lisp/international/characters.el

   1 ;;; characters.el --- set syntax and category for multibyte characters
   2
   3 ;; Copyright (C) 1995, 1997 Electrotechnical Laboratory, JAPAN.
   4 ;; Licensed to the Free Software Foundation.
   5 ;; Copyright (C) 2001, 2002 Free Software Foundation, Inc.
   6 ;; Copyright (C) 2001, 2002
   7 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   8 ;;   Registration Number H13PRO009
   9
  10 ;; Keywords: multibyte character, character set, syntax, category
  11
  12 ;; This file is part of GNU Emacs.
  13
  14 ;; GNU Emacs is free software; you can redistribute it and/or modify
  15 ;; it under the terms of the GNU General Public License as published by
  16 ;; the Free Software Foundation; either version 2, or (at your option)
  17 ;; any later version.
  18
  19 ;; GNU Emacs is distributed in the hope that it will be useful,
  20 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  21 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  22 ;; GNU General Public License for more details.
  23
  24 ;; You should have received a copy of the GNU General Public License
  25 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  26 ;; Free Software Foundation, Inc., 59 Temple Place - Suite 330,
  27 ;; Boston, MA 02111-1307, USA.
  28
  29 ;;; Commentary:
  30
  31 ;; This file contains multibyte characters.  Save this file always in
  32 ;; the coding system `iso-2022-7bit'.
  33
  34 ;; This file does not define the syntax for Latin-N character sets;
  35 ;; those are defined by the files latin-N.el.
  36
  37 ;;; Code:
  38
  39 ;;; Predefined categories.
  40
  41 ;; For each character set.
  42
  43 (define-category ?a "ASCII")
  44 (define-category ?l "Latin")
  45 (define-category ?t "Thai")
  46 (define-category ?g "Greek")
  47 (define-category ?b "Arabic")
  48 (define-category ?w "Hebrew")
  49 (define-category ?y "Cyrillic")
  50 (define-category ?k "Japanese katakana")
  51 (define-category ?r "Japanese roman")
  52 (define-category ?c "Chinese")
  53 (define-category ?j "Japanese")
  54 (define-category ?h "Korean")
  55 (define-category ?e "Ethiopic (Ge'ez)")
  56 (define-category ?v "Vietnamese")
  57 (define-category ?i "Indian")
  58 (define-category ?o "Lao")
  59 (define-category ?q "Tibetan")
  60
  61 ;; For each group (row) of 2-byte character sets.
  62
  63 (define-category ?A "Alpha-numeric characters of 2-byte character sets")
  64 (define-category ?C "Chinese (Han) characters of 2-byte character sets")
  65 (define-category ?G "Greek characters of 2-byte character sets")
  66 (define-category ?H "Japanese Hiragana characters of 2-byte character sets")
  67 (define-category ?K "Japanese Katakana characters of 2-byte character sets")
  68 (define-category ?N "Korean Hangul characters of 2-byte character sets")
  69 (define-category ?Y "Cyrillic characters of 2-byte character sets")
  70 (define-category ?I "Indian Glyphs")
  71
  72 ;; For phonetic classifications.
  73
  74 (define-category ?0 "consonant")
  75 (define-category ?1 "base (independent) vowel")
  76 (define-category ?2 "upper diacritical mark (including upper vowel)")
  77 (define-category ?3 "lower diacritical mark (including lower vowel)")
  78 (define-category ?4 "tone mark")
  79 (define-category ?5 "symbol")
  80 (define-category ?6 "digit")
  81 (define-category ?7 "vowel-modifying diacritical mark")
  82 (define-category ?8 "vowel-signs")
  83 (define-category ?9 "semivowel lower")
  84
  85 ;; For filling.
  86 (define-category ?| "While filling, we can break a line at this character.")
  87
  88 ;; For indentation calculation.
  89 (define-category ?
  90   "This character counts as a space for indentation purposes.")
  91
  92 ;; Keep the following for `kinsoku' processing.  See comments in
  93 ;; kinsoku.el.
  94 (define-category ?> "A character which can't be placed at beginning of line.")
  95 (define-category ?< "A character which can't be placed at end of line.")
  96
  97 ;; Combining
  98 (define-category ?^ "Combining diacritic or mark")
  99 \f
 100 ;;; Setting syntax and category.
 101
 102 ;; ASCII
 103
 104 ;; All ASCII characters have the category `a' (ASCII) and `l' (Latin).
 105 (modify-category-entry '(32 . 127) ?a)
 106 (modify-category-entry '(32 . 127) ?l)
 107
 108 ;; Arabic character set
 109
 110 (let ((charsets '(arabic-iso8859-6
 111                   arabic-digit
 112                   arabic-1-column
 113                   arabic-2-column)))
 114   (while charsets
 115     (map-charset-chars #'modify-category-entry (car charsets) ?b)
 116     (setq charsets (cdr charsets))))
 117 (modify-category-entry '(#x600 . #x6ff) ?b)
 118 (modify-category-entry '(#xfb50 . #xfdff) ?b)
 119 (modify-category-entry '(#xfe70 . #xfefe) ?b)
 120
 121 ;; Chinese characters (Unicode)
 122 (modify-category-entry '(#x3400 . #x9FAF) ?C)
 123 (modify-category-entry '(#x3400 . #x9FAF) ?c)
 124 (modify-category-entry '(#x3400 . #x9FAF) ?|)
 125 (modify-category-entry '(#xF900 . #xFAFF) ?C)
 126 (modify-category-entry '(#xF900 . #xFAFF) ?c)
 127 (modify-category-entry '(#xF900 . #xFAFF) ?|)
 128
 129 ;; Chinese character set (GB2312)
 130
 131 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2121 #x217E)
 132 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2221 #x227E)
 133 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2921 #x297E)
 134 (modify-syntax-entry ?\〔 "(〕")
 135 (modify-syntax-entry ?\〈 "(〉")
 136 (modify-syntax-entry ?\《 "(》")
 137 (modify-syntax-entry ?\「 "(」")
 138 (modify-syntax-entry ?\『 "(』")
 139 (modify-syntax-entry ?\〖 "(〗")
 140 (modify-syntax-entry ?\【 "(】")
 141 (modify-syntax-entry ?\〕 ")〔")
 142 (modify-syntax-entry ?\〉 ")〈")
 143 (modify-syntax-entry ?\》 ")《")
 144 (modify-syntax-entry ?\」 ")「")
 145 (modify-syntax-entry ?\』 ")『")
 146 (modify-syntax-entry ?\〗 ")〖")
 147 (modify-syntax-entry ?\】 ")【")
 148
 149 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?c)
 150 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?|)
 151 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2330 #x2339)
 152 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2341 #x235A)
 153 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2361 #x237A)
 154 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?H #x2421 #x247E)
 155 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?K #x2521 #x257E)
 156 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?G #x2621 #x267E)
 157 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?Y #x2721 #x277E)
 158 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?C #x3021 #x7E7E)
 159
 160 ;; Chinese character set (BIG5)
 161
 162 (map-charset-chars #'modify-category-entry 'big5 ?c)
 163 (map-charset-chars #'modify-category-entry 'big5 ?C #xA259 #xA25F)
 164 (map-charset-chars #'modify-category-entry 'big5 ?C #xA440 #xC67E)
 165 (map-charset-chars #'modify-category-entry 'big5 ?C #xC940 #xF9DF)
 166 (map-charset-chars #'modify-category-entry 'big5 ?|)
 167
 168
 169 ;; Chinese character set (CNS11643)
 170
 171 (dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
 172              chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
 173              chinese-cns11643-7))
 174   (map-charset-chars #'modify-category-entry c ?c)
 175   (if (eq c 'chinese-cns11643-1)
 176       (map-charset-chars #'modify-category-entry c ?C #x4421 #x7E7E)
 177     (map-charset-chars #'modify-category-entry c ?C))
 178   (map-charset-chars #'modify-category-entry c ?|))
 179
 180 ;; Cyrillic character set (ISO-8859-5)
 181
 182 (modify-syntax-entry ?№ ".")
 183 (let ((tbl (standard-case-table)))
 184   (set-case-syntax-pair ?Ё ?ё tbl)
 185   (set-case-syntax-pair ?Ђ ?ђ tbl)
 186   (set-case-syntax-pair ?Ѓ ?ѓ tbl)
 187   (set-case-syntax-pair ?Є ?є tbl)
 188   (set-case-syntax-pair ?Ѕ ?ѕ tbl)
 189   (set-case-syntax-pair ?І ?і tbl)
 190   (set-case-syntax-pair ?Ї ?ї tbl)
 191   (set-case-syntax-pair ?Ј ?ј tbl)
 192   (set-case-syntax-pair ?Љ ?љ tbl)
 193   (set-case-syntax-pair ?Њ ?њ tbl)
 194   (set-case-syntax-pair ?Ћ ?ћ tbl)
 195   (set-case-syntax-pair ?Ќ ?ќ tbl)
 196   (set-case-syntax-pair ?Ў ?ў tbl)
 197   (set-case-syntax-pair ?Џ ?џ tbl)
 198   (set-case-syntax-pair ?А ?а tbl)
 199   (set-case-syntax-pair ?Б ?б tbl)
 200   (set-case-syntax-pair ?В ?в tbl)
 201   (set-case-syntax-pair ?Г ?г tbl)
 202   (set-case-syntax-pair ?Д ?д tbl)
 203   (set-case-syntax-pair ?Е ?е tbl)
 204   (set-case-syntax-pair ?Ж ?ж tbl)
 205   (set-case-syntax-pair ?З ?з tbl)
 206   (set-case-syntax-pair ?И ?и tbl)
 207   (set-case-syntax-pair ?Й ?й tbl)
 208   (set-case-syntax-pair ?К ?к tbl)
 209   (set-case-syntax-pair ?Л ?л tbl)
 210   (set-case-syntax-pair ?М ?м tbl)
 211   (set-case-syntax-pair ?Н ?н tbl)
 212   (set-case-syntax-pair ?О ?о tbl)
 213   (set-case-syntax-pair ?П ?п tbl)
 214   (set-case-syntax-pair ?Р ?р tbl)
 215   (set-case-syntax-pair ?С ?с tbl)
 216   (set-case-syntax-pair ?Т ?т tbl)
 217   (set-case-syntax-pair ?У ?у tbl)
 218   (set-case-syntax-pair ?Ф ?ф tbl)
 219   (set-case-syntax-pair ?Х ?х tbl)
 220   (set-case-syntax-pair ?Ц ?ц tbl)
 221   (set-case-syntax-pair ?Ч ?ч tbl)
 222   (set-case-syntax-pair ?Ш ?ш tbl)
 223   (set-case-syntax-pair ?Щ ?щ tbl)
 224   (set-case-syntax-pair ?Ъ ?ъ tbl)
 225   (set-case-syntax-pair ?Ы ?ы tbl)
 226   (set-case-syntax-pair ?Ь ?ь tbl)
 227   (set-case-syntax-pair ?Э ?э tbl)
 228   (set-case-syntax-pair ?Ю ?ю tbl)
 229   (set-case-syntax-pair ?Я ?я tbl))
 230
 231 ;; Ethiopic character set
 232
 233 (modify-category-entry '(#x1200 . #x137b) ?e)
 234 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨ ?���� ?���� ?���� ?���� ?���� ?����)))
 235   (while chars
 236     (modify-syntax-entry (car chars) ".")
 237     (setq chars (cdr chars))))
 238 (map-charset-chars #'modify-category-entry 'ethiopic ?e)
 239
 240 ;; Greek character set (ISO-8859-7)
 241
 242 (modify-category-entry '(#x370 . #x3ff) ?g)
 243
 244 (let ((tbl (standard-case-table)))
 245   (set-case-syntax-pair ?Α ?α tbl)
 246   (set-case-syntax-pair ?Β ?β tbl)
 247   (set-case-syntax-pair ?Γ ?γ tbl)
 248   (set-case-syntax-pair ?Δ ?δ tbl)
 249   (set-case-syntax-pair ?Ε ?ε tbl)
 250   (set-case-syntax-pair ?Ζ ?ζ tbl)
 251   (set-case-syntax-pair ?Η ?η tbl)
 252   (set-case-syntax-pair ?Θ ?θ tbl)
 253   (set-case-syntax-pair ?Ι ?ι tbl)
 254   (set-case-syntax-pair ?Κ ?κ tbl)
 255   (set-case-syntax-pair ?Λ ?λ tbl)
 256   (set-case-syntax-pair ?Μ ?μ tbl)
 257   (set-case-syntax-pair ?Ν ?ν tbl)
 258   (set-case-syntax-pair ?Ξ ?ξ tbl)
 259   (set-case-syntax-pair ?Ο ?ο tbl)
 260   (set-case-syntax-pair ?Π ?π tbl)
 261   (set-case-syntax-pair ?Ρ ?ρ tbl)
 262   (set-case-syntax-pair ?Σ ?σ tbl)
 263   (set-case-syntax-pair ?Τ ?τ tbl)
 264   (set-case-syntax-pair ?Υ ?υ tbl)
 265   (set-case-syntax-pair ?Φ ?φ tbl)
 266   (set-case-syntax-pair ?Χ ?χ tbl)
 267   (set-case-syntax-pair ?Ψ ?ψ tbl)
 268   (set-case-syntax-pair ?Ω ?ω tbl)
 269   (set-case-syntax-pair ?Ϊ ?ϊ tbl)
 270   (set-case-syntax-pair ?Ϋ ?ϋ tbl)
 271   (set-case-syntax-pair ?Ώ ?ώ tbl)
 272   (set-case-syntax-pair ?Ύ ?ύ tbl)
 273   (set-case-syntax-pair ?Ό ?ό tbl)
 274   (set-case-syntax-pair ?Ά ?ά tbl)
 275   (set-case-syntax-pair ?Έ ?έ tbl)
 276   (set-case-syntax-pair ?Ή ?ή tbl)
 277   (set-case-syntax-pair ?Ί ?ί tbl))
 278
 279 ;; Hebrew character set (ISO-8859-8)
 280
 281 (modify-syntax-entry #x5be ".") ; MAQAF
 282 (modify-syntax-entry #x5c0 ".") ; PASEQ
 283 (modify-syntax-entry #x5c3 ".") ; SOF PASUQ
 284 (modify-syntax-entry #x5f3 ".") ; GERESH
 285 (modify-syntax-entry #x5f4 ".") ; GERSHAYIM
 286
 287 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
 288
 289 (modify-category-entry '(#x901 . #x970) ?i)
 290 (map-charset-chars #'modify-category-entry 'indian-is13194 ?i)
 291 (map-charset-chars #'modify-category-entry 'indian-2-column ?i)
 292
 293
 294 ;; Japanese character set (JISX0201-kana, JISX0201-roman, JISX0208, JISX0212)
 295
 296 (map-charset-chars #'modify-category-entry 'katakana-jisx0201 ?k)
 297
 298 (map-charset-chars #'modify-category-entry 'latin-jisx0201 ?r)
 299
 300 (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212))
 301   (map-charset-chars #'modify-category-entry l ?j)
 302   (map-charset-chars #'modify-category-entry l ?\|))
 303
 304 ;; Unicode equivalents of JISX0201-kana
 305 (let ((range '(#xff61 . #xff9f)))
 306   (modify-category-entry range  ?k)
 307   (modify-category-entry range ?j)
 308   (modify-category-entry range ?\|))
 309
 310 ;; Katakana block
 311 (let ((range '(#x30a0 . #x30ff)))
 312   ;; ?K is double width, ?k isn't specified
 313   (modify-category-entry range ?K)
 314   (modify-category-entry range ?\|))
 315
 316 ;; Hiragana block
 317 (let ((range '(#x3040 . #x309f)))
 318   ;; ?H is actually defined to be double width
 319   ;;(modify-category-entry range ?H)
 320   ;;(modify-category-entry range ?\|)
 321   )
 322
 323 ;; JISX0208
 324 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2121 #x227E)
 325 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2821 #x287E)
 326 (let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
 327   (dolist (elt chars)
 328     (modify-syntax-entry (car chars) "w")))
 329 (modify-syntax-entry ?\（ "(）")
 330 (modify-syntax-entry ?\［ "(］")
 331 (modify-syntax-entry ?\｛ "(｝")
 332 (modify-syntax-entry ?\「 "(」")
 333 (modify-syntax-entry ?\『 "(』")
 334 (modify-syntax-entry ?\） ")（")
 335 (modify-syntax-entry ?\］ ")［")
 336 (modify-syntax-entry ?\｝ ")｛")
 337 (modify-syntax-entry ?\」 ")「")
 338 (modify-syntax-entry ?\』 ")『")
 339
 340 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?A #x2321 #x237E)
 341 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?H #x2421 #x247E)
 342 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?K #x2521 #x257E)
 343 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?G #x2621 #x267E)
 344 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?Y #x2721 #x277E)
 345 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?C #x3021 #x7E7E)
 346 (modify-category-entry ?ー ?K)
 347 (let ((chars '(?゛ ?゜)))
 348   (while chars
 349     (modify-category-entry (car chars) ?K)
 350     (modify-category-entry (car chars) ?H)
 351     (setq chars (cdr chars))))
 352 (let ((chars '(?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
 353   (while chars
 354     (modify-category-entry (car chars) ?C)
 355     (setq chars (cdr chars))))
 356
 357 ;; JISX0212
 358
 359 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E)
 360
 361 ;; JISX0201-Kana
 362
 363 (let ((chars '(?｡ ?､ ?･)))
 364   (while chars
 365     (modify-syntax-entry (car chars) ".")
 366     (setq chars (cdr chars))))
 367
 368 (modify-syntax-entry ?\｢ "(｣")
 369 (modify-syntax-entry ?\｣ "(｢")
 370
 371 ;; Korean character set (KSC5601)
 372
 373 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?h)
 374
 375 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2121 #x227E)
 376 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2621 #x297E)
 377 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2330 #x2339)
 378 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2341 #x235A)
 379 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2361 #x237A)
 380 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?G #x2521 #x257E)
 381 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?H #x2A21 #x2A7E)
 382 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?K #x2B21 #x2B7E)
 383 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?Y #x2C21 #x2C7E)
 384
 385 ;; Latin
 386
 387 (modify-category-entry '(#x80 . #x024F) ?l)
 388
 389 ;; Lao character set
 390
 391 (modify-category-entry '(#xe80 . #xeff) ?o)
 392 (map-charset-chars #'modify-category-entry 'lao ?o)
 393
 394 (let ((deflist  '(("ກ-ຮ"    "w"     ?0) ; consonant
 395                   ("ະາຳຽເ-ໄ"        "w"     ?1) ; vowel base
 396                   ("ັິ-ືົໍ"   "w"     ?2) ; vowel upper
 397                   ("ຸູ"     "w"     ?3) ; vowel lower
 398                   ("່-໋"    "w"     ?4) ; tone mark
 399                   ("ຼຽ"     "w"     ?9) ; semivowel lower
 400                   ("໐-໙"    "w"     ?6) ; digit
 401                   ("ຯໆ"     "_"     ?5) ; symbol
 402                   ))
 403       elm chars len syntax category to ch i)
 404   (while deflist
 405     (setq elm (car deflist))
 406     (setq chars (car elm)
 407           len (length chars)
 408           syntax (nth 1 elm)
 409           category (nth 2 elm)
 410           i 0)
 411     (while (< i len)
 412       (if (= (aref chars i) ?-)
 413           (setq i (1+ i)
 414                 to (aref chars i))
 415         (setq ch (aref chars i)
 416               to ch))
 417       (while (<= ch to)
 418         (unless (string-equal syntax "w")
 419           (modify-syntax-entry ch syntax))
 420         (modify-category-entry ch category)
 421         (setq ch (1+ ch)))
 422       (setq i (1+ i)))
 423     (setq deflist (cdr deflist))))
 424
 425 ;; Thai character set (TIS620)
 426
 427 (modify-category-entry '(#xe00 . #xe7f) ?t)
 428 (map-charset-chars #'modify-category-entry 'thai-tis620 ?t)
 429
 430 (let ((deflist  '(;; chars      syntax  category
 431                   ("ก-รลว-ฮ"  "w"     ?0) ; consonant
 432                   ("ฤฦะาำเ-ๅ"     "w"     ?1) ; vowel base
 433                   ("ัิ-ื็๎"   "w"     ?2) ; vowel upper
 434                   ("ุ-ฺ"    "w"     ?3) ; vowel lower
 435                   ("่-ํ"    "w"     ?4) ; tone mark
 436                   ("๐-๙"    "w"     ?6) ; digit
 437                   ("ฯๆ฿๏๚๛" "_"     ?5) ; symbol
 438                   ))
 439       elm chars len syntax category to ch i)
 440   (while deflist
 441     (setq elm (car deflist))
 442     (setq chars (car elm)
 443           len (length chars)
 444           syntax (nth 1 elm)
 445           category (nth 2 elm)
 446           i 0)
 447     (while (< i len)
 448       (if (= (aref chars i) ?-)
 449           (setq i (1+ i)
 450                 to (aref chars i))
 451         (setq ch (aref chars i)
 452               to ch))
 453       (while (<= ch to)
 454         (unless (string-equal syntax "w")
 455           (modify-syntax-entry ch syntax))
 456         (modify-category-entry ch category)
 457         (setq ch (1+ ch)))
 458       (setq i (1+ i)))
 459     (setq deflist (cdr deflist))))
 460
 461 ;; Tibetan character set
 462
 463 (modify-category-entry '(#xf00 . #xfff) ?q)
 464 (map-charset-chars #'modify-category-entry 'tibetan ?q)
 465 (map-charset-chars #'modify-category-entry 'tibetan-1-column ?q)
 466
 467 (let ((deflist  '(;; chars             syntax category
 468                   ("ཀ-ཀྵཪ"         "w"     ?0) ; consonant
 469                   ("ྐ-ྐྵྺྻྼ��������"       "w"     ?0) ;
 470                   ("����-����"              "w"     ?0) ;
 471                   ("����-����"              "w"     ?0) ;
 472                   ("ིེཻོཽྀ"       "w"       ?2) ; upper vowel
 473                   ("ཾྂྃ྆྇ྈྉྊྋ" "w"    ?2) ; upper modifier
 474                   ("༙����྄ཱུ༵༷"       "w"   ?3) ; lowel vowel/modifier
 475                   ("༠-༩༪-༳"             "w"     ?6) ; digit
 476                   ("་།-༒༔ཿ"        "."     ?|) ; line-break char
 477                   ("་།༏༐༑༔ཿ"            "."     ?|) ;
 478                   ("༈་།-༒༔ཿ༽༴"  "."     ?>) ; prohibition
 479                   ("་།༏༐༑༔ཿ"            "."     ?>) ;
 480                   ("ༀ-༊༼࿁࿂྅"      "."     ?<) ; prohibition
 481                   ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q) ; others
 482                   ))
 483       elm chars len syntax category to ch i)
 484   (while deflist
 485     (setq elm (car deflist))
 486     (setq chars (car elm)
 487           len (length chars)
 488           syntax (nth 1 elm)
 489           category (nth 2 elm)
 490           i 0)
 491     (while (< i len)
 492       (if (= (aref chars i) ?-)
 493           (setq i (1+ i)
 494                 to (aref chars i))
 495         (setq ch (aref chars i)
 496               to ch))
 497       (while (<= ch to)
 498         (unless (string-equal syntax "w")
 499           (modify-syntax-entry ch syntax))
 500         (modify-category-entry ch category)
 501         (setq ch (1+ ch)))
 502       (setq i (1+ i)))
 503     (setq deflist (cdr deflist))))
 504
 505 ;; Vietnamese character set
 506
 507 ;; To make a word with Latin characters
 508 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?l)
 509 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?v)
 510
 511 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?l)
 512 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?v)
 513
 514 (let ((tbl (standard-case-table))
 515       (i 32))
 516   (while (< i 128)
 517     (let* ((char (decode-char 'vietnamese-viscii-upper i))
 518            (charl (decode-char 'vietnamese-viscii-lower i))
 519            (uc (encode-char char 'ucs))
 520            (lc (encode-char charl 'ucs)))
 521       (set-case-syntax-pair char (decode-char 'vietnamese-viscii-lower i)
 522                             tbl)
 523       (if uc (modify-category-entry uc ?v))
 524       (if lc (modify-category-entry lc ?v)))
 525     (setq i (1+ i))))
 526
 527 (let ((tbl (standard-case-table)) c)
 528
 529 ;; In some languages, U+0049 LATIN CAPITAL LETTER I and U+0131 LATIN
 530 ;; SMALL LETTER DOTLESS I make a case pair, and so do U+0130 LATIN
 531 ;; CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN SMALL LETTER I.
 532 ;; Thus we have to check language-environment to handle casing
 533 ;; correctly.  Currently only I<->i is available.
 534
 535   ;; Latin Extended-A, Latin Extended-B
 536   (setq c #x0100)
 537   (while (<= c #x0233)
 538     (and (or (<= c #x012e)
 539              (and (>= c #x014a) (<= c #x0177)))
 540          (zerop (% c 2))
 541          (set-case-syntax-pair c (1+ c) tbl))
 542     (and (>= c #x013a)
 543          (<= c #x0148)
 544          (zerop (% c 2))
 545          (set-case-syntax-pair (1- c) c tbl))
 546     (setq c (1+ c)))
 547   (set-case-syntax-pair ?Ĳ ?ĳ tbl)
 548   (set-case-syntax-pair ?Ĵ ?ĵ tbl)
 549   (set-case-syntax-pair ?Ķ ?ķ tbl)
 550 ;;;  (set-case-syntax-pair ?Ÿ ?ÿ tbl) ; these two have different length!
 551   (set-case-syntax-pair ?Ź ?ź tbl)
 552   (set-case-syntax-pair ?Ż ?ż tbl)
 553   (set-case-syntax-pair ?Ž ?ž tbl)
 554
 555   ;; Latin Extended-B
 556   (set-case-syntax-pair ?Ɓ ?ɓ tbl)
 557   (set-case-syntax-pair ?Ƃ ?ƃ tbl)
 558   (set-case-syntax-pair ?Ƅ ?ƅ tbl)
 559   (set-case-syntax-pair ?Ɔ ?ɔ tbl)
 560   (set-case-syntax-pair ?Ƈ ?ƈ tbl)
 561   (set-case-syntax-pair ?Ɖ ?ɖ tbl)
 562   (set-case-syntax-pair ?Ɗ ?ɗ tbl)
 563   (set-case-syntax-pair ?Ƌ ?ƌ tbl)
 564   (set-case-syntax-pair ?Ǝ ?ǝ tbl)
 565   (set-case-syntax-pair ?Ə ?ə tbl)
 566   (set-case-syntax-pair ?Ɛ ?ɛ tbl)
 567   (set-case-syntax-pair ?Ƒ ?ƒ tbl)
 568   (set-case-syntax-pair ?Ɠ ?ɠ tbl)
 569   (set-case-syntax-pair ?Ɣ ?ɣ tbl)
 570   (set-case-syntax-pair ?Ɩ ?ɩ tbl)
 571   (set-case-syntax-pair ?Ɨ ?ɨ tbl)
 572   (set-case-syntax-pair ?Ƙ ?ƙ tbl)
 573   (set-case-syntax-pair ?Ɯ ?ɯ tbl)
 574   (set-case-syntax-pair ?Ɲ ?ɲ tbl)
 575   (set-case-syntax-pair ?Ɵ ?ɵ tbl)
 576   (set-case-syntax-pair ?Ơ ?ơ tbl)
 577   (set-case-syntax-pair ?Ƣ ?ƣ tbl)
 578   (set-case-syntax-pair ?Ƥ ?ƥ tbl)
 579   (set-case-syntax-pair ?Ʀ ?ʀ tbl)
 580   (set-case-syntax-pair ?Ƨ ?ƨ tbl)
 581   (set-case-syntax-pair ?Ʃ ?ʃ tbl)
 582   (set-case-syntax-pair ?Ƭ ?ƭ tbl)
 583   (set-case-syntax-pair ?Ʈ ?ʈ tbl)
 584   (set-case-syntax-pair ?Ư ?ư tbl)
 585   (set-case-syntax-pair ?Ʊ ?ʊ tbl)
 586   (set-case-syntax-pair ?Ʋ ?ʋ tbl)
 587   (set-case-syntax-pair ?Ƴ ?ƴ tbl)
 588   (set-case-syntax-pair ?Ƶ ?ƶ tbl)
 589   (set-case-syntax-pair ?Ʒ ?ʒ tbl)
 590   (set-case-syntax-pair ?Ƹ ?ƹ tbl)
 591   (set-case-syntax-pair ?Ƽ ?ƽ tbl)
 592   (set-case-syntax-pair ?Ǆ ?ǆ tbl)
 593   (set-case-syntax-pair ?ǅ ?ǆ tbl)
 594   (set-case-syntax-pair ?Ǉ ?ǉ tbl)
 595   (set-case-syntax-pair ?ǈ ?ǉ tbl)
 596   (set-case-syntax-pair ?Ǌ ?ǌ tbl)
 597   (set-case-syntax-pair ?ǋ ?ǌ tbl)
 598   (set-case-syntax-pair ?Ǎ ?ǎ tbl)
 599   (set-case-syntax-pair ?Ǐ ?ǐ tbl)
 600   (set-case-syntax-pair ?Ǒ ?ǒ tbl)
 601   (set-case-syntax-pair ?Ǔ ?ǔ tbl)
 602   (set-case-syntax-pair ?Ǖ ?ǖ tbl)
 603   (set-case-syntax-pair ?Ǘ ?ǘ tbl)
 604   (set-case-syntax-pair ?Ǚ ?ǚ tbl)
 605   (set-case-syntax-pair ?Ǜ ?ǜ tbl)
 606   (set-case-syntax-pair ?Ǟ ?ǟ tbl)
 607   (set-case-syntax-pair ?Ǡ ?ǡ tbl)
 608   (set-case-syntax-pair ?Ǣ ?ǣ tbl)
 609   (set-case-syntax-pair ?Ǥ ?ǥ tbl)
 610   (set-case-syntax-pair ?Ǧ ?ǧ tbl)
 611   (set-case-syntax-pair ?Ǩ ?ǩ tbl)
 612   (set-case-syntax-pair ?Ǫ ?ǫ tbl)
 613   (set-case-syntax-pair ?Ǭ ?ǭ tbl)
 614   (set-case-syntax-pair ?Ǯ ?ǯ tbl)
 615   ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
 616   (set-case-syntax-pair ?Ǳ ?ǳ tbl)
 617   (set-case-syntax-pair ?ǲ ?ǳ tbl)
 618   (set-case-syntax-pair ?Ǵ ?ǵ tbl)
 619   (set-case-syntax-pair ?Ƕ ?ƕ tbl)
 620   (set-case-syntax-pair ?Ƿ ?ƿ tbl)
 621   (set-case-syntax-pair ?Ǹ ?ǹ tbl)
 622   (set-case-syntax-pair ?Ǻ ?ǻ tbl)
 623   (set-case-syntax-pair ?Ǽ ?ǽ tbl)
 624   (set-case-syntax-pair ?Ǿ ?ǿ tbl)
 625   (set-case-syntax-pair ?Ȁ ?ȁ tbl)
 626   (set-case-syntax-pair ?Ȃ ?ȃ tbl)
 627   (set-case-syntax-pair ?Ȅ ?ȅ tbl)
 628   (set-case-syntax-pair ?Ȇ ?ȇ tbl)
 629   (set-case-syntax-pair ?Ȉ ?ȉ tbl)
 630   (set-case-syntax-pair ?Ȋ ?ȋ tbl)
 631   (set-case-syntax-pair ?Ȍ ?ȍ tbl)
 632   (set-case-syntax-pair ?Ȏ ?ȏ tbl)
 633   (set-case-syntax-pair ?Ȑ ?ȑ tbl)
 634   (set-case-syntax-pair ?Ȓ ?ȓ tbl)
 635   (set-case-syntax-pair ?Ȕ ?ȕ tbl)
 636   (set-case-syntax-pair ?Ȗ ?ȗ tbl)
 637   (set-case-syntax-pair ?Ș ?ș tbl)
 638   (set-case-syntax-pair ?Ț ?ț tbl)
 639   (set-case-syntax-pair ?Ȝ ?ȝ tbl)
 640   (set-case-syntax-pair ?Ȟ ?ȟ tbl)
 641   (set-case-syntax-pair ?Ȣ ?ȣ tbl)
 642   (set-case-syntax-pair ?Ȥ ?ȥ tbl)
 643   (set-case-syntax-pair ?Ȧ ?ȧ tbl)
 644   (set-case-syntax-pair ?Ȩ ?ȩ tbl)
 645   (set-case-syntax-pair ?Ȫ ?ȫ tbl)
 646   (set-case-syntax-pair ?Ȭ ?ȭ tbl)
 647   (set-case-syntax-pair ?Ȯ ?ȯ tbl)
 648   (set-case-syntax-pair ?Ȱ ?ȱ tbl)
 649   (set-case-syntax-pair ?Ȳ ?ȳ tbl)
 650
 651   ;; Latin Extended Additional
 652   (modify-category-entry '(#x1e00 . #x1ef9) ?l)
 653   (setq c #x1e00)
 654   (while (<= c #x1ef9)
 655     (and (zerop (% c 2))
 656          (or (<= c #x1e94) (>= c #x1ea0))
 657          (set-case-syntax-pair c (1+ c) tbl))
 658     (setq c (1+ c)))
 659
 660   ;; Greek
 661   (modify-category-entry '(#x0370 . #x03ff) ?g)
 662   (setq c #x0370)
 663   (while (<= c #x03ff)
 664     (if (or (and (>= c #x0391) (<= c #x03a1))
 665             (and (>= c #x03a3) (<= c #x03ab)))
 666         (set-case-syntax-pair c (+ c 32) tbl))
 667     (and (>= c #x03da)
 668          (<= c #x03ee)
 669          (zerop (% c 2))
 670          (set-case-syntax-pair c (1+ c) tbl))
 671     (setq c (1+ c)))
 672   (set-case-syntax-pair ?Ά ?ά tbl)
 673   (set-case-syntax-pair ?Έ ?έ tbl)
 674   (set-case-syntax-pair ?Ή ?ή tbl)
 675   (set-case-syntax-pair ?Ί ?ί tbl)
 676   (set-case-syntax-pair ?Ό ?ό tbl)
 677   (set-case-syntax-pair ?Ύ ?ύ tbl)
 678   (set-case-syntax-pair ?Ώ ?ώ tbl)
 679
 680   ;; Armenian
 681   (setq c #x531)
 682   (while (<= c #x556)
 683     (set-case-syntax-pair c (+ c #x30) tbl)
 684     (setq c (1+ c)))
 685
 686   ;; Greek Extended
 687   (modify-category-entry '(#x1f00 . #x1fff) ?g)
 688   (setq c #x1f00)
 689   (while (<= c #x1fff)
 690     (and (<= (logand c #x000f) 7)
 691          (<= c #x1fa7)
 692          (not (memq c '(#x1f50 #x1f52 #x1f54 #x1f56)))
 693          (/= (logand c #x00f0) 7)
 694          (set-case-syntax-pair (+ c 8) c tbl))
 695     (setq c (1+ c)))
 696   (set-case-syntax-pair ?Ᾰ ?ᾰ tbl)
 697   (set-case-syntax-pair ?Ᾱ ?ᾱ tbl)
 698   (set-case-syntax-pair ?Ὰ ?ὰ tbl)
 699   (set-case-syntax-pair ?Ά ?ά tbl)
 700   (set-case-syntax-pair ?ᾼ ?ᾳ tbl)
 701   (set-case-syntax-pair ?Ὲ ?ὲ tbl)
 702   (set-case-syntax-pair ?Έ ?έ tbl)
 703   (set-case-syntax-pair ?Ὴ ?ὴ tbl)
 704   (set-case-syntax-pair ?Ή ?ή tbl)
 705   (set-case-syntax-pair ?ῌ ?ῃ tbl)
 706   (set-case-syntax-pair ?Ῐ ?ῐ tbl)
 707   (set-case-syntax-pair ?Ῑ ?ῑ tbl)
 708   (set-case-syntax-pair ?Ὶ ?ὶ tbl)
 709   (set-case-syntax-pair ?Ί ?ί tbl)
 710   (set-case-syntax-pair ?Ῠ ?ῠ tbl)
 711   (set-case-syntax-pair ?Ῡ ?ῡ tbl)
 712   (set-case-syntax-pair ?Ὺ ?ὺ tbl)
 713   (set-case-syntax-pair ?Ύ ?ύ tbl)
 714   (set-case-syntax-pair ?Ῥ ?ῥ tbl)
 715   (set-case-syntax-pair ?Ὸ ?ὸ tbl)
 716   (set-case-syntax-pair ?Ό ?ό tbl)
 717   (set-case-syntax-pair ?Ὼ ?ὼ tbl)
 718   (set-case-syntax-pair ?Ώ ?ώ tbl)
 719   (set-case-syntax-pair ?ῼ ?ῳ tbl)
 720
 721   ;; cyrillic
 722   (modify-category-entry '(#x0400 . #x04FF) ?y)
 723   (setq c #x0400)
 724   (while (<= c #x04ff)
 725     (and (>= c #x0400)
 726          (<= c #x040f)
 727          (set-case-syntax-pair c (+ c 80) tbl))
 728     (and (>= c #x0410)
 729          (<= c #x042f)
 730          (set-case-syntax-pair c (+ c 32) tbl))
 731     (and (zerop (% c 2))
 732          (or (and (>= c #x0460) (<= c #x0480))
 733              (and (>= c #x048c) (<= c #x04be))
 734              (and (>= c #x04d0) (<= c #x04f4)))
 735          (set-case-syntax-pair c (1+ c) tbl))
 736     (setq c (1+ c)))
 737   (set-case-syntax-pair ?Ӂ ?ӂ tbl)
 738   (set-case-syntax-pair ?Ӄ ?ӄ tbl)
 739   (set-case-syntax-pair ?Ӈ ?ӈ tbl)
 740   (set-case-syntax-pair ?Ӌ ?ӌ tbl)
 741   (set-case-syntax-pair ?Ӹ ?ӹ tbl)
 742
 743   ;; general punctuation
 744   (setq c #x2000)
 745   (while (<= c #x200b)
 746     (set-case-syntax c " " tbl)
 747     (setq c (1+ c)))
 748   (setq c #x2010)
 749   (while (<= c #x2027)
 750     (set-case-syntax c "_" tbl)
 751     (setq c (1+ c)))
 752
 753   ;; Roman numerals
 754   (setq c #x2160)
 755   (while (<= c #x216f)
 756     (set-case-syntax-pair c (+ c #x10) tbl)
 757     (setq c (1+ c)))
 758
 759   ;; Circled Latin
 760   (setq c #x24b6)
 761   (while (<= c #x24cf)
 762     (set-case-syntax-pair c (+ c 26) tbl)
 763     (modify-category-entry c ?l)
 764     (modify-category-entry (+ c 26) ?l)
 765     (setq c (1+ c)))
 766
 767   ;; Fullwidth Latin
 768   (setq c #xff21)
 769   (while (<= c #xff3a)
 770     (set-case-syntax-pair c (+ c #x20) tbl)
 771     (modify-category-entry c ?l)
 772     (modify-category-entry (+ c #x20) ?l)
 773     (setq c (1+ c)))
 774
 775   ;; Combining diacritics
 776   (modify-category-entry '(#x300 . #x362) ?^)
 777   ;; Combining marks
 778   (modify-category-entry '(#x20d0 . #x20e3) ?^)
 779
 780   ;; Fixme: syntax for symbols &c
 781   )
 782 \f
 783 ;; For each character set, put the information of the most proper
 784 ;; coding system to encode it by `preferred-coding-system' property.
 785
 786 ;; Fixme: should this be junked?
 787 (let ((l '((latin-iso8859-1     . iso-latin-1)
 788            (latin-iso8859-2     . iso-latin-2)
 789            (latin-iso8859-3     . iso-latin-3)
 790            (latin-iso8859-4     . iso-latin-4)
 791            (thai-tis620         . thai-tis620)
 792            (greek-iso8859-7     . greek-iso-8bit)
 793            (arabic-iso8859-6    . iso-2022-7bit)
 794            (hebrew-iso8859-8    . hebrew-iso-8bit)
 795            (katakana-jisx0201   . japanese-shift-jis)
 796            (latin-jisx0201      . japanese-shift-jis)
 797            (cyrillic-iso8859-5  . cyrillic-iso-8bit)
 798            (latin-iso8859-9     . iso-latin-5)
 799            (japanese-jisx0208-1978 . iso-2022-jp)
 800            (chinese-gb2312      . cn-gb-2312)
 801            (japanese-jisx0208   . iso-2022-jp)
 802            (korean-ksc5601      . iso-2022-kr)
 803            (japanese-jisx0212   . iso-2022-jp)
 804            (chinese-cns11643-1  . iso-2022-cn)
 805            (chinese-cns11643-2  . iso-2022-cn)
 806            (chinese-big5-1      . chinese-big5)
 807            (chinese-big5-2      . chinese-big5)
 808            (chinese-sisheng     . iso-2022-7bit)
 809            (ipa                 . iso-2022-7bit)
 810            (vietnamese-viscii-lower . vietnamese-viscii)
 811            (vietnamese-viscii-upper . vietnamese-viscii)
 812            (arabic-digit        . iso-2022-7bit)
 813            (arabic-1-column     . iso-2022-7bit)
 814            (lao                 . lao)
 815            (arabic-2-column     . iso-2022-7bit)
 816            (indian-is13194      . devanagari)
 817            (indian-glyph        . devanagari)
 818            (tibetan-1-column    . tibetan)
 819            (ethiopic            . iso-2022-7bit)
 820            (chinese-cns11643-3  . iso-2022-cn)
 821            (chinese-cns11643-4  . iso-2022-cn)
 822            (chinese-cns11643-5  . iso-2022-cn)
 823            (chinese-cns11643-6  . iso-2022-cn)
 824            (chinese-cns11643-7  . iso-2022-cn)
 825            (indian-2-column     . devanagari)
 826            (tibetan             . tibetan)
 827            (latin-iso8859-14    . iso-latin-8)
 828            (latin-iso8859-15    . iso-latin-9))))
 829   (while l
 830     (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
 831     (setq l (cdr l))))
 832
 833 \f
 834 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
 835 ;; SPACE and NEWLINE are already set.  Also put `nospace-between-words'
 836 ;; property on the charsets.
 837 (let ((l '(katakana-jisx0201
 838            japanese-jisx0208 japanese-jisx0212
 839            chinese-gb2312 chinese-big5-1 chinese-big5-2)))
 840   (while l
 841     ;;(aset auto-fill-chars (make-char (car l)) t)
 842     (put-charset-property (car l) 'nospace-between-words t)
 843     (setq l (cdr l))))
 844
 845 \f
 846 (set-char-table-range printable-chars '(32 . 126) t)
 847 (set-char-table-range printable-chars  (cons 160 (max-char)) t)
 848
 849 ;; CJK double width characters.
 850 (let ((l '((#x1100 . #x11FF)
 851            (#x2E80 . #x9FAF)
 852            (#xAC00 . #xD7AF)
 853            (#xF900 . #xFAFF)
 854            (#xFE30 . #xFE4F)
 855            (#xFF00 . #xFF5F)
 856            (#xFFE0 . #xFFEF))))
 857   (dolist (elt l)
 858     (set-char-table-range char-width-table
 859                           (cons (car elt) (cdr elt))
 860                           2)))
 861 (map-charset-chars
 862  #'(lambda (range ignore) (set-char-table-range char-width-table range 2))
 863  'japanese-jisx0208)
 864 (map-charset-chars
 865  #'(lambda (range ignore) (set-char-table-range char-width-table range 2))
 866  'japanese-jisx0212)
 867 (map-charset-chars
 868  #'(lambda (range ignore) (set-char-table-range char-width-table range 2))
 869  'japanese-jisx0213-1)
 870 (map-charset-chars
 871  #'(lambda (range ignore) (set-char-table-range char-width-table range 2))
 872  'japanese-jisx0213-2)
 873
 874 ;; Other double width
 875 (map-charset-chars
 876  (lambda (range ignore) (set-char-table-range char-width-table range 2))
 877  'ethiopic)
 878 (map-charset-chars
 879  (lambda (range ignore) (set-char-table-range char-width-table range 2))
 880  'tibetan)
 881 (map-charset-chars
 882  (lambda (range ignore) (set-char-table-range char-width-table range 2))
 883  'indian-2-column)
 884 (map-charset-chars
 885  (lambda (range ignore) (set-char-table-range char-width-table range 2))
 886  'arabic-2-column)
 887 (map-charset-chars
 888  (lambda (range ignore) (set-char-table-range char-width-table range 2))
 889  'korean-ksc5601)
 890
 891 (optimize-char-table (standard-case-table))
 892 (optimize-char-table char-width-table)
 893 (optimize-char-table (standard-category-table))
 894 (optimize-char-table (standard-syntax-table))
 895
 896 (let ((script-list nil))
 897   (dolist
 898       (elt
 899        '((#x0000 #x007F latin)
 900          (#x00A0 #x036F latin)
 901          (#x0370 #x03E1 greek)
 902          (#x03E2 #x03EF coptic)
 903          (#x03F0 #x03F3 greek)
 904          (#x0400 #x04FF cyrillic)
 905          (#x0530 #x058F armenian)
 906          (#x0590 #x05FF hebrew)
 907          (#x0600 #x06FF arabic)
 908          (#x0700 #x074F syriac)
 909          (#x0780 #x07BF thaana)
 910          (#x0900 #x097F devanagari)
 911          (#x0980 #x09FF bengali)
 912          (#x0A00 #x0A7F gurmukhi)
 913          (#x0A80 #x0AFF gujarati)
 914          (#x0B00 #x0B7F oriya)
 915          (#x0B80 #x0BFF tamil)
 916          (#x0C00 #x0C7F telugu)
 917          (#x0C80 #x0CFF kannada)
 918          (#x0D00 #x0D7F malayalam)
 919          (#x0D80 #x0DFF sinhala)
 920          (#x0E00 #x0E5F thai)
 921          (#x0E80 #x0EDF lao)
 922          (#x0F00 #x0FFF tibetan)
 923          (#x1000 #x105F myanmar)
 924          (#x10A0 #x10FF georgian)
 925          (#x1100 #x11FF hangul)
 926          (#x1200 #x137F ethiopic)
 927          (#x13A0 #x13FF cherokee)
 928          (#x1400 #x167F canadian-aboriginal)
 929          (#x1680 #x169F ogham)
 930          (#x16A0 #x16FF runic)
 931          (#x1780 #x17FF khmer)
 932          (#x1800 #x18AF mongolian)
 933          (#x1E00 #x1EFF latin)
 934          (#x1F00 #x1FFF greek)
 935          (#x20A0 #x20AF currency)
 936          (#x2800 #x28FF braille)
 937          (#x2E80 #x2FDF han)
 938          (#x2FF0 #x2FFF ideographic-description)
 939          (#x3000 #x303F cjk-misc)
 940          (#x3040 #x30FF kana)
 941          (#x3100 #x312F bopomofo)
 942          (#x3130 #x318F hangul)
 943          (#x3190 #x319F kanbun)
 944          (#x31A0 #x31BF bopomofo)
 945          (#x3400 #x9FAF han)
 946          (#xA000 #xA4CF yi)
 947          (#xAC00 #xD7AF hangul)
 948          (#xF900 #xFA5F han)
 949          (#xFB1D #xFB4F hebrew)
 950          (#xFB50 #xFDFF arabic)
 951          (#xFE70 #xFEFC arabic)
 952          (#xFF00 #xFF5F cjk-misc)
 953          (#xFF61 #xFF9F kana)
 954          (#xFFE0 #xFFE6 cjk-misc)
 955          (#x20000 #x2AFFF han)
 956          (#x2F800 #x2FFFF han)))
 957     (set-char-table-range char-script-table
 958                           (cons (car elt) (nth 1 elt)) (nth 2 elt))
 959     (or (memq (nth 2 elt) script-list)
 960         (setq script-list (cons (nth 2 elt) script-list))))
 961   (set-char-table-extra-slot char-script-table 0 (nreverse script-list)))
 962
 963 \f
 964 ;;; Setting word boundary.
 965
 966 (defun next-word-boundary-han (pos limit)
 967   (if (<= pos limit)
 968       (save-excursion
 969         (goto-char pos)
 970         (looking-at "\\cC+")
 971         (goto-char (match-end 0))
 972         (if (looking-at "\\cH+")
 973             (goto-char (match-end 0)))
 974         (point))
 975     (while (and (> pos limit)
 976                 (eq (aref char-script-table (char-after (1- pos))) 'han))
 977       (setq pos (1- pos)))
 978     pos))
 979
 980 (defun next-word-boundary-kana (pos limit)
 981   (if (<= pos limit)
 982       (save-excursion
 983         (goto-char pos)
 984         (if (looking-at "\\cK+")
 985             (goto-char (match-end 0)))
 986         (if (looking-at "\\cH+")
 987             (goto-char (match-end 0)))
 988         (point))
 989     (let ((category-set (char-category-set (char-after pos)))
 990           category)
 991       (if (aref category-set ?K)
 992           (while (and (> pos limit)
 993                       (aref (char-category-set (char-after (1- pos))) ?K))
 994             (setq pos (1- pos)))
 995         (while (and (> pos limit)
 996                     (aref (setq category-set
 997                                 (char-category-set (char-after (1- pos)))) ?H))
 998           (setq pos (1- pos)))
 999         (setq category (cond ((aref category-set ?C) ?C)
1000                              ((aref category-set ?K) ?K)
1001                              ((aref category-set ?A) ?A)))
1002         (when category
1003           (setq pos (1- pos))
1004           (while (and (> pos limit)
1005                       (aref (char-category-set (char-after (1- pos)))
1006                             category))
1007             (setq pos (1- pos)))))
1008       pos)))
1009
1010 (map-char-table
1011  #'(lambda (char script)
1012      (cond ((eq script 'han)
1013             (set-char-table-range next-word-boundary-function-table
1014                                   char #'next-word-boundary-han))
1015            ((eq script 'kana)
1016             (set-char-table-range next-word-boundary-function-table
1017                                   char #'next-word-boundary-kana))))
1018  char-script-table)
1019
1020 (setq word-combining-categories
1021       '((?l . ?l)))
1022
1023 (setq word-separating-categories        ;  (2-byte character sets)
1024       '((?A . ?K)                       ; Alpha numeric - Katakana
1025         (?A . ?C)                       ; Alpha numeric - Chinese
1026         (?H . ?A)                       ; Hiragana - Alpha numeric
1027         (?H . ?K)                       ; Hiragana - Katakana
1028         (?H . ?C)                       ; Hiragana - Chinese
1029         (?K . ?A)                       ; Katakana - Alpha numeric
1030         (?K . ?C)                       ; Katakana - Chinese
1031         (?C . ?A)                       ; Chinese - Alpha numeric
1032         (?C . ?K)                       ; Chinese - Katakana
1033         ))
1034
1035 ;;; Local Variables:
1036 ;;; coding: utf-8-emacs
1037 ;;; End:
1038
1039 ;;; characters.el ends here