lisp/international/characters.el

   1 ;;; characters.el --- set syntax and category for multibyte characters
   2
   3 ;; Copyright (C) 1997, 2000-2012  Free Software Foundation, Inc.
   4 ;; Copyright (C) 1995, 1996, 1997, 1998, 1999, 2000, 2001, 2002, 2003, 2004,
   5 ;;   2005, 2006, 2007, 2008, 2009, 2010, 2011
   6 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
   7 ;;   Registration Number H14PRO021
   8 ;; Copyright (C) 2003
   9 ;;   National Institute of Advanced Industrial Science and Technology (AIST)
  10 ;;   Registration Number H13PRO009
  11
  12 ;; Keywords: multibyte character, character set, syntax, category
  13
  14 ;; This file is part of GNU Emacs.
  15
  16 ;; GNU Emacs is free software: you can redistribute it and/or modify
  17 ;; it under the terms of the GNU General Public License as published by
  18 ;; the Free Software Foundation, either version 3 of the License, or
  19 ;; (at your option) any later version.
  20
  21 ;; GNU Emacs is distributed in the hope that it will be useful,
  22 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  23 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  24 ;; GNU General Public License for more details.
  25
  26 ;; You should have received a copy of the GNU General Public License
  27 ;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  28
  29 ;;; Commentary:
  30
  31 ;;; Code:
  32
  33 ;;; Predefined categories.
  34
  35 ;; For each character set.
  36
  37 (define-category ?a "ASCII
  38 ASCII graphic characters 32-126 (ISO646 IRV:1983[4/0])")
  39 (define-category ?l "Latin")
  40 (define-category ?t "Thai")
  41 (define-category ?g "Greek")
  42 (define-category ?b "Arabic")
  43 (define-category ?w "Hebrew")
  44 (define-category ?y "Cyrillic")
  45 (define-category ?k "Katakana
  46 Japanese katakana")
  47 (define-category ?r "Roman
  48 Japanese roman")
  49 (define-category ?c "Chinese")
  50 (define-category ?j "Japanese")
  51 (define-category ?h "Korean")
  52 (define-category ?e "Ethiopic
  53 Ethiopic (Ge'ez)")
  54 (define-category ?v "Viet
  55 Vietnamese")
  56 (define-category ?i "Indian")
  57 (define-category ?o "Lao")
  58 (define-category ?q "Tibetan")
  59
  60 ;; For each group (row) of 2-byte character sets.
  61
  62 (define-category ?A "2-byte alnum
  63 Alpha-numeric characters of 2-byte character sets")
  64 (define-category ?C "2-byte han
  65 Chinese (Han) characters of 2-byte character sets")
  66 (define-category ?G "2-byte Greek
  67 Greek characters of 2-byte character sets")
  68 (define-category ?H "2-byte Hiragana
  69 Japanese Hiragana characters of 2-byte character sets")
  70 (define-category ?K "2-byte Katakana
  71 Japanese Katakana characters of 2-byte character sets")
  72 (define-category ?N "2-byte Korean
  73 Korean Hangul characters of 2-byte character sets")
  74 (define-category ?Y "2-byte Cyrillic
  75 Cyrillic characters of 2-byte character sets")
  76 (define-category ?I "Indian Glyphs")
  77
  78 ;; For phonetic classifications.
  79
  80 (define-category ?0 "consonant")
  81 (define-category ?1 "base vowel
  82 Base (independent) vowel")
  83 (define-category ?2 "upper diacritic
  84 Upper diacritical mark (including upper vowel)")
  85 (define-category ?3 "lower diacritic
  86 Lower diacritical mark (including lower vowel)")
  87 (define-category ?4 "combining tone
  88 Combining tone mark")
  89 (define-category ?5 "symbol")
  90 (define-category ?6 "digit")
  91 (define-category ?7 "vowel diacritic
  92 Vowel-modifying diacritical mark")
  93 (define-category ?8 "vowel-signs")
  94 (define-category ?9 "semivowel lower")
  95
  96 ;; For filling.
  97 (define-category ?| "line breakable
  98 While filling, we can break a line at this character.")
  99
 100 ;; For indentation calculation.
 101 (define-category ?\s
 102   "space for indent
 103 This character counts as a space for indentation purposes.")
 104
 105 ;; Keep the following for `kinsoku' processing.  See comments in
 106 ;; kinsoku.el.
 107 (define-category ?> "Not at bol
 108 A character which can't be placed at beginning of line.")
 109 (define-category ?< "Not at eol
 110 A character which can't be placed at end of line.")
 111
 112 ;; Base and Combining
 113 (define-category ?. "Base
 114 Base characters (Unicode General Category L,N,P,S,Zs)")
 115 (define-category ?^ "Combining
 116 Combining diacritic or mark (Unicode General Category M)")
 117
 118 ;; bidi types
 119 (define-category ?R "Right-to-left (strong)
 120 Characters with \"strong\" right-to-left directionality, i.e.
 121 with R, AL, RLE, or RLO Unicode bidi character type.")
 122
 123 (define-category ?L "Left-to-right (strong)
 124 Characters with \"strong\" left-to-right directionality, i.e.
 125 with L, LRE, or LRO Unicode bidi character type.")
 126
 127 \f
 128 ;;; Setting syntax and category.
 129
 130 ;; ASCII
 131
 132 ;; All ASCII characters have the category `a' (ASCII) and `l' (Latin).
 133 (modify-category-entry '(32 . 127) ?a)
 134 (modify-category-entry '(32 . 127) ?l)
 135
 136 ;; Deal with the CJK charsets first.  Since the syntax of blocks is
 137 ;; defined per charset, and the charsets may contain e.g. Latin
 138 ;; characters, we end up with the wrong syntax definitions if we're
 139 ;; not careful.
 140
 141 ;; Chinese characters (Unicode)
 142 (modify-category-entry '(#x2E80 . #x312F) ?|)
 143 (modify-category-entry '(#x3190 . #x33FF) ?|)
 144 (modify-category-entry '(#x3400 . #x4DBF) ?C)
 145 (modify-category-entry '(#x4E00 . #x9FAF) ?C)
 146 (modify-category-entry '(#x3400 . #x9FAF) ?c)
 147 (modify-category-entry '(#x3400 . #x9FAF) ?|)
 148 (modify-category-entry '(#xF900 . #xFAFF) ?C)
 149 (modify-category-entry '(#xF900 . #xFAFF) ?c)
 150 (modify-category-entry '(#xF900 . #xFAFF) ?|)
 151 (modify-category-entry '(#x20000 . #x2FFFF) ?|)
 152 (modify-category-entry '(#x20000 . #x2FFFF) ?C)
 153 (modify-category-entry '(#x20000 . #x2FFFF) ?c)
 154
 155
 156 ;; Chinese character set (GB2312)
 157
 158 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2121 #x217E)
 159 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2221 #x227E)
 160 (map-charset-chars #'modify-syntax-entry 'chinese-gb2312 "_" #x2921 #x297E)
 161
 162 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?c)
 163 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2330 #x2339)
 164 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2341 #x235A)
 165 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?A #x2361 #x237A)
 166 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?H #x2421 #x247E)
 167 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?K #x2521 #x257E)
 168 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?G #x2621 #x267E)
 169 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?Y #x2721 #x277E)
 170 (map-charset-chars #'modify-category-entry 'chinese-gb2312 ?C #x3021 #x7E7E)
 171
 172 ;; Chinese character set (BIG5)
 173
 174 (map-charset-chars #'modify-category-entry 'big5 ?c)
 175 (map-charset-chars #'modify-category-entry 'big5 ?C #xA259 #xA261)
 176 (map-charset-chars #'modify-category-entry 'big5 ?C #xA440 #xC67E)
 177 (map-charset-chars #'modify-category-entry 'big5 ?C #xC940 #xF9DC)
 178
 179 ;; Chinese character set (CNS11643)
 180
 181 (dolist (c '(chinese-cns11643-1 chinese-cns11643-2 chinese-cns11643-3
 182              chinese-cns11643-4 chinese-cns11643-5 chinese-cns11643-6
 183              chinese-cns11643-7))
 184   (map-charset-chars #'modify-category-entry c ?c)
 185   (if (eq c 'chinese-cns11643-1)
 186       (map-charset-chars #'modify-category-entry c ?C #x4421 #x7E7E)
 187     (map-charset-chars #'modify-category-entry c ?C)))
 188
 189 ;; Japanese character set (JISX0201, JISX0208, JISX0212, JISX0213)
 190
 191 (map-charset-chars #'modify-category-entry 'katakana-jisx0201 ?k)
 192
 193 (map-charset-chars #'modify-category-entry 'latin-jisx0201 ?r)
 194
 195 (dolist (l '(katakana-jisx0201 japanese-jisx0208 japanese-jisx0212
 196                                japanese-jisx0213-1 japanese-jisx0213-2
 197                                cp932-2-byte))
 198   (map-charset-chars #'modify-category-entry l ?j))
 199
 200 ;; Fullwidth characters
 201 (modify-category-entry '(#xff01 . #xff60) ?\|)
 202
 203 ;; Unicode equivalents of JISX0201-kana
 204 (let ((range '(#xff61 . #xff9f)))
 205   (modify-category-entry range  ?k)
 206   (modify-category-entry range ?j)
 207   (modify-category-entry range ?\|))
 208
 209 ;; Katakana block
 210 (modify-category-entry '(#x3099 . #x309C) ?K)
 211 (modify-category-entry '(#x30A0 . #x30FF) ?K)
 212 (modify-category-entry '(#x31F0 . #x31FF) ?K)
 213 (modify-category-entry '(#x30A0 . #x30FA) ?\|)
 214 (modify-category-entry #x30FF ?\|)
 215
 216 ;; Hiragana block
 217 (modify-category-entry '(#x3040 . #x309F) ?H)
 218 (modify-category-entry '(#x3040 . #x3096) ?\|)
 219 (modify-category-entry #x309F ?\|)
 220 (modify-category-entry #x30A0 ?H)
 221 (modify-category-entry #x30FC ?H)
 222
 223
 224 ;; JISX0208
 225 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2121 #x227E)
 226 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0208 "_" #x2821 #x287E)
 227 (let ((chars '(?ー ?゛ ?゜ ?ヽ ?ヾ ?ゝ ?ゞ ?〃 ?仝 ?々 ?〆 ?〇)))
 228   (dolist (elt chars)
 229     (modify-syntax-entry (car chars) "w")))
 230
 231 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?A #x2321 #x237E)
 232 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?H #x2421 #x247E)
 233 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?K #x2521 #x257E)
 234 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?G #x2621 #x267E)
 235 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?Y #x2721 #x277E)
 236 (map-charset-chars #'modify-category-entry 'japanese-jisx0208 ?C #x3021 #x7E7E)
 237 (modify-category-entry ?ー ?K)
 238 (let ((chars '(?゛ ?゜)))
 239   (while chars
 240     (modify-category-entry (car chars) ?K)
 241     (modify-category-entry (car chars) ?H)
 242     (setq chars (cdr chars))))
 243 (let ((chars '(?仝 ?々 ?〆 ?〇)))
 244   (while chars
 245     (modify-category-entry (car chars) ?C)
 246     (setq chars (cdr chars))))
 247
 248 ;; JISX0212
 249
 250 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E)
 251
 252 ;; JISX0201-Kana
 253
 254 (let ((chars '(?｡ ?､ ?･)))
 255   (while chars
 256     (modify-syntax-entry (car chars) ".")
 257     (setq chars (cdr chars))))
 258
 259 (modify-syntax-entry ?\｢ "(｣")
 260 (modify-syntax-entry ?\｣ "(｢")
 261
 262 ;; Korean character set (KSC5601)
 263
 264 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?h)
 265
 266 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2121 #x227E)
 267 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2621 #x277E)
 268 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2830 #x287E)
 269 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2930 #x297E)
 270 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2330 #x2339)
 271 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2341 #x235A)
 272 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2361 #x237A)
 273 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?G #x2521 #x257E)
 274 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?H #x2A21 #x2A7E)
 275 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?K #x2B21 #x2B7E)
 276 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?Y #x2C21 #x2C7E)
 277
 278 ;; These are in more than one charset.
 279 (let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛"
 280                       "︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄"
 281                       "（）［］｛｝"))
 282       open close)
 283   (dotimes (i (/ (length parens) 2))
 284     (setq open (aref parens (* i 2))
 285           close (aref parens (1+ (* i 2))))
 286     (modify-syntax-entry open (format "(%c" close))
 287     (modify-syntax-entry close (format ")%c" open))))
 288
 289 ;; Arabic character set
 290
 291 (let ((charsets '(arabic-iso8859-6
 292                   arabic-digit
 293                   arabic-1-column
 294                   arabic-2-column)))
 295   (while charsets
 296     (map-charset-chars #'modify-category-entry (car charsets) ?b)
 297     (setq charsets (cdr charsets))))
 298 (modify-category-entry '(#x600 . #x6ff) ?b)
 299 (modify-category-entry '(#xfb50 . #xfdff) ?b)
 300 (modify-category-entry '(#xfe70 . #xfefe) ?b)
 301
 302 ;; Cyrillic character set (ISO-8859-5)
 303
 304 (modify-syntax-entry ?№ ".")
 305
 306 ;; Ethiopic character set
 307
 308 (modify-category-entry '(#x1200 . #x1399) ?e)
 309 (modify-category-entry '(#x2d80 . #x2dde) ?e)
 310 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨)))
 311   (while chars
 312     (modify-syntax-entry (car chars) ".")
 313     (setq chars (cdr chars))))
 314 (map-charset-chars #'modify-category-entry 'ethiopic ?e)
 315
 316 ;; Hebrew character set (ISO-8859-8)
 317
 318 (modify-syntax-entry #x5be ".") ; MAQAF
 319 (modify-syntax-entry #x5c0 ".") ; PASEQ
 320 (modify-syntax-entry #x5c3 ".") ; SOF PASUQ
 321 (modify-syntax-entry #x5f3 ".") ; GERESH
 322 (modify-syntax-entry #x5f4 ".") ; GERSHAYIM
 323
 324 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
 325
 326 (modify-category-entry '(#x901 . #x970) ?i)
 327 (map-charset-chars #'modify-category-entry 'indian-is13194 ?i)
 328 (map-charset-chars #'modify-category-entry 'indian-2-column ?i)
 329
 330 ;; Lao character set
 331
 332 (modify-category-entry '(#xe80 . #xeff) ?o)
 333 (map-charset-chars #'modify-category-entry 'lao ?o)
 334
 335 (let ((deflist  '(("ກ-ຮ"    "w"     ?0) ; consonant
 336                   ("ະາຳຽເ-ໄ"        "w"     ?1) ; vowel base
 337                   ("ັິ-ືົໍ"   "w"     ?2) ; vowel upper
 338                   ("ຸູ"     "w"     ?3) ; vowel lower
 339                   ("່-໋"    "w"     ?4) ; tone mark
 340                   ("ຼຽ"     "w"     ?9) ; semivowel lower
 341                   ("໐-໙"    "w"     ?6) ; digit
 342                   ("ຯໆ"     "_"     ?5) ; symbol
 343                   ))
 344       elm chars len syntax category to ch i)
 345   (while deflist
 346     (setq elm (car deflist))
 347     (setq chars (car elm)
 348           len (length chars)
 349           syntax (nth 1 elm)
 350           category (nth 2 elm)
 351           i 0)
 352     (while (< i len)
 353       (if (= (aref chars i) ?-)
 354           (setq i (1+ i)
 355                 to (aref chars i))
 356         (setq ch (aref chars i)
 357               to ch))
 358       (while (<= ch to)
 359         (unless (string-equal syntax "w")
 360           (modify-syntax-entry ch syntax))
 361         (modify-category-entry ch category)
 362         (setq ch (1+ ch)))
 363       (setq i (1+ i)))
 364     (setq deflist (cdr deflist))))
 365
 366 ;; Thai character set (TIS620)
 367
 368 (modify-category-entry '(#xe00 . #xe7f) ?t)
 369 (map-charset-chars #'modify-category-entry 'thai-tis620 ?t)
 370
 371 (let ((deflist  '(;; chars      syntax  category
 372                   ("ก-รลว-ฮ"  "w"     ?0) ; consonant
 373                   ("ฤฦะาำเ-ๅ"     "w"     ?1) ; vowel base
 374                   ("ัิ-ื็๎"   "w"     ?2) ; vowel upper
 375                   ("ุ-ฺ"    "w"     ?3) ; vowel lower
 376                   ("่-ํ"    "w"     ?4) ; tone mark
 377                   ("๐-๙"    "w"     ?6) ; digit
 378                   ("ฯๆ฿๏๚๛" "_"     ?5) ; symbol
 379                   ))
 380       elm chars len syntax category to ch i)
 381   (while deflist
 382     (setq elm (car deflist))
 383     (setq chars (car elm)
 384           len (length chars)
 385           syntax (nth 1 elm)
 386           category (nth 2 elm)
 387           i 0)
 388     (while (< i len)
 389       (if (= (aref chars i) ?-)
 390           (setq i (1+ i)
 391                 to (aref chars i))
 392         (setq ch (aref chars i)
 393               to ch))
 394       (while (<= ch to)
 395         (unless (string-equal syntax "w")
 396           (modify-syntax-entry ch syntax))
 397         (modify-category-entry ch category)
 398         (setq ch (1+ ch)))
 399       (setq i (1+ i)))
 400     (setq deflist (cdr deflist))))
 401
 402 ;; Tibetan character set
 403
 404 (modify-category-entry '(#xf00 . #xfff) ?q)
 405 (map-charset-chars #'modify-category-entry 'tibetan ?q)
 406 (map-charset-chars #'modify-category-entry 'tibetan-1-column ?q)
 407
 408 (let ((deflist  '(;; chars             syntax category
 409                   ("ཀ-ཀྵཪ"         "w"     ?0) ; consonant
 410                   ("ྐ-ྐྵྺྻྼ"       "w"     ?0) ;
 411                   ("ིེཻོཽྀ"       "w"       ?2) ; upper vowel
 412                   ("ཾྂྃ྆྇ྈྉྊྋ" "w"    ?2) ; upper modifier
 413                   ("྄ཱུ༙༵༷"       "w"       ?3) ; lower vowel/modifier
 414                   ("཰"                "w" ?3)             ; invisible vowel a
 415                   ("༠-༩༪-༳"             "w"     ?6) ; digit
 416                   ("་།-༒༔ཿ"        "."     ?|) ; line-break char
 417                   ("་།༏༐༑༔ཿ"            "."     ?|) ;
 418                   ("༈་།-༒༔ཿ༽༴"  "."     ?>) ; prohibition
 419                   ("་།༏༐༑༔ཿ"            "."     ?>) ;
 420                   ("ༀ-༊༼࿁࿂྅"      "."     ?<) ; prohibition
 421                   ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q) ; others
 422                   ))
 423       elm chars len syntax category to ch i)
 424   (while deflist
 425     (setq elm (car deflist))
 426     (setq chars (car elm)
 427           len (length chars)
 428           syntax (nth 1 elm)
 429           category (nth 2 elm)
 430           i 0)
 431     (while (< i len)
 432       (if (= (aref chars i) ?-)
 433           (setq i (1+ i)
 434                 to (aref chars i))
 435         (setq ch (aref chars i)
 436               to ch))
 437       (while (<= ch to)
 438         (unless (string-equal syntax "w")
 439           (modify-syntax-entry ch syntax))
 440         (modify-category-entry ch category)
 441         (setq ch (1+ ch)))
 442       (setq i (1+ i)))
 443     (setq deflist (cdr deflist))))
 444
 445 ;; Vietnamese character set
 446
 447 ;; To make a word with Latin characters
 448 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?l)
 449 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?v)
 450
 451 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?l)
 452 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?v)
 453
 454 (let ((tbl (standard-case-table))
 455       (i 32))
 456   (while (< i 128)
 457     (let* ((char (decode-char 'vietnamese-viscii-upper i))
 458            (charl (decode-char 'vietnamese-viscii-lower i))
 459            (uc (encode-char char 'ucs))
 460            (lc (encode-char charl 'ucs)))
 461       (set-case-syntax-pair char (decode-char 'vietnamese-viscii-lower i)
 462                             tbl)
 463       (if uc (modify-category-entry uc ?v))
 464       (if lc (modify-category-entry lc ?v)))
 465     (setq i (1+ i))))
 466
 467 ;; Tai Viet
 468 (let ((deflist '(;; chars       syntax  category
 469                  ((?ꪀ.  ?ꪯ) "w"     ?0) ; consonant
 470                  ("ꪱꪵꪶ"           "w"     ?1) ; vowel base
 471                  ((?ꪹ . ?ꪽ) "w"     ?1) ; vowel base
 472                  ("ꪰꪲꪳꪷꪸꪾ"  "w"     ?2) ; vowel upper
 473                  ("ꪴ"         "w"     ?3) ; vowel lower
 474                  ("ꫀꫂ"              "w"     ?1) ; non-combining tone-mark
 475                  ("꪿꫁"              "w"     ?4) ; combining tone-mark
 476                  ((?ꫛ . ?꫟) "_"     ?5) ; symbol
 477                  )))
 478   (dolist (elm deflist)
 479     (let ((chars (car elm))
 480           (syntax (nth 1 elm))
 481           (category (nth 2 elm)))
 482       (if (consp chars)
 483           (progn
 484             (modify-syntax-entry chars syntax)
 485             (modify-category-entry chars category))
 486         (mapc #'(lambda (x)
 487                   (modify-syntax-entry x syntax)
 488                   (modify-category-entry x category))
 489               chars)))))
 490
 491 ;; Bidi categories
 492
 493 (map-char-table (lambda (key val)
 494                   (cond
 495                    ((memq val '(R AL RLO RLE))
 496                     (modify-category-entry key ?R))
 497                    ((memq val '(L LRE LRO))
 498                     (modify-category-entry key ?L))))
 499                 (unicode-property-table-internal 'bidi-class))
 500
 501 ;; Latin
 502
 503 (modify-category-entry '(#x80 . #x024F) ?l)
 504
 505 (let ((tbl (standard-case-table)) c)
 506
 507   ;; Latin-1
 508
 509   ;; Fixme: Some of the non-word syntaxes here perhaps should be
 510   ;; reviewed.  (Note that the following all implicitly have word
 511   ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.)  There should be a well-defined way of
 512   ;; relating Unicode categories to Emacs syntax codes.
 513
 514   ;; NBSP isn't semantically interchangeable with other whitespace chars,
 515   ;; so it's more like punctuation.
 516   (set-case-syntax ?  "." tbl)
 517   (set-case-syntax ?¡ "." tbl)
 518   (set-case-syntax ?¦ "_" tbl)
 519   (set-case-syntax ?§ "." tbl)
 520   (set-case-syntax ?© "_" tbl)
 521   (set-case-syntax-delims 171 187 tbl)  ; « »
 522   (set-case-syntax ?¬ "_" tbl)
 523   (set-case-syntax ? "_" tbl)
 524   (set-case-syntax ?® "_" tbl)
 525   (set-case-syntax ?° "_" tbl)
 526   (set-case-syntax ?± "_" tbl)
 527   (set-case-syntax ?µ "_" tbl)
 528   (set-case-syntax ?· "_" tbl)
 529   (set-case-syntax ?¼ "_" tbl)
 530   (set-case-syntax ?½ "_" tbl)
 531   (set-case-syntax ?¾ "_" tbl)
 532   (set-case-syntax ?¿ "." tbl)
 533   (let ((c 192))
 534     (while (<= c 222)
 535       (set-case-syntax-pair c (+ c 32) tbl)
 536       (setq c (1+ c))))
 537   (set-case-syntax ?× "_" tbl)
 538   (set-case-syntax ?ß "w" tbl)
 539   (set-case-syntax ?÷ "_" tbl)
 540   ;; See below for ÿ.
 541
 542   ;; Latin Extended-A, Latin Extended-B
 543   (setq c #x0100)
 544   (while (<= c #x02B8)
 545     (modify-category-entry c ?l)
 546     (setq c (1+ c)))
 547
 548   (let ((pair-ranges '((#x0100 . #x012F)
 549                        (#x0132 . #x0137)
 550                        (#x0139 . #x0148)
 551                        (#x014a . #x0177)
 552                        (#x0179 . #x017E)
 553                        (#x0182 . #x0185)
 554                        (#x0187 . #x0188)
 555                        (#x018B . #x018C)
 556                        (#x0191 . #x0192)
 557                        (#x0198 . #x0199)
 558                        (#x01A0 . #x01A5)
 559                        (#x01A7 . #x01A8)
 560                        (#x01AC . #x01AD)
 561                        (#x01AF . #x01B0)
 562                        (#x01B3 . #x01B6)
 563                        (#x01B8 . #x01B9)
 564                        (#x01BC . #x01BD)
 565                        (#x01CD . #x01DC)
 566                        (#x01DE . #x01EF)
 567                        (#x01F4 . #x01F5)
 568                        (#x01F8 . #x021F)
 569                        (#x0222 . #x0233)
 570                        (#x023B . #x023C)
 571                        (#x0241 . #x0242)
 572                        (#x0246 . #x024F))))
 573     (dolist (elt pair-ranges)
 574       (let ((from (car elt)) (to (cdr elt)))
 575         (while (< from to)
 576           (set-case-syntax-pair from (1+ from) tbl)
 577           (setq from (+ from 2))))))
 578
 579   (set-case-syntax-pair ?Ÿ ?ÿ tbl)
 580
 581   ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
 582   ;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
 583   ;; do U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN
 584   ;; SMALL LETTER I.
 585
 586   ;; We used to set up half of those correspondence unconditionally,
 587   ;; but that makes searches slow.  So now we don't set up either half
 588   ;; of these correspondences by default.
 589
 590   ;; (set-downcase-syntax  ?İ ?i tbl)
 591   ;; (set-upcase-syntax    ?I ?ı tbl)
 592
 593   (set-case-syntax-pair ?Ɓ ?ɓ tbl)
 594   (set-case-syntax-pair ?Ɔ ?ɔ tbl)
 595   (set-case-syntax-pair ?Ɖ ?ɖ tbl)
 596   (set-case-syntax-pair ?Ɗ ?ɗ tbl)
 597   (set-case-syntax-pair ?Ǝ ?ǝ tbl)
 598   (set-case-syntax-pair ?Ə ?ə tbl)
 599   (set-case-syntax-pair ?Ɛ ?ɛ tbl)
 600   (set-case-syntax-pair ?Ɠ ?ɠ tbl)
 601   (set-case-syntax-pair ?Ɣ ?ɣ tbl)
 602   (set-case-syntax-pair ?Ɩ ?ɩ tbl)
 603   (set-case-syntax-pair ?Ɨ ?ɨ tbl)
 604   (set-case-syntax-pair ?Ɯ ?ɯ tbl)
 605   (set-case-syntax-pair ?Ɲ ?ɲ tbl)
 606   (set-case-syntax-pair ?Ɵ ?ɵ tbl)
 607   (set-case-syntax-pair ?Ʀ ?ʀ tbl)
 608   (set-case-syntax-pair ?Ʃ ?ʃ tbl)
 609   (set-case-syntax-pair ?Ʈ ?ʈ tbl)
 610   (set-case-syntax-pair ?Ʊ ?ʊ tbl)
 611   (set-case-syntax-pair ?Ʋ ?ʋ tbl)
 612   (set-case-syntax-pair ?Ʒ ?ʒ tbl)
 613   (set-case-syntax-pair ?Ǆ ?ǆ tbl)
 614   (set-case-syntax-pair ?ǅ ?ǆ tbl)
 615   (set-case-syntax-pair ?Ǉ ?ǉ tbl)
 616   (set-case-syntax-pair ?ǈ ?ǉ tbl)
 617   (set-case-syntax-pair ?Ǌ ?ǌ tbl)
 618   (set-case-syntax-pair ?ǋ ?ǌ tbl)
 619
 620   ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
 621   (set-case-syntax-pair ?Ǳ ?ǳ tbl)
 622   (set-case-syntax-pair ?ǲ ?ǳ tbl)
 623   (set-case-syntax-pair ?Ƕ ?ƕ tbl)
 624   (set-case-syntax-pair ?Ƿ ?ƿ tbl)
 625   (set-case-syntax-pair ?Ⱥ ?ⱥ tbl)
 626   (set-case-syntax-pair ?Ƚ ?ƚ tbl)
 627   (set-case-syntax-pair ?Ⱦ ?ⱦ tbl)
 628   (set-case-syntax-pair ?Ƀ ?ƀ tbl)
 629   (set-case-syntax-pair ?Ʉ ?ʉ tbl)
 630   (set-case-syntax-pair ?Ʌ ?ʌ tbl)
 631
 632   ;; Latin Extended Additional
 633   (modify-category-entry '(#x1e00 . #x1ef9) ?l)
 634   (setq c #x1e00)
 635   (while (<= c #x1ef9)
 636     (and (zerop (% c 2))
 637          (or (<= c #x1e94) (>= c #x1ea0))
 638          (set-case-syntax-pair c (1+ c) tbl))
 639     (setq c (1+ c)))
 640
 641   ;; Greek
 642   (modify-category-entry '(#x0370 . #x03ff) ?g)
 643   (setq c #x0370)
 644   (while (<= c #x03ff)
 645     (if (or (and (>= c #x0391) (<= c #x03a1))
 646             (and (>= c #x03a3) (<= c #x03ab)))
 647         (set-case-syntax-pair c (+ c 32) tbl))
 648     (and (>= c #x03da)
 649          (<= c #x03ee)
 650          (zerop (% c 2))
 651          (set-case-syntax-pair c (1+ c) tbl))
 652     (setq c (1+ c)))
 653   (set-case-syntax-pair ?Ά ?ά tbl)
 654   (set-case-syntax-pair ?Έ ?έ tbl)
 655   (set-case-syntax-pair ?Ή ?ή tbl)
 656   (set-case-syntax-pair ?Ί ?ί tbl)
 657   (set-case-syntax-pair ?Ό ?ό tbl)
 658   (set-case-syntax-pair ?Ύ ?ύ tbl)
 659   (set-case-syntax-pair ?Ώ ?ώ tbl)
 660
 661   ;; Armenian
 662   (setq c #x531)
 663   (while (<= c #x556)
 664     (set-case-syntax-pair c (+ c #x30) tbl)
 665     (setq c (1+ c)))
 666
 667   ;; Greek Extended
 668   (modify-category-entry '(#x1f00 . #x1fff) ?g)
 669   (setq c #x1f00)
 670   (while (<= c #x1fff)
 671     (and (<= (logand c #x000f) 7)
 672          (<= c #x1fa7)
 673          (not (memq c '(#x1f16 #x1f17 #x1f56 #x1f57
 674                                #x1f50 #x1f52 #x1f54 #x1f56)))
 675          (/= (logand c #x00f0) #x70)
 676          (set-case-syntax-pair (+ c 8) c tbl))
 677     (setq c (1+ c)))
 678   (set-case-syntax-pair ?Ᾰ ?ᾰ tbl)
 679   (set-case-syntax-pair ?Ᾱ ?ᾱ tbl)
 680   (set-case-syntax-pair ?Ὰ ?ὰ tbl)
 681   (set-case-syntax-pair ?Ά ?ά tbl)
 682   (set-case-syntax-pair ?ᾼ ?ᾳ tbl)
 683   (set-case-syntax-pair ?Ὲ ?ὲ tbl)
 684   (set-case-syntax-pair ?Έ ?έ tbl)
 685   (set-case-syntax-pair ?Ὴ ?ὴ tbl)
 686   (set-case-syntax-pair ?Ή ?ή tbl)
 687   (set-case-syntax-pair ?ῌ ?ῃ tbl)
 688   (set-case-syntax-pair ?Ῐ ?ῐ tbl)
 689   (set-case-syntax-pair ?Ῑ ?ῑ tbl)
 690   (set-case-syntax-pair ?Ὶ ?ὶ tbl)
 691   (set-case-syntax-pair ?Ί ?ί tbl)
 692   (set-case-syntax-pair ?Ῠ ?ῠ tbl)
 693   (set-case-syntax-pair ?Ῡ ?ῡ tbl)
 694   (set-case-syntax-pair ?Ὺ ?ὺ tbl)
 695   (set-case-syntax-pair ?Ύ ?ύ tbl)
 696   (set-case-syntax-pair ?Ῥ ?ῥ tbl)
 697   (set-case-syntax-pair ?Ὸ ?ὸ tbl)
 698   (set-case-syntax-pair ?Ό ?ό tbl)
 699   (set-case-syntax-pair ?Ὼ ?ὼ tbl)
 700   (set-case-syntax-pair ?Ώ ?ώ tbl)
 701   (set-case-syntax-pair ?ῼ ?ῳ tbl)
 702
 703   ;; cyrillic
 704   (modify-category-entry '(#x0400 . #x04FF) ?y)
 705   (setq c #x0400)
 706   (while (<= c #x04ff)
 707     (and (>= c #x0400)
 708          (<= c #x040f)
 709          (set-case-syntax-pair c (+ c 80) tbl))
 710     (and (>= c #x0410)
 711          (<= c #x042f)
 712          (set-case-syntax-pair c (+ c 32) tbl))
 713     (and (zerop (% c 2))
 714          (or (and (>= c #x0460) (<= c #x0480))
 715              (and (>= c #x048c) (<= c #x04be))
 716              (and (>= c #x04d0) (<= c #x04f4)))
 717          (set-case-syntax-pair c (1+ c) tbl))
 718     (setq c (1+ c)))
 719   (set-case-syntax-pair ?Ӂ ?ӂ tbl)
 720   (set-case-syntax-pair ?Ӄ ?ӄ tbl)
 721   (set-case-syntax-pair ?Ӈ ?ӈ tbl)
 722   (set-case-syntax-pair ?Ӌ ?ӌ tbl)
 723   (set-case-syntax-pair ?Ӹ ?ӹ tbl)
 724
 725   ;; general punctuation
 726   (setq c #x2000)
 727   (while (<= c #x200b)
 728     (set-case-syntax c " " tbl)
 729     (setq c (1+ c)))
 730   (while (<= c #x200F)
 731     (set-case-syntax c "." tbl)
 732     (setq c (1+ c)))
 733   ;; Fixme: These aren't all right:
 734   (setq c #x2010)
 735   (while (<= c #x2016)
 736     (set-case-syntax c "_" tbl)
 737     (setq c (1+ c)))
 738   ;; Punctuation syntax for quotation marks (like `)
 739   (while (<= c #x201f)
 740     (set-case-syntax  c "." tbl)
 741     (setq c (1+ c)))
 742   ;; Fixme: These aren't all right:
 743   (while (<= c #x2027)
 744     (set-case-syntax c "_" tbl)
 745     (setq c (1+ c)))
 746   (while (<= c #x206F)
 747     (set-case-syntax c "." tbl)
 748     (setq c (1+ c)))
 749
 750   ;; Roman numerals
 751   (setq c #x2160)
 752   (while (<= c #x216f)
 753     (set-case-syntax-pair c (+ c #x10) tbl)
 754     (setq c (1+ c)))
 755
 756   ;; Fixme: The following blocks might be better as symbol rather than
 757   ;; punctuation.
 758   ;; Arrows
 759   (setq c #x2190)
 760   (while (<= c #x21FF)
 761     (set-case-syntax c "." tbl)
 762     (setq c (1+ c)))
 763   ;; Mathematical Operators
 764   (while (<= c #x22FF)
 765     (set-case-syntax c "." tbl)
 766     (setq c (1+ c)))
 767   ;; Miscellaneous Technical
 768   (while (<= c #x23FF)
 769     (set-case-syntax c "." tbl)
 770     (setq c (1+ c)))
 771   ;; Control Pictures
 772   (while (<= c #x243F)
 773     (set-case-syntax c "_" tbl)
 774     (setq c (1+ c)))
 775
 776   ;; Circled Latin
 777   (setq c #x24b6)
 778   (while (<= c #x24cf)
 779     (set-case-syntax-pair c (+ c 26) tbl)
 780     (modify-category-entry c ?l)
 781     (modify-category-entry (+ c 26) ?l)
 782     (setq c (1+ c)))
 783
 784   ;; Fullwidth Latin
 785   (setq c #xff21)
 786   (while (<= c #xff3a)
 787     (set-case-syntax-pair c (+ c #x20) tbl)
 788     (modify-category-entry c ?l)
 789     (modify-category-entry (+ c #x20) ?l)
 790     (setq c (1+ c)))
 791
 792   ;; Combining diacritics
 793   (modify-category-entry '(#x300 . #x362) ?^)
 794   ;; Combining marks
 795   (modify-category-entry '(#x20d0 . #x20e3) ?^)
 796
 797   ;; Fixme: syntax for symbols &c
 798   )
 799
 800 (let ((pairs
 801        '("⁅⁆"                               ; U+2045 U+2046
 802          "⁽⁾"                               ; U+207D U+207E
 803          "₍₎"                               ; U+208D U+208E
 804          "〈〉"                               ; U+2329 U+232A
 805          "⎴⎵"                               ; U+23B4 U+23B5
 806          "❨❩"                               ; U+2768 U+2769
 807          "❪❫"                               ; U+276A U+276B
 808          "❬❭"                               ; U+276C U+276D
 809          "❰❱"                               ; U+2770 U+2771
 810          "❲❳"                               ; U+2772 U+2773
 811          "❴❵"                               ; U+2774 U+2775
 812          "⟦⟧"                               ; U+27E6 U+27E7
 813          "⟨⟩"                               ; U+27E8 U+27E9
 814          "⟪⟫"                               ; U+27EA U+27EB
 815          "⦃⦄"                               ; U+2983 U+2984
 816          "⦅⦆"                               ; U+2985 U+2986
 817          "⦇⦈"                               ; U+2987 U+2988
 818          "⦉⦊"                               ; U+2989 U+298A
 819          "⦋⦌"                               ; U+298B U+298C
 820          "⦍⦎"                               ; U+298D U+298E
 821          "⦏⦐"                               ; U+298F U+2990
 822          "⦑⦒"                               ; U+2991 U+2992
 823          "⦓⦔"                               ; U+2993 U+2994
 824          "⦕⦖"                               ; U+2995 U+2996
 825          "⦗⦘"                               ; U+2997 U+2998
 826          "⧼⧽"                               ; U+29FC U+29FD
 827          "〈〉"                               ; U+3008 U+3009
 828          "《》"                               ; U+300A U+300B
 829          "「」"                               ; U+300C U+300D
 830          "『』"                               ; U+300E U+300F
 831          "【】"                               ; U+3010 U+3011
 832          "〔〕"                               ; U+3014 U+3015
 833          "〖〗"                               ; U+3016 U+3017
 834          "〘〙"                               ; U+3018 U+3019
 835          "〚〛"                               ; U+301A U+301B
 836          "﴾﴿"                               ; U+FD3E U+FD3F
 837          "︵︶"                               ; U+FE35 U+FE36
 838          "︷︸"                               ; U+FE37 U+FE38
 839          "︹︺"                               ; U+FE39 U+FE3A
 840          "︻︼"                               ; U+FE3B U+FE3C
 841          "︽︾"                               ; U+FE3D U+FE3E
 842          "︿﹀"                               ; U+FE3F U+FE40
 843          "﹁﹂"                               ; U+FE41 U+FE42
 844          "﹃﹄"                               ; U+FE43 U+FE44
 845          "﹙﹚"                               ; U+FE59 U+FE5A
 846          "﹛﹜"                               ; U+FE5B U+FE5C
 847          "﹝﹞"                               ; U+FE5D U+FE5E
 848          "（）"                               ; U+FF08 U+FF09
 849          "［］"                               ; U+FF3B U+FF3D
 850          "｛｝"                               ; U+FF5B U+FF5D
 851          "｟｠"                               ; U+FF5F U+FF60
 852          "｢｣"                               ; U+FF62 U+FF63
 853          )))
 854   (dolist (elt pairs)
 855     (modify-syntax-entry (aref elt 0) (string ?\( (aref elt 1)))
 856     (modify-syntax-entry (aref elt 1) (string ?\) (aref elt 0)))))
 857
 858 \f
 859 ;; For each character set, put the information of the most proper
 860 ;; coding system to encode it by `preferred-coding-system' property.
 861
 862 ;; Fixme: should this be junked?
 863 (let ((l '((latin-iso8859-1     . iso-latin-1)
 864            (latin-iso8859-2     . iso-latin-2)
 865            (latin-iso8859-3     . iso-latin-3)
 866            (latin-iso8859-4     . iso-latin-4)
 867            (thai-tis620         . thai-tis620)
 868            (greek-iso8859-7     . greek-iso-8bit)
 869            (arabic-iso8859-6    . iso-2022-7bit)
 870            (hebrew-iso8859-8    . hebrew-iso-8bit)
 871            (katakana-jisx0201   . japanese-shift-jis)
 872            (latin-jisx0201      . japanese-shift-jis)
 873            (cyrillic-iso8859-5  . cyrillic-iso-8bit)
 874            (latin-iso8859-9     . iso-latin-5)
 875            (japanese-jisx0208-1978 . iso-2022-jp)
 876            (chinese-gb2312      . chinese-iso-8bit)
 877            (chinese-gbk         . chinese-gbk)
 878            (gb18030-2-byte      . chinese-gb18030)
 879            (gb18030-4-byte-bmp  . chinese-gb18030)
 880            (gb18030-4-byte-smp  . chinese-gb18030)
 881            (gb18030-4-byte-ext-1 . chinese-gb18030)
 882            (gb18030-4-byte-ext-2 . chinese-gb18030)
 883            (japanese-jisx0208   . iso-2022-jp)
 884            (korean-ksc5601      . iso-2022-kr)
 885            (japanese-jisx0212   . iso-2022-jp)
 886            (chinese-big5-1      . chinese-big5)
 887            (chinese-big5-2      . chinese-big5)
 888            (chinese-sisheng     . iso-2022-7bit)
 889            (ipa                 . iso-2022-7bit)
 890            (vietnamese-viscii-lower . vietnamese-viscii)
 891            (vietnamese-viscii-upper . vietnamese-viscii)
 892            (arabic-digit        . iso-2022-7bit)
 893            (arabic-1-column     . iso-2022-7bit)
 894            (lao                 . lao)
 895            (arabic-2-column     . iso-2022-7bit)
 896            (indian-is13194      . devanagari)
 897            (indian-glyph        . devanagari)
 898            (tibetan-1-column    . tibetan)
 899            (ethiopic            . iso-2022-7bit)
 900            (chinese-cns11643-1  . iso-2022-cn)
 901            (chinese-cns11643-2  . iso-2022-cn)
 902            (chinese-cns11643-3  . iso-2022-cn)
 903            (chinese-cns11643-4  . iso-2022-cn)
 904            (chinese-cns11643-5  . iso-2022-cn)
 905            (chinese-cns11643-6  . iso-2022-cn)
 906            (chinese-cns11643-7  . iso-2022-cn)
 907            (indian-2-column     . devanagari)
 908            (tibetan             . tibetan)
 909            (latin-iso8859-14    . iso-latin-8)
 910            (latin-iso8859-15    . iso-latin-9))))
 911   (while l
 912     (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
 913     (setq l (cdr l))))
 914
 915 \f
 916 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
 917 ;; SPACE and NEWLINE are already set.
 918
 919 (set-char-table-range auto-fill-chars '(#x3041 . #x30FF) t)
 920 (set-char-table-range auto-fill-chars '(#x3400 . #x4DB5) t)
 921 (set-char-table-range auto-fill-chars '(#x4e00 . #x9fbb) t)
 922 (set-char-table-range auto-fill-chars '(#xF900 . #xFAFF) t)
 923 (set-char-table-range auto-fill-chars '(#xFF00 . #xFF9F) t)
 924 (set-char-table-range auto-fill-chars '(#x20000 . #x2FFFF) t)
 925
 926 \f
 927 ;;; Setting char-width-table.  The default is 1.
 928
 929 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
 930 ;;    and final characters.
 931 (let ((l '((#x0300 . #x036F)
 932            (#x0483 . #x0489)
 933            (#x0591 . #x05BD)
 934            (#x05BF . #x05BF)
 935            (#x05C1 . #x05C2)
 936            (#x05C4 . #x05C5)
 937            (#x05C7 . #x05C7)
 938            (#x0600 . #x0603)
 939            (#x0610 . #x0615)
 940            (#x064B . #x065E)
 941            (#x0670 . #x0670)
 942            (#x06D6 . #x06E4)
 943            (#x06E7 . #x06E8)
 944            (#x06EA . #x06ED)
 945            (#x070F . #x070F)
 946            (#x0711 . #x0711)
 947            (#x0730 . #x074A)
 948            (#x07A6 . #x07B0)
 949            (#x07EB . #x07F3)
 950            (#x0901 . #x0902)
 951            (#x093C . #x093C)
 952            (#x0941 . #x0948)
 953            (#x094D . #x094D)
 954            (#x0951 . #x0954)
 955            (#x0962 . #x0963)
 956            (#x0981 . #x0981)
 957            (#x09BC . #x09BC)
 958            (#x09C1 . #x09C4)
 959            (#x09CD . #x09CD)
 960            (#x09E2 . #x09E3)
 961            (#x0A01 . #x0A02)
 962            (#x0A3C . #x0A3C)
 963            (#x0A41 . #x0A4D)
 964            (#x0A70 . #x0A71)
 965            (#x0A81 . #x0A82)
 966            (#x0ABC . #x0ABC)
 967            (#x0AC1 . #x0AC8)
 968            (#x0ACD . #x0ACD)
 969            (#x0AE2 . #x0AE3)
 970            (#x0B01 . #x0B01)
 971            (#x0B3C . #x0B3C)
 972            (#x0B3F . #x0B3F)
 973            (#x0B41 . #x0B43)
 974            (#x0B4D . #x0B56)
 975            (#x0B82 . #x0B82)
 976            (#x0BC0 . #x0BC0)
 977            (#x0BCD . #x0BCD)
 978            (#x0C3E . #x0C40)
 979            (#x0C46 . #x0C56)
 980            (#x0CBC . #x0CBC)
 981            (#x0CBF . #x0CBF)
 982            (#x0CC6 . #x0CC6)
 983            (#x0CCC . #x0CCD)
 984            (#x0CE2 . #x0CE3)
 985            (#x0D41 . #x0D43)
 986            (#x0D4D . #x0D4D)
 987            (#x0DCA . #x0DCA)
 988            (#x0DD2 . #x0DD6)
 989            (#x0E31 . #x0E31)
 990            (#x0E34 . #x0E3A)
 991            (#x0E47 . #x0E4E)
 992            (#x0EB1 . #x0EB1)
 993            (#x0EB4 . #x0EBC)
 994            (#x0EC8 . #x0ECD)
 995            (#x0F18 . #x0F19)
 996            (#x0F35 . #x0F35)
 997            (#x0F37 . #x0F37)
 998            (#x0F39 . #x0F39)
 999            (#x0F71 . #x0F7E)
1000            (#x0F80 . #x0F84)
1001            (#x0F86 . #x0F87)
1002            (#x0F90 . #x0FBC)
1003            (#x0FC6 . #x0FC6)
1004            (#x102D . #x1030)
1005            (#x1032 . #x1037)
1006            (#x1039 . #x1039)
1007            (#x1058 . #x1059)
1008            (#x1160 . #x11FF)
1009            (#x135F . #x135F)
1010            (#x1712 . #x1714)
1011            (#x1732 . #x1734)
1012            (#x1752 . #x1753)
1013            (#x1772 . #x1773)
1014            (#x17B4 . #x17B5)
1015            (#x17B7 . #x17BD)
1016            (#x17C6 . #x17C6)
1017            (#x17C9 . #x17D3)
1018            (#x17DD . #x17DD)
1019            (#x180B . #x180D)
1020            (#x18A9 . #x18A9)
1021            (#x1920 . #x1922)
1022            (#x1927 . #x1928)
1023            (#x1932 . #x1932)
1024            (#x1939 . #x193B)
1025            (#x1A17 . #x1A18)
1026            (#x1B00 . #x1B03)
1027            (#x1B34 . #x1B34)
1028            (#x1B36 . #x1B3A)
1029            (#x1B3C . #x1B3C)
1030            (#x1B42 . #x1B42)
1031            (#x1B6B . #x1B73)
1032            (#x1DC0 . #x1DFF)
1033            (#x200B . #x200F)
1034            (#x202A . #x202E)
1035            (#x2060 . #x206F)
1036            (#x20D0 . #x20EF)
1037            (#x302A . #x302F)
1038            (#x3099 . #x309A)
1039            (#xA806 . #xA806)
1040            (#xA80B . #xA80B)
1041            (#xA825 . #xA826)
1042            (#xFB1E . #xFB1E)
1043            (#xFE00 . #xFE0F)
1044            (#xFE20 . #xFE23)
1045            (#xFEFF . #xFEFF)
1046            (#xFFF9 . #xFFFB)
1047            (#x10A01 . #x10A0F)
1048            (#x10A38 . #x10A3F)
1049            (#x1D167 . #x1D169)
1050            (#x1D173 . #x1D182)
1051            (#x1D185 . #x1D18B)
1052            (#x1D1AA . #x1D1AD)
1053            (#x1D242 . #x1D244)
1054            (#xE0001 . #xE01EF))))
1055   (dolist (elt l)
1056     (set-char-table-range char-width-table elt 0)))
1057
1058 ;; 2: East Asian Wide and Full-width characters.
1059 (let ((l '((#x1100 . #x115F)
1060            (#x2329 . #x232A)
1061            (#x2E80 . #x303E)
1062            (#x3040 . #xA4CF)
1063            (#xAC00 . #xD7A3)
1064            (#xF900 . #xFAFF)
1065            (#xFE30 . #xFE6F)
1066            (#xFF01 . #xFF60)
1067            (#xFFE0 . #xFFE6)
1068            (#x20000 . #x2FFFF)
1069            (#x30000 . #x3FFFF))))
1070   (dolist (elt l)
1071     (set-char-table-range char-width-table elt 2)))
1072
1073 ;; Other double width
1074 ;;(map-charset-chars
1075 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1076 ;; 'ethiopic)
1077 ;; (map-charset-chars
1078 ;;  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1079 ;; 'tibetan)
1080 (map-charset-chars
1081  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1082  'indian-2-column)
1083 (map-charset-chars
1084  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1085  'arabic-2-column)
1086
1087 ;; Internal use only.
1088 ;; Alist of locale symbol vs charsets.  In a language environment
1089 ;; corresponding to the locale, width of characters in the charsets is
1090 ;; set to 2.  Each element has the form:
1091 ;;   (LOCALE TABLE (CHARSET (FROM-CODE . TO-CODE) ...) ...)
1092 ;; LOCALE: locale symbol
1093 ;; TABLE: char-table used for char-width-table, initially nil.
1094 ;; CAHRSET: character set
1095 ;; FROM-CODE, TO-CODE: range of code-points in CHARSET
1096
1097 (defvar cjk-char-width-table-list
1098   '((ja_JP nil (japanese-jisx0208 (#x2121 . #x287E))
1099                (cp932-2-byte (#x8140 . #x879F)))
1100     (zh_CN nil (chinese-gb2312 (#x2121 . #x297E)))
1101     (zh_HK nil (big5-hkscs (#xA140 . #xA3FE) (#xC6A0 . #xC8FE)))
1102     (zh_TW nil (big5 (#xA140 . #xA3FE))
1103                (chinese-cns11643-1 (#x2121 . #x427E)))
1104     (ko_KR nil (korean-ksc5601 (#x2121 . #x2C7E)))))
1105
1106 ;; Internal use only.
1107 ;; Setup char-width-table appropriate for a language environment
1108 ;; corresponding to LOCALE-NAME (symbol).
1109
1110 (defun use-cjk-char-width-table (locale-name)
1111   (while (char-table-parent char-width-table)
1112     (setq char-width-table (char-table-parent char-width-table)))
1113   (let ((slot (assq locale-name cjk-char-width-table-list))
1114         table)
1115     (or slot (error "Unknown locale for CJK language environment: %s"
1116                     locale-name))
1117     (unless (nth 1 slot)
1118       (let ((table (make-char-table nil)))
1119         (dolist (charset-info (nthcdr 2 slot))
1120           (let ((charset (car charset-info)))
1121             (dolist (code-range (cdr charset-info))
1122               (map-charset-chars #'(lambda (range arg)
1123                                      (set-char-table-range table range 2))
1124                                  charset nil
1125                                  (car code-range) (cdr code-range)))))
1126         (optimize-char-table table)
1127         (set-char-table-parent table char-width-table)
1128         (setcar (cdr slot) table)))
1129     (setq char-width-table (nth 1 slot))))
1130
1131 (defun use-default-char-width-table ()
1132   "Internal use only.
1133 Setup char-width-table appropriate for non-CJK language environment."
1134   (while (char-table-parent char-width-table)
1135     (setq char-width-table (char-table-parent char-width-table))))
1136
1137 (optimize-char-table (standard-case-table))
1138 (optimize-char-table (standard-syntax-table))
1139
1140 \f
1141 ;; Setting char-script-table.
1142
1143 ;; The data is compiled from Blocks.txt and Scripts.txt in the
1144 ;; "Unicode Character Database", simplified to lump together all the
1145 ;; blocks belonging to the same language.  E.g., "Basic Latin",
1146 ;; "Latin-1 Supplement", "Latin Extended-A", etc. are all lumped
1147 ;; together under "latin".
1148 ;;
1149 ;; The Unicode blocks actually extend past some of these ranges with
1150 ;; undefined codepoints.
1151 (let ((script-list nil))
1152   (dolist
1153       (elt
1154        '((#x0000 #x007F latin)
1155          (#x00A0 #x024F latin)
1156          (#x0250 #x02AF phonetic)
1157          (#x02B0 #x036F latin)
1158          (#x0370 #x03E1 greek)
1159          (#x03E2 #x03EF coptic)
1160          (#x03F0 #x03F3 greek)
1161          (#x0400 #x052F cyrillic)
1162          (#x0530 #x058F armenian)
1163          (#x0590 #x05FF hebrew)
1164          (#x0600 #x06FF arabic)
1165          (#x0700 #x074F syriac)
1166          (#x0750 #x077F arabic)
1167          (#x0780 #x07BF thaana)
1168          (#x07C0 #x07FF nko)
1169          (#x0800 #x083F samaritan)
1170          (#x0840 #x085F mandaic)
1171          (#x08A0 #x08FF arabic)
1172          (#x0900 #x097F devanagari)
1173          (#x0980 #x09FF bengali)
1174          (#x0A00 #x0A7F gurmukhi)
1175          (#x0A80 #x0AFF gujarati)
1176          (#x0B00 #x0B7F oriya)
1177          (#x0B80 #x0BFF tamil)
1178          (#x0C00 #x0C7F telugu)
1179          (#x0C80 #x0CFF kannada)
1180          (#x0D00 #x0D7F malayalam)
1181          (#x0D80 #x0DFF sinhala)
1182          (#x0E00 #x0E7F thai)
1183          (#x0E80 #x0EFF lao)
1184          (#x0F00 #x0FFF tibetan)
1185          (#x1000 #x109F burmese) ; according to Unicode 6.1, should be "myanmar"
1186          (#x10A0 #x10FF georgian)
1187          (#x1100 #x11FF hangul)
1188          (#x1200 #x139F ethiopic)
1189          (#x13A0 #x13FF cherokee)
1190          (#x1400 #x167F canadian-aboriginal)
1191          (#x1680 #x169F ogham)
1192          (#x16A0 #x16FF runic)
1193          (#x1700 #x171F tagalog)
1194          (#x1720 #x173F hanunoo)
1195          (#x1740 #x175F buhid)
1196          (#x1760 #x177F tagbanwa)
1197          (#x1780 #x17FF khmer)
1198          (#x1800 #x18AF mongolian)
1199          (#x18B0 #x18FF canadian-aboriginal)
1200          (#x1900 #x194F limbu)
1201          (#x1950 #x197F tai-le)
1202          (#x1980 #x19DF tai-lue)
1203          (#x19E0 #x19FF khmer)
1204          (#x1A00 #x1A00 buginese)
1205          (#x1A20 #x1AAF tai-tham)
1206          (#x1B00 #x1B7F balinese)
1207          (#x1B80 #x1BBF sundanese)
1208          (#x1BC0 #x1BFF batak)
1209          (#x1C00 #x1C4F lepcha)
1210          (#x1C50 #x1C7F ol-chiki)
1211          (#x1CC0 #x1CCF sundanese)
1212          (#x1CD0 #x1CFF vedic)
1213          (#x1D00 #x1DBF phonetic)
1214          (#x1DC0 #x1EFF latin)
1215          (#x1F00 #x1FFF greek)
1216          (#x2000 #x27FF symbol)
1217          (#x2800 #x28FF braille)
1218          (#x2900 #x2BFF symbol)
1219          (#x2C00 #x2C5F glagolitic)
1220          (#x2C60 #x2C7F latin)
1221          (#x2C80 #x2CFF coptic)
1222          (#x2D00 #x2D2F georgian)
1223          (#x2D30 #x2D7F tifinagh)
1224          (#x2D80 #x2DDF ethiopic)
1225          (#x2DE0 #x2DFF cyrillic)
1226          (#x2E00 #x2E7F symbol)
1227          (#x2E80 #x2FDF han)
1228          (#x2FF0 #x2FFF ideographic-description)
1229          (#x3000 #x303F cjk-misc)
1230          (#x3040 #x30FF kana)
1231          (#x3100 #x312F bopomofo)
1232          (#x3130 #x318F hangul)
1233          (#x3190 #x319F kanbun)
1234          (#x31A0 #x31BF bopomofo)
1235          (#x31C0 #x31EF cjk-misc)
1236          (#x31F0 #x31FF kana)
1237          (#x3200 #x9FAF han)
1238          (#xA000 #xA4CF yi)
1239          (#xA4D0 #xA4FF lisu)
1240          (#xA500 #xA63F vai)
1241          (#xA640 #xA69F cyrillic)
1242          (#xA6A0 #xA6FF bamum)
1243          (#xA700 #xA7FF latin)
1244          (#xA800 #xA82F syloti-nagri)
1245          (#xA830 #xA83F north-indic-number)
1246          (#xA840 #xA87F phags-pa)
1247          (#xA880 #xA8DF saurashtra)
1248          (#xA8E0 #xA8FF devanagari)
1249          (#xA900 #xA92F kayah-li)
1250          (#xA930 #xA95F rejang)
1251          (#xA960 #xA97F hangul)
1252          (#xA980 #xA9DF javanese)
1253          (#xAA00 #xAA5F cham)
1254          (#xAA60 #xAA7B burmese)        ; Unicode 6.1: "myanmar"
1255          (#xAA80 #xAADF tai-viet)
1256          (#xAAE0 #xAAFF meetei-mayek)
1257          (#xAB00 #xAB2F ethiopic)
1258          (#xABC0 #xABFF meetei-mayek)
1259          (#xAC00 #xD7FF hangul)
1260          (#xF900 #xFAFF han)
1261          (#xFB1D #xFB4F hebrew)
1262          (#xFB50 #xFDFF arabic)
1263          (#xFE30 #xFE4F han)
1264          (#xFE70 #xFEFF arabic)
1265          (#xFF00 #xFF5F cjk-misc)
1266          (#xFF61 #xFF9F kana)
1267          (#xFFE0 #xFFE6 cjk-misc)
1268          (#x10000 #x100FF linear-b)
1269          (#x10100 #x1013F aegean-number)
1270          (#x10140 #x1018F ancient-greek-number)
1271          (#x10190 #x101CF ancient-symbol)
1272          (#x101D0 #x101FF phaistos-disc)
1273          (#x10280 #x1029F lycian)
1274          (#x102A0 #x102DF carian)
1275          (#x10300 #x1032F olt-italic)
1276          (#x10330 #x1034F gothic)
1277          (#x10380 #x1039F ugaritic)
1278          (#x103A0 #x103DF old-persian)
1279          (#x10400 #x1044F deseret)
1280          (#x10450 #x1047F shavian)
1281          (#x10480 #x104AF osmanya)
1282          (#x10800 #x1083F cypriot-syllabary)
1283          (#x10840 #x1085F aramaic)
1284          (#x10900 #x1091F phoenician)
1285          (#x10920 #x1093F lydian)
1286          (#x10980 #x109FF meroitic)
1287          (#x10A00 #x10A5F kharoshthi)
1288          (#x10A60 #x10A7F old-south-arabian)
1289          (#x10B00 #x10B3F avestan)
1290          (#x10B40 #x10B5F inscriptional-parthian)
1291          (#x10B60 #x10B7F inscriptional-pahlavi)
1292          (#x10C00 #x10C4F old-turkic)
1293          (#x10E60 #x10E7F rumi-number)
1294          (#x11000 #x1107F brahmi)
1295          (#x11080 #x110CF kaithi)
1296          (#x110D0 #x110FF sora-sompeng)
1297          (#x11100 #x1114F chakma)
1298          (#x11180 #x111DF sharada)
1299          (#x11680 #x116CF takri)
1300          (#x12000 #x123FF cuneiform)
1301          (#x12400 #x1247F cuneiform-numbers-and-punctuation)
1302          (#x13000 #x1342F egyptian)
1303          (#x16800 #x16A3F bamum)
1304          (#x16F00 #x16F9F miao)
1305          (#x1B000 #x1B0FF kana)
1306          (#x1D000 #x1D0FF byzantine-musical-symbol)
1307          (#x1D100 #x1D1FF musical-symbol)
1308          (#x1D200 #x1D24F ancient-greek-musical-notation)
1309          (#x1D300 #x1D35F tai-xuan-jing-symbol)
1310          (#x1D360 #x1D37F counting-rod-numeral)
1311          (#x1D400 #x1D7FF mathematical)
1312          (#x1EE00 #x1EEFF arabic)
1313          (#x1F000 #x1F02F mahjong-tile)
1314          (#x1F030 #x1F09F domino-tile)
1315          (#x1F0A0 #x1F0FF playing-cards)
1316          (#x1F100 #x1F1FF symbol)
1317          (#x1F200 #x1F2FF han)
1318          (#x1F300 #x1F64F symbol)
1319          (#x1F680 #x1F77F symbol)
1320          (#x20000 #x2B81F han)
1321          (#x2F800 #x2FFFF han)))
1322     (set-char-table-range char-script-table
1323                           (cons (car elt) (nth 1 elt)) (nth 2 elt))
1324     (or (memq (nth 2 elt) script-list)
1325         (setq script-list (cons (nth 2 elt) script-list))))
1326   (set-char-table-extra-slot char-script-table 0 (nreverse script-list)))
1327
1328 (map-charset-chars
1329  #'(lambda (range ignore)
1330      (set-char-table-range char-script-table range 'tibetan))
1331  'tibetan)
1332
1333 \f
1334 ;;; Setting unicode-category-table.
1335
1336 (setq unicode-category-table
1337       (unicode-property-table-internal 'general-category))
1338 (map-char-table #'(lambda (key val)
1339                     (if (and val
1340                              (or (and (/= (aref (symbol-name val) 0) ?M)
1341                                       (/= (aref (symbol-name val) 0) ?C))
1342                                  (eq val 'Zs)))
1343                         (modify-category-entry key ?.)))
1344                 unicode-category-table)
1345
1346 (optimize-char-table (standard-category-table))
1347
1348 \f
1349 ;; Display of glyphless characters.
1350
1351 (defvar char-acronym-table
1352   (make-char-table 'char-acronym-table nil)
1353   "Char table of acronyms for non-graphic characters.")
1354
1355 (let ((c0-acronyms '("NUL" "SOH" "STX" "ETX" "EOT" "ENQ" "ACK" "BEL"
1356                      "BS"   nil   nil  "VT"  "FF"  "CR"  "SO"  "SI"
1357                      "DLE" "DC1" "DC2" "DC3" "DC4" "NAK" "SYN" "ETB"
1358                      "CAN" "EM"  "SUB" "ESC" "FC"  "GS"  "RS"  "US")))
1359   (dotimes (i 32)
1360     (aset char-acronym-table i (car c0-acronyms))
1361     (setq c0-acronyms (cdr c0-acronyms))))
1362
1363 (let ((c1-acronyms '("XXX" "XXX" "BPH" "NBH" "IND" "NEL" "SSA" "ESA"
1364                      "HTS" "HTJ" "VTS" "PLD" "PLU" "R1"  "SS2" "SS1"
1365                      "DCS" "PU1" "PU2" "STS" "CCH" "MW"  "SPA" "EPA"
1366                      "SOS" "XXX" "SC1" "CSI" "ST"  "OSC" "PM"  "APC")))
1367   (dotimes (i 32)
1368     (aset char-acronym-table (+ #x0080 i) (car c1-acronyms))
1369     (setq c1-acronyms (cdr c1-acronyms))))
1370
1371 (aset char-acronym-table #x17B4 "KIVAQ")   ; KHMER VOWEL INHERENT AQ
1372 (aset char-acronym-table #x17B5 "KIVAA")   ; KHMER VOWEL INHERENT AA
1373 (aset char-acronym-table #x200B "ZWSP")    ; ZERO WIDTH SPACE
1374 (aset char-acronym-table #x200C "ZWNJ")    ; ZERO WIDTH NON-JOINER
1375 (aset char-acronym-table #x200D "ZWJ")     ; ZERO WIDTH JOINER
1376 (aset char-acronym-table #x200E "LRM")     ; LEFT-TO-RIGHT MARK
1377 (aset char-acronym-table #x200F "RLM")     ; RIGHT-TO-LEFT MARK
1378 (aset char-acronym-table #x202A "LRE")     ; LEFT-TO-RIGHT EMBEDDING
1379 (aset char-acronym-table #x202B "RLE")     ; RIGHT-TO-LEFT EMBEDDING
1380 (aset char-acronym-table #x202C "PDF")     ; POP DIRECTIONAL FORMATTING
1381 (aset char-acronym-table #x202D "LRO")     ; LEFT-TO-RIGHT OVERRIDE
1382 (aset char-acronym-table #x202E "RLO")     ; RIGHT-TO-LEFT OVERRIDE
1383 (aset char-acronym-table #x2060 "WJ")      ; WORD JOINER
1384 (aset char-acronym-table #x206A "ISS")     ; INHIBIT SYMMETRIC SWAPPING
1385 (aset char-acronym-table #x206B "ASS")     ; ACTIVATE SYMMETRIC SWAPPING
1386 (aset char-acronym-table #x206C "IAFS")    ; INHIBIT ARABIC FORM SHAPING
1387 (aset char-acronym-table #x206D "AAFS")    ; ACTIVATE ARABIC FORM SHAPING
1388 (aset char-acronym-table #x206E "NADS")    ; NATIONAL DIGIT SHAPES
1389 (aset char-acronym-table #x206F "NODS")    ; NOMINAL DIGIT SHAPES
1390 (aset char-acronym-table #xFEFF "ZWNBSP")  ; ZERO WIDTH NO-BREAK SPACE
1391 (aset char-acronym-table #xFFF9 "IAA")     ; INTERLINEAR ANNOTATION ANCHOR
1392 (aset char-acronym-table #xFFFA "IAS")     ; INTERLINEAR ANNOTATION SEPARATOR
1393 (aset char-acronym-table #xFFFB "IAT")     ; INTERLINEAR ANNOTATION TERMINATOR
1394 (aset char-acronym-table #x1D173 "BEGBM")  ; MUSICAL SYMBOL BEGIN BEAM
1395 (aset char-acronym-table #x1D174 "ENDBM")  ; MUSICAL SYMBOL END BEAM
1396 (aset char-acronym-table #x1D175 "BEGTIE") ; MUSICAL SYMBOL BEGIN TIE
1397 (aset char-acronym-table #x1D176 "END")    ; MUSICAL SYMBOL END TIE
1398 (aset char-acronym-table #x1D177 "BEGSLR") ; MUSICAL SYMBOL BEGIN SLUR
1399 (aset char-acronym-table #x1D178 "ENDSLR") ; MUSICAL SYMBOL END SLUR
1400 (aset char-acronym-table #x1D179 "BEGPHR") ; MUSICAL SYMBOL BEGIN PHRASE
1401 (aset char-acronym-table #x1D17A "ENDPHR") ; MUSICAL SYMBOL END PHRASE
1402 (aset char-acronym-table #xE0001 "|->TAG") ; LANGUAGE TAG
1403 (aset char-acronym-table #xE0020 "SP TAG") ; TAG SPACE
1404 (dotimes (i 94)
1405   (aset char-acronym-table (+ #xE0021 i) (format " %c TAG" (+ 33 i))))
1406 (aset char-acronym-table #xE007F "->|TAG") ; CANCEL TAG
1407
1408 (defun update-glyphless-char-display (&optional variable value)
1409   "Make the setting of `glyphless-char-display-control' take effect.
1410 This function updates the char-table `glyphless-char-display'."
1411   (when value
1412     (set-default variable value))
1413   (dolist (elt value)
1414     (let ((target (car elt))
1415           (method (cdr elt)))
1416       (or (memq method '(zero-width thin-space empty-box acronym hex-code))
1417           (error "Invalid glyphless character display method: %s" method))
1418       (cond ((eq target 'c0-control)
1419              (set-char-table-range glyphless-char-display '(#x00 . #x1F)
1420                                    method)
1421              ;; Users will not expect their newlines and TABs be
1422              ;; displayed as anything but themselves, so exempt those
1423              ;; two characters from c0-control.
1424              (set-char-table-range glyphless-char-display #x9 nil)
1425              (set-char-table-range glyphless-char-display #xa nil))
1426             ((eq target 'c1-control)
1427              (set-char-table-range glyphless-char-display '(#x80 . #x9F)
1428                                    method))
1429             ((eq target 'format-control)
1430              (map-char-table
1431               #'(lambda (char category)
1432                   (if (eq category 'Cf)
1433                       (let ((this-method method)
1434                             from to)
1435                         (if (consp char)
1436                             (setq from (car char) to (cdr char))
1437                           (setq from char to char))
1438                         (while (<= from to)
1439                           (when (/= from #xAD)
1440                             (if (eq method 'acronym)
1441                                 (setq this-method
1442                                       (aref char-acronym-table from)))
1443                             (set-char-table-range glyphless-char-display
1444                                                   from this-method))
1445                           (setq from (1+ from))))))
1446               unicode-category-table))
1447             ((eq target 'no-font)
1448              (set-char-table-extra-slot glyphless-char-display 0 method))
1449             (t
1450              (error "Invalid glyphless character group: %s" target))))))
1451
1452 ;;; Control of displaying glyphless characters.
1453 (defcustom glyphless-char-display-control
1454   '((format-control . thin-space)
1455     (no-font . hex-code))
1456   "List of directives to control display of glyphless characters.
1457
1458 Each element has the form (GROUP . METHOD), where GROUP is a
1459 symbol specifying the character group, and METHOD is a symbol
1460 specifying the method of displaying characters belonging to that
1461 group.
1462
1463 GROUP must be one of these symbols:
1464   `c0-control':     U+0000..U+001F, but excluding newline and TAB.
1465   `c1-control':     U+0080..U+009F.
1466   `format-control': Characters of Unicode General Category `Cf',
1467                     such as U+200C (ZWNJ), U+200E (LRM), but
1468                     excluding characters that have graphic images,
1469                     such as U+00AD (SHY).
1470   `no-font':        characters for which no suitable font is found.
1471                     For character terminals, characters that cannot
1472                     be encoded by `terminal-coding-system'.
1473
1474 METHOD must be one of these symbols:
1475   `zero-width': don't display.
1476   `thin-space': display a thin (1-pixel width) space.  On character
1477                 terminals, display as 1-character space.
1478   `empty-box':  display an empty box.
1479   `acronym':    display an acronym of the character in a box.  The
1480                 acronym is taken from `char-acronym-table', which see.
1481   `hex-code':   display the hexadecimal character code in a box."
1482   :version "24.1"
1483   :type '(alist :key-type (symbol :tag "Character Group")
1484                 :value-type (symbol :tag "Display Method"))
1485   :options '((c0-control
1486               (choice (const :tag "Don't display" zero-width)
1487                       (const :tag "Display as thin space" thin-space)
1488                       (const :tag "Display as empty box" empty-box)
1489                       (const :tag "Display acronym" acronym)
1490                       (const :tag "Display hex code in a box" hex-code)))
1491              (c1-control
1492               (choice (const :tag "Don't display" zero-width)
1493                       (const :tag "Display as thin space" thin-space)
1494                       (const :tag "Display as empty box" empty-box)
1495                       (const :tag "Display acronym" acronym)
1496                       (const :tag "Display hex code in a box" hex-code)))
1497              (format-control
1498               (choice (const :tag "Don't display" zero-width)
1499                       (const :tag "Display as thin space" thin-space)
1500                       (const :tag "Display as empty box" empty-box)
1501                       (const :tag "Display acronym" acronym)
1502                       (const :tag "Display hex code in a box" hex-code)))
1503              (no-font
1504               (choice (const :tag "Don't display" zero-width)
1505                       (const :tag "Display as thin space" thin-space)
1506                       (const :tag "Display as empty box" empty-box)
1507                       (const :tag "Display acronym" acronym)
1508                       (const :tag "Display hex code in a box" hex-code))))
1509   :set 'update-glyphless-char-display
1510   :group 'display)
1511
1512 \f
1513 ;;; Setting word boundary.
1514
1515 (setq word-combining-categories
1516       '((nil . ?^)
1517         (?^ . nil)
1518         (?C . ?H)
1519         (?C . ?K)))
1520
1521 (setq word-separating-categories        ;  (2-byte character sets)
1522       '((?H . ?K)                       ; Hiragana - Katakana
1523         ))
1524
1525 ;; Local Variables:
1526 ;; coding: utf-8
1527 ;; End:
1528
1529 ;;; characters.el ends here