code.delx.au - gnu-emacs/blob - lisp/international/characters.el

   1 ;;; characters.el --- set syntax and category for multibyte characters
   2
   3 ;; Copyright (C) 1997, 2000, 2001, 2002, 2003, 2004, 2005, 2006
   4 ;;   Free Software Foundation, Inc.
   5 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
   6 ;;   2005, 2006
   7 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   8 ;;   Registration Number H14PRO021
   9 ;; Copyright (C) 2003
  10 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  11 ;;   Registration Number H13PRO009
  12
  13 ;; Keywords: multibyte character, character set, syntax, category
  14
  15 ;; This file is part of GNU Emacs.
  16
  17 ;; GNU Emacs is free software; you can redistribute it and/or modify
  18 ;; it under the terms of the GNU General Public License as published by
  19 ;; the Free Software Foundation; either version 2, or (at your option)
  20 ;; any later version.
  21
  22 ;; GNU Emacs is distributed in the hope that it will be useful,
  23 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  24 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  25 ;; GNU General Public License for more details.
  26
  27 ;; You should have received a copy of the GNU General Public License
  28 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  29 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  30 ;; Boston, MA 02110-1301, USA.
  31
  32 ;;; Commentary:
  33
  34 ;;; Code:
  35
  36 ;;; Predefined categories.
  37
  38 ;; For each character set.
  39
  40 (define-category ?a "ASCII")
  41 (define-category ?l "Latin")
  42 (define-category ?t "Thai")
  43 (define-category ?g "Greek")
  44 (define-category ?b "Arabic")
  45 (define-category ?w "Hebrew")
  46 (define-category ?y "Cyrillic")
  47 (define-category ?k "Japanese katakana")
  48 (define-category ?r "Japanese roman")
  49 (define-category ?c "Chinese")
  50 (define-category ?j "Japanese")
  51 (define-category ?h "Korean")
  52 (define-category ?e "Ethiopic (Ge'ez)")
  53 (define-category ?v "Vietnamese")
  54 (define-category ?i "Indian")
  55 (define-category ?o "Lao")
  56 (define-category ?q "Tibetan")
  57
  58 ;; For each group (row) of 2-byte character sets.
  59
  60 (define-category ?A "Alpha-numeric characters of 2-byte character sets")
  61 (define-category ?C "Chinese (Han) characters of 2-byte character sets")
  62 (define-category ?G "Greek characters of 2-byte character sets")
  63 (define-category ?H "Japanese Hiragana characters of 2-byte character sets")
  64 (define-category ?K "Japanese Katakana characters of 2-byte character sets")
  65 (define-category ?N "Korean Hangul characters of 2-byte character sets")
  66 (define-category ?Y "Cyrillic characters of 2-byte character sets")
  67 (define-category ?I "Indian Glyphs")
  68
  69 ;; For phonetic classifications.
  70
  71 (define-category ?0 "consonant")
  72 (define-category ?1 "base (independent) vowel")
  73 (define-category ?2 "upper diacritical mark (including upper vowel)")
  74 (define-category ?3 "lower diacritical mark (including lower vowel)")
  75 (define-category ?4 "tone mark")
  76 (define-category ?5 "symbol")
  77 (define-category ?6 "digit")
  78 (define-category ?7 "vowel-modifying diacritical mark")
  79 (define-category ?8 "vowel-signs")
  80 (define-category ?9 "semivowel lower")
  81
  82 ;; For filling.
  83 (define-category ?| "While filling, we can break a line at this character.")
  84
  85 ;; For indentation calculation.
  86 (define-category ?\s
  87   "This character counts as a space for indentation purposes.")
  88
  89 ;; Keep the following for `kinsoku' processing.  See comments in
  90 ;; kinsoku.el.
  91 (define-category ?> "A character which can't be placed at beginning of line.")
  92 (define-category ?< "A character which can't be placed at end of line.")
  93
  94 ;; Combining
  95 (define-category ?^ "Combining diacritic or mark")
  96 \f
  97 ;;; Setting syntax and category.
  98
  99 ;; ASCII
 100
 101 ;; All ASCII characters have the category `a' (ASCII) and `l' (Latin).
 102 (modify-category-entry '(32 . 127) ?a)
 103 (modify-category-entry '(32 . 127) ?l)
 104
 105 ;; Deal with the CJK charsets first.  Since the syntax of blocks is
 106 ;; defined per charset, and the charsets may contain e.g. Latin
 107 ;; characters, we end up with the wrong syntax definitions if we're
 108 ;; not careful.
 109
 110 ;; Chinese characters (Unicode)
 111 (modify-category-entry '(#x2E80 . #x312F) ?|)
 112 (modify-category-entry '(#x3190 . #x33FF) ?|)
 113 (modify-category-entry '(#x3400 . #x9FAF) ?C)
 114 (modify-category-entry '(#x3400 . #x9FAF) ?c)
 115 (modify-category-entry '(#x3400 . #x9FAF) ?|)
 116 (modify-category-entry '(#xF900 . #xFAFF) ?C)
 117 (modify-category-entry '(#xF900 . #xFAFF) ?c)
 118 (modify-category-entry '(#xF900 . #xFAFF) ?|)
 119 (modify-category-entry '(#x20000 . #x2AFFF) ?|)
 120 (modify-category-entry '(#x2F800 . #x2FFFF) ?|)
 121
 122
 123 ;; Chinese character set (GB2312)
 124
 125 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2121 #x217E)
 126 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2221 #x227E)
 127 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2921 #x297E)
 128
 129 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?c)
 130 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2330 #x2339)
 131 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2341 #x235A)
 132 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2361 #x237A)
 133 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?H #x2421 #x247E)
 134 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?K #x2521 #x257E)
 135 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?G #x2621 #x267E)
 136 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?Y #x2721 #x277E)
 137 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?C #x3021 #x7E7E)
 138
 139 ;; Chinese character set (BIG5)
 140
 141 (map-charset-chars #'modify-category-entry 'big5 ?c)
 142 (map-charset-chars #'modify-category-entry 'big5 ?C #xA259 #xA25F)
 143 (map-charset-chars #'modify-category-entry 'big5 ?C #xA440 #xC67E)
 144 (map-charset-chars #'modify-category-entry 'big5 ?C #xC940 #xF9DF)
 145
 146 ;; Chinese character set (CNS11643)
 147
 148 (dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
 149              chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
 150              chinese-cns11643-7))
 151   (map-charset-chars #'modify-category-entry c ?c)
 152   (if (eq c 'chinese-cns11643-1)
 153       (map-charset-chars #'modify-category-entry c ?C #x4421 #x7E7E)
 154     (map-charset-chars #'modify-category-entry c ?C)))
 155
 156 ;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213)
 157
 158 (map-charset-chars #'modify-category-entry 'katakana-jisx0201 ?k)
 159
 160 (map-charset-chars #'modify-category-entry 'latin-jisx0201 ?r)
 161
 162 (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212
 163                                japanese-jisx0213-1 japanese-jisx0213-2))
 164   (map-charset-chars #'modify-category-entry l ?j))
 165
 166 ;; Unicode equivalents of JISX0201-kana
 167 (let ((range '(#xff61 . #xff9f)))
 168   (modify-category-entry range  ?k)
 169   (modify-category-entry range ?j)
 170   (modify-category-entry range ?\|))
 171
 172 ;; Katakana block
 173 (let ((range '(#x30a0 . #x30ff)))
 174   ;; ?K is double width, ?k isn't specified
 175   (modify-category-entry range ?K)
 176   (modify-category-entry range ?\|))
 177
 178 ;; Hiragana block
 179 (let ((range '(#x3040 . #x309d)))
 180   ;; ?H is actually defined to be double width
 181   ;;(modify-category-entry range ?H)
 182   (modify-category-entry range ?\|)
 183   )
 184
 185 ;; JISX0208
 186 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2121 #x227E)
 187 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2821 #x287E)
 188 (let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
 189   (dolist (elt chars)
 190     (modify-syntax-entry (car chars) "w")))
 191
 192 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?A #x2321 #x237E)
 193 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?H #x2421 #x247E)
 194 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?K #x2521 #x257E)
 195 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?G #x2621 #x267E)
 196 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?Y #x2721 #x277E)
 197 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?C #x3021 #x7E7E)
 198 (modify-category-entry ?ー ?K)
 199 (let ((chars '(?゛ ?゜)))
 200   (while chars
 201     (modify-category-entry (car chars) ?K)
 202     (modify-category-entry (car chars) ?H)
 203     (setq chars (cdr chars))))
 204 (let ((chars '(?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
 205   (while chars
 206     (modify-category-entry (car chars) ?C)
 207     (setq chars (cdr chars))))
 208
 209 ;; JISX0212
 210
 211 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E)
 212
 213 ;; JISX0201-Kana
 214
 215 (let ((chars '(?｡ ?､ ?･)))
 216   (while chars
 217     (modify-syntax-entry (car chars) ".")
 218     (setq chars (cdr chars))))
 219
 220 (modify-syntax-entry ?\｢ "(｣")
 221 (modify-syntax-entry ?\｣ "(｢")
 222
 223 ;; Korean character set (KSC5601)
 224
 225 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?h)
 226
 227 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2121 #x227E)
 228 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2621 #x277E)
 229 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2830 #x287E)
 230 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2930 #x297E)
 231 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2330 #x2339)
 232 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2341 #x235A)
 233 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2361 #x237A)
 234 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?G #x2521 #x257E)
 235 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?H #x2A21 #x2A7E)
 236 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?K #x2B21 #x2B7E)
 237 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?Y #x2C21 #x2C7E)
 238
 239 ;; These are in more than one charset.
 240 (let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛"
 241                       "︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄"
 242                       "（）［］｛｝"))
 243       open close)
 244   (dotimes (i (/ (length parens) 2))
 245     (setq open (aref parens (* i 2))
 246           close (aref parens (1+ (* i 2))))
 247     (modify-syntax-entry open (format "(%c" close))
 248     (modify-syntax-entry close (format ")%c" open))))
 249
 250 ;; Arabic character set
 251
 252 (let ((charsets '(arabic-iso8859-6
 253                   arabic-digit
 254                   arabic-1-column
 255                   arabic-2-column)))
 256   (while charsets
 257     (map-charset-chars #'modify-category-entry (car charsets) ?b)
 258     (setq charsets (cdr charsets))))
 259 (modify-category-entry '(#x600 . #x6ff) ?b)
 260 (modify-category-entry '(#xfb50 . #xfdff) ?b)
 261 (modify-category-entry '(#xfe70 . #xfefe) ?b)
 262
 263 ;; Cyrillic character set (ISO-8859-5)
 264
 265 (modify-syntax-entry ?№ ".")
 266
 267 ;; Ethiopic character set
 268
 269 (modify-category-entry '(#x1200 . #x1399) ?e)
 270 (modify-category-entry '(#x2d80 . #x2dde) ?e)
 271 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨ ?���� ?���� ?���� ?���� ?���� ?����)))
 272   (while chars
 273     (modify-syntax-entry (car chars) ".")
 274     (setq chars (cdr chars))))
 275 (map-charset-chars #'modify-category-entry 'ethiopic ?e)
 276
 277 ;; Hebrew character set (ISO-8859-8)
 278
 279 (modify-syntax-entry #x5be ".") ; MAQAF
 280 (modify-syntax-entry #x5c0 ".") ; PASEQ
 281 (modify-syntax-entry #x5c3 ".") ; SOF PASUQ
 282 (modify-syntax-entry #x5f3 ".") ; GERESH
 283 (modify-syntax-entry #x5f4 ".") ; GERSHAYIM
 284
 285 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
 286
 287 (modify-category-entry '(#x901 . #x970) ?i)
 288 (map-charset-chars #'modify-category-entry 'indian-is13194 ?i)
 289 (map-charset-chars #'modify-category-entry 'indian-2-column ?i)
 290
 291 ;; Lao character set
 292
 293 (modify-category-entry '(#xe80 . #xeff) ?o)
 294 (map-charset-chars #'modify-category-entry 'lao ?o)
 295
 296 (let ((deflist  '(("ກ-ຮ"    "w"     ?0) ; consonant
 297                   ("ະາຳຽເ-ໄ"        "w"     ?1) ; vowel base
 298                   ("ັິ-ືົໍ"   "w"     ?2) ; vowel upper
 299                   ("ຸູ"     "w"     ?3) ; vowel lower
 300                   ("່-໋"    "w"     ?4) ; tone mark
 301                   ("ຼຽ"     "w"     ?9) ; semivowel lower
 302                   ("໐-໙"    "w"     ?6) ; digit
 303                   ("ຯໆ"     "_"     ?5) ; symbol
 304                   ))
 305       elm chars len syntax category to ch i)
 306   (while deflist
 307     (setq elm (car deflist))
 308     (setq chars (car elm)
 309           len (length chars)
 310           syntax (nth 1 elm)
 311           category (nth 2 elm)
 312           i 0)
 313     (while (< i len)
 314       (if (= (aref chars i) ?-)
 315           (setq i (1+ i)
 316                 to (aref chars i))
 317         (setq ch (aref chars i)
 318               to ch))
 319       (while (<= ch to)
 320         (unless (string-equal syntax "w")
 321           (modify-syntax-entry ch syntax))
 322         (modify-category-entry ch category)
 323         (setq ch (1+ ch)))
 324       (setq i (1+ i)))
 325     (setq deflist (cdr deflist))))
 326
 327 ;; Thai character set (TIS620)
 328
 329 (modify-category-entry '(#xe00 . #xe7f) ?t)
 330 (map-charset-chars #'modify-category-entry 'thai-tis620 ?t)
 331
 332 (let ((deflist  '(;; chars      syntax  category
 333                   ("ก-รลว-ฮ"  "w"     ?0) ; consonant
 334                   ("ฤฦะาำเ-ๅ"     "w"     ?1) ; vowel base
 335                   ("ัิ-ื็๎"   "w"     ?2) ; vowel upper
 336                   ("ุ-ฺ"    "w"     ?3) ; vowel lower
 337                   ("่-ํ"    "w"     ?4) ; tone mark
 338                   ("๐-๙"    "w"     ?6) ; digit
 339                   ("ฯๆ฿๏๚๛" "_"     ?5) ; symbol
 340                   ))
 341       elm chars len syntax category to ch i)
 342   (while deflist
 343     (setq elm (car deflist))
 344     (setq chars (car elm)
 345           len (length chars)
 346           syntax (nth 1 elm)
 347           category (nth 2 elm)
 348           i 0)
 349     (while (< i len)
 350       (if (= (aref chars i) ?-)
 351           (setq i (1+ i)
 352                 to (aref chars i))
 353         (setq ch (aref chars i)
 354               to ch))
 355       (while (<= ch to)
 356         (unless (string-equal syntax "w")
 357           (modify-syntax-entry ch syntax))
 358         (modify-category-entry ch category)
 359         (setq ch (1+ ch)))
 360       (setq i (1+ i)))
 361     (setq deflist (cdr deflist))))
 362
 363 ;; Tibetan character set
 364
 365 (modify-category-entry '(#xf00 . #xfff) ?q)
 366 (map-charset-chars #'modify-category-entry 'tibetan ?q)
 367 (map-charset-chars #'modify-category-entry 'tibetan-1-column ?q)
 368
 369 (let ((deflist  '(;; chars             syntax category
 370                   ("ཀ-ཀྵཪ"         "w"     ?0) ; consonant
 371                   ("ྐ-ྐྵྺྻྼ��������"       "w"     ?0) ;
 372                   ("����-����"              "w"     ?0) ;
 373                   ("����-����"              "w"     ?0) ;
 374                   ("ིེཻོཽྀ"       "w"       ?2) ; upper vowel
 375                   ("ཾྂྃ྆྇ྈྉྊྋ" "w"    ?2) ; upper modifier
 376                   ("༙����྄ཱུ༵༷"       "w"   ?3) ; lowel vowel/modifier
 377                   ("཰"                "w" ?3)             ; invisible vowel a
 378                   ("༠-༩༪-༳"             "w"     ?6) ; digit
 379                   ("་།-༒༔ཿ"        "."     ?|) ; line-break char
 380                   ("་།༏༐༑༔ཿ"            "."     ?|) ;
 381                   ("༈་།-༒༔ཿ༽༴"  "."     ?>) ; prohibition
 382                   ("་།༏༐༑༔ཿ"            "."     ?>) ;
 383                   ("ༀ-༊༼࿁࿂྅"      "."     ?<) ; prohibition
 384                   ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q) ; others
 385                   ))
 386       elm chars len syntax category to ch i)
 387   (while deflist
 388     (setq elm (car deflist))
 389     (setq chars (car elm)
 390           len (length chars)
 391           syntax (nth 1 elm)
 392           category (nth 2 elm)
 393           i 0)
 394     (while (< i len)
 395       (if (= (aref chars i) ?-)
 396           (setq i (1+ i)
 397                 to (aref chars i))
 398         (setq ch (aref chars i)
 399               to ch))
 400       (while (<= ch to)
 401         (unless (string-equal syntax "w")
 402           (modify-syntax-entry ch syntax))
 403         (modify-category-entry ch category)
 404         (setq ch (1+ ch)))
 405       (setq i (1+ i)))
 406     (setq deflist (cdr deflist))))
 407
 408 ;; Vietnamese character set
 409
 410 ;; To make a word with Latin characters
 411 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?l)
 412 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?v)
 413
 414 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?l)
 415 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?v)
 416
 417 (let ((tbl (standard-case-table))
 418       (i 32))
 419   (while (< i 128)
 420     (let* ((char (decode-char 'vietnamese-viscii-upper i))
 421            (charl (decode-char 'vietnamese-viscii-lower i))
 422            (uc (encode-char char 'ucs))
 423            (lc (encode-char charl 'ucs)))
 424       (set-case-syntax-pair char (decode-char 'vietnamese-viscii-lower i)
 425                             tbl)
 426       (if uc (modify-category-entry uc ?v))
 427       (if lc (modify-category-entry lc ?v)))
 428     (setq i (1+ i))))
 429
 430
 431 ;; Latin
 432
 433 (modify-category-entry '(#x80 . #x024F) ?l)
 434
 435 (let ((tbl (standard-case-table)) c)
 436
 437   ;; Latin-1
 438
 439   ;; Fixme: Some of the non-word syntaxes here perhaps should be
 440   ;; reviewed.  (Note that the following all implicitly have word
 441   ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.)  There should be a well-defined way of
 442   ;; relating Unicode categories to Emacs syntax codes.
 443
 444   ;; NBSP isn't semantically interchangeable with other whitespace chars,
 445   ;; so it's more like punctation.
 446   (set-case-syntax ?  "." tbl)
 447   (set-case-syntax ?¡ "." tbl)
 448   (set-case-syntax ?¦ "_" tbl)
 449   (set-case-syntax ?§ "." tbl)
 450   (set-case-syntax ?© "_" tbl)
 451   (set-case-syntax-delims 171 187 tbl)  ; « »
 452   (set-case-syntax ?¬ "_" tbl)
 453   (set-case-syntax ? "_" tbl)
 454   (set-case-syntax ?® "_" tbl)
 455   (set-case-syntax ?° "_" tbl)
 456   (set-case-syntax ?± "_" tbl)
 457   (set-case-syntax ?µ "_" tbl)
 458   (set-case-syntax ?· "_" tbl)
 459   (set-case-syntax ?¼ "_" tbl)
 460   (set-case-syntax ?½ "_" tbl)
 461   (set-case-syntax ?¾ "_" tbl)
 462   (set-case-syntax ?¿ "." tbl)
 463   (let ((c 192))
 464     (while (<= c 222)
 465       (set-case-syntax-pair c (+ c 32) tbl)
 466       (setq c (1+ c))))
 467   (set-case-syntax ?× "_" tbl)
 468   (set-case-syntax ?ß "w" tbl)
 469   (set-case-syntax ?÷ "_" tbl)
 470   ;; See below for ÿ.
 471
 472   ;; Latin Extended-A, Latin Extended-B
 473   (setq c #x0100)
 474   (while (<= c #x0233)
 475     (and (or (<= c #x012e)
 476              (and (>= c #x014a) (<= c #x0177)))
 477          (zerop (% c 2))
 478          (set-case-syntax-pair c (1+ c) tbl))
 479     (and (>= c #x013a)
 480          (<= c #x0148)
 481          (zerop (% c 2))
 482          (set-case-syntax-pair (1- c) c tbl))
 483     (setq c (1+ c)))
 484
 485
 486   ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
 487   ;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
 488   ;; do U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN
 489   ;; SMALL LETTER I.
 490
 491   ;; We used to set up half of those correspondence unconditionally,
 492   ;; but that makes searches slow.  So now we don't set up either half
 493   ;; of these correspondences by default.
 494
 495   ;; (set-downcase-syntax  ?İ ?i tbl)
 496   ;; (set-upcase-syntax    ?I ?ı tbl)
 497
 498   (set-case-syntax-pair ?Ĳ ?ĳ tbl)
 499   (set-case-syntax-pair ?Ĵ ?ĵ tbl)
 500   (set-case-syntax-pair ?Ķ ?ķ tbl)
 501   (set-case-syntax-pair ?Ÿ ?ÿ tbl)
 502   (set-case-syntax-pair ?Ź ?ź tbl)
 503   (set-case-syntax-pair ?Ż ?ż tbl)
 504   (set-case-syntax-pair ?Ž ?ž tbl)
 505
 506   ;; Latin Extended-B
 507   (set-case-syntax-pair ?Ɓ ?ɓ tbl)
 508   (set-case-syntax-pair ?Ƃ ?ƃ tbl)
 509   (set-case-syntax-pair ?Ƅ ?ƅ tbl)
 510   (set-case-syntax-pair ?Ɔ ?ɔ tbl)
 511   (set-case-syntax-pair ?Ƈ ?ƈ tbl)
 512   (set-case-syntax-pair ?Ɖ ?ɖ tbl)
 513   (set-case-syntax-pair ?Ɗ ?ɗ tbl)
 514   (set-case-syntax-pair ?Ƌ ?ƌ tbl)
 515   (set-case-syntax-pair ?Ǝ ?ǝ tbl)
 516   (set-case-syntax-pair ?Ə ?ə tbl)
 517   (set-case-syntax-pair ?Ɛ ?ɛ tbl)
 518   (set-case-syntax-pair ?Ƒ ?ƒ tbl)
 519   (set-case-syntax-pair ?Ɠ ?ɠ tbl)
 520   (set-case-syntax-pair ?Ɣ ?ɣ tbl)
 521   (set-case-syntax-pair ?Ɩ ?ɩ tbl)
 522   (set-case-syntax-pair ?Ɨ ?ɨ tbl)
 523   (set-case-syntax-pair ?Ƙ ?ƙ tbl)
 524   (set-case-syntax-pair ?Ɯ ?ɯ tbl)
 525   (set-case-syntax-pair ?Ɲ ?ɲ tbl)
 526   (set-case-syntax-pair ?Ɵ ?ɵ tbl)
 527   (set-case-syntax-pair ?Ơ ?ơ tbl)
 528   (set-case-syntax-pair ?Ƣ ?ƣ tbl)
 529   (set-case-syntax-pair ?Ƥ ?ƥ tbl)
 530   (set-case-syntax-pair ?Ʀ ?ʀ tbl)
 531   (set-case-syntax-pair ?Ƨ ?ƨ tbl)
 532   (set-case-syntax-pair ?Ʃ ?ʃ tbl)
 533   (set-case-syntax-pair ?Ƭ ?ƭ tbl)
 534   (set-case-syntax-pair ?Ʈ ?ʈ tbl)
 535   (set-case-syntax-pair ?Ư ?ư tbl)
 536   (set-case-syntax-pair ?Ʊ ?ʊ tbl)
 537   (set-case-syntax-pair ?Ʋ ?ʋ tbl)
 538   (set-case-syntax-pair ?Ƴ ?ƴ tbl)
 539   (set-case-syntax-pair ?Ƶ ?ƶ tbl)
 540   (set-case-syntax-pair ?Ʒ ?ʒ tbl)
 541   (set-case-syntax-pair ?Ƹ ?ƹ tbl)
 542   (set-case-syntax-pair ?Ƽ ?ƽ tbl)
 543   (set-case-syntax-pair ?Ǆ ?ǆ tbl)
 544   (set-case-syntax-pair ?ǅ ?ǆ tbl)
 545   (set-case-syntax-pair ?Ǉ ?ǉ tbl)
 546   (set-case-syntax-pair ?ǈ ?ǉ tbl)
 547   (set-case-syntax-pair ?Ǌ ?ǌ tbl)
 548   (set-case-syntax-pair ?ǋ ?ǌ tbl)
 549   (set-case-syntax-pair ?Ǎ ?ǎ tbl)
 550   (set-case-syntax-pair ?Ǐ ?ǐ tbl)
 551   (set-case-syntax-pair ?Ǒ ?ǒ tbl)
 552   (set-case-syntax-pair ?Ǔ ?ǔ tbl)
 553   (set-case-syntax-pair ?Ǖ ?ǖ tbl)
 554   (set-case-syntax-pair ?Ǘ ?ǘ tbl)
 555   (set-case-syntax-pair ?Ǚ ?ǚ tbl)
 556   (set-case-syntax-pair ?Ǜ ?ǜ tbl)
 557   (set-case-syntax-pair ?Ǟ ?ǟ tbl)
 558   (set-case-syntax-pair ?Ǡ ?ǡ tbl)
 559   (set-case-syntax-pair ?Ǣ ?ǣ tbl)
 560   (set-case-syntax-pair ?Ǥ ?ǥ tbl)
 561   (set-case-syntax-pair ?Ǧ ?ǧ tbl)
 562   (set-case-syntax-pair ?Ǩ ?ǩ tbl)
 563   (set-case-syntax-pair ?Ǫ ?ǫ tbl)
 564   (set-case-syntax-pair ?Ǭ ?ǭ tbl)
 565   (set-case-syntax-pair ?Ǯ ?ǯ tbl)
 566   ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
 567   (set-case-syntax-pair ?Ǳ ?ǳ tbl)
 568   (set-case-syntax-pair ?ǲ ?ǳ tbl)
 569   (set-case-syntax-pair ?Ǵ ?ǵ tbl)
 570   (set-case-syntax-pair ?Ƕ ?ƕ tbl)
 571   (set-case-syntax-pair ?Ƿ ?ƿ tbl)
 572   (set-case-syntax-pair ?Ǹ ?ǹ tbl)
 573   (set-case-syntax-pair ?Ǻ ?ǻ tbl)
 574   (set-case-syntax-pair ?Ǽ ?ǽ tbl)
 575   (set-case-syntax-pair ?Ǿ ?ǿ tbl)
 576   (set-case-syntax-pair ?Ȁ ?ȁ tbl)
 577   (set-case-syntax-pair ?Ȃ ?ȃ tbl)
 578   (set-case-syntax-pair ?Ȅ ?ȅ tbl)
 579   (set-case-syntax-pair ?Ȇ ?ȇ tbl)
 580   (set-case-syntax-pair ?Ȉ ?ȉ tbl)
 581   (set-case-syntax-pair ?Ȋ ?ȋ tbl)
 582   (set-case-syntax-pair ?Ȍ ?ȍ tbl)
 583   (set-case-syntax-pair ?Ȏ ?ȏ tbl)
 584   (set-case-syntax-pair ?Ȑ ?ȑ tbl)
 585   (set-case-syntax-pair ?Ȓ ?ȓ tbl)
 586   (set-case-syntax-pair ?Ȕ ?ȕ tbl)
 587   (set-case-syntax-pair ?Ȗ ?ȗ tbl)
 588   (set-case-syntax-pair ?Ș ?ș tbl)
 589   (set-case-syntax-pair ?Ț ?ț tbl)
 590   (set-case-syntax-pair ?Ȝ ?ȝ tbl)
 591   (set-case-syntax-pair ?Ȟ ?ȟ tbl)
 592   (set-case-syntax-pair ?Ȣ ?ȣ tbl)
 593   (set-case-syntax-pair ?Ȥ ?ȥ tbl)
 594   (set-case-syntax-pair ?Ȧ ?ȧ tbl)
 595   (set-case-syntax-pair ?Ȩ ?ȩ tbl)
 596   (set-case-syntax-pair ?Ȫ ?ȫ tbl)
 597   (set-case-syntax-pair ?Ȭ ?ȭ tbl)
 598   (set-case-syntax-pair ?Ȯ ?ȯ tbl)
 599   (set-case-syntax-pair ?Ȱ ?ȱ tbl)
 600   (set-case-syntax-pair ?Ȳ ?ȳ tbl)
 601
 602   ;; Latin Extended Additional
 603   (modify-category-entry '(#x1e00 . #x1ef9) ?l)
 604   (setq c #x1e00)
 605   (while (<= c #x1ef9)
 606     (and (zerop (% c 2))
 607          (or (<= c #x1e94) (>= c #x1ea0))
 608          (set-case-syntax-pair c (1+ c) tbl))
 609     (setq c (1+ c)))
 610
 611   ;; Greek
 612   (modify-category-entry '(#x0370 . #x03ff) ?g)
 613   (setq c #x0370)
 614   (while (<= c #x03ff)
 615     (if (or (and (>= c #x0391) (<= c #x03a1))
 616             (and (>= c #x03a3) (<= c #x03ab)))
 617         (set-case-syntax-pair c (+ c 32) tbl))
 618     (and (>= c #x03da)
 619          (<= c #x03ee)
 620          (zerop (% c 2))
 621          (set-case-syntax-pair c (1+ c) tbl))
 622     (setq c (1+ c)))
 623   (set-case-syntax-pair ?Ά ?ά tbl)
 624   (set-case-syntax-pair ?Έ ?έ tbl)
 625   (set-case-syntax-pair ?Ή ?ή tbl)
 626   (set-case-syntax-pair ?Ί ?ί tbl)
 627   (set-case-syntax-pair ?Ό ?ό tbl)
 628   (set-case-syntax-pair ?Ύ ?ύ tbl)
 629   (set-case-syntax-pair ?Ώ ?ώ tbl)
 630
 631   ;; Armenian
 632   (setq c #x531)
 633   (while (<= c #x556)
 634     (set-case-syntax-pair c (+ c #x30) tbl)
 635     (setq c (1+ c)))
 636
 637   ;; Greek Extended
 638   (modify-category-entry '(#x1f00 . #x1fff) ?g)
 639   (setq c #x1f00)
 640   (while (<= c #x1fff)
 641     (and (<= (logand c #x000f) 7)
 642          (<= c #x1fa7)
 643          (not (memq c '(#x1f50 #x1f52 #x1f54 #x1f56)))
 644          (/= (logand c #x00f0) 7)
 645          (set-case-syntax-pair (+ c 8) c tbl))
 646     (setq c (1+ c)))
 647   (set-case-syntax-pair ?Ᾰ ?ᾰ tbl)
 648   (set-case-syntax-pair ?Ᾱ ?ᾱ tbl)
 649   (set-case-syntax-pair ?Ὰ ?ὰ tbl)
 650   (set-case-syntax-pair ?Ά ?ά tbl)
 651   (set-case-syntax-pair ?ᾼ ?ᾳ tbl)
 652   (set-case-syntax-pair ?Ὲ ?ὲ tbl)
 653   (set-case-syntax-pair ?Έ ?έ tbl)
 654   (set-case-syntax-pair ?Ὴ ?ὴ tbl)
 655   (set-case-syntax-pair ?Ή ?ή tbl)
 656   (set-case-syntax-pair ?ῌ ?ῃ tbl)
 657   (set-case-syntax-pair ?Ῐ ?ῐ tbl)
 658   (set-case-syntax-pair ?Ῑ ?ῑ tbl)
 659   (set-case-syntax-pair ?Ὶ ?ὶ tbl)
 660   (set-case-syntax-pair ?Ί ?ί tbl)
 661   (set-case-syntax-pair ?Ῠ ?ῠ tbl)
 662   (set-case-syntax-pair ?Ῡ ?ῡ tbl)
 663   (set-case-syntax-pair ?Ὺ ?ὺ tbl)
 664   (set-case-syntax-pair ?Ύ ?ύ tbl)
 665   (set-case-syntax-pair ?Ῥ ?ῥ tbl)
 666   (set-case-syntax-pair ?Ὸ ?ὸ tbl)
 667   (set-case-syntax-pair ?Ό ?ό tbl)
 668   (set-case-syntax-pair ?Ὼ ?ὼ tbl)
 669   (set-case-syntax-pair ?Ώ ?ώ tbl)
 670   (set-case-syntax-pair ?ῼ ?ῳ tbl)
 671
 672   ;; cyrillic
 673   (modify-category-entry '(#x0400 . #x04FF) ?y)
 674   (setq c #x0400)
 675   (while (<= c #x04ff)
 676     (and (>= c #x0400)
 677          (<= c #x040f)
 678          (set-case-syntax-pair c (+ c 80) tbl))
 679     (and (>= c #x0410)
 680          (<= c #x042f)
 681          (set-case-syntax-pair c (+ c 32) tbl))
 682     (and (zerop (% c 2))
 683          (or (and (>= c #x0460) (<= c #x0480))
 684              (and (>= c #x048c) (<= c #x04be))
 685              (and (>= c #x04d0) (<= c #x04f4)))
 686          (set-case-syntax-pair c (1+ c) tbl))
 687     (setq c (1+ c)))
 688   (set-case-syntax-pair ?Ӂ ?ӂ tbl)
 689   (set-case-syntax-pair ?Ӄ ?ӄ tbl)
 690   (set-case-syntax-pair ?Ӈ ?ӈ tbl)
 691   (set-case-syntax-pair ?Ӌ ?ӌ tbl)
 692   (set-case-syntax-pair ?Ӹ ?ӹ tbl)
 693
 694   ;; general punctuation
 695   (setq c #x2000)
 696   (while (<= c #x200b)
 697     (set-case-syntax c " " tbl)
 698     (setq c (1+ c)))
 699   (while (<= c #x200F)
 700     (set-case-syntax c "." tbl)
 701     (setq c (1+ c)))
 702   ;; Fixme: These aren't all right:
 703   (setq c #x2010)
 704   (while (<= c #x2016)
 705     (set-case-syntax c "_" tbl)
 706     (setq c (1+ c)))
 707   ;; Punctuation syntax for quotation marks (like `)
 708   (while (<= c #x201f)
 709     (set-case-syntax  c "." tbl)
 710     (setq c (1+ c)))
 711   ;; Fixme: These aren't all right:
 712   (while (<= c #x2027)
 713     (set-case-syntax c "_" tbl)
 714     (setq c (1+ c)))
 715   (while (<= c #x206F)
 716     (set-case-syntax c "." tbl)
 717     (setq c (1+ c)))
 718
 719   ;; Roman numerals
 720   (setq c #x2160)
 721   (while (<= c #x216f)
 722     (set-case-syntax-pair c (+ c #x10) tbl)
 723     (setq c (1+ c)))
 724
 725   ;; Fixme: The following blocks might be better as symbol rather than
 726   ;; punctuation.
 727   ;; Arrows
 728   (setq c #x2190)
 729   (while (<= c #x21FF)
 730     (set-case-syntax c "." tbl)
 731     (setq c (1+ c)))
 732   ;; Mathematical Operators
 733   (while (<= c #x22FF)
 734     (set-case-syntax c "." tbl)
 735     (setq c (1+ c)))
 736   ;; Miscellaneous Technical
 737   (while (<= c #x23FF)
 738     (set-case-syntax c "." tbl)
 739     (setq c (1+ c)))
 740   ;; Control Pictures
 741   (while (<= c #x243F)
 742     (set-case-syntax c "_" tbl)
 743     (setq c (1+ c)))
 744
 745   ;; Circled Latin
 746   (setq c #x24b6)
 747   (while (<= c #x24cf)
 748     (set-case-syntax-pair c (+ c 26) tbl)
 749     (modify-category-entry c ?l)
 750     (modify-category-entry (+ c 26) ?l)
 751     (setq c (1+ c)))
 752
 753   ;; Fullwidth Latin
 754   (setq c #xff21)
 755   (while (<= c #xff3a)
 756     (set-case-syntax-pair c (+ c #x20) tbl)
 757     (modify-category-entry c ?l)
 758     (modify-category-entry (+ c #x20) ?l)
 759     (setq c (1+ c)))
 760
 761   ;; Combining diacritics
 762   (modify-category-entry '(#x300 . #x362) ?^)
 763   ;; Combining marks
 764   (modify-category-entry '(#x20d0 . #x20e3) ?^)
 765
 766   ;; Fixme: syntax for symbols &c
 767   )
 768
 769 (let ((pairs
 770        '("⁅⁆"                               ; U+2045 U+2046
 771          "⁽⁾"                               ; U+207D U+207E
 772          "₍₎"                               ; U+208D U+208E
 773          "〈〉"                               ; U+2329 U+232A
 774          "⎴⎵"                               ; U+23B4 U+23B5
 775          "❨❩"                               ; U+2768 U+2769
 776          "❪❫"                               ; U+276A U+276B
 777          "❬❭"                               ; U+276C U+276D
 778          "❰❱"                               ; U+2770 U+2771
 779          "❲❳"                               ; U+2772 U+2773
 780          "❴❵"                               ; U+2774 U+2775
 781          "⟦⟧"                               ; U+27E6 U+27E7
 782          "⟨⟩"                               ; U+27E8 U+27E9
 783          "⟪⟫"                               ; U+27EA U+27EB
 784          "⦃⦄"                               ; U+2983 U+2984
 785          "⦅⦆"                               ; U+2985 U+2986
 786          "⦇⦈"                               ; U+2987 U+2988
 787          "⦉⦊"                               ; U+2989 U+298A
 788          "⦋⦌"                               ; U+298B U+298C
 789          "⦍⦎"                               ; U+298D U+298E
 790          "⦏⦐"                               ; U+298F U+2990
 791          "⦑⦒"                               ; U+2991 U+2992
 792          "⦓⦔"                               ; U+2993 U+2994
 793          "⦕⦖"                               ; U+2995 U+2996
 794          "⦗⦘"                               ; U+2997 U+2998
 795          "⧼⧽"                               ; U+29FC U+29FD
 796          "〈〉"                               ; U+3008 U+3009
 797          "《》"                               ; U+300A U+300B
 798          "「」"                               ; U+300C U+300D
 799          "『』"                               ; U+300E U+300F
 800          "【】"                               ; U+3010 U+3011
 801          "〔〕"                               ; U+3014 U+3015
 802          "〖〗"                               ; U+3016 U+3017
 803          "〘〙"                               ; U+3018 U+3019
 804          "〚〛"                               ; U+301A U+301B
 805          "﴾﴿"                               ; U+FD3E U+FD3F
 806          "︵︶"                               ; U+FE35 U+FE36
 807          "︷︸"                               ; U+FE37 U+FE38
 808          "︹︺"                               ; U+FE39 U+FE3A
 809          "︻︼"                               ; U+FE3B U+FE3C
 810          "︽︾"                               ; U+FE3D U+FE3E
 811          "︿﹀"                               ; U+FE3F U+FE40
 812          "﹁﹂"                               ; U+FE41 U+FE42
 813          "﹃﹄"                               ; U+FE43 U+FE44
 814          "﹙﹚"                               ; U+FE59 U+FE5A
 815          "﹛﹜"                               ; U+FE5B U+FE5C
 816          "﹝﹞"                               ; U+FE5D U+FE5E
 817          "（）"                               ; U+FF08 U+FF09
 818          "［］"                               ; U+FF3B U+FF3D
 819          "｛｝"                               ; U+FF5B U+FF5D
 820          "｟｠"                               ; U+FF5F U+FF60
 821          "｢｣"                               ; U+FF62 U+FF63
 822          )))
 823   (dolist (elt pairs)
 824     (modify-syntax-entry (aref elt 0) (string ?\( (aref elt 1)))
 825     (modify-syntax-entry (aref elt 1) (string ?\) (aref elt 0)))))
 826
 827 \f
 828 ;; For each character set, put the information of the most proper
 829 ;; coding system to encode it by `preferred-coding-system' property.
 830
 831 ;; Fixme: should this be junked?
 832 (let ((l '((latin-iso8859-1     . iso-latin-1)
 833            (latin-iso8859-2     . iso-latin-2)
 834            (latin-iso8859-3     . iso-latin-3)
 835            (latin-iso8859-4     . iso-latin-4)
 836            (thai-tis620         . thai-tis620)
 837            (greek-iso8859-7     . greek-iso-8bit)
 838            (arabic-iso8859-6    . iso-2022-7bit)
 839            (hebrew-iso8859-8    . hebrew-iso-8bit)
 840            (katakana-jisx0201   . japanese-shift-jis)
 841            (latin-jisx0201      . japanese-shift-jis)
 842            (cyrillic-iso8859-5  . cyrillic-iso-8bit)
 843            (latin-iso8859-9     . iso-latin-5)
 844            (japanese-jisx0208-1978 . iso-2022-jp)
 845            (chinese-gb2312      . chinese-iso-8bit)
 846            (chinese-gbk         . chinese-gbk)
 847            (gb18030-2-byte      . chinese-gb18030)
 848            (gb18030-4-byte-bmp  . chinese-gb18030)
 849            (gb18030-4-byte-smp  . chinese-gb18030)
 850            (gb18030-4-byte-ext-1 . chinese-gb18030)
 851            (gb18030-4-byte-ext-2 . chinese-gb18030)
 852            (japanese-jisx0208   . iso-2022-jp)
 853            (korean-ksc5601      . iso-2022-kr)
 854            (japanese-jisx0212   . iso-2022-jp)
 855            (chinese-big5-1      . chinese-big5)
 856            (chinese-big5-2      . chinese-big5)
 857            (chinese-sisheng     . iso-2022-7bit)
 858            (ipa                 . iso-2022-7bit)
 859            (vietnamese-viscii-lower . vietnamese-viscii)
 860            (vietnamese-viscii-upper . vietnamese-viscii)
 861            (arabic-digit        . iso-2022-7bit)
 862            (arabic-1-column     . iso-2022-7bit)
 863            (lao                 . lao)
 864            (arabic-2-column     . iso-2022-7bit)
 865            (indian-is13194      . devanagari)
 866            (indian-glyph        . devanagari)
 867            (tibetan-1-column    . tibetan)
 868            (ethiopic            . iso-2022-7bit)
 869            (chinese-cns11643-1  . iso-2022-cn)
 870            (chinese-cns11643-2  . iso-2022-cn)
 871            (chinese-cns11643-3  . iso-2022-cn)
 872            (chinese-cns11643-4  . iso-2022-cn)
 873            (chinese-cns11643-5  . iso-2022-cn)
 874            (chinese-cns11643-6  . iso-2022-cn)
 875            (chinese-cns11643-7  . iso-2022-cn)
 876            (indian-2-column     . devanagari)
 877            (tibetan             . tibetan)
 878            (latin-iso8859-14    . iso-latin-8)
 879            (latin-iso8859-15    . iso-latin-9))))
 880   (while l
 881     (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
 882     (setq l (cdr l))))
 883
 884 \f
 885 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
 886 ;; SPACE and NEWLINE are already set.
 887
 888 (set-char-table-range auto-fill-chars '(#x3041 . #x30FF) t)
 889 (set-char-table-range auto-fill-chars '(#x3400 . #x4DB5) t)
 890 (set-char-table-range auto-fill-chars '(#x4e00 . #x9fbb) t)
 891 (set-char-table-range auto-fill-chars '(#xF900 . #xFAFF) t)
 892 (set-char-table-range auto-fill-chars '(#xFF00 . #xFF9F) t)
 893 (set-char-table-range auto-fill-chars '(#x20000 . #x2FFFF) t)
 894
 895 \f
 896 ;;; Setting char-width-table.  The default is 1.
 897
 898 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
 899 ;;    and final characters.
 900 (let ((l '((#x00AD . #x00AD)
 901            (#x0300 . #x036F)
 902            (#x0483 . #x0489)
 903            (#x0591 . #x05BD)
 904            (#x05BF . #x05BF)
 905            (#x05C1 . #x05C2)
 906            (#x05C4 . #x05C5)
 907            (#x05C7 . #x05C7)
 908            (#x0600 . #x0603)
 909            (#x0610 . #x0615)
 910            (#x064B . #x065E)
 911            (#x0670 . #x0670)
 912            (#x06D6 . #x06E4)
 913            (#x06E7 . #x06E8)
 914            (#x06EA . #x06ED)
 915            (#x070F . #x070F)
 916            (#x0711 . #x0711)
 917            (#x0730 . #x074A)
 918            (#x07A6 . #x07B0)
 919            (#x07EB . #x07F3)
 920            (#x0901 . #x0902)
 921            (#x093C . #x093C)
 922            (#x0941 . #x0948)
 923            (#x094D . #x094D)
 924            (#x0951 . #x0954)
 925            (#x0962 . #x0963)
 926            (#x0981 . #x0981)
 927            (#x09BC . #x09BC)
 928            (#x09C1 . #x09C4)
 929            (#x09CD . #x09CD)
 930            (#x09E2 . #x09E3)
 931            (#x0A01 . #x0A02)
 932            (#x0A3C . #x0A3C)
 933            (#x0A41 . #x0A4D)
 934            (#x0A70 . #x0A71)
 935            (#x0A81 . #x0A82)
 936            (#x0ABC . #x0ABC)
 937            (#x0AC1 . #x0AC8)
 938            (#x0ACD . #x0ACD)
 939            (#x0AE2 . #x0AE3)
 940            (#x0B01 . #x0B01)
 941            (#x0B3C . #x0B3C)
 942            (#x0B3F . #x0B3F)
 943            (#x0B41 . #x0B43)
 944            (#x0B4D . #x0B56)
 945            (#x0B82 . #x0B82)
 946            (#x0BC0 . #x0BC0)
 947            (#x0BCD . #x0BCD)
 948            (#x0C3E . #x0C40)
 949            (#x0C46 . #x0C56)
 950            (#x0CBC . #x0CBC)
 951            (#x0CBF . #x0CBF)
 952            (#x0CC6 . #x0CC6)
 953            (#x0CCC . #x0CCD)
 954            (#x0CE2 . #x0CE3)
 955            (#x0D41 . #x0D43)
 956            (#x0D4D . #x0D4D)
 957            (#x0DCA . #x0DCA)
 958            (#x0DD2 . #x0DD6)
 959            (#x0E31 . #x0E31)
 960            (#x0E34 . #x0E3A)
 961            (#x0E47 . #x0E4E)
 962            (#x0EB1 . #x0EB1)
 963            (#x0EB4 . #x0EBC)
 964            (#x0EC8 . #x0ECD)
 965            (#x0F18 . #x0F19)
 966            (#x0F35 . #x0F35)
 967            (#x0F37 . #x0F37)
 968            (#x0F39 . #x0F39)
 969            (#x0F71 . #x0F7E)
 970            (#x0F80 . #x0F84)
 971            (#x0F86 . #x0F87)
 972            (#x0F90 . #x0FBC)
 973            (#x0FC6 . #x0FC6)
 974            (#x102D . #x1030)
 975            (#x1032 . #x1037)
 976            (#x1039 . #x1039)
 977            (#x1058 . #x1059)
 978            (#x1160 . #x11FF)
 979            (#x135F . #x135F)
 980            (#x1712 . #x1714)
 981            (#x1732 . #x1734)
 982            (#x1752 . #x1753)
 983            (#x1772 . #x1773)
 984            (#x17B4 . #x17B5)
 985            (#x17B7 . #x17BD)
 986            (#x17C6 . #x17C6)
 987            (#x17C9 . #x17D3)
 988            (#x17DD . #x17DD)
 989            (#x180B . #x180D)
 990            (#x18A9 . #x18A9)
 991            (#x1920 . #x1922)
 992            (#x1927 . #x1928)
 993            (#x1932 . #x1932)
 994            (#x1939 . #x193B)
 995            (#x1A17 . #x1A18)
 996            (#x1B00 . #x1B03)
 997            (#x1B34 . #x1B34)
 998            (#x1B36 . #x1B3A)
 999            (#x1B3C . #x1B3C)
1000            (#x1B42 . #x1B42)
1001            (#x1B6B . #x1B73)
1002            (#x1DC0 . #x1DFF)
1003            (#x200B . #x200F)
1004            (#x202A . #x202E)
1005            (#x2060 . #x206F)
1006            (#x20D0 . #x20EF)
1007            (#x302A . #x302F)
1008            (#x3099 . #x309A)
1009            (#xA806 . #xA806)
1010            (#xA80B . #xA80B)
1011            (#xA825 . #xA826)
1012            (#xFB1E . #xFB1E)
1013            (#xFE00 . #xFE0F)
1014            (#xFE20 . #xFE23)
1015            (#xFEFF . #xFEFF)
1016            (#xFFF9 . #xFFFB)
1017            (#x10A01 . #x10A0F)
1018            (#x10A38 . #x10A3F)
1019            (#x1D167 . #x1D169)
1020            (#x1D173 . #x1D182)
1021            (#x1D185 . #x1D18B)
1022            (#x1D1AA . #x1D1AD)
1023            (#x1D242 . #x1D244)
1024            (#xE0001 . #xE01EF))))
1025   (dolist (elt l)
1026     (set-char-table-range char-width-table elt 0)))
1027
1028 ;; 2: East Asian Wide and Full-width characters.
1029 (let ((l '((#x1100 . #x115F)
1030            (#x2329 . #x232A)
1031            (#x2E80 . #x303E)
1032            (#x3040 . #xA4CF)
1033            (#xAC00 . #xD7A3)
1034            (#xF900 . #xFAFF)
1035            (#xFE30 . #xFE6F)
1036            (#xFF01 . #xFF60)
1037            (#xFFE0 . #xFFE6)
1038            (#x20000 . #x2FFFF)
1039            (#x30000 . #x3FFFF))))
1040   (dolist (elt l)
1041     (set-char-table-range char-width-table elt 2)))
1042
1043 ;; Other double width
1044 ;;(map-charset-chars
1045 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1046 ;; 'ethiopic)
1047 ;; (map-charset-chars
1048 ;;  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1049 ;; 'tibetan)
1050 (map-charset-chars
1051  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1052  'indian-2-column)
1053 (map-charset-chars
1054  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1055  'arabic-2-column)
1056
1057 (optimize-char-table (standard-case-table))
1058 (optimize-char-table (standard-category-table))
1059 (optimize-char-table (standard-syntax-table))
1060
1061 ;; The Unicode blocks actually extend past some of these ranges with
1062 ;; undefined codepoints.
1063 (let ((script-list nil))
1064   (dolist
1065       (elt
1066        '((#x0000 #x007F latin)
1067          (#x00A0 #x036F latin)
1068          (#x0370 #x03E1 greek)
1069          (#x03E2 #x03EF coptic)
1070          (#x03F0 #x03F3 greek)
1071          (#x0400 #x04FF cyrillic)
1072          (#x0530 #x058F armenian)
1073          (#x0590 #x05FF hebrew)
1074          (#x0600 #x06FF arabic)
1075          (#x0700 #x074F syriac)
1076          (#x07C0 #x07FA nko)
1077          (#x0780 #x07BF thaana)
1078          (#x0900 #x097F devanagari)
1079          (#x0980 #x09FF bengali)
1080          (#x0A00 #x0A7F gurmukhi)
1081          (#x0A80 #x0AFF gujarati)
1082          (#x0B00 #x0B7F oriya)
1083          (#x0B80 #x0BFF tamil)
1084          (#x0C00 #x0C7F telugu)
1085          (#x0C80 #x0CFF kannada)
1086          (#x0D00 #x0D7F malayalam)
1087          (#x0D80 #x0DFF sinhala)
1088          (#x0E00 #x0E5F thai)
1089          (#x0E80 #x0EDF lao)
1090          (#x0F00 #x0FFF tibetan)
1091          (#x1000 #x105F myanmar)
1092          (#x10A0 #x10FF georgian)
1093          (#x1100 #x11FF hangul)
1094          (#x1200 #x139F ethiopic)
1095          (#x13A0 #x13FF cherokee)
1096          (#x1400 #x167F canadian-aboriginal)
1097          (#x1680 #x169F ogham)
1098          (#x16A0 #x16FF runic)
1099          (#x1780 #x17FF khmer)
1100          (#x1800 #x18AF mongolian)
1101          (#x1E00 #x1EFF latin)
1102          (#x1F00 #x1FFF greek)
1103          (#x2000 #x27FF symbol)
1104          (#x2800 #x28FF braille)
1105          (#x2D80 #x2DDF ethiopic)
1106          (#x2E80 #x2FDF han)
1107          (#x2FF0 #x2FFF ideographic-description)
1108          (#x3000 #x303F cjk-misc)
1109          (#x3040 #x30FF kana)
1110          (#x3100 #x312F bopomofo)
1111          (#x3130 #x318F hangul)
1112          (#x3190 #x319F kanbun)
1113          (#x31A0 #x31BF bopomofo)
1114          (#x3400 #x9FAF han)
1115          (#xA000 #xA4CF yi)
1116          (#xAC00 #xD7AF hangul)
1117          (#xF900 #xFAFF han)
1118          (#xFB1D #xFB4F hebrew)
1119          (#xFB50 #xFDFF arabic)
1120          (#xFE70 #xFEFC arabic)
1121          (#xFF00 #xFF5F cjk-misc)
1122          (#xFF61 #xFF9F kana)
1123          (#xFFE0 #xFFE6 cjk-misc)
1124          (#x1D000 #x1D0FF byzantine-musical-symbol)
1125          (#x1D100 #x1D1FF musical-symbol)
1126          (#x1D400 #x1D7FF mathematical)
1127          (#x20000 #x2AFFF han)
1128          (#x2F800 #x2FFFF han)))
1129     (set-char-table-range char-script-table
1130                           (cons (car elt) (nth 1 elt)) (nth 2 elt))
1131     (or (memq (nth 2 elt) script-list)
1132         (setq script-list (cons (nth 2 elt) script-list))))
1133   (set-char-table-extra-slot char-script-table 0 (nreverse script-list)))
1134
1135 (map-charset-chars
1136  #'(lambda (range ignore)
1137      (set-char-table-range char-script-table range 'tibetan))
1138  'tibetan)
1139
1140 \f
1141 ;;; Setting word boundary.
1142
1143 (defun next-word-boundary-han (pos limit)
1144   (if (<= pos limit)
1145       (save-excursion
1146         (goto-char pos)
1147         (looking-at "\\cC+")
1148         (goto-char (match-end 0))
1149         (if (looking-at "\\cH+")
1150             (goto-char (match-end 0)))
1151         (point))
1152     (while (and (> pos limit)
1153                 (eq (aref char-script-table (char-after (1- pos))) 'han))
1154       (setq pos (1- pos)))
1155     pos))
1156
1157 (defun next-word-boundary-kana (pos limit)
1158   (if (<= pos limit)
1159       (save-excursion
1160         (goto-char pos)
1161         (if (looking-at "\\cK+")
1162             (goto-char (match-end 0)))
1163         (if (looking-at "\\cH+")
1164             (goto-char (match-end 0)))
1165         (if (looking-at "\\ck+")
1166             (goto-char (match-end 0)))
1167         (point))
1168     (let ((category-set (char-category-set (char-after pos)))
1169           category)
1170       (if (or (aref category-set ?K) (aref category-set ?k))
1171           (while (and (> pos limit)
1172                       (setq category-set
1173                             (char-category-set (char-after (1- pos))))
1174                       (or (aref category-set ?K) (aref category-set ?k)))
1175             (setq pos (1- pos)))
1176         (while (and (> pos limit)
1177                     (aref (setq category-set
1178                                 (char-category-set (char-after (1- pos)))) ?H))
1179           (setq pos (1- pos)))
1180         (setq category (cond ((aref category-set ?C) ?C)
1181                              ((aref category-set ?K) ?K)
1182                              ((aref category-set ?A) ?A)))
1183         (when category
1184           (setq pos (1- pos))
1185           (while (and (> pos limit)
1186                       (aref (char-category-set (char-after (1- pos)))
1187                             category))
1188             (setq pos (1- pos)))))
1189       pos)))
1190
1191 (map-char-table
1192  #'(lambda (char script)
1193      (cond ((eq script 'han)
1194             (set-char-table-range find-word-boundary-function-table
1195                                   char #'next-word-boundary-han))
1196            ((eq script 'kana)
1197             (set-char-table-range find-word-boundary-function-table
1198                                   char #'next-word-boundary-kana))))
1199  char-script-table)
1200
1201 (setq word-combining-categories
1202       '((?l . ?l)
1203         (?C . ?C)
1204         (?C . ?H)
1205         (?C . ?K)))
1206
1207 (setq word-separating-categories        ;  (2-byte character sets)
1208       '((?A . ?K)                       ; Alpha numeric - Katakana
1209         (?A . ?C)                       ; Alpha numeric - Chinese
1210         (?H . ?A)                       ; Hiragana - Alpha numeric
1211         (?H . ?K)                       ; Hiragana - Katakana
1212         (?H . ?C)                       ; Hiragana - Chinese
1213         (?K . ?A)                       ; Katakana - Alpha numeric
1214         (?K . ?C)                       ; Katakana - Chinese
1215         (?C . ?A)                       ; Chinese - Alpha numeric
1216         (?C . ?K)                       ; Chinese - Katakana
1217         ))
1218
1219 ;;; Local Variables:
1220 ;;; coding: utf-8-emacs
1221 ;;; End:
1222
1223 ;;; arch-tag: 85889c35-9f4d-4912-9bf5-82de31b0d42d
1224 ;;; characters.el ends here