbl) + (set-case-syntax-pair ?Έ ?έ tbl) + (set-case-syntax-pair ?Ή ?ή tbl) + (set-case-syntax-pair ?Ί ?ί tbl) + (set-case-syntax-pair ?Ό ?ό tbl) + (set-case-syntax-pair ?Ύ ?ύ tbl) + (set-case-syntax-pair ?Ώ ?ώ tbl) ;; Armenian (setq c #x531) (while (<= c #x556) - (set-case-syntax-pair (decode-char 'ucs c) - (decode-char 'ucs (+ c #x30)) tbl) + (set-case-syntax-pair c (+ c #x30) tbl) (setq c (1+ c))) ;; Greek Extended + (modify-category-entry '(#x1f00 . #x1fff) ?g) (setq c #x1f00) (while (<= c #x1fff) - (modify-category-entry (decode-char 'ucs c) ?g) (and (<= (logand c #x000f) 7) (<= c #x1fa7) (not (memq c '(#x1f50 #x1f52 #x1f54 #x1f56))) (/= (logand c #x00f0) 7) - (set-case-syntax-pair - (decode-char 'ucs (+ c 8)) (decode-char 'ucs c) tbl)) + (set-case-syntax-pair (+ c 8) c tbl)) (setq c (1+ c))) - (set-case-syntax-pair ?$,1qx(B ?$,1qp(B tbl) - (set-case-syntax-pair ?$,1qy(B ?$,1qq(B tbl) - (set-case-syntax-pair ?$,1qz(B ?$,1q0(B tbl) - (set-case-syntax-pair ?$,1q{(B ?$,1q1(B tbl) - (set-case-syntax-pair ?$,1q|(B ?$,1qs(B tbl) - (set-case-syntax-pair ?$,1r((B ?$,1q2(B tbl) - (set-case-syntax-pair ?$,1r)(B ?$,1q3(B tbl) - (set-case-syntax-pair ?$,1r*(B ?$,1q4(B tbl) - (set-case-syntax-pair ?$,1r+(B ?$,1q5(B tbl) - (set-case-syntax-pair ?$,1r,(B ?$,1r#(B tbl) - (set-case-syntax-pair ?$,1r8(B ?$,1r0(B tbl) - (set-case-syntax-pair ?$,1r9(B ?$,1r1(B tbl) - (set-case-syntax-pair ?$,1r:(B ?$,1q6(B tbl) - (set-case-syntax-pair ?$,1r;(B ?$,1q7(B tbl) - (set-case-syntax-pair ?$,1rH(B ?$,1r@(B tbl) - (set-case-syntax-pair ?$,1rI(B ?$,1rA(B tbl) - (set-case-syntax-pair ?$,1rJ(B ?$,1q:(B tbl) - (set-case-syntax-pair ?$,1rK(B ?$,1q;(B tbl) - (set-case-syntax-pair ?$,1rL(B ?$,1rE(B tbl) - (set-case-syntax-pair ?$,1rX(B ?$,1q8(B tbl) - (set-case-syntax-pair ?$,1rY(B ?$,1q9(B tbl) - (set-case-syntax-pair ?$,1rZ(B ?$,1q<(B tbl) - (set-case-syntax-pair ?$,1r[(B ?$,1q=(B tbl) - (set-case-syntax-pair ?$,1r\(B ?$,1rS(B tbl) + (set-case-syntax-pair ?Ᾰ ?ᾰ tbl) + (set-case-syntax-pair ?Ᾱ ?ᾱ tbl) + (set-case-syntax-pair ?Ὰ ?ὰ tbl) + (set-case-syntax-pair ?Ά ?ά tbl) + (set-case-syntax-pair ?ᾼ ?ᾳ tbl) + (set-case-syntax-pair ?Ὲ ?ὲ tbl) + (set-case-syntax-pair ?Έ ?έ tbl) + (set-case-syntax-pair ?Ὴ ?ὴ tbl) + (set-case-syntax-pair ?Ή ?ή tbl) + (set-case-syntax-pair ?ῌ ?ῃ tbl) + (set-case-syntax-pair ?Ῐ ?ῐ tbl) + (set-case-syntax-pair ?Ῑ ?ῑ tbl) + (set-case-syntax-pair ?Ὶ ?ὶ tbl) + (set-case-syntax-pair ?Ί ?ί tbl) + (set-case-syntax-pair ?Ῠ ?ῠ tbl) + (set-case-syntax-pair ?Ῡ ?ῡ tbl) + (set-case-syntax-pair ?Ὺ ?ὺ tbl) + (set-case-syntax-pair ?Ύ ?ύ tbl) + (set-case-syntax-pair ?Ῥ ?ῥ tbl) + (set-case-syntax-pair ?Ὸ ?ὸ tbl) + (set-case-syntax-pair ?Ό ?ό tbl) + (set-case-syntax-pair ?Ὼ ?ὼ tbl) + (set-case-syntax-pair ?Ώ ?ώ tbl) + (set-case-syntax-pair ?ῼ ?ῳ tbl) ;; cyrillic + (modify-category-entry '(#x0400 . #x04FF) ?y) (setq c #x0400) (while (<= c #x04ff) - (modify-category-entry (decode-char 'ucs c) ?y) (and (>= c #x0400) (<= c #x040f) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (+ c 80)) tbl)) + (set-case-syntax-pair c (+ c 80) tbl)) (and (>= c #x0410) (<= c #x042f) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (+ c 32)) tbl)) + (set-case-syntax-pair c (+ c 32) tbl)) (and (zerop (% c 2)) (or (and (>= c #x0460) (<= c #x0480)) (and (>= c #x048c) (<= c #x04be)) (and (>= c #x04d0) (<= c #x04f4))) - (set-case-syntax-pair - (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl)) + (set-case-syntax-pair c (1+ c) tbl)) (setq c (1+ c))) - (set-case-syntax-pair ?$,1*!(B ?$,1*"(B tbl) - (set-case-syntax-pair ?$,1*#(B ?$,1*$(B tbl) - (set-case-syntax-pair ?$,1*'(B ?$,1*((B tbl) - (set-case-syntax-pair ?$,1*+(B ?$,1*,(B tbl) - (set-case-syntax-pair ?$,1*X(B ?$,1*Y(B tbl) + (set-case-syntax-pair ?Ӂ ?ӂ tbl) + (set-case-syntax-pair ?Ӄ ?ӄ tbl) + (set-case-syntax-pair ?Ӈ ?ӈ tbl) + (set-case-syntax-pair ?Ӌ ?ӌ tbl) + (set-case-syntax-pair ?Ӹ ?ӹ tbl) ;; general punctuation (setq c #x2000) (while (<= c #x200b) - (set-case-syntax (decode-char 'ucs c) " " tbl) - (setq c (decode-char 'ucs (1+ c)))) - (setq c #x2010) + (set-case-syntax c " " tbl) + (setq c (1+ c))) + (while (<= c #x200F) + (set-case-syntax c "." tbl) + (setq c (1+ c))) + ;; Fixme: These aren't all right: (while (<= c #x2027) - (set-case-syntax (decode-char 'ucs c) "_" tbl) - (setq c (decode-char 'ucs (1+ c)))) + (set-case-syntax c "_" tbl) + (setq c (1+ c))) + (while (<= c #x206F) + (set-case-syntax c "." tbl) + (setq c (1+ c))) ;; Roman numerals (setq c #x2160) (while (<= c #x216f) - (set-case-syntax-pair (decode-char 'ucs c) - (decode-char 'ucs (+ c #x10)) tbl) + (set-case-syntax-pair c (+ c #x10) tbl) + (setq c (1+ c))) + + ;; Fixme: The following blocks might be better as symbol rather than + ;; punctuation. + ;; Arrows + (setq c #x2190) + (while (<= c #x21FF) + (set-case-syntax c "." tbl) + (setq c (1+ c))) + ;; Mathematical Operators + (while (<= c #x22FF) + (set-case-syntax c "." tbl) + (setq c (1+ c))) + ;; Miscellaneous Technical + (while (<= c #x23FF) + (set-case-syntax c "." tbl) + (setq c (1+ c))) + ;; Control Pictures + (while (<= c #x243F) + (set-case-syntax c "_" tbl) (setq c (1+ c))) ;; Circled Latin (setq c #x24b6) (while (<= c #x24cf) - (set-case-syntax-pair (decode-char 'ucs c) - (decode-char 'ucs (+ c 26)) tbl) - (modify-category-entry (decode-char 'ucs c) ?l) - (modify-category-entry (decode-char 'ucs (+ c 26)) ?l) + (set-case-syntax-pair c (+ c 26) tbl) + (modify-category-entry c ?l) + (modify-category-entry (+ c 26) ?l) (setq c (1+ c))) ;; Fullwidth Latin (setq c #xff21) (while (<= c #xff3a) - (set-case-syntax-pair (decode-char 'ucs c) - (decode-char 'ucs (+ c #x20)) tbl) - (modify-category-entry (decode-char 'ucs c) ?l) - (modify-category-entry (decode-char 'ucs (+ c #x20)) ?l) + (set-case-syntax-pair c (+ c #x20) tbl) + (modify-category-entry c ?l) + (modify-category-entry (+ c #x20) ?l) (setq c (1+ c))) ;; Combining diacritics - (setq c #x300) - (while (<= c #x362) - (modify-category-entry (decode-char 'ucs c) ?^) - (setq c (1+ c))) - + (modify-category-entry '(#x300 . #x362) ?^) ;; Combining marks - (setq c #x20d0) - (while (<= c #x20e3) - (modify-category-entry (decode-char 'ucs c) ?^) - (setq c (1+ c))) + (modify-category-entry '(#x20d0 . #x20e3) ?^) ;; Fixme: syntax for symbols &c ) -;;; Setting word boundary. - -(setq word-combining-categories - '((?l . ?l))) - -(setq word-separating-categories ; (2-byte character sets) - '((?A . ?K) ; Alpha numeric - Katakana - (?A . ?C) ; Alpha numeric - Chinese - (?H . ?A) ; Hiragana - Alpha numeric - (?H . ?K) ; Hiragana - Katakana - (?H . ?C) ; Hiragana - Chinese - (?K . ?A) ; Katakana - Alpha numeric - (?K . ?C) ; Katakana - Chinese - (?C . ?A) ; Chinese - Alpha numeric - (?C . ?K) ; Chinese - Katakana - )) - - ;; For each character set, put the information of the most proper ;; coding system to encode it by `preferred-coding-system' property. +;; Fixme: should this be junked? (let ((l '((latin-iso8859-1 . iso-latin-1) (latin-iso8859-2 . iso-latin-2) (latin-iso8859-3 . iso-latin-3) @@ -1183,7 +774,6 @@ (vietnamese-viscii-upper . vietnamese-viscii) (arabic-digit . iso-2022-7bit) (arabic-1-column . iso-2022-7bit) - (ascii-right-to-left . iso-2022-7bit) (lao . lao) (arabic-2-column . iso-2022-7bit) (indian-is13194 . devanagari) @@ -1211,12 +801,211 @@ japanese-jisx0208 japanese-jisx0212 chinese-gb2312 chinese-big5-1 chinese-big5-2))) (while l - (aset auto-fill-chars (make-char (car l)) t) + ;;(aset auto-fill-chars (make-char (car l)) t) (put-charset-property (car l) 'nospace-between-words t) (setq l (cdr l)))) + +;; CJK double width characters. +(let ((l '((#x1100 . #x11FF) + (#x2E80 . #x9FAF) + (#xAC00 . #xD7AF) + (#xF900 . #xFAFF) + (#xFE30 . #xFE4F) + (#xFF00 . #xFF5F) + (#xFFE0 . #xFFEF) + (#x20000 . #x2AFFF) + (#x2F800 . #x2FFFF)))) + (dolist (elt l) + (set-char-table-range char-width-table + (cons (car elt) (cdr elt)) + 2))) +;; Fixme: Doing this affects non-CJK characters through unification, +;; but presumably CJK users expect those characters to be +;; double-width when using these charsets. +;; (map-charset-chars +;; #'(lambda (range ignore) (set-char-table-range char-width-table range 2)) +;; 'japanese-jisx0208) +;; (map-charset-chars +;; #'(lambda (range ignore) (set-char-table-range char-width-table range 2)) +;; 'japanese-jisx0212) +;; (map-charset-chars +;; #'(lambda (range ignore) (set-char-table-range char-width-table range 2)) +;; 'japanese-jisx0213-1) +;; (map-charset-chars +;; #'(lambda (range ignore) (set-char-table-range char-width-table range 2)) +;; 'japanese-jisx0213-2) +;; (map-charset-chars +;; (lambda (range ignore) (set-char-table-range char-width-table range 2)) +;; 'korean-ksc5601) + +;; Other double width +(map-charset-chars + (lambda (range ignore) (set-char-table-range char-width-table range 2)) + 'ethiopic) +(map-charset-chars + (lambda (range ignore) (set-char-table-range char-width-table range 2)) + 'tibetan) +(map-charset-chars + (lambda (range ignore) (set-char-table-range char-width-table range 2)) + 'indian-2-column) +(map-charset-chars + (lambda (range ignore) (set-char-table-range char-width-table range 2)) + 'arabic-2-column) + +(optimize-char-table (standard-case-table)) +(optimize-char-table char-width-table) +(optimize-char-table (standard-category-table)) +(optimize-char-table (standard-syntax-table)) + +;; The Unicode blocks actually extend past some of these ranges with +;; undefined codepoints. +(let ((script-list nil)) + (dolist + (elt + '((#x0000 #x007F latin) + (#x00A0 #x036F latin) + (#x0370 #x03E1 greek) + (#x03E2 #x03EF coptic) + (#x03F0 #x03F3 greek) + (#x0400 #x04FF cyrillic) + (#x0530 #x058F armenian) + (#x0590 #x05FF hebrew) + (#x0600 #x06FF arabic) + (#x0700 #x074F syriac) + (#x0780 #x07BF thaana) + (#x0900 #x097F devanagari) + (#x0980 #x09FF bengali) + (#x0A00 #x0A7F gurmukhi) + (#x0A80 #x0AFF gujarati) + (#x0B00 #x0B7F oriya) + (#x0B80 #x0BFF tamil) + (#x0C00 #x0C7F telugu) + (#x0C80 #x0CFF kannada) + (#x0D00 #x0D7F malayalam) + (#x0D80 #x0DFF sinhala) + (#x0E00 #x0E5F thai) + (#x0E80 #x0EDF lao) + (#x0F00 #x0FFF tibetan) + (#x1000 #x105F myanmar) + (#x10A0 #x10FF georgian) + (#x1100 #x11FF hangul) + (#x1200 #x137F ethiopic) + (#x13A0 #x13FF cherokee) + (#x1400 #x167F canadian-aboriginal) + (#x1680 #x169F ogham) + (#x16A0 #x16FF runic) + (#x1780 #x17FF khmer) + (#x1800 #x18AF mongolian) + (#x1E00 #x1EFF latin) + (#x1F00 #x1FFF greek) + (#x20A0 #x20AF currency) + (#x2800 #x28FF braille) + (#x2E80 #x2FDF han) + (#x2FF0 #x2FFF ideographic-description) + (#x3000 #x303F cjk-misc) + (#x3040 #x30FF kana) + (#x3100 #x312F bopomofo) + (#x3130 #x318F hangul) + (#x3190 #x319F kanbun) + (#x31A0 #x31BF bopomofo) + (#x3400 #x9FAF han) + (#xA000 #xA4CF yi) + (#xAC00 #xD7AF hangul) + (#xF900 #xFA5F han) + (#xFB1D #xFB4F hebrew) + (#xFB50 #xFDFF arabic) + (#xFE70 #xFEFC arabic) + (#xFF00 #xFF5F cjk-misc) + (#xFF61 #xFF9F kana) + (#xFFE0 #xFFE6 cjk-misc) + (#x20000 #x2AFFF han) + (#x2F800 #x2FFFF han))) + (set-char-table-range char-script-table + (cons (car elt) (nth 1 elt)) (nth 2 elt)) + (or (memq (nth 2 elt) script-list) + (setq script-list (cons (nth 2 elt) script-list)))) + (set-char-table-extra-slot char-script-table 0 (nreverse script-list))) + +(map-charset-chars + #'(lambda (range ignore) + (set-char-table-range char-script-table range 'tibetan)) + 'tibetan) + + +;;; Setting word boundary. + +(defun next-word-boundary-han (pos limit) + (if (<= pos limit) + (save-excursion + (goto-char pos) + (looking-at "\\cC+") + (goto-char (match-end 0)) + (if (looking-at "\\cH+") + (goto-char (match-end 0))) + (point)) + (while (and (> pos limit) + (eq (aref char-script-table (char-after (1- pos))) 'han)) + (setq pos (1- pos))) + pos)) + +(defun next-word-boundary-kana (pos limit) + (if (<= pos limit) + (save-excursion + (goto-char pos) + (if (looking-at "\\cK+") + (goto-char (match-end 0))) + (if (looking-at "\\cH+") + (goto-char (match-end 0))) + (point)) + (let ((category-set (char-category-set (char-after pos))) + category) + (if (aref category-set ?K) + (while (and (> pos limit) + (aref (char-category-set (char-after (1- pos))) ?K)) + (setq pos (1- pos))) + (while (and (> pos limit) + (aref (setq category-set + (char-category-set (char-after (1- pos)))) ?H)) + (setq pos (1- pos))) + (setq category (cond ((aref category-set ?C) ?C) + ((aref category-set ?K) ?K) + ((aref category-set ?A) ?A))) + (when category + (setq pos (1- pos)) + (while (and (> pos limit) + (aref (char-category-set (char-after (1- pos))) + category)) + (setq pos (1- pos))))) + pos))) + +(map-char-table + #'(lambda (char script) + (cond ((eq script 'han) + (set-char-table-range find-word-boundary-function-table + char #'next-word-boundary-han)) + ((eq script 'kana) + (set-char-table-range find-word-boundary-function-table + char #'next-word-boundary-kana)))) + char-script-table) + +(setq word-combining-categories + '((?l . ?l))) + +(setq word-separating-categories ; (2-byte character sets) + '((?A . ?K) ; Alpha numeric - Katakana + (?A . ?C) ; Alpha numeric - Chinese + (?H . ?A) ; Hiragana - Alpha numeric + (?H . ?K) ; Hiragana - Katakana + (?H . ?C) ; Hiragana - Chinese + (?K . ?A) ; Katakana - Alpha numeric + (?K . ?C) ; Katakana - Chinese + (?C . ?A) ; Chinese - Alpha numeric + (?C . ?K) ; Chinese - Katakana + )) + ;;; Local Variables: -;;; coding: iso-2022-7bit +;;; coding: utf-8-emacs ;;; End: ;;; characters.el ends here