;; 2005, 2006, 2007, 2008
;; National Institute of Advanced Industrial Science and Technology (AIST)
;; Registration Number H14PRO021
+;; Copyright (C) 2003
+;; National Institute of Advanced Industrial Science and Technology (AIST)
+;; Registration Number H13PRO009
;; Keywords: multibyte character, character set, syntax, category
;;; 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:
-;; We must set utf-translate-cjk-mode to nil while loading this file
-;; to avoid translating CJK characters in decode-char.
-(defvar saved-utf-translate-cjk-mode utf-translate-cjk-mode)
-(setq utf-translate-cjk-mode nil)
-
;;; Predefined categories.
;; For each character set.
(define-category ?1 "base (independent) vowel")
(define-category ?2 "upper diacritical mark (including upper vowel)")
(define-category ?3 "lower diacritical mark (including lower vowel)")
-(define-category ?4 "tone mark")
+(define-category ?4 "combining tone mark")
(define-category ?5 "symbol")
(define-category ?6 "digit")
(define-category ?7 "vowel-modifying diacritical mark")
;; 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)
-;; Arabic character set
+;; 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.
-(let ((charsets '(arabic-iso8859-6
- arabic-digit
- arabic-1-column
- arabic-2-column)))
- (while charsets
-;; (modify-syntax-entry (make-char (car charsets)) "w")
- (modify-category-entry (make-char (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 ?\\e$A!2\e(B "(\e$A!3\e(B")
-(modify-syntax-entry ?\\e$A!4\e(B "(\e$A!5\e(B")
-(modify-syntax-entry ?\\e$A!6\e(B "(\e$A!7\e(B")
-(modify-syntax-entry ?\\e$A!8\e(B "(\e$A!9\e(B")
-(modify-syntax-entry ?\\e$A!:\e(B "(\e$A!;\e(B")
-(modify-syntax-entry ?\\e$A!<\e(B "(\e$A!=\e(B")
-(modify-syntax-entry ?\\e$A!>\e(B "(\e$A!?\e(B")
-(modify-syntax-entry ?\\e$A#(\e(B "(\e$A#)\e(B")
-(modify-syntax-entry ?\\e$A#{\e(B "(\e$A#}\e(B")
-(modify-syntax-entry ?\\e$A#[\e(B "(\e$A#]\e(B")
-(modify-syntax-entry ?\\e$A!3\e(B ")\e$A!2\e(B")
-(modify-syntax-entry ?\\e$A!5\e(B ")\e$A!4\e(B")
-(modify-syntax-entry ?\\e$A!7\e(B ")\e$A!6\e(B")
-(modify-syntax-entry ?\\e$A!9\e(B ")\e$A!8\e(B")
-(modify-syntax-entry ?\\e$A!;\e(B ")\e$A!:\e(B")
-(modify-syntax-entry ?\\e$A!=\e(B ")\e$A!<\e(B")
-(modify-syntax-entry ?\\e$A!?\e(B ")\e$A!>\e(B")
-(modify-syntax-entry ?\\e$A#)\e(B ")\e$A#(\e(B")
-(modify-syntax-entry ?\\e$A#}\e(B ")\e$A#{\e(B")
-(modify-syntax-entry ?\\e$A#]\e(B ")\e$A#[\e(B")
-
-(let ((chars "\e$A#,!"!##.!$#;#:#?#!!C!-!'#|#_!.!/!0!1#"!e#`!d\e(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))))
-
-(let ((tbl (standard-case-table)))
- (dotimes (i 26)
- (set-case-syntax-pair (make-char 'chinese-gb2312 #x23 (+ #x41 i))
- (make-char 'chinese-gb2312 #x23 (+ #x61 i)) tbl))
- (dotimes (i 24)
- (set-case-syntax-pair (make-char 'chinese-gb2312 #x26 (+ #x21 i))
- (make-char 'chinese-gb2312 #x26 (+ #x41 i)) tbl))
- (dotimes (i 33)
- (set-case-syntax-pair (make-char 'chinese-gb2312 #x27 (+ #x21 i))
- (make-char 'chinese-gb2312 #x27 (+ #x51 i)) tbl)))
-
-;; 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 "\e$(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\e(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))))
+;; Chinese characters (Unicode)
+(modify-category-entry '(#x2E80 . #x312F) ?|)
+(modify-category-entry '(#x3190 . #x33FF) ?|)
+(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) ?|)
+(modify-category-entry '(#x20000 . #x2AFFF) ?|)
+(modify-category-entry '(#x2F800 . #x2FFFF) ?|)
-(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)
+;; Chinese character set (GB2312)
- (modify-category-entry generic-big5-1-char ?C)
- (modify-category-entry generic-big5-2-char ?C)
+(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)
- (modify-category-entry generic-big5-1-char ?\|)
- (modify-category-entry generic-big5-2-char ?\|))
+(map-charset-chars #'modify-category-entry 'chinese-gb2312 ?c)
+(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)
-(let ((tbl (standard-case-table)))
- (dotimes (i 22)
- (set-case-syntax-pair (decode-big5-char (+ #xA2CF i))
- (decode-big5-char (+ #xA2CF i 26)) tbl))
- (dotimes (i 4)
- (set-case-syntax-pair (decode-big5-char (+ #xA2E4 i))
- (decode-big5-char (+ #xA340 i)) tbl))
- (dotimes (i 24)
- (set-case-syntax-pair (decode-big5-char (+ #xA344 i))
- (decode-big5-char (+ #xA344 i 24)) tbl)))
+;; 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)
;; 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))))
-
-(let ((parens "\e$(G!>!?!@!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\e(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))))
+(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)))
-;; Cyrillic character set (ISO-8859-5)
+;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213)
-(modify-category-entry (make-char 'cyrillic-iso8859-5) ?y)
-
-(modify-syntax-entry (make-char 'cyrillic-iso8859-5 160) " ")
-(modify-syntax-entry ?\e,L-\e(B ".")
-(modify-syntax-entry ?\e,Lp\e(B ".")
-(modify-syntax-entry ?\e,L}\e(B ".")
-(let ((tbl (standard-case-table)))
- (set-case-syntax-pair ?\e,L!\e(B ?\e,Lq\e(B tbl)
- (set-case-syntax-pair ?\e,L"\e(B ?\e,Lr\e(B tbl)
- (set-case-syntax-pair ?\e,L#\e(B ?\e,Ls\e(B tbl)
- (set-case-syntax-pair ?\e,L$\e(B ?\e,Lt\e(B tbl)
- (set-case-syntax-pair ?\e,L%\e(B ?\e,Lu\e(B tbl)
- (set-case-syntax-pair ?\e,L&\e(B ?\e,Lv\e(B tbl)
- (set-case-syntax-pair ?\e,L'\e(B ?\e,Lw\e(B tbl)
- (set-case-syntax-pair ?\e,L(\e(B ?\e,Lx\e(B tbl)
- (set-case-syntax-pair ?\e,L)\e(B ?\e,Ly\e(B tbl)
- (set-case-syntax-pair ?\e,L*\e(B ?\e,Lz\e(B tbl)
- (set-case-syntax-pair ?\e,L+\e(B ?\e,L{\e(B tbl)
- (set-case-syntax-pair ?\e,L,\e(B ?\e,L|\e(B tbl)
- (set-case-syntax-pair ?\e,L.\e(B ?\e,L~\e(B tbl)
- (set-case-syntax-pair ?\e,L/\e(B ?\e,L\7f\e(B tbl)
- (set-case-syntax-pair ?\e,L0\e(B ?\e,LP\e(B tbl)
- (set-case-syntax-pair ?\e,L1\e(B ?\e,LQ\e(B tbl)
- (set-case-syntax-pair ?\e,L2\e(B ?\e,LR\e(B tbl)
- (set-case-syntax-pair ?\e,L3\e(B ?\e,LS\e(B tbl)
- (set-case-syntax-pair ?\e,L4\e(B ?\e,LT\e(B tbl)
- (set-case-syntax-pair ?\e,L5\e(B ?\e,LU\e(B tbl)
- (set-case-syntax-pair ?\e,L6\e(B ?\e,LV\e(B tbl)
- (set-case-syntax-pair ?\e,L7\e(B ?\e,LW\e(B tbl)
- (set-case-syntax-pair ?\e,L8\e(B ?\e,LX\e(B tbl)
- (set-case-syntax-pair ?\e,L9\e(B ?\e,LY\e(B tbl)
- (set-case-syntax-pair ?\e,L:\e(B ?\e,LZ\e(B tbl)
- (set-case-syntax-pair ?\e,L;\e(B ?\e,L[\e(B tbl)
- (set-case-syntax-pair ?\e,L<\e(B ?\e,L\\e(B tbl)
- (set-case-syntax-pair ?\e,L=\e(B ?\e,L]\e(B tbl)
- (set-case-syntax-pair ?\e,L>\e(B ?\e,L^\e(B tbl)
- (set-case-syntax-pair ?\e,L?\e(B ?\e,L_\e(B tbl)
- (set-case-syntax-pair ?\e,L@\e(B ?\e,L`\e(B tbl)
- (set-case-syntax-pair ?\e,LA\e(B ?\e,La\e(B tbl)
- (set-case-syntax-pair ?\e,LB\e(B ?\e,Lb\e(B tbl)
- (set-case-syntax-pair ?\e,LC\e(B ?\e,Lc\e(B tbl)
- (set-case-syntax-pair ?\e,LD\e(B ?\e,Ld\e(B tbl)
- (set-case-syntax-pair ?\e,LE\e(B ?\e,Le\e(B tbl)
- (set-case-syntax-pair ?\e,LF\e(B ?\e,Lf\e(B tbl)
- (set-case-syntax-pair ?\e,LG\e(B ?\e,Lg\e(B tbl)
- (set-case-syntax-pair ?\e,LH\e(B ?\e,Lh\e(B tbl)
- (set-case-syntax-pair ?\e,LI\e(B ?\e,Li\e(B tbl)
- (set-case-syntax-pair ?\e,LJ\e(B ?\e,Lj\e(B tbl)
- (set-case-syntax-pair ?\e,LK\e(B ?\e,Lk\e(B tbl)
- (set-case-syntax-pair ?\e,LL\e(B ?\e,Ll\e(B tbl)
- (set-case-syntax-pair ?\e,LM\e(B ?\e,Lm\e(B tbl)
- (set-case-syntax-pair ?\e,LN\e(B ?\e,Ln\e(B tbl)
- (set-case-syntax-pair ?\e,LO\e(B ?\e,Lo\e(B tbl)
- (set-case-syntax-pair ?\e$,1(!\e(B ?\e$,1(q\e(B tbl)
- (set-case-syntax-pair ?\e$,1("\e(B ?\e$,1(r\e(B tbl)
- (set-case-syntax-pair ?\e$,1(#\e(B ?\e$,1(s\e(B tbl)
- (set-case-syntax-pair ?\e$,1($\e(B ?\e$,1(t\e(B tbl)
- (set-case-syntax-pair ?\e$,1(%\e(B ?\e$,1(u\e(B tbl)
- (set-case-syntax-pair ?\e$,1(&\e(B ?\e$,1(v\e(B tbl)
- (set-case-syntax-pair ?\e$,1('\e(B ?\e$,1(w\e(B tbl)
- (set-case-syntax-pair ?\e$,1((\e(B ?\e$,1(x\e(B tbl)
- (set-case-syntax-pair ?\e$,1()\e(B ?\e$,1(y\e(B tbl)
- (set-case-syntax-pair ?\e$,1(*\e(B ?\e$,1(z\e(B tbl)
- (set-case-syntax-pair ?\e$,1(+\e(B ?\e$,1({\e(B tbl)
- (set-case-syntax-pair ?\e$,1(,\e(B ?\e$,1(|\e(B tbl)
- (set-case-syntax-pair ?\e$,1(.\e(B ?\e$,1(~\e(B tbl)
- (set-case-syntax-pair ?\e$,1(/\e(B ?\e$,1(\7f\e(B tbl)
- (set-case-syntax-pair ?\e$,1(0\e(B ?\e$,1(P\e(B tbl)
- (set-case-syntax-pair ?\e$,1(1\e(B ?\e$,1(Q\e(B tbl)
- (set-case-syntax-pair ?\e$,1(2\e(B ?\e$,1(R\e(B tbl)
- (set-case-syntax-pair ?\e$,1(3\e(B ?\e$,1(S\e(B tbl)
- (set-case-syntax-pair ?\e$,1(4\e(B ?\e$,1(T\e(B tbl)
- (set-case-syntax-pair ?\e$,1(5\e(B ?\e$,1(U\e(B tbl)
- (set-case-syntax-pair ?\e$,1(6\e(B ?\e$,1(V\e(B tbl)
- (set-case-syntax-pair ?\e$,1(7\e(B ?\e$,1(W\e(B tbl)
- (set-case-syntax-pair ?\e$,1(8\e(B ?\e$,1(X\e(B tbl)
- (set-case-syntax-pair ?\e$,1(9\e(B ?\e$,1(Y\e(B tbl)
- (set-case-syntax-pair ?\e$,1(:\e(B ?\e$,1(Z\e(B tbl)
- (set-case-syntax-pair ?\e$,1(;\e(B ?\e$,1([\e(B tbl)
- (set-case-syntax-pair ?\e$,1(<\e(B ?\e$,1(\\e(B tbl)
- (set-case-syntax-pair ?\e$,1(=\e(B ?\e$,1(]\e(B tbl)
- (set-case-syntax-pair ?\e$,1(>\e(B ?\e$,1(^\e(B tbl)
- (set-case-syntax-pair ?\e$,1(?\e(B ?\e$,1(_\e(B tbl)
- (set-case-syntax-pair ?\e$,1(@\e(B ?\e$,1(`\e(B tbl)
- (set-case-syntax-pair ?\e$,1(A\e(B ?\e$,1(a\e(B tbl)
- (set-case-syntax-pair ?\e$,1(B\e(B ?\e$,1(b\e(B tbl)
- (set-case-syntax-pair ?\e$,1(C\e(B ?\e$,1(c\e(B tbl)
- (set-case-syntax-pair ?\e$,1(D\e(B ?\e$,1(d\e(B tbl)
- (set-case-syntax-pair ?\e$,1(E\e(B ?\e$,1(e\e(B tbl)
- (set-case-syntax-pair ?\e$,1(F\e(B ?\e$,1(f\e(B tbl)
- (set-case-syntax-pair ?\e$,1(G\e(B ?\e$,1(g\e(B tbl)
- (set-case-syntax-pair ?\e$,1(H\e(B ?\e$,1(h\e(B tbl)
- (set-case-syntax-pair ?\e$,1(I\e(B ?\e$,1(i\e(B tbl)
- (set-case-syntax-pair ?\e$,1(J\e(B ?\e$,1(j\e(B tbl)
- (set-case-syntax-pair ?\e$,1(K\e(B ?\e$,1(k\e(B tbl)
- (set-case-syntax-pair ?\e$,1(L\e(B ?\e$,1(l\e(B tbl)
- (set-case-syntax-pair ?\e$,1(M\e(B ?\e$,1(m\e(B tbl)
- (set-case-syntax-pair ?\e$,1(N\e(B ?\e$,1(n\e(B tbl)
- (set-case-syntax-pair ?\e$,1(O\e(B ?\e$,1(o\e(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
-;; ("\e$(5!!!"!#\e(B" "w" ?7) ; vowel-modifying diacritical mark
-;; ; chandrabindu, anuswar, visarga
-;; ("\e$(5!$\e(B-\e$(5!2\e(B" "w" ?1) ; independent vowel
-;; ("\e$(5!3\e(B-\e$(5!X\e(B" "w" ?0) ; consonant
-;; ("\e$(5!Z\e(B-\e$(5!g\e(B" "w" ?8) ; matra
-;; ("\e$(5!q\e(B-\e$(5!z\e(B" "w" ?6) ; digit
-;; ;; Unicode equivalents
-;; ("\e$,15A5B5C\e(B" "w" ?7) ; vowel-modifying diacritical mark
-;; ; chandrabindu, anuswar, visarga
-;; ("\e$,15E\e(B-\e$,15M\e(B" "w" ?1) ; independent vowel
-;; ("\e$,15U\e(B-\e$,15y\e(B" "w" ?0) ; consonant
-;; ("\e$,15~\e(B-\e$,16)\e(B" "w" ?8) ; matra
-;; ("\e$,16F\e(B-\e$,16O\e(B" "w" ?6) ; digit
-;; ))
-;; elm chars len syntax category to ch i)
-;; (while deflist
-;; (setq elm (car deflist))
-;; (setq chars (car elm)
-;; len (length chars)
-;; syntax (nth 1 elm)
-;; category (nth 2 elm)
-;; i 0)
-;; (while (< i len)
-;; (if (= (aref chars i) ?-)
-;; (setq i (1+ i)
-;; to (aref chars i))
-;; (setq ch (aref chars i)
-;; to ch))
-;; (while (<= ch to)
-;; (modify-syntax-entry ch syntax)
-;; (modify-category-entry ch category)
-;; (setq ch (1+ ch)))
-;; (setq i (1+ i)))
-;; (setq deflist (cdr deflist))))
+(map-charset-chars #'modify-category-entry 'katakana-jisx0201 ?k)
-;; Ethiopic character set
+(map-charset-chars #'modify-category-entry 'latin-jisx0201 ?r)
-(modify-category-entry (make-char 'ethiopic) ?e)
-;; (modify-syntax-entry (make-char 'ethiopic) "w")
-(dotimes (i (1+ (- #x137c #x1200)))
- (modify-category-entry (decode-char 'ucs (+ #x1200 i)) ?e))
-(let ((chars '(?\e$(3$h\e(B ?\e$(3$i\e(B ?\e$(3$j\e(B ?\e$(3$k\e(B ?\e$(3$l\e(B ?\e$(3$m\e(B ?\e$(3$n\e(B ?\e$(3$o\e(B ?\e$(3%i\e(B ?\e$(3%t\e(B ?\e$(3%u\e(B ?\e$(3%v\e(B ?\e$(3%w\e(B ?\e$(3%x\e(B
- ;; Unicode equivalents of the above:
- ?\e$,1Q!\e(B ?\e$,1Q"\e(B ?\e$,1Q#\e(B ?\e$,1Q$\e(B ?\e$,1Q%\e(B ?\e$,1Q&\e(B ?\e$,1Q'\e(B ?\e$,1Q(\e(B ?\e$,3op\e(B ?\e$,3o{\e(B ?\e$,3o|\e(B ?\e$,3o}\e(B ?\e$,3o~\e(B ?\e$,3o\7f\e(B)))
- (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 ?\e,F7\e(B ".")
-(modify-syntax-entry ?\e,F;\e(B ".")
-(modify-syntax-entry ?\e,F=\e(B ".")
-(let ((tbl (standard-case-table)))
- ;; Fixme: non-letter syntax copied from latin-1, but that's dubious
- ;; in several cases.
- (set-case-syntax ?\e,F!\e(B "." tbl)
- (set-case-syntax ?\e,F"\e(B "." tbl)
- (set-case-syntax ?\e,F&\e(B "." tbl)
- (set-case-syntax ?\e,F&\e(B "_" tbl)
- (set-case-syntax ?\e,F'\e(B "." tbl)
- (set-case-syntax ?\e,F)\e(B "_" tbl)
- (set-case-syntax ?\e,F+\e(B "." tbl)
- (set-case-syntax ?\e,F,\e(B "_" tbl)
- (set-case-syntax ?\e,F-\e(B "_" tbl)
- (set-case-syntax ?\e,F/\e(B "." tbl)
- (set-case-syntax ?\e,F0\e(B "_" tbl)
- (set-case-syntax ?\e,F1\e(B "_" tbl)
-;; (set-case-syntax ?\e,F7\e(B "_" tbl)
-;; (set-case-syntax ?\e,F=\e(B "_" tbl)
- (set-case-syntax-pair ?\e,FA\e(B ?\e,Fa\e(B tbl)
- (set-case-syntax-pair ?\e,FB\e(B ?\e,Fb\e(B tbl)
- (set-case-syntax-pair ?\e,FC\e(B ?\e,Fc\e(B tbl)
- (set-case-syntax-pair ?\e,FD\e(B ?\e,Fd\e(B tbl)
- (set-case-syntax-pair ?\e,FE\e(B ?\e,Fe\e(B tbl)
- (set-case-syntax-pair ?\e,FF\e(B ?\e,Ff\e(B tbl)
- (set-case-syntax-pair ?\e,FG\e(B ?\e,Fg\e(B tbl)
- (set-case-syntax-pair ?\e,FH\e(B ?\e,Fh\e(B tbl)
- (set-case-syntax-pair ?\e,FI\e(B ?\e,Fi\e(B tbl)
- (set-case-syntax-pair ?\e,FJ\e(B ?\e,Fj\e(B tbl)
- (set-case-syntax-pair ?\e,FK\e(B ?\e,Fk\e(B tbl)
- (set-case-syntax-pair ?\e,FL\e(B ?\e,Fl\e(B tbl)
- (set-case-syntax-pair ?\e,FM\e(B ?\e,Fm\e(B tbl)
- (set-case-syntax-pair ?\e,FN\e(B ?\e,Fn\e(B tbl)
- (set-case-syntax-pair ?\e,FO\e(B ?\e,Fo\e(B tbl)
- (set-case-syntax-pair ?\e,FP\e(B ?\e,Fp\e(B tbl)
- (set-case-syntax-pair ?\e,FQ\e(B ?\e,Fq\e(B tbl)
- (set-upcase-syntax ?\e,FS\e(B ?\e,Fr\e(B tbl)
- (set-case-syntax-pair ?\e,FS\e(B ?\e,Fs\e(B tbl)
- (set-case-syntax-pair ?\e,FT\e(B ?\e,Ft\e(B tbl)
- (set-case-syntax-pair ?\e,FU\e(B ?\e,Fu\e(B tbl)
- (set-case-syntax-pair ?\e,FV\e(B ?\e,Fv\e(B tbl)
- (set-case-syntax-pair ?\e,FW\e(B ?\e,Fw\e(B tbl)
- (set-case-syntax-pair ?\e,FX\e(B ?\e,Fx\e(B tbl)
- (set-case-syntax-pair ?\e,FY\e(B ?\e,Fy\e(B tbl)
- (set-case-syntax-pair ?\e,FZ\e(B ?\e,Fz\e(B tbl)
- (set-case-syntax-pair ?\e,F[\e(B ?\e,F{\e(B tbl)
- (set-case-syntax-pair ?\e,F?\e(B ?\e,F~\e(B tbl)
- (set-case-syntax-pair ?\e,F>\e(B ?\e,F}\e(B tbl)
- (set-case-syntax-pair ?\e,F<\e(B ?\e,F|\e(B tbl)
- (set-case-syntax-pair ?\e,F6\e(B ?\e,F\\e(B tbl)
- (set-case-syntax-pair ?\e,F8\e(B ?\e,F]\e(B tbl)
- (set-case-syntax-pair ?\e,F9\e(B ?\e,F^\e(B tbl)
- (set-case-syntax-pair ?\e,F:\e(B ?\e,F_\e(B tbl)
- ;; Unicode equivalents
- (set-case-syntax-pair ?\e$,1&q\e(B ?\e$,1'1\e(B tbl)
- (set-case-syntax-pair ?\e$,1&r\e(B ?\e$,1'2\e(B tbl)
- (set-case-syntax-pair ?\e$,1&s\e(B ?\e$,1'3\e(B tbl)
- (set-case-syntax-pair ?\e$,1&t\e(B ?\e$,1'4\e(B tbl)
- (set-case-syntax-pair ?\e$,1&u\e(B ?\e$,1'5\e(B tbl)
- (set-case-syntax-pair ?\e$,1&v\e(B ?\e$,1'6\e(B tbl)
- (set-case-syntax-pair ?\e$,1&w\e(B ?\e$,1'7\e(B tbl)
- (set-case-syntax-pair ?\e$,1&x\e(B ?\e$,1'8\e(B tbl)
- (set-case-syntax-pair ?\e$,1&y\e(B ?\e$,1'9\e(B tbl)
- (set-case-syntax-pair ?\e$,1&z\e(B ?\e$,1':\e(B tbl)
- (set-case-syntax-pair ?\e$,1&{\e(B ?\e$,1';\e(B tbl)
- (set-case-syntax-pair ?\e$,1&|\e(B ?\e$,1'<\e(B tbl)
- (set-case-syntax-pair ?\e$,1&}\e(B ?\e$,1'=\e(B tbl)
- (set-case-syntax-pair ?\e$,1&~\e(B ?\e$,1'>\e(B tbl)
- (set-case-syntax-pair ?\e$,1&\7f\e(B ?\e$,1'?\e(B tbl)
- (set-case-syntax-pair ?\e$,1' \e(B ?\e$,1'@\e(B tbl)
- (set-case-syntax-pair ?\e$,1'!\e(B ?\e$,1'A\e(B tbl)
- (set-upcase-syntax ?\e$,1'#\e(B ?\e$,1'B\e(B tbl)
- (set-case-syntax-pair ?\e$,1'#\e(B ?\e$,1'C\e(B tbl)
- (set-case-syntax-pair ?\e$,1'$\e(B ?\e$,1'D\e(B tbl)
- (set-case-syntax-pair ?\e$,1'%\e(B ?\e$,1'E\e(B tbl)
- (set-case-syntax-pair ?\e$,1'&\e(B ?\e$,1'F\e(B tbl)
- (set-case-syntax-pair ?\e$,1''\e(B ?\e$,1'G\e(B tbl)
- (set-case-syntax-pair ?\e$,1'(\e(B ?\e$,1'H\e(B tbl)
- (set-case-syntax-pair ?\e$,1')\e(B ?\e$,1'I\e(B tbl)
- (set-case-syntax-pair ?\e$,1'*\e(B ?\e$,1'J\e(B tbl)
- (set-case-syntax-pair ?\e$,1'+\e(B ?\e$,1'K\e(B tbl)
- (set-case-syntax-pair ?\e$,1&o\e(B ?\e$,1'N\e(B tbl)
- (set-case-syntax-pair ?\e$,1&n\e(B ?\e$,1'M\e(B tbl)
- (set-case-syntax-pair ?\e$,1&l\e(B ?\e$,1'L\e(B tbl)
- (set-case-syntax-pair ?\e$,1&f\e(B ?\e$,1',\e(B tbl)
- (set-case-syntax-pair ?\e$,1&h\e(B ?\e$,1'-\e(B tbl)
- (set-case-syntax-pair ?\e$,1&i\e(B ?\e$,1'.\e(B tbl)
- (set-case-syntax-pair ?\e$,1&j\e(B ?\e$,1'/\e(B tbl))
-
-;; 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
-
-;; 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) ?\|)
+(dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212
+ japanese-jisx0213-1 japanese-jisx0213-2))
+ (map-charset-chars #'modify-category-entry l ?j))
;; 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))))
+(let ((range '(#xff61 . #xff9f)))
+ (modify-category-entry range ?k)
+ (modify-category-entry range ?j)
+ (modify-category-entry range ?\|))
;; 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))))
+(let ((range '(#x30a0 . #x30ff)))
+ ;; ?K is double width, ?k isn't specified
+ (modify-category-entry range ?K)
+ (modify-category-entry range ?\|))
;; 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))))
+(let ((range '(#x3040 . #x309d)))
+ ;; ?H is actually defined to be double width
+ ;;(modify-category-entry range ?H)
+ (modify-category-entry range ?\|)
+ )
;; 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 '(?\e$B!<\e(B ?\e$B!+\e(B ?\e$B!,\e(B ?\e$B!3\e(B ?\e$B!4\e(B ?\e$B!5\e(B ?\e$B!6\e(B ?\e$B!7\e(B ?\e$B!8\e(B ?\e$B!9\e(B ?\e$B!:\e(B ?\e$B!;\e(B)))
- (while chars
- (modify-syntax-entry (car chars) "w")
- (setq chars (cdr chars))))
-(let ((parens "\e$B!J!K!L!M!N!O!P!Q!R!S!T!U!V!W!X!Y!Z![\e(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))))
-
-(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 ?\e$B!<\e(B ?K)
-(let ((chars '(?\e$B!+\e(B ?\e$B!,\e(B)))
+(map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2121 #x227E)
+(map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2821 #x287E)
+(let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
+ (dolist (elt chars)
+ (modify-syntax-entry (car chars) "w")))
+
+(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?A #x2321 #x237E)
+(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?H #x2421 #x247E)
+(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?K #x2521 #x257E)
+(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?G #x2621 #x267E)
+(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?Y #x2721 #x277E)
+(map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?C #x3021 #x7E7E)
+(modify-category-entry ?ー ?K)
+(let ((chars '(?゛ ?゜)))
(while chars
(modify-category-entry (car chars) ?K)
(modify-category-entry (car chars) ?H)
(setq chars (cdr chars))))
-(let ((chars '(?\e$B!3\e(B ?\e$B!4\e(B ?\e$B!5\e(B ?\e$B!6\e(B ?\e$B!7\e(B ?\e$B!8\e(B ?\e$B!9\e(B ?\e$B!:\e(B ?\e$B!;\e(B)))
+(let ((chars '(?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
(while chars
(modify-category-entry (car chars) ?C)
(setq chars (cdr chars))))
-(let ((tbl (standard-case-table)))
- (dotimes (i 26)
- (set-case-syntax-pair (make-char 'japanese-jisx0208 #x23 (+ #x41 i))
- (make-char 'japanese-jisx0208 #x23 (+ #x61 i)) tbl))
- (dotimes (i 24)
- (set-case-syntax-pair (make-char 'japanese-jisx0208 #x26 (+ #x21 i))
- (make-char 'japanese-jisx0208 #x26 (+ #x41 i)) tbl))
- (dotimes (i 33)
- (set-case-syntax-pair (make-char 'japanese-jisx0208 #x27 (+ #x21 i))
- (make-char 'japanese-jisx0208 #x27 (+ #x51 i)) tbl)))
-
;; 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)
+(map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E)
;; JISX0201-Kana
-;; (modify-syntax-entry (make-char 'katakana-jisx0201) "w")
-(let ((chars '(?\e(I!\e(B ?\e(I$\e(B ?\e(I%\e(B
- ;; Unicode:
- ?\e$,3sa\e(B ?\e$,3sd\e(B ?\e$,3se\e(B)))
+
+(let ((chars '(?｡ ?､ ?･)))
(while chars
(modify-syntax-entry (car chars) ".")
(setq chars (cdr chars))))
-(modify-syntax-entry ?\\e(I"\e(B "(\e(I#\e(B")
-(modify-syntax-entry ?\\e(I#\e(B "(\e(I"\e(B")
+(modify-syntax-entry ?\｢ "(｣")
+(modify-syntax-entry ?\｣ "(｢")
;; 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)
-
-(let ((parens "\e$(C!2!3!4!5!6!7!8!9!:!;!<!=#(#)#[#]#{#}\e(B" )
+(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))
(modify-syntax-entry open (format "(%c" close))
(modify-syntax-entry close (format ")%c" open))))
-(let ((tbl (standard-case-table)))
- (dotimes (i 26)
- (set-case-syntax-pair (make-char 'korean-ksc5601 #x23 (+ #x41 i))
- (make-char 'korean-ksc5601 #x23 (+ #x61 i)) tbl))
- (dotimes (i 10)
- (set-case-syntax-pair (make-char 'korean-ksc5601 #x25 (+ #x21 i))
- (make-char 'korean-ksc5601 #x25 (+ #x30 i)) tbl))
- (dotimes (i 24)
- (set-case-syntax-pair (make-char 'korean-ksc5601 #x25 (+ #x41 i))
- (make-char 'korean-ksc5601 #x25 (+ #x61 i)) tbl))
- (dotimes (i 33)
- (set-case-syntax-pair (make-char 'korean-ksc5601 #x2C (+ #x21 i))
- (make-char 'korean-ksc5601 #x2C (+ #x51 i)) tbl)))
-
-;; 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) ?\ )
+;; Arabic character set
-;; Lao character set
+(let ((charsets '(arabic-iso8859-6
+ arabic-digit
+ arabic-1-column
+ arabic-2-column)))
+ (while charsets
+ (map-charset-chars #'modify-category-entry (car charsets) ?b)
+ (setq charsets (cdr charsets))))
+(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 'lao) ?o)
-(dotimes (i (1+ (- #xeff #xe80)))
- (modify-category-entry (decode-char 'ucs (+ i #xe80)) ?o))
+(modify-syntax-entry ?№ ".")
-(let ((deflist '(;; chars syntax category
- ("\e(1!\e(B-\e(1N\e(B" "w" ?0) ; consonant
- ("\e(1PRS]`\e(B-\e(1d\e(B" "w" ?1) ; vowel base
- ("\e(1QT\e(B-\e(1W[m\e(B" "w" ?2) ; vowel upper
- ("\e(1XY\e(B" "w" ?3) ; vowel lower
- ("\e(1h\e(B-\e(1l\e(B" "w" ?4) ; tone mark
- ("\e(1\\e(B" "w" ?9) ; semivowel lower
- ("\e(1p\e(B-\e(1y\e(B" "w" ?6) ; digit
- ("\e(1Of\e(B" "_" ?5) ; symbol
- ;; Unicode equivalents
- ("\e$,1D!\e(B-\e$,1DN\e(B" "w" ?0) ; consonant
- ("\e$,1DPDRDSD]D`\e(B-\e$,1Dd\e(B" "w" ?1) ; vowel base
- ("\e$,1DQDT\e(B-\e$,1DWD[Dm\e(B" "w" ?2) ; vowel upper
- ("\e$,1DXDY\e(B" "w" ?3) ; vowel lower
- ("\e$,1Dh\e(B-\e$,1Dk\e(B" "w" ?4) ; tone mark
- ("\e$,1D\D]\e(B" "w" ?9) ; semivowel lower
- ("\e$,1Dp\e(B-\e$,1Dy\e(B" "w" ?6) ; digit
- ("\e$,1DODf\e(B" "_" ?5) ; symbol
+;; Ethiopic character set
+
+(modify-category-entry '(#x1200 . #x1399) ?e)
+(modify-category-entry '(#x2d80 . #x2dde) ?e)
+(let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨ ? ? ? ? ? ?)))
+ (while chars
+ (modify-syntax-entry (car chars) ".")
+ (setq chars (cdr chars))))
+(map-charset-chars #'modify-category-entry 'ethiopic ?e)
+
+;; Hebrew character set (ISO-8859-8)
+
+(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 '(#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 '(#xe80 . #xeff) ?o)
+(map-charset-chars #'modify-category-entry 'lao ?o)
+
+(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
;; 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
- ("\e,T!\e(B-\e,TCEG\e(B-\e,TN\e(B" "w" ?0) ; consonant
- ("\e,TDFPRS`\e(B-\e,Te\e(B" "w" ?1) ; vowel base
- ("\e,TQT\e(B-\e,TWgn\e(B" "w" ?2) ; vowel upper
- ("\e,TX\e(B-\e,TZ\e(B" "w" ?3) ; vowel lower
- ("\e,Th\e(B-\e,Tm\e(B" "w" ?4) ; tone mark
- ("\e,Tp\e(B-\e,Ty\e(B" "w" ?6) ; digit
- ("\e,TOf_oz{\e(B" "_" ?5) ; symbol
- ;; Unicode equivalents
- ("\e$,1Ba\e(B-\e$,1C#C%C'\e(B-\e$,1C.\e(B" "w" ?0) ; consonant
- ("\e$,1C$C&C0C2C3C@\e(B-\e$,1CE\e(B" "w" ?1) ; vowel base
- ("\e$,1C1C4\e(B-\e$,1C7CGCN\e(B" "w" ?2) ; vowel upper
- ("\e$,1C8\e(B-\e$,1C:\e(B" "w" ?3) ; vowel lower
- ("\e$,1CH\e(B-\e$,1CM\e(B" "w" ?4) ; tone mark
- ("\e$,1CP\e(B-\e$,1CY\e(B" "w" ?6) ; digit
- ("\e$,1C/CFC?COCZC[\e(B" "_" ?5) ; symbol
+ ("ก-รลว-ฮ" "w" ?0) ; consonant
+ ("ฤฦะาำเ-ๅ" "w" ?1) ; vowel base
+ ("ัิ-ื็๎" "w" ?2) ; vowel upper
+ ("ุ-ฺ" "w" ?3) ; vowel lower
+ ("่-ํ" "w" ?4) ; tone mark
+ ("๐-๙" "w" ?6) ; digit
+ ("ฯๆ฿๏๚๛" "_" ?5) ; symbol
))
elm chars len syntax category to ch i)
(while deflist
;; Tibetan character set
-(modify-category-entry (make-char 'tibetan) ?q)
-(modify-category-entry (make-char 'tibetan-1-column) ?q)
-(dotimes (i (1+ (- #xfff #xf00)))
- (modify-category-entry (decode-char 'ucs (+ i #xf00)) ?q))
+(modify-category-entry '(#xf00 . #xfff) ?q)
+(map-charset-chars #'modify-category-entry 'tibetan ?q)
+(map-charset-chars #'modify-category-entry 'tibetan-1-column ?q)
(let ((deflist '(;; chars syntax category
- ("\e4\e$(7"!\e0"!\e1\e(B-\e4\e$(7"J\e0"J\e1\e4"K\e0"K\e1\e(B" "w" ?0) ; consonant
- ("\e$(7#!\e(B-\e$(7#J#K#L#M!"!#\e(B" "w" ?0) ;
- ("\e$(7$!\e(B-\e$(7$e\e(B" "w" ?0) ;
- ("\e$(7%!\e(B-\e$(7%u\e(B" "w" ?0) ;
- ("\e$(7"S"["\"]"^"a\e(B" "w" ?2) ; upper vowel
- ("\e$(7"_"c"d"g"h"i"j"k"l\e(B" "w" ?2) ; upper modifier
- ("\e$(7!I"Q"R"U"e!e!g\e(B" "w" ?3) ; lowel vowel/modifier
- ("\e$(7!P\e(B-\e$(7!Y!Z\e(B-\e$(7!c\e(B" "w" ?6) ; digit
- ("\e$(7!;!=\e(B-\e$(7!B!D"`\e(B" "." ?|) ; line-break char
- ("\e$(8!;!=!?!@!A!D"`\e(B" "." ?|) ;
- ("\e$(7!8!;!=\e(B-\e$(7!B!D"`!m!d\e(B" "." ?>) ; prohibition
- ("\e$(8!;!=!?!@!A!D"`\e(B" "." ?>) ;
- ("\e$(7!0\e(B-\e$(7!:!l#R#S"f\e(B" "." ?<) ; prohibition
- ("\e$(7!C!E\e(B-\e$(7!H!J\e(B-\e$(7!O!f!h\e(B-\e$(7!k!n!o#O#P\e(B-\e$(7#`\e(B" "." ?q) ; others
-
- ;; Unicode version (not complete)
- ("\e$,1F \e(B-\e$,1FIFJ\e(B" "w" ?0) ; consonant
- ("\e$,1Fp\e(B-\e$,1G9G:G;G<\e(B" "w" ?0) ;
- ("\e$,1FRFZF[F\F]F`\e(B" "w" ?2) ; upper vowel
- ("\e$,1F^FbFcFfFgFhFiFjFk\e(B" "w" ?2) ; upper modifier
- ("\e$,1EYFPFQFTFdEuEw\e(B" "w" ?3) ; lowel vowel/modifier
- ("\e$,1E`\e(B-\e$,1EiEj\e(B-\e$,1Es\e(B" "w" ?6) ; digit
- ("\e$,1EKEM\e(B-\e$,1ERETF_\e(B" "." ?|) ; line-break char
- ("\e$,1EHEKEM\e(B-\e$,1ERETF_E}Et\e(B" "." ?>) ; prohibition
- ("\e$,1E@\e(B-\e$,1EJE|GAGBFe\e(B" "." ?<) ; prohibition
- ("\e$,1ESEU\e(B-\e$,1EXEZ\e(B-\e$,1E_EvEx\e(B-\e$,1E{E~E\7fG>G?\e(B-\e$,1GO\e(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
;; 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)
+;; Tai Viet
+(let ((deflist '(;; chars syntax category
+ ((?ꪀ. ?ꪯ) "w" ?0) ; cosonant
+ ("ꪱꪵꪶ" "w" ?1) ; vowel base
+ ((?ꪹ . ?ꪽ) "w" ?1) ; vowel base
+ ("ꪰꪲꪳꪷꪸꪾ" "w" ?2) ; vowel upper
+ ("ꪴ" "w" ?3) ; vowel lower
+ ("ꫀꫂ" "w" ?1) ; non-combining tone-mark
+ ("꪿꫁" "w" ?4) ; combining tone-mark
+ ((?ꫛ . ?꫟) "_" ?5) ; symbol
+ )))
+ (dolist (elm deflist)
+ (let ((chars (car elm))
+ (syntax (nth 1 elm))
+ (category (nth 2 elm)))
+ (if (consp chars)
+ (progn
+ (modify-syntax-entry chars syntax)
+ (modify-category-entry chars category))
+ (mapc #'(lambda (x)
+ (modify-syntax-entry x syntax)
+ (modify-category-entry x category))
+ chars)))))
+
+;; Latin
+
+(modify-category-entry '(#x80 . #x024F) ?l)
(let ((tbl (standard-case-table)) c)
- ;; Latin Extended-A, Latin Extended-B, IPA
+ ;; 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.
+
+ ;; NBSP isn't semantically interchangeable with other whitespace chars,
+ ;; so it's more like punctation.
+ (set-case-syntax ? "." tbl)
+ (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 #x02AF)
- (modify-category-entry (decode-char 'ucs c) ?l)
- (setq c (1+ c)))
-
- (setq c #x0100)
- (while (<= c #x0177)
- (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))
- (and (>= c #x013a)
- (<= c #x0148)
- (zerop (% c 2))
- (set-case-syntax-pair
- (decode-char 'ucs (1- c)) (decode-char 'ucs c) tbl))
+ (while (<= c #x02B8)
+ (modify-category-entry c ?l)
(setq c (1+ c)))
+ (let ((pair-ranges '((#x0100 . #x012F)
+ (#x0132 . #x0137)
+ (#x0139 . #x0148)
+ (#x014a . #x0177)
+ (#x0179 . #x017E)
+ (#x0182 . #x0185)
+ (#x0187 . #x018C)
+ (#x0191 . #x0192)
+ (#x0198 . #x0199)
+ (#x01A0 . #x01A5)
+ (#x01A7 . #x01A8)
+ (#x01AC . #x01AD)
+ (#x01AF . #x01B0)
+ (#x01B3 . #x01B6)
+ (#x01BC . #x01BD)
+ (#x01CD . #x01DC)
+ (#x01DE . #x01EF)
+ (#x01F4 . #x01F5)
+ (#x01F8 . #x021F)
+ (#x0222 . #x0233)
+ (#x023B . #x023C)
+ (#x0241 . #x0242)
+ (#x0246 . #x024F))))
+ (dolist (elt pair-ranges)
+ (let ((from (car elt)) (to (cdr elt)))
+ (while (< from to)
+ (set-case-syntax-pair from (1+ from) tbl)
+ (setq from (+ from 2))))))
;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
;; but that makes searches slow. So now we don't set up either half
;; of these correspondences by default.
- ;; (set-downcase-syntax ?\e$,1 P\e(B ?i tbl)
- ;; (set-upcase-syntax ?I ?\e$,1 Q\e(B tbl)
-
- (set-case-syntax-pair ?\e$,1 R\e(B ?\e$,1 S\e(B tbl)
- (set-case-syntax-pair ?\e$,1 T\e(B ?\e$,1 U\e(B tbl)
- (set-case-syntax-pair ?\e$,1 V\e(B ?\e$,1 W\e(B tbl)
- (set-case-syntax-pair ?\e$,1!8\e(B ?\e,A\7f\e(B tbl)
- (set-case-syntax-pair ?\e$,1!9\e(B ?\e$,1!:\e(B tbl)
- (set-case-syntax-pair ?\e$,1!;\e(B ?\e$,1!<\e(B tbl)
- (set-case-syntax-pair ?\e$,1!=\e(B ?\e$,1!>\e(B tbl)
-
- ;; Latin Extended-B
- (set-case-syntax-pair ?\e$,1!A\e(B ?\e$,1#S\e(B tbl)
- (set-case-syntax-pair ?\e$,1!B\e(B ?\e$,1!C\e(B tbl)
- (set-case-syntax-pair ?\e$,1!D\e(B ?\e$,1!E\e(B tbl)
- (set-case-syntax-pair ?\e$,1!F\e(B ?\e$,1#T\e(B tbl)
- (set-case-syntax-pair ?\e$,1!G\e(B ?\e$,1!H\e(B tbl)
- (set-case-syntax-pair ?\e$,1!I\e(B ?\e$,1#V\e(B tbl)
- (set-case-syntax-pair ?\e$,1!J\e(B ?\e$,1#W\e(B tbl)
- (set-case-syntax-pair ?\e$,1!K\e(B ?\e$,1!L\e(B tbl)
- (set-case-syntax-pair ?\e$,1!N\e(B ?\e$,1"=\e(B tbl)
- (set-case-syntax-pair ?\e$,1!O\e(B ?\e$,1#Y\e(B tbl)
- (set-case-syntax-pair ?\e$,1!P\e(B ?\e$,1#[\e(B tbl)
- (set-case-syntax-pair ?\e$,1!Q\e(B ?\e$,1!R\e(B tbl)
- (set-case-syntax-pair ?\e$,1!S\e(B ?\e$,1#`\e(B tbl)
- (set-case-syntax-pair ?\e$,1!T\e(B ?\e$,1#c\e(B tbl)
- (set-case-syntax-pair ?\e$,1!V\e(B ?\e$,1#i\e(B tbl)
- (set-case-syntax-pair ?\e$,1!W\e(B ?\e$,1#h\e(B tbl)
- (set-case-syntax-pair ?\e$,1!X\e(B ?\e$,1!Y\e(B tbl)
- (set-case-syntax-pair ?\e$,1!\\e(B ?\e$,1#o\e(B tbl)
- (set-case-syntax-pair ?\e$,1!]\e(B ?\e$,1#r\e(B tbl)
- (set-case-syntax-pair ?\e$,1!_\e(B ?\e$,1#u\e(B tbl)
- (set-case-syntax-pair ?\e$,1!`\e(B ?\e$,1!a\e(B tbl)
- (set-case-syntax-pair ?\e$,1!b\e(B ?\e$,1!c\e(B tbl)
- (set-case-syntax-pair ?\e$,1!d\e(B ?\e$,1!e\e(B tbl)
- (set-case-syntax-pair ?\e$,1!f\e(B ?\e$,1$ \e(B tbl)
- (set-case-syntax-pair ?\e$,1!g\e(B ?\e$,1!h\e(B tbl)
- (set-case-syntax-pair ?\e$,1!i\e(B ?\e$,1$#\e(B tbl)
- (set-case-syntax-pair ?\e$,1!l\e(B ?\e$,1!m\e(B tbl)
- (set-case-syntax-pair ?\e$,1!n\e(B ?\e$,1$(\e(B tbl)
- (set-case-syntax-pair ?\e$,1!o\e(B ?\e$,1!p\e(B tbl)
- (set-case-syntax-pair ?\e$,1!q\e(B ?\e$,1$*\e(B tbl)
- (set-case-syntax-pair ?\e$,1!r\e(B ?\e$,1$+\e(B tbl)
- (set-case-syntax-pair ?\e$,1!s\e(B ?\e$,1!t\e(B tbl)
- (set-case-syntax-pair ?\e$,1!u\e(B ?\e$,1!v\e(B tbl)
- (set-case-syntax-pair ?\e$,1!w\e(B ?\e$,1$2\e(B tbl)
- (set-case-syntax-pair ?\e$,1!x\e(B ?\e$,1!y\e(B tbl)
- (set-case-syntax-pair ?\e$,1!|\e(B ?\e$,1!}\e(B tbl)
- (set-case-syntax-pair ?\e$,1"$\e(B ?\e$,1"&\e(B tbl)
- (set-case-syntax-pair ?\e$,1"%\e(B ?\e$,1"&\e(B tbl)
- (set-case-syntax-pair ?\e$,1"'\e(B ?\e$,1")\e(B tbl)
- (set-case-syntax-pair ?\e$,1"(\e(B ?\e$,1")\e(B tbl)
- (set-case-syntax-pair ?\e$,1"*\e(B ?\e$,1",\e(B tbl)
- (set-case-syntax-pair ?\e$,1"+\e(B ?\e$,1",\e(B tbl)
- (set-case-syntax-pair ?\e$,1"-\e(B ?\e$,1".\e(B tbl)
- (set-case-syntax-pair ?\e$,1"/\e(B ?\e$,1"0\e(B tbl)
- (set-case-syntax-pair ?\e$,1"1\e(B ?\e$,1"2\e(B tbl)
- (set-case-syntax-pair ?\e$,1"3\e(B ?\e$,1"4\e(B tbl)
- (set-case-syntax-pair ?\e$,1"5\e(B ?\e$,1"6\e(B tbl)
- (set-case-syntax-pair ?\e$,1"7\e(B ?\e$,1"8\e(B tbl)
- (set-case-syntax-pair ?\e$,1"9\e(B ?\e$,1":\e(B tbl)
- (set-case-syntax-pair ?\e$,1";\e(B ?\e$,1"<\e(B tbl)
- (set-case-syntax-pair ?\e$,1">\e(B ?\e$,1"?\e(B tbl)
- (set-case-syntax-pair ?\e$,1"@\e(B ?\e$,1"A\e(B tbl)
- (set-case-syntax-pair ?\e$,1"B\e(B ?\e$,1"C\e(B tbl)
- (set-case-syntax-pair ?\e$,1"D\e(B ?\e$,1"E\e(B tbl)
- (set-case-syntax-pair ?\e$,1"F\e(B ?\e$,1"G\e(B tbl)
- (set-case-syntax-pair ?\e$,1"H\e(B ?\e$,1"I\e(B tbl)
- (set-case-syntax-pair ?\e$,1"J\e(B ?\e$,1"K\e(B tbl)
- (set-case-syntax-pair ?\e$,1"L\e(B ?\e$,1"M\e(B tbl)
- (set-case-syntax-pair ?\e$,1"N\e(B ?\e$,1"O\e(B tbl)
+ ;; (set-downcase-syntax ?İ ?i tbl)
+ ;; (set-upcase-syntax ?I ?ı 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)
+
;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
- (set-case-syntax-pair ?\e$,1"Q\e(B ?\e$,1"S\e(B tbl)
- (set-case-syntax-pair ?\e$,1"R\e(B ?\e$,1"S\e(B tbl)
- (set-case-syntax-pair ?\e$,1"T\e(B ?\e$,1"U\e(B tbl)
- (set-case-syntax-pair ?\e$,1"V\e(B ?\e$,1!U\e(B tbl)
- (set-case-syntax-pair ?\e$,1"W\e(B ?\e$,1!\7f\e(B tbl)
- (set-case-syntax-pair ?\e$,1"X\e(B ?\e$,1"Y\e(B tbl)
- (set-case-syntax-pair ?\e$,1"Z\e(B ?\e$,1"[\e(B tbl)
- (set-case-syntax-pair ?\e$,1"\\e(B ?\e$,1"]\e(B tbl)
- (set-case-syntax-pair ?\e$,1"^\e(B ?\e$,1"_\e(B tbl)
- (set-case-syntax-pair ?\e$,1"`\e(B ?\e$,1"a\e(B tbl)
- (set-case-syntax-pair ?\e$,1"b\e(B ?\e$,1"c\e(B tbl)
- (set-case-syntax-pair ?\e$,1"d\e(B ?\e$,1"e\e(B tbl)
- (set-case-syntax-pair ?\e$,1"f\e(B ?\e$,1"g\e(B tbl)
- (set-case-syntax-pair ?\e$,1"h\e(B ?\e$,1"i\e(B tbl)
- (set-case-syntax-pair ?\e$,1"j\e(B ?\e$,1"k\e(B tbl)
- (set-case-syntax-pair ?\e$,1"l\e(B ?\e$,1"m\e(B tbl)
- (set-case-syntax-pair ?\e$,1"n\e(B ?\e$,1"o\e(B tbl)
- (set-case-syntax-pair ?\e$,1"p\e(B ?\e$,1"q\e(B tbl)
- (set-case-syntax-pair ?\e$,1"r\e(B ?\e$,1"s\e(B tbl)
- (set-case-syntax-pair ?\e$,1"t\e(B ?\e$,1"u\e(B tbl)
- (set-case-syntax-pair ?\e$,1"v\e(B ?\e$,1"w\e(B tbl)
- (set-case-syntax-pair ?\e$,1"x\e(B ?\e$,1"y\e(B tbl)
- (set-case-syntax-pair ?\e$,1"z\e(B ?\e$,1"{\e(B tbl)
- (set-case-syntax-pair ?\e$,1"|\e(B ?\e$,1"}\e(B tbl)
- (set-case-syntax-pair ?\e$,1"~\e(B ?\e$,1"\7f\e(B tbl)
- (set-case-syntax-pair ?\e$,1#"\e(B ?\e$,1##\e(B tbl)
- (set-case-syntax-pair ?\e$,1#$\e(B ?\e$,1#%\e(B tbl)
- (set-case-syntax-pair ?\e$,1#&\e(B ?\e$,1#'\e(B tbl)
- (set-case-syntax-pair ?\e$,1#(\e(B ?\e$,1#)\e(B tbl)
- (set-case-syntax-pair ?\e$,1#*\e(B ?\e$,1#+\e(B tbl)
- (set-case-syntax-pair ?\e$,1#,\e(B ?\e$,1#-\e(B tbl)
- (set-case-syntax-pair ?\e$,1#.\e(B ?\e$,1#/\e(B tbl)
- (set-case-syntax-pair ?\e$,1#0\e(B ?\e$,1#1\e(B tbl)
- (set-case-syntax-pair ?\e$,1#2\e(B ?\e$,1#3\e(B tbl)
+ (set-case-syntax-pair ?DZ ?dz tbl)
+ (set-case-syntax-pair ?Dz ?dz tbl)
+ (set-case-syntax-pair ?Ƕ ?ƕ tbl)
+ (set-case-syntax-pair ?Ƿ ?ƿ tbl)
;; Latin Extended Additional
+ (modify-category-entry '(#x1e00 . #x1ef9) ?l)
(setq c #x1e00)
(while (<= c #x1ef9)
- (modify-category-entry (decode-char 'ucs c) ?l)
(and (zerop (% c 2))
(or (<= c #x1e94) (>= c #x1ea0))
- (set-case-syntax-pair
- (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
+ (set-case-syntax-pair c (1+ c) tbl))
(setq c (1+ c)))
;; Greek
+ (modify-category-entry '(#x0370 . #x03ff) ?g)
(setq c #x0370)
(while (<= c #x03ff)
- (modify-category-entry (decode-char 'ucs c) ?g)
(if (or (and (>= c #x0391) (<= c #x03a1))
(and (>= c #x03a3) (<= c #x03ab)))
- (set-case-syntax-pair
- (decode-char 'ucs c) (decode-char 'ucs (+ c 32)) tbl))
+ (set-case-syntax-pair c (+ c 32) tbl))
(and (>= c #x03da)
(<= c #x03ee)
(zerop (% c 2))
- (set-case-syntax-pair
- (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
+ (set-case-syntax-pair c (1+ c) tbl))
(setq c (1+ c)))
- (set-case-syntax-pair ?\e$,1&f\e(B ?\e$,1',\e(B tbl)
- (set-case-syntax-pair ?\e$,1&h\e(B ?\e$,1'-\e(B tbl)
- (set-case-syntax-pair ?\e$,1&i\e(B ?\e$,1'.\e(B tbl)
- (set-case-syntax-pair ?\e$,1&j\e(B ?\e$,1'/\e(B tbl)
- (set-case-syntax-pair ?\e$,1&l\e(B ?\e$,1'L\e(B tbl)
- (set-case-syntax-pair ?\e$,1&n\e(B ?\e$,1'M\e(B tbl)
- (set-case-syntax-pair ?\e$,1&o\e(B ?\e$,1'N\e(B tbl)
+ (set-case-syntax-pair ?Ά ?ά tbl)
+ (set-case-syntax-pair ?Έ ?έ tbl)
+ (set-case-syntax-pair ?Ή ?ή tbl)
+ (set-case-syntax-pair ?Ί ?ί tbl)
+ (set-case-syntax-pair ?Ό ?ό tbl)
+ (set-case-syntax-pair ?Ύ ?ύ tbl)
+ (set-case-syntax-pair ?Ώ ?ώ tbl)
;; Armenian
(setq c #x531)
(while (<= c #x556)
- (set-case-syntax-pair (decode-char 'ucs c)
- (decode-char 'ucs (+ c #x30)) tbl)
+ (set-case-syntax-pair c (+ c #x30) tbl)
(setq c (1+ c)))
;; Greek Extended
+ (modify-category-entry '(#x1f00 . #x1fff) ?g)
(setq c #x1f00)
(while (<= c #x1fff)
- (modify-category-entry (decode-char 'ucs c) ?g)
(and (<= (logand c #x000f) 7)
(<= c #x1fa7)
(not (memq c '(#x1f50 #x1f52 #x1f54 #x1f56)))
(/= (logand c #x00f0) 7)
- (set-case-syntax-pair
- (decode-char 'ucs (+ c 8)) (decode-char 'ucs c) tbl))
+ (set-case-syntax-pair (+ c 8) c tbl))
(setq c (1+ c)))
- (set-case-syntax-pair ?\e$,1qx\e(B ?\e$,1qp\e(B tbl)
- (set-case-syntax-pair ?\e$,1qy\e(B ?\e$,1qq\e(B tbl)
- (set-case-syntax-pair ?\e$,1qz\e(B ?\e$,1q0\e(B tbl)
- (set-case-syntax-pair ?\e$,1q{\e(B ?\e$,1q1\e(B tbl)
- (set-case-syntax-pair ?\e$,1q|\e(B ?\e$,1qs\e(B tbl)
- (set-case-syntax-pair ?\e$,1r(\e(B ?\e$,1q2\e(B tbl)
- (set-case-syntax-pair ?\e$,1r)\e(B ?\e$,1q3\e(B tbl)
- (set-case-syntax-pair ?\e$,1r*\e(B ?\e$,1q4\e(B tbl)
- (set-case-syntax-pair ?\e$,1r+\e(B ?\e$,1q5\e(B tbl)
- (set-case-syntax-pair ?\e$,1r,\e(B ?\e$,1r#\e(B tbl)
- (set-case-syntax-pair ?\e$,1r8\e(B ?\e$,1r0\e(B tbl)
- (set-case-syntax-pair ?\e$,1r9\e(B ?\e$,1r1\e(B tbl)
- (set-case-syntax-pair ?\e$,1r:\e(B ?\e$,1q6\e(B tbl)
- (set-case-syntax-pair ?\e$,1r;\e(B ?\e$,1q7\e(B tbl)
- (set-case-syntax-pair ?\e$,1rH\e(B ?\e$,1r@\e(B tbl)
- (set-case-syntax-pair ?\e$,1rI\e(B ?\e$,1rA\e(B tbl)
- (set-case-syntax-pair ?\e$,1rJ\e(B ?\e$,1q:\e(B tbl)
- (set-case-syntax-pair ?\e$,1rK\e(B ?\e$,1q;\e(B tbl)
- (set-case-syntax-pair ?\e$,1rL\e(B ?\e$,1rE\e(B tbl)
- (set-case-syntax-pair ?\e$,1rX\e(B ?\e$,1q8\e(B tbl)
- (set-case-syntax-pair ?\e$,1rY\e(B ?\e$,1q9\e(B tbl)
- (set-case-syntax-pair ?\e$,1rZ\e(B ?\e$,1q<\e(B tbl)
- (set-case-syntax-pair ?\e$,1r[\e(B ?\e$,1q=\e(B tbl)
- (set-case-syntax-pair ?\e$,1r\\e(B ?\e$,1rS\e(B tbl)
+ (set-case-syntax-pair ?Ᾰ ?ᾰ tbl)
+ (set-case-syntax-pair ?Ᾱ ?ᾱ tbl)
+ (set-case-syntax-pair ?Ὰ ?ὰ tbl)
+ (set-case-syntax-pair ?Ά ?ά tbl)
+ (set-case-syntax-pair ?ᾼ ?ᾳ tbl)
+ (set-case-syntax-pair ?Ὲ ?ὲ tbl)
+ (set-case-syntax-pair ?Έ ?έ tbl)
+ (set-case-syntax-pair ?Ὴ ?ὴ tbl)
+ (set-case-syntax-pair ?Ή ?ή tbl)
+ (set-case-syntax-pair ?ῌ ?ῃ tbl)
+ (set-case-syntax-pair ?Ῐ ?ῐ tbl)
+ (set-case-syntax-pair ?Ῑ ?ῑ tbl)
+ (set-case-syntax-pair ?Ὶ ?ὶ tbl)
+ (set-case-syntax-pair ?Ί ?ί tbl)
+ (set-case-syntax-pair ?Ῠ ?ῠ tbl)
+ (set-case-syntax-pair ?Ῡ ?ῡ tbl)
+ (set-case-syntax-pair ?Ὺ ?ὺ tbl)
+ (set-case-syntax-pair ?Ύ ?ύ tbl)
+ (set-case-syntax-pair ?Ῥ ?ῥ tbl)
+ (set-case-syntax-pair ?Ὸ ?ὸ tbl)
+ (set-case-syntax-pair ?Ό ?ό tbl)
+ (set-case-syntax-pair ?Ὼ ?ὼ tbl)
+ (set-case-syntax-pair ?Ώ ?ώ tbl)
+ (set-case-syntax-pair ?ῼ ?ῳ tbl)
;; cyrillic
+ (modify-category-entry '(#x0400 . #x04FF) ?y)
(setq c #x0400)
(while (<= c #x04ff)
- (modify-category-entry (decode-char 'ucs c) ?y)
(and (>= c #x0400)
(<= c #x040f)
- (set-case-syntax-pair
- (decode-char 'ucs c) (decode-char 'ucs (+ c 80)) tbl))
+ (set-case-syntax-pair c (+ c 80) tbl))
(and (>= c #x0410)
(<= c #x042f)
- (set-case-syntax-pair
- (decode-char 'ucs c) (decode-char 'ucs (+ c 32)) tbl))
+ (set-case-syntax-pair c (+ c 32) tbl))
(and (zerop (% c 2))
(or (and (>= c #x0460) (<= c #x0480))
(and (>= c #x048c) (<= c #x04be))
(and (>= c #x04d0) (<= c #x04f4)))
- (set-case-syntax-pair
- (decode-char 'ucs c) (decode-char 'ucs (1+ c)) tbl))
+ (set-case-syntax-pair c (1+ c) tbl))
(setq c (1+ c)))
- (set-case-syntax-pair ?\e$,1*!\e(B ?\e$,1*"\e(B tbl)
- (set-case-syntax-pair ?\e$,1*#\e(B ?\e$,1*$\e(B tbl)
- (set-case-syntax-pair ?\e$,1*'\e(B ?\e$,1*(\e(B tbl)
- (set-case-syntax-pair ?\e$,1*+\e(B ?\e$,1*,\e(B tbl)
- (set-case-syntax-pair ?\e$,1*X\e(B ?\e$,1*Y\e(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)
+ (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:
(setq c #x2010)
(while (<= c #x2016)
- (set-case-syntax (decode-char 'ucs c) "_" tbl)
+ (set-case-syntax c "_" tbl)
(setq c (1+ c)))
;; Punctuation syntax for quotation marks (like `)
(while (<= c #x201f)
- (set-case-syntax (decode-char 'ucs c) "." tbl)
+ (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)
+ (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
)
(let ((pairs
- '("\e$,1sEsF\e(B" ; U+2045 U+2046
- "\e$,1s}s~\e(B" ; U+207D U+207E
- "\e$,1t-t.\e(B" ; U+208D U+208E
- "\e$,1{){*\e(B" ; U+2329 U+232A
- "\e$,1|T|U\e(B" ; U+23B4 U+23B5
- "\e$,2&H&I\e(B" ; U+2768 U+2769
- "\e$,2&J&K\e(B" ; U+276A U+276B
- "\e$,2&L&M\e(B" ; U+276C U+276D
- "\e$,2&P&Q\e(B" ; U+2770 U+2771
- "\e$,2&R&S\e(B" ; U+2772 U+2773
- "\e$,2&T&U\e(B" ; U+2774 U+2775
- "\e$,2'f'g\e(B" ; U+27E6 U+27E7
- "\e$,2'h'i\e(B" ; U+27E8 U+27E9
- "\e$,2'j'k\e(B" ; U+27EA U+27EB
- "\e$,2,#,$\e(B" ; U+2983 U+2984
- "\e$,2,%,&\e(B" ; U+2985 U+2986
- "\e$,2,',(\e(B" ; U+2987 U+2988
- "\e$,2,),*\e(B" ; U+2989 U+298A
- "\e$,2,+,,\e(B" ; U+298B U+298C
- "\e$,2,-,.\e(B" ; U+298D U+298E
- "\e$,2,/,0\e(B" ; U+298F U+2990
- "\e$,2,1,2\e(B" ; U+2991 U+2992
- "\e$,2,3,4\e(B" ; U+2993 U+2994
- "\e$,2,5,6\e(B" ; U+2995 U+2996
- "\e$,2,7,8\e(B" ; U+2997 U+2998
- "\e$,2-<-=\e(B" ; U+29FC U+29FD
- "\e$,2=H=I\e(B" ; U+3008 U+3009
- "\e$,2=J=K\e(B" ; U+300A U+300B
- "\e$,2=L=M\e(B" ; U+300C U+300D
- "\e$,2=N=O\e(B" ; U+300E U+300F
- "\e$,2=P=Q\e(B" ; U+3010 U+3011
- "\e$,2=T=U\e(B" ; U+3014 U+3015
- "\e$,2=V=W\e(B" ; U+3016 U+3017
- "\e$,2=X=Y\e(B" ; U+3018 U+3019
- "\e$,2=Z=[\e(B" ; U+301A U+301B
- "\e$,3m~m\7f\e(B" ; U+FD3E U+FD3F
- "\e$,3pUpV\e(B" ; U+FE35 U+FE36
- "\e$,3pWpX\e(B" ; U+FE37 U+FE38
- "\e$,3pYpZ\e(B" ; U+FE39 U+FE3A
- "\e$,3p[p\\e(B" ; U+FE3B U+FE3C
- "\e$,3p]p^\e(B" ; U+FE3D U+FE3E
- "\e$,3p_p`\e(B" ; U+FE3F U+FE40
- "\e$,3papb\e(B" ; U+FE41 U+FE42
- "\e$,3pcpd\e(B" ; U+FE43 U+FE44
- "\e$,3pypz\e(B" ; U+FE59 U+FE5A
- "\e$,3p{p|\e(B" ; U+FE5B U+FE5C
- "\e$,3p}p~\e(B" ; U+FE5D U+FE5E
- "\e$,3rhri\e(B" ; U+FF08 U+FF09
- "\e$,3s;s=\e(B" ; U+FF3B U+FF3D
- "\e$,3s[s]\e(B" ; U+FF5B U+FF5D
- "\e$,3s_s`\e(B" ; U+FF5F U+FF60
- "\e$,3sbsc\e(B" ; U+FF62 U+FF63
+ '("⁅⁆" ; U+2045 U+2046
+ "⁽⁾" ; U+207D U+207E
+ "₍₎" ; U+208D U+208E
+ "〈〉" ; U+2329 U+232A
+ "⎴⎵" ; U+23B4 U+23B5
+ "❨❩" ; U+2768 U+2769
+ "❪❫" ; U+276A U+276B
+ "❬❭" ; U+276C U+276D
+ "❰❱" ; U+2770 U+2771
+ "❲❳" ; U+2772 U+2773
+ "❴❵" ; U+2774 U+2775
+ "⟦⟧" ; U+27E6 U+27E7
+ "⟨⟩" ; U+27E8 U+27E9
+ "⟪⟫" ; U+27EA U+27EB
+ "⦃⦄" ; U+2983 U+2984
+ "⦅⦆" ; U+2985 U+2986
+ "⦇⦈" ; U+2987 U+2988
+ "⦉⦊" ; U+2989 U+298A
+ "⦋⦌" ; U+298B U+298C
+ "⦍⦎" ; U+298D U+298E
+ "⦏⦐" ; U+298F U+2990
+ "⦑⦒" ; U+2991 U+2992
+ "⦓⦔" ; U+2993 U+2994
+ "⦕⦖" ; U+2995 U+2996
+ "⦗⦘" ; U+2997 U+2998
+ "⧼⧽" ; U+29FC U+29FD
+ "〈〉" ; U+3008 U+3009
+ "《》" ; U+300A U+300B
+ "「」" ; U+300C U+300D
+ "『』" ; U+300E U+300F
+ "【】" ; U+3010 U+3011
+ "〔〕" ; U+3014 U+3015
+ "〖〗" ; U+3016 U+3017
+ "〘〙" ; U+3018 U+3019
+ "〚〛" ; U+301A U+301B
+ "﴾﴿" ; U+FD3E U+FD3F
+ "︵︶" ; U+FE35 U+FE36
+ "︷︸" ; U+FE37 U+FE38
+ "︹︺" ; U+FE39 U+FE3A
+ "︻︼" ; U+FE3B U+FE3C
+ "︽︾" ; U+FE3D U+FE3E
+ "︿﹀" ; U+FE3F U+FE40
+ "﹁﹂" ; U+FE41 U+FE42
+ "﹃﹄" ; U+FE43 U+FE44
+ "﹙﹚" ; U+FE59 U+FE5A
+ "﹛﹜" ; U+FE5B U+FE5C
+ "﹝﹞" ; U+FE5D U+FE5E
+ "（）" ; U+FF08 U+FF09
+ "［］" ; U+FF3B U+FF3D
+ "｛｝" ; U+FF5B U+FF5D
+ "｟｠" ; U+FF5F U+FF60
+ "｢｣" ; U+FF62 U+FF63
)))
(dolist (elt pairs)
(modify-syntax-entry (aref elt 0) (string ?\( (aref elt 1)))
(modify-syntax-entry (aref elt 1) (string ?\) (aref elt 0)))))
-\f
-;;; Setting word boundary.
-
-(setq word-combining-categories
- '((?l . ?l)
- (?C . ?C)
- (?C . ?H)
- (?C . ?K)))
-
-(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
- ))
-
\f
;; 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)
(cyrillic-iso8859-5 . cyrillic-iso-8bit)
(latin-iso8859-9 . iso-latin-5)
(japanese-jisx0208-1978 . iso-2022-jp)
- (chinese-gb2312 . cn-gb-2312)
+ (chinese-gb2312 . chinese-iso-8bit)
+ (chinese-gbk . chinese-gbk)
+ (gb18030-2-byte . chinese-gb18030)
+ (gb18030-4-byte-bmp . chinese-gb18030)
+ (gb18030-4-byte-smp . chinese-gb18030)
+ (gb18030-4-byte-ext-1 . chinese-gb18030)
+ (gb18030-4-byte-ext-2 . chinese-gb18030)
(japanese-jisx0208 . iso-2022-jp)
(korean-ksc5601 . iso-2022-kr)
(japanese-jisx0212 . iso-2022-jp)
- (chinese-cns11643-1 . iso-2022-cn)
- (chinese-cns11643-2 . iso-2022-cn)
(chinese-big5-1 . chinese-big5)
(chinese-big5-2 . chinese-big5)
(chinese-sisheng . iso-2022-7bit)
(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)
(indian-glyph . devanagari)
(tibetan-1-column . tibetan)
(ethiopic . iso-2022-7bit)
+ (chinese-cns11643-1 . iso-2022-cn)
+ (chinese-cns11643-2 . iso-2022-cn)
(chinese-cns11643-3 . iso-2022-cn)
(chinese-cns11643-4 . iso-2022-cn)
(chinese-cns11643-5 . iso-2022-cn)
\f
;; Setup auto-fill-chars for charsets that should invoke auto-filling.
-;; SPACE and NEWLINE are already set. Also put `nospace-between-words'
-;; property on the charsets.
-(let ((l '(katakana-jisx0201
- japanese-jisx0208 japanese-jisx0212
- chinese-gb2312 chinese-big5-1 chinese-big5-2)))
- (while l
- (aset auto-fill-chars (make-char (car l)) t)
- (put-charset-property (car l) 'nospace-between-words t)
- (setq l (cdr l))))
+;; SPACE and NEWLINE are already set.
+
+(set-char-table-range auto-fill-chars '(#x3041 . #x30FF) t)
+(set-char-table-range auto-fill-chars '(#x3400 . #x4DB5) t)
+(set-char-table-range auto-fill-chars '(#x4e00 . #x9fbb) t)
+(set-char-table-range auto-fill-chars '(#xF900 . #xFAFF) t)
+(set-char-table-range auto-fill-chars '(#xFF00 . #xFF9F) t)
+(set-char-table-range auto-fill-chars '(#x20000 . #x2FFFF) t)
\f
-(setq utf-translate-cjk-mode saved-utf-translate-cjk-mode)
-(makunbound 'saved-utf-translate-cjk-mode)
+;;; Setting char-width-table. The default is 1.
+
+;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
+;; and final characters.
+(let ((l '((#x00AD . #x00AD)
+ (#x0300 . #x036F)
+ (#x0483 . #x0489)
+ (#x0591 . #x05BD)
+ (#x05BF . #x05BF)
+ (#x05C1 . #x05C2)
+ (#x05C4 . #x05C5)
+ (#x05C7 . #x05C7)
+ (#x0600 . #x0603)
+ (#x0610 . #x0615)
+ (#x064B . #x065E)
+ (#x0670 . #x0670)
+ (#x06D6 . #x06E4)
+ (#x06E7 . #x06E8)
+ (#x06EA . #x06ED)
+ (#x070F . #x070F)
+ (#x0711 . #x0711)
+ (#x0730 . #x074A)
+ (#x07A6 . #x07B0)
+ (#x07EB . #x07F3)
+ (#x0901 . #x0902)
+ (#x093C . #x093C)
+ (#x0941 . #x0948)
+ (#x094D . #x094D)
+ (#x0951 . #x0954)
+ (#x0962 . #x0963)
+ (#x0981 . #x0981)
+ (#x09BC . #x09BC)
+ (#x09C1 . #x09C4)
+ (#x09CD . #x09CD)
+ (#x09E2 . #x09E3)
+ (#x0A01 . #x0A02)
+ (#x0A3C . #x0A3C)
+ (#x0A41 . #x0A4D)
+ (#x0A70 . #x0A71)
+ (#x0A81 . #x0A82)
+ (#x0ABC . #x0ABC)
+ (#x0AC1 . #x0AC8)
+ (#x0ACD . #x0ACD)
+ (#x0AE2 . #x0AE3)
+ (#x0B01 . #x0B01)
+ (#x0B3C . #x0B3C)
+ (#x0B3F . #x0B3F)
+ (#x0B41 . #x0B43)
+ (#x0B4D . #x0B56)
+ (#x0B82 . #x0B82)
+ (#x0BC0 . #x0BC0)
+ (#x0BCD . #x0BCD)
+ (#x0C3E . #x0C40)
+ (#x0C46 . #x0C56)
+ (#x0CBC . #x0CBC)
+ (#x0CBF . #x0CBF)
+ (#x0CC6 . #x0CC6)
+ (#x0CCC . #x0CCD)
+ (#x0CE2 . #x0CE3)
+ (#x0D41 . #x0D43)
+ (#x0D4D . #x0D4D)
+ (#x0DCA . #x0DCA)
+ (#x0DD2 . #x0DD6)
+ (#x0E31 . #x0E31)
+ (#x0E34 . #x0E3A)
+ (#x0E47 . #x0E4E)
+ (#x0EB1 . #x0EB1)
+ (#x0EB4 . #x0EBC)
+ (#x0EC8 . #x0ECD)
+ (#x0F18 . #x0F19)
+ (#x0F35 . #x0F35)
+ (#x0F37 . #x0F37)
+ (#x0F39 . #x0F39)
+ (#x0F71 . #x0F7E)
+ (#x0F80 . #x0F84)
+ (#x0F86 . #x0F87)
+ (#x0F90 . #x0FBC)
+ (#x0FC6 . #x0FC6)
+ (#x102D . #x1030)
+ (#x1032 . #x1037)
+ (#x1039 . #x1039)
+ (#x1058 . #x1059)
+ (#x1160 . #x11FF)
+ (#x135F . #x135F)
+ (#x1712 . #x1714)
+ (#x1732 . #x1734)
+ (#x1752 . #x1753)
+ (#x1772 . #x1773)
+ (#x17B4 . #x17B5)
+ (#x17B7 . #x17BD)
+ (#x17C6 . #x17C6)
+ (#x17C9 . #x17D3)
+ (#x17DD . #x17DD)
+ (#x180B . #x180D)
+ (#x18A9 . #x18A9)
+ (#x1920 . #x1922)
+ (#x1927 . #x1928)
+ (#x1932 . #x1932)
+ (#x1939 . #x193B)
+ (#x1A17 . #x1A18)
+ (#x1B00 . #x1B03)
+ (#x1B34 . #x1B34)
+ (#x1B36 . #x1B3A)
+ (#x1B3C . #x1B3C)
+ (#x1B42 . #x1B42)
+ (#x1B6B . #x1B73)
+ (#x1DC0 . #x1DFF)
+ (#x200B . #x200F)
+ (#x202A . #x202E)
+ (#x2060 . #x206F)
+ (#x20D0 . #x20EF)
+ (#x302A . #x302F)
+ (#x3099 . #x309A)
+ (#xA806 . #xA806)
+ (#xA80B . #xA80B)
+ (#xA825 . #xA826)
+ (#xFB1E . #xFB1E)
+ (#xFE00 . #xFE0F)
+ (#xFE20 . #xFE23)
+ (#xFEFF . #xFEFF)
+ (#xFFF9 . #xFFFB)
+ (#x10A01 . #x10A0F)
+ (#x10A38 . #x10A3F)
+ (#x1D167 . #x1D169)
+ (#x1D173 . #x1D182)
+ (#x1D185 . #x1D18B)
+ (#x1D1AA . #x1D1AD)
+ (#x1D242 . #x1D244)
+ (#xE0001 . #xE01EF))))
+ (dolist (elt l)
+ (set-char-table-range char-width-table elt 0)))
+
+;; 2: East Asian Wide and Full-width characters.
+(let ((l '((#x1100 . #x115F)
+ (#x2329 . #x232A)
+ (#x2E80 . #x303E)
+ (#x3040 . #xA4CF)
+ (#xAC00 . #xD7A3)
+ (#xF900 . #xFAFF)
+ (#xFE30 . #xFE6F)
+ (#xFF01 . #xFF60)
+ (#xFFE0 . #xFFE6)
+ (#x20000 . #x2FFFF)
+ (#x30000 . #x3FFFF))))
+ (dolist (elt l)
+ (set-char-table-range char-width-table elt 2)))
+
+;; 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 (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)
+ (#x07C0 #x07FA nko)
+ (#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 #x139F 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)
+ (#x2000 #x27FF symbol)
+ (#x2800 #x28FF braille)
+ (#x2D80 #x2DDF ethiopic)
+ (#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)
+ (#xAA80 #xAADF tai-viet)
+ (#xAC00 #xD7AF hangul)
+ (#xF900 #xFAFF han)
+ (#xFB1D #xFB4F hebrew)
+ (#xFB50 #xFDFF arabic)
+ (#xFE70 #xFEFC arabic)
+ (#xFF00 #xFF5F cjk-misc)
+ (#xFF61 #xFF9F kana)
+ (#xFFE0 #xFFE6 cjk-misc)
+ (#x1D000 #x1D0FF byzantine-musical-symbol)
+ (#x1D100 #x1D1FF musical-symbol)
+ (#x1D400 #x1D7FF mathematical)
+ (#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)
+
+\f
+;;; 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)))
+ (if (looking-at "\\ck+")
+ (goto-char (match-end 0)))
+ (point))
+ (let ((category-set (char-category-set (char-after pos)))
+ category)
+ (if (or (aref category-set ?K) (aref category-set ?k))
+ (while (and (> pos limit)
+ (setq category-set
+ (char-category-set (char-after (1- pos))))
+ (or (aref category-set ?K) (aref category-set ?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)
+ (?C . ?C)
+ (?C . ?H)
+ (?C . ?K)))
+
+(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
;; End:
;; arch-tag: 85889c35-9f4d-4912-9bf5-82de31b0d42d