lisp/international/characters.el

   1 ;;; characters.el --- set syntax and category for multibyte characters
   2
   3 ;; Copyright (C) 1997, 2000-2014 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 elt "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 (let ((chars '(?仝 ?々 ?〆 ?〇)))
 238   (while chars
 239     (modify-category-entry (car chars) ?C)
 240     (setq chars (cdr chars))))
 241
 242 ;; JISX0212
 243
 244 (map-charset-chars #'modify-syntax-entry 'japanese-jisx0212 "_" #x2121 #x237E)
 245
 246 ;; JISX0201-Kana
 247
 248 (let ((chars '(?｡ ?､ ?･)))
 249   (while chars
 250     (modify-syntax-entry (car chars) ".")
 251     (setq chars (cdr chars))))
 252
 253 (modify-syntax-entry ?\｢ "(｣")
 254 (modify-syntax-entry ?\｣ "(｢")
 255
 256 ;; Korean character set (KSC5601)
 257
 258 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?h)
 259
 260 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2121 #x227E)
 261 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2621 #x277E)
 262 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2830 #x287E)
 263 (map-charset-chars #'modify-syntax-entry 'korean-ksc5601 "_" #x2930 #x297E)
 264 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2330 #x2339)
 265 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2341 #x235A)
 266 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?A #x2361 #x237A)
 267 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?G #x2521 #x257E)
 268 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?H #x2A21 #x2A7E)
 269 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?K #x2B21 #x2B7E)
 270 (map-charset-chars #'modify-category-entry 'korean-ksc5601 ?Y #x2C21 #x2C7E)
 271
 272 ;; These are in more than one charset.
 273 (let ((parens (concat "〈〉《》「」『』【】〔〕〖〗〘〙〚〛"
 274                       "︵︶︷︸︹︺︻︼︽︾︿﹀﹁﹂﹃﹄"
 275                       "（）［］｛｝"))
 276       open close)
 277   (dotimes (i (/ (length parens) 2))
 278     (setq open (aref parens (* i 2))
 279           close (aref parens (1+ (* i 2))))
 280     (modify-syntax-entry open (format "(%c" close))
 281     (modify-syntax-entry close (format ")%c" open))))
 282
 283 ;; Arabic character set
 284
 285 (let ((charsets '(arabic-iso8859-6
 286                   arabic-digit
 287                   arabic-1-column
 288                   arabic-2-column)))
 289   (while charsets
 290     (map-charset-chars #'modify-category-entry (car charsets) ?b)
 291     (setq charsets (cdr charsets))))
 292 (modify-category-entry '(#x600 . #x6ff) ?b)
 293 (modify-category-entry '(#xfb50 . #xfdff) ?b)
 294 (modify-category-entry '(#xfe70 . #xfefe) ?b)
 295
 296 ;; Cyrillic character set (ISO-8859-5)
 297
 298 (modify-syntax-entry ?№ ".")
 299
 300 ;; Ethiopic character set
 301
 302 (modify-category-entry '(#x1200 . #x1399) ?e)
 303 (modify-category-entry '(#x2d80 . #x2dde) ?e)
 304 (let ((chars '(?፡ ?። ?፣ ?፤ ?፥ ?፦ ?፧ ?፨)))
 305   (while chars
 306     (modify-syntax-entry (car chars) ".")
 307     (setq chars (cdr chars))))
 308 (map-charset-chars #'modify-category-entry 'ethiopic ?e)
 309
 310 ;; Hebrew character set (ISO-8859-8)
 311
 312 (modify-syntax-entry #x5be ".") ; MAQAF
 313 (modify-syntax-entry #x5c0 ".") ; PASEQ
 314 (modify-syntax-entry #x5c3 ".") ; SOF PASUQ
 315 (modify-syntax-entry #x5f3 ".") ; GERESH
 316 (modify-syntax-entry #x5f4 ".") ; GERSHAYIM
 317
 318 ;; Indian character set (IS 13194 and other Emacs original Indian charsets)
 319
 320 (modify-category-entry '(#x901 . #x970) ?i)
 321 (map-charset-chars #'modify-category-entry 'indian-is13194 ?i)
 322 (map-charset-chars #'modify-category-entry 'indian-2-column ?i)
 323
 324 ;; Lao character set
 325
 326 (modify-category-entry '(#xe80 . #xeff) ?o)
 327 (map-charset-chars #'modify-category-entry 'lao ?o)
 328
 329 (let ((deflist  '(("ກ-ຮ"    "w"     ?0) ; consonant
 330                   ("ະາຳຽເ-ໄ"        "w"     ?1) ; vowel base
 331                   ("ັິ-ືົໍ"   "w"     ?2) ; vowel upper
 332                   ("ຸູ"     "w"     ?3) ; vowel lower
 333                   ("່-໋"    "w"     ?4) ; tone mark
 334                   ("ຼຽ"     "w"     ?9) ; semivowel lower
 335                   ("໐-໙"    "w"     ?6) ; digit
 336                   ("ຯໆ"     "_"     ?5) ; symbol
 337                   ))
 338       elm chars len syntax category to ch i)
 339   (while deflist
 340     (setq elm (car deflist))
 341     (setq chars (car elm)
 342           len (length chars)
 343           syntax (nth 1 elm)
 344           category (nth 2 elm)
 345           i 0)
 346     (while (< i len)
 347       (if (= (aref chars i) ?-)
 348           (setq i (1+ i)
 349                 to (aref chars i))
 350         (setq ch (aref chars i)
 351               to ch))
 352       (while (<= ch to)
 353         (unless (string-equal syntax "w")
 354           (modify-syntax-entry ch syntax))
 355         (modify-category-entry ch category)
 356         (setq ch (1+ ch)))
 357       (setq i (1+ i)))
 358     (setq deflist (cdr deflist))))
 359
 360 ;; Thai character set (TIS620)
 361
 362 (modify-category-entry '(#xe00 . #xe7f) ?t)
 363 (map-charset-chars #'modify-category-entry 'thai-tis620 ?t)
 364
 365 (let ((deflist  '(;; chars      syntax  category
 366                   ("ก-รลว-ฮ"  "w"     ?0) ; consonant
 367                   ("ฤฦะาำเ-ๅ"     "w"     ?1) ; vowel base
 368                   ("ัิ-ื็๎"   "w"     ?2) ; vowel upper
 369                   ("ุ-ฺ"    "w"     ?3) ; vowel lower
 370                   ("่-ํ"    "w"     ?4) ; tone mark
 371                   ("๐-๙"    "w"     ?6) ; digit
 372                   ("ฯๆ฿๏๚๛" "_"     ?5) ; symbol
 373                   ))
 374       elm chars len syntax category to ch i)
 375   (while deflist
 376     (setq elm (car deflist))
 377     (setq chars (car elm)
 378           len (length chars)
 379           syntax (nth 1 elm)
 380           category (nth 2 elm)
 381           i 0)
 382     (while (< i len)
 383       (if (= (aref chars i) ?-)
 384           (setq i (1+ i)
 385                 to (aref chars i))
 386         (setq ch (aref chars i)
 387               to ch))
 388       (while (<= ch to)
 389         (unless (string-equal syntax "w")
 390           (modify-syntax-entry ch syntax))
 391         (modify-category-entry ch category)
 392         (setq ch (1+ ch)))
 393       (setq i (1+ i)))
 394     (setq deflist (cdr deflist))))
 395
 396 ;; Tibetan character set
 397
 398 (modify-category-entry '(#xf00 . #xfff) ?q)
 399 (map-charset-chars #'modify-category-entry 'tibetan ?q)
 400 (map-charset-chars #'modify-category-entry 'tibetan-1-column ?q)
 401
 402 (let ((deflist  '(;; chars             syntax category
 403                   ("ཀ-ཀྵཪ"         "w"     ?0) ; consonant
 404                   ("ྐ-ྐྵྺྻྼ"       "w"     ?0) ;
 405                   ("ིེཻོཽྀ"       "w"       ?2) ; upper vowel
 406                   ("ཾྂྃ྆྇ྈྉྊྋ" "w"    ?2) ; upper modifier
 407                   ("྄ཱུ༙༵༷"       "w"       ?3) ; lower vowel/modifier
 408                   ("཰"                "w" ?3)             ; invisible vowel a
 409                   ("༠-༩༪-༳"             "w"     ?6) ; digit
 410                   ("་།-༒༔ཿ"        "."     ?|) ; line-break char
 411                   ("་།༏༐༑༔ཿ"            "."     ?|) ;
 412                   ("༈་།-༒༔ཿ༽༴"  "."     ?>) ; prohibition
 413                   ("་།༏༐༑༔ཿ"            "."     ?>) ;
 414                   ("ༀ-༊༼࿁࿂྅"      "."     ?<) ; prohibition
 415                   ("༓༕-༘༚-༟༶༸-༻༾༿྾྿-࿏" "." ?q) ; others
 416                   ))
 417       elm chars len syntax category to ch i)
 418   (while deflist
 419     (setq elm (car deflist))
 420     (setq chars (car elm)
 421           len (length chars)
 422           syntax (nth 1 elm)
 423           category (nth 2 elm)
 424           i 0)
 425     (while (< i len)
 426       (if (= (aref chars i) ?-)
 427           (setq i (1+ i)
 428                 to (aref chars i))
 429         (setq ch (aref chars i)
 430               to ch))
 431       (while (<= ch to)
 432         (unless (string-equal syntax "w")
 433           (modify-syntax-entry ch syntax))
 434         (modify-category-entry ch category)
 435         (setq ch (1+ ch)))
 436       (setq i (1+ i)))
 437     (setq deflist (cdr deflist))))
 438
 439 ;; Vietnamese character set
 440
 441 ;; To make a word with Latin characters
 442 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?l)
 443 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-lower ?v)
 444
 445 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?l)
 446 (map-charset-chars #'modify-category-entry 'vietnamese-viscii-upper ?v)
 447
 448 (let ((tbl (standard-case-table))
 449       (i 32))
 450   (while (< i 128)
 451     (let* ((char (decode-char 'vietnamese-viscii-upper i))
 452            (charl (decode-char 'vietnamese-viscii-lower i))
 453            (uc (encode-char char 'ucs))
 454            (lc (encode-char charl 'ucs)))
 455       (set-case-syntax-pair char (decode-char 'vietnamese-viscii-lower i)
 456                             tbl)
 457       (if uc (modify-category-entry uc ?v))
 458       (if lc (modify-category-entry lc ?v)))
 459     (setq i (1+ i))))
 460
 461 ;; Tai Viet
 462 (let ((deflist '(;; chars       syntax  category
 463                  ((?ꪀ.  ?ꪯ) "w"     ?0) ; consonant
 464                  ("ꪱꪵꪶ"           "w"     ?1) ; vowel base
 465                  ((?ꪹ . ?ꪽ) "w"     ?1) ; vowel base
 466                  ("ꪰꪲꪳꪷꪸꪾ"  "w"     ?2) ; vowel upper
 467                  ("ꪴ"         "w"     ?3) ; vowel lower
 468                  ("ꫀꫂ"              "w"     ?1) ; non-combining tone-mark
 469                  ("꪿꫁"              "w"     ?4) ; combining tone-mark
 470                  ((?ꫛ . ?꫟) "_"     ?5) ; symbol
 471                  )))
 472   (dolist (elm deflist)
 473     (let ((chars (car elm))
 474           (syntax (nth 1 elm))
 475           (category (nth 2 elm)))
 476       (if (consp chars)
 477           (progn
 478             (modify-syntax-entry chars syntax)
 479             (modify-category-entry chars category))
 480         (mapc #'(lambda (x)
 481                   (modify-syntax-entry x syntax)
 482                   (modify-category-entry x category))
 483               chars)))))
 484
 485 ;; Bidi categories
 486
 487 ;; If bootstrapping without generated uni-*.el files, table not defined.
 488 (let ((table (unicode-property-table-internal 'bidi-class)))
 489   (when table
 490     (map-char-table (lambda (key val)
 491                       (cond
 492                        ((memq val '(R AL RLO RLE))
 493                         (modify-category-entry key ?R))
 494                        ((memq val '(L LRE LRO))
 495                         (modify-category-entry key ?L))))
 496                     table)))
 497
 498 ;; Latin
 499
 500 (modify-category-entry '(#x80 . #x024F) ?l)
 501
 502 (let ((tbl (standard-case-table)) c)
 503
 504   ;; Latin-1
 505
 506   ;; Fixme: Some of the non-word syntaxes here perhaps should be
 507   ;; reviewed.  (Note that the following all implicitly have word
 508   ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.)  There should be a well-defined way of
 509   ;; relating Unicode categories to Emacs syntax codes.
 510
 511   ;; NBSP isn't semantically interchangeable with other whitespace chars,
 512   ;; so it's more like punctuation.
 513   (set-case-syntax ?  "." tbl)
 514   (set-case-syntax ?¡ "." tbl)
 515   (set-case-syntax ?¦ "_" tbl)
 516   (set-case-syntax ?§ "." tbl)
 517   (set-case-syntax ?© "_" tbl)
 518   ;; French wants
 519   ;;   (set-case-syntax-delims ?« ?» tbl)
 520   ;; And German wants
 521   ;;   (set-case-syntax-delims ?» ?« tbl)
 522   ;; So let's stay neutral and let users set these up if/when they want to.
 523   (set-case-syntax ?« "." tbl)
 524   (set-case-syntax ?» "." tbl)
 525   (set-case-syntax ?¬ "_" tbl)
 526   (set-case-syntax ? "_" tbl)
 527   (set-case-syntax ?® "_" tbl)
 528   (set-case-syntax ?° "_" tbl)
 529   (set-case-syntax ?± "_" tbl)
 530   (set-case-syntax ?µ "_" tbl)
 531   (set-case-syntax ?· "_" tbl)
 532   (set-case-syntax ?¼ "_" tbl)
 533   (set-case-syntax ?½ "_" tbl)
 534   (set-case-syntax ?¾ "_" tbl)
 535   (set-case-syntax ?¿ "." tbl)
 536   (let ((c 192))
 537     (while (<= c 222)
 538       (set-case-syntax-pair c (+ c 32) tbl)
 539       (setq c (1+ c))))
 540   (set-case-syntax ?× "_" tbl)
 541   (set-case-syntax ?ß "w" tbl)
 542   (set-case-syntax ?÷ "_" tbl)
 543   ;; See below for ÿ.
 544
 545   ;; Latin Extended-A, Latin Extended-B
 546   (setq c #x0100)
 547   (while (<= c #x02B8)
 548     (modify-category-entry c ?l)
 549     (setq c (1+ c)))
 550
 551   (let ((pair-ranges '((#x0100 . #x012F)
 552                        (#x0132 . #x0137)
 553                        (#x0139 . #x0148)
 554                        (#x014a . #x0177)
 555                        (#x0179 . #x017E)
 556                        (#x0182 . #x0185)
 557                        (#x0187 . #x0188)
 558                        (#x018B . #x018C)
 559                        (#x0191 . #x0192)
 560                        (#x0198 . #x0199)
 561                        (#x01A0 . #x01A5)
 562                        (#x01A7 . #x01A8)
 563                        (#x01AC . #x01AD)
 564                        (#x01AF . #x01B0)
 565                        (#x01B3 . #x01B6)
 566                        (#x01B8 . #x01B9)
 567                        (#x01BC . #x01BD)
 568                        (#x01CD . #x01DC)
 569                        (#x01DE . #x01EF)
 570                        (#x01F4 . #x01F5)
 571                        (#x01F8 . #x021F)
 572                        (#x0222 . #x0233)
 573                        (#x023B . #x023C)
 574                        (#x0241 . #x0242)
 575                        (#x0246 . #x024F))))
 576     (dolist (elt pair-ranges)
 577       (let ((from (car elt)) (to (cdr elt)))
 578         (while (< from to)
 579           (set-case-syntax-pair from (1+ from) tbl)
 580           (setq from (+ from 2))))))
 581
 582   (set-case-syntax-pair ?Ÿ ?ÿ tbl)
 583
 584   ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
 585   ;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
 586   ;; do U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN
 587   ;; SMALL LETTER I.
 588
 589   ;; We used to set up half of those correspondence unconditionally,
 590   ;; but that makes searches slow.  So now we don't set up either half
 591   ;; of these correspondences by default.
 592
 593   ;; (set-downcase-syntax  ?İ ?i tbl)
 594   ;; (set-upcase-syntax    ?I ?ı tbl)
 595
 596   (set-case-syntax-pair ?Ɓ ?ɓ tbl)
 597   (set-case-syntax-pair ?Ɔ ?ɔ tbl)
 598   (set-case-syntax-pair ?Ɖ ?ɖ tbl)
 599   (set-case-syntax-pair ?Ɗ ?ɗ tbl)
 600   (set-case-syntax-pair ?Ǝ ?ǝ tbl)
 601   (set-case-syntax-pair ?Ə ?ə tbl)
 602   (set-case-syntax-pair ?Ɛ ?ɛ tbl)
 603   (set-case-syntax-pair ?Ɠ ?ɠ tbl)
 604   (set-case-syntax-pair ?Ɣ ?ɣ tbl)
 605   (set-case-syntax-pair ?Ɩ ?ɩ tbl)
 606   (set-case-syntax-pair ?Ɨ ?ɨ tbl)
 607   (set-case-syntax-pair ?Ɯ ?ɯ tbl)
 608   (set-case-syntax-pair ?Ɲ ?ɲ tbl)
 609   (set-case-syntax-pair ?Ɵ ?ɵ tbl)
 610   (set-case-syntax-pair ?Ʀ ?ʀ tbl)
 611   (set-case-syntax-pair ?Ʃ ?ʃ tbl)
 612   (set-case-syntax-pair ?Ʈ ?ʈ tbl)
 613   (set-case-syntax-pair ?Ʊ ?ʊ tbl)
 614   (set-case-syntax-pair ?Ʋ ?ʋ tbl)
 615   (set-case-syntax-pair ?Ʒ ?ʒ tbl)
 616   (set-case-syntax-pair ?Ǆ ?ǆ tbl)
 617   (set-case-syntax-pair ?ǅ ?ǆ tbl)
 618   (set-case-syntax-pair ?Ǉ ?ǉ tbl)
 619   (set-case-syntax-pair ?ǈ ?ǉ tbl)
 620   (set-case-syntax-pair ?Ǌ ?ǌ tbl)
 621   (set-case-syntax-pair ?ǋ ?ǌ tbl)
 622
 623   ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
 624   (set-case-syntax-pair ?Ǳ ?ǳ tbl)
 625   (set-case-syntax-pair ?ǲ ?ǳ tbl)
 626   (set-case-syntax-pair ?Ƕ ?ƕ tbl)
 627   (set-case-syntax-pair ?Ƿ ?ƿ tbl)
 628   (set-case-syntax-pair ?Ⱥ ?ⱥ tbl)
 629   (set-case-syntax-pair ?Ƚ ?ƚ tbl)
 630   (set-case-syntax-pair ?Ⱦ ?ⱦ tbl)
 631   (set-case-syntax-pair ?Ƀ ?ƀ tbl)
 632   (set-case-syntax-pair ?Ʉ ?ʉ tbl)
 633   (set-case-syntax-pair ?Ʌ ?ʌ tbl)
 634
 635   ;; Latin Extended Additional
 636   (modify-category-entry '(#x1e00 . #x1ef9) ?l)
 637   (setq c #x1e00)
 638   (while (<= c #x1ef9)
 639     (and (zerop (% c 2))
 640          (or (<= c #x1e94) (>= c #x1ea0))
 641          (set-case-syntax-pair c (1+ c) tbl))
 642     (setq c (1+ c)))
 643
 644   ;; Greek
 645   (modify-category-entry '(#x0370 . #x03ff) ?g)
 646   (setq c #x0370)
 647   (while (<= c #x03ff)
 648     (if (or (and (>= c #x0391) (<= c #x03a1))
 649             (and (>= c #x03a3) (<= c #x03ab)))
 650         (set-case-syntax-pair c (+ c 32) tbl))
 651     (and (>= c #x03da)
 652          (<= c #x03ee)
 653          (zerop (% c 2))
 654          (set-case-syntax-pair c (1+ c) tbl))
 655     (setq c (1+ c)))
 656   (set-case-syntax-pair ?Ά ?ά tbl)
 657   (set-case-syntax-pair ?Έ ?έ tbl)
 658   (set-case-syntax-pair ?Ή ?ή tbl)
 659   (set-case-syntax-pair ?Ί ?ί tbl)
 660   (set-case-syntax-pair ?Ό ?ό tbl)
 661   (set-case-syntax-pair ?Ύ ?ύ tbl)
 662   (set-case-syntax-pair ?Ώ ?ώ tbl)
 663
 664   ;; Armenian
 665   (setq c #x531)
 666   (while (<= c #x556)
 667     (set-case-syntax-pair c (+ c #x30) tbl)
 668     (setq c (1+ c)))
 669
 670   ;; Greek Extended
 671   (modify-category-entry '(#x1f00 . #x1fff) ?g)
 672   (setq c #x1f00)
 673   (while (<= c #x1fff)
 674     (and (<= (logand c #x000f) 7)
 675          (<= c #x1fa7)
 676          (not (memq c '(#x1f16 #x1f17 #x1f56 #x1f57
 677                                #x1f50 #x1f52 #x1f54 #x1f56)))
 678          (/= (logand c #x00f0) #x70)
 679          (set-case-syntax-pair (+ c 8) c tbl))
 680     (setq c (1+ c)))
 681   (set-case-syntax-pair ?Ᾰ ?ᾰ tbl)
 682   (set-case-syntax-pair ?Ᾱ ?ᾱ tbl)
 683   (set-case-syntax-pair ?Ὰ ?ὰ tbl)
 684   (set-case-syntax-pair ?Ά ?ά tbl)
 685   (set-case-syntax-pair ?ᾼ ?ᾳ tbl)
 686   (set-case-syntax-pair ?Ὲ ?ὲ tbl)
 687   (set-case-syntax-pair ?Έ ?έ tbl)
 688   (set-case-syntax-pair ?Ὴ ?ὴ tbl)
 689   (set-case-syntax-pair ?Ή ?ή tbl)
 690   (set-case-syntax-pair ?ῌ ?ῃ tbl)
 691   (set-case-syntax-pair ?Ῐ ?ῐ tbl)
 692   (set-case-syntax-pair ?Ῑ ?ῑ tbl)
 693   (set-case-syntax-pair ?Ὶ ?ὶ tbl)
 694   (set-case-syntax-pair ?Ί ?ί tbl)
 695   (set-case-syntax-pair ?Ῠ ?ῠ tbl)
 696   (set-case-syntax-pair ?Ῡ ?ῡ tbl)
 697   (set-case-syntax-pair ?Ὺ ?ὺ tbl)
 698   (set-case-syntax-pair ?Ύ ?ύ tbl)
 699   (set-case-syntax-pair ?Ῥ ?ῥ tbl)
 700   (set-case-syntax-pair ?Ὸ ?ὸ tbl)
 701   (set-case-syntax-pair ?Ό ?ό tbl)
 702   (set-case-syntax-pair ?Ὼ ?ὼ tbl)
 703   (set-case-syntax-pair ?Ώ ?ώ tbl)
 704   (set-case-syntax-pair ?ῼ ?ῳ tbl)
 705
 706   ;; cyrillic
 707   (modify-category-entry '(#x0400 . #x04FF) ?y)
 708   (setq c #x0400)
 709   (while (<= c #x04ff)
 710     (and (>= c #x0400)
 711          (<= c #x040f)
 712          (set-case-syntax-pair c (+ c 80) tbl))
 713     (and (>= c #x0410)
 714          (<= c #x042f)
 715          (set-case-syntax-pair c (+ c 32) tbl))
 716     (and (zerop (% c 2))
 717          (or (and (>= c #x0460) (<= c #x0480))
 718              (and (>= c #x048c) (<= c #x04be))
 719              (and (>= c #x04d0) (<= c #x04f4)))
 720          (set-case-syntax-pair c (1+ c) tbl))
 721     (setq c (1+ c)))
 722   (set-case-syntax-pair ?Ӂ ?ӂ tbl)
 723   (set-case-syntax-pair ?Ӄ ?ӄ tbl)
 724   (set-case-syntax-pair ?Ӈ ?ӈ tbl)
 725   (set-case-syntax-pair ?Ӌ ?ӌ tbl)
 726   (set-case-syntax-pair ?Ӹ ?ӹ tbl)
 727
 728   ;; general punctuation
 729   (setq c #x2000)
 730   (while (<= c #x200b)
 731     (set-case-syntax c " " tbl)
 732     (setq c (1+ c)))
 733   (while (<= c #x200F)
 734     (set-case-syntax c "." tbl)
 735     (setq c (1+ c)))
 736   ;; Fixme: These aren't all right:
 737   (setq c #x2010)
 738   (while (<= c #x2016)
 739     (set-case-syntax c "_" tbl)
 740     (setq c (1+ c)))
 741   ;; Punctuation syntax for quotation marks (like `)
 742   (while (<= c #x201f)
 743     (set-case-syntax  c "." tbl)
 744     (setq c (1+ c)))
 745   ;; Fixme: These aren't all right:
 746   (while (<= c #x2027)
 747     (set-case-syntax c "_" tbl)
 748     (setq c (1+ c)))
 749   (while (<= c #x206F)
 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   ;; Fixme: The following blocks might be better as symbol rather than
 760   ;; punctuation.
 761   ;; Arrows
 762   (setq c #x2190)
 763   (while (<= c #x21FF)
 764     (set-case-syntax c "." tbl)
 765     (setq c (1+ c)))
 766   ;; Mathematical Operators
 767   (while (<= c #x22FF)
 768     (set-case-syntax c "." tbl)
 769     (setq c (1+ c)))
 770   ;; Miscellaneous Technical
 771   (while (<= c #x23FF)
 772     (set-case-syntax c "." tbl)
 773     (setq c (1+ c)))
 774   ;; Control Pictures
 775   (while (<= c #x243F)
 776     (set-case-syntax c "_" tbl)
 777     (setq c (1+ c)))
 778
 779   ;; Circled Latin
 780   (setq c #x24b6)
 781   (while (<= c #x24cf)
 782     (set-case-syntax-pair c (+ c 26) tbl)
 783     (modify-category-entry c ?l)
 784     (modify-category-entry (+ c 26) ?l)
 785     (setq c (1+ c)))
 786
 787   ;; Fullwidth Latin
 788   (setq c #xff21)
 789   (while (<= c #xff3a)
 790     (set-case-syntax-pair c (+ c #x20) tbl)
 791     (modify-category-entry c ?l)
 792     (modify-category-entry (+ c #x20) ?l)
 793     (setq c (1+ c)))
 794
 795   ;; Combining diacritics
 796   (modify-category-entry '(#x300 . #x362) ?^)
 797   ;; Combining marks
 798   (modify-category-entry '(#x20d0 . #x20ff) ?^)
 799
 800   ;; Fixme: syntax for symbols &c
 801   )
 802
 803 (let ((pairs
 804        '("⁅⁆"                               ; U+2045 U+2046
 805          "⁽⁾"                               ; U+207D U+207E
 806          "₍₎"                               ; U+208D U+208E
 807          "〈〉"                               ; U+2329 U+232A
 808          "⎴⎵"                               ; U+23B4 U+23B5
 809          "❨❩"                               ; U+2768 U+2769
 810          "❪❫"                               ; U+276A U+276B
 811          "❬❭"                               ; U+276C U+276D
 812          "❰❱"                               ; U+2770 U+2771
 813          "❲❳"                               ; U+2772 U+2773
 814          "❴❵"                               ; U+2774 U+2775
 815          "⟦⟧"                               ; U+27E6 U+27E7
 816          "⟨⟩"                               ; U+27E8 U+27E9
 817          "⟪⟫"                               ; U+27EA U+27EB
 818          "⦃⦄"                               ; U+2983 U+2984
 819          "⦅⦆"                               ; U+2985 U+2986
 820          "⦇⦈"                               ; U+2987 U+2988
 821          "⦉⦊"                               ; U+2989 U+298A
 822          "⦋⦌"                               ; U+298B U+298C
 823          "⦍⦎"                               ; U+298D U+298E
 824          "⦏⦐"                               ; U+298F U+2990
 825          "⦑⦒"                               ; U+2991 U+2992
 826          "⦓⦔"                               ; U+2993 U+2994
 827          "⦕⦖"                               ; U+2995 U+2996
 828          "⦗⦘"                               ; U+2997 U+2998
 829          "⧼⧽"                               ; U+29FC U+29FD
 830          "〈〉"                               ; U+3008 U+3009
 831          "《》"                               ; U+300A U+300B
 832          "「」"                               ; U+300C U+300D
 833          "『』"                               ; U+300E U+300F
 834          "【】"                               ; U+3010 U+3011
 835          "〔〕"                               ; U+3014 U+3015
 836          "〖〗"                               ; U+3016 U+3017
 837          "〘〙"                               ; U+3018 U+3019
 838          "〚〛"                               ; U+301A U+301B
 839          "﴾﴿"                               ; U+FD3E U+FD3F
 840          "︵︶"                               ; U+FE35 U+FE36
 841          "︷︸"                               ; U+FE37 U+FE38
 842          "︹︺"                               ; U+FE39 U+FE3A
 843          "︻︼"                               ; U+FE3B U+FE3C
 844          "︽︾"                               ; U+FE3D U+FE3E
 845          "︿﹀"                               ; U+FE3F U+FE40
 846          "﹁﹂"                               ; U+FE41 U+FE42
 847          "﹃﹄"                               ; U+FE43 U+FE44
 848          "﹙﹚"                               ; U+FE59 U+FE5A
 849          "﹛﹜"                               ; U+FE5B U+FE5C
 850          "﹝﹞"                               ; U+FE5D U+FE5E
 851          "（）"                               ; U+FF08 U+FF09
 852          "［］"                               ; U+FF3B U+FF3D
 853          "｛｝"                               ; U+FF5B U+FF5D
 854          "｟｠"                               ; U+FF5F U+FF60
 855          "｢｣"                               ; U+FF62 U+FF63
 856          )))
 857   (dolist (elt pairs)
 858     (modify-syntax-entry (aref elt 0) (string ?\( (aref elt 1)))
 859     (modify-syntax-entry (aref elt 1) (string ?\) (aref elt 0)))))
 860
 861 \f
 862 ;; For each character set, put the information of the most proper
 863 ;; coding system to encode it by `preferred-coding-system' property.
 864
 865 ;; Fixme: should this be junked?
 866 (let ((l '((latin-iso8859-1     . iso-latin-1)
 867            (latin-iso8859-2     . iso-latin-2)
 868            (latin-iso8859-3     . iso-latin-3)
 869            (latin-iso8859-4     . iso-latin-4)
 870            (thai-tis620         . thai-tis620)
 871            (greek-iso8859-7     . greek-iso-8bit)
 872            (arabic-iso8859-6    . iso-2022-7bit)
 873            (hebrew-iso8859-8    . hebrew-iso-8bit)
 874            (katakana-jisx0201   . japanese-shift-jis)
 875            (latin-jisx0201      . japanese-shift-jis)
 876            (cyrillic-iso8859-5  . cyrillic-iso-8bit)
 877            (latin-iso8859-9     . iso-latin-5)
 878            (japanese-jisx0208-1978 . iso-2022-jp)
 879            (chinese-gb2312      . chinese-iso-8bit)
 880            (chinese-gbk         . chinese-gbk)
 881            (gb18030-2-byte      . chinese-gb18030)
 882            (gb18030-4-byte-bmp  . chinese-gb18030)
 883            (gb18030-4-byte-smp  . chinese-gb18030)
 884            (gb18030-4-byte-ext-1 . chinese-gb18030)
 885            (gb18030-4-byte-ext-2 . chinese-gb18030)
 886            (japanese-jisx0208   . iso-2022-jp)
 887            (korean-ksc5601      . iso-2022-kr)
 888            (japanese-jisx0212   . iso-2022-jp)
 889            (chinese-big5-1      . chinese-big5)
 890            (chinese-big5-2      . chinese-big5)
 891            (chinese-sisheng     . iso-2022-7bit)
 892            (ipa                 . iso-2022-7bit)
 893            (vietnamese-viscii-lower . vietnamese-viscii)
 894            (vietnamese-viscii-upper . vietnamese-viscii)
 895            (arabic-digit        . iso-2022-7bit)
 896            (arabic-1-column     . iso-2022-7bit)
 897            (lao                 . lao)
 898            (arabic-2-column     . iso-2022-7bit)
 899            (indian-is13194      . devanagari)
 900            (indian-glyph        . devanagari)
 901            (tibetan-1-column    . tibetan)
 902            (ethiopic            . iso-2022-7bit)
 903            (chinese-cns11643-1  . iso-2022-cn)
 904            (chinese-cns11643-2  . iso-2022-cn)
 905            (chinese-cns11643-3  . iso-2022-cn)
 906            (chinese-cns11643-4  . iso-2022-cn)
 907            (chinese-cns11643-5  . iso-2022-cn)
 908            (chinese-cns11643-6  . iso-2022-cn)
 909            (chinese-cns11643-7  . iso-2022-cn)
 910            (indian-2-column     . devanagari)
 911            (tibetan             . tibetan)
 912            (latin-iso8859-14    . iso-latin-8)
 913            (latin-iso8859-15    . iso-latin-9))))
 914   (while l
 915     (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
 916     (setq l (cdr l))))
 917
 918 \f
 919 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
 920 ;; SPACE and NEWLINE are already set.
 921
 922 (set-char-table-range auto-fill-chars '(#x3041 . #x30FF) t)
 923 (set-char-table-range auto-fill-chars '(#x3400 . #x4DB5) t)
 924 (set-char-table-range auto-fill-chars '(#x4e00 . #x9fbb) t)
 925 (set-char-table-range auto-fill-chars '(#xF900 . #xFAFF) t)
 926 (set-char-table-range auto-fill-chars '(#xFF00 . #xFF9F) t)
 927 (set-char-table-range auto-fill-chars '(#x20000 . #x2FFFF) t)
 928
 929 \f
 930 ;;; Setting char-width-table.  The default is 1.
 931
 932 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
 933 ;;    and final characters.
 934 (let ((l '((#x0300 . #x036F)
 935            (#x0483 . #x0489)
 936            (#x0591 . #x05BD)
 937            (#x05BF . #x05BF)
 938            (#x05C1 . #x05C2)
 939            (#x05C4 . #x05C5)
 940            (#x05C7 . #x05C7)
 941            (#x0600 . #x0603)
 942            (#x0610 . #x0615)
 943            (#x064B . #x065E)
 944            (#x0670 . #x0670)
 945            (#x06D6 . #x06E4)
 946            (#x06E7 . #x06E8)
 947            (#x06EA . #x06ED)
 948            (#x070F . #x070F)
 949            (#x0711 . #x0711)
 950            (#x0730 . #x074A)
 951            (#x07A6 . #x07B0)
 952            (#x07EB . #x07F3)
 953            (#x0901 . #x0902)
 954            (#x093C . #x093C)
 955            (#x0941 . #x0948)
 956            (#x094D . #x094D)
 957            (#x0951 . #x0954)
 958            (#x0962 . #x0963)
 959            (#x0981 . #x0981)
 960            (#x09BC . #x09BC)
 961            (#x09C1 . #x09C4)
 962            (#x09CD . #x09CD)
 963            (#x09E2 . #x09E3)
 964            (#x0A01 . #x0A02)
 965            (#x0A3C . #x0A3C)
 966            (#x0A41 . #x0A4D)
 967            (#x0A70 . #x0A71)
 968            (#x0A81 . #x0A82)
 969            (#x0ABC . #x0ABC)
 970            (#x0AC1 . #x0AC8)
 971            (#x0ACD . #x0ACD)
 972            (#x0AE2 . #x0AE3)
 973            (#x0B01 . #x0B01)
 974            (#x0B3C . #x0B3C)
 975            (#x0B3F . #x0B3F)
 976            (#x0B41 . #x0B43)
 977            (#x0B4D . #x0B56)
 978            (#x0B82 . #x0B82)
 979            (#x0BC0 . #x0BC0)
 980            (#x0BCD . #x0BCD)
 981            (#x0C3E . #x0C40)
 982            (#x0C46 . #x0C56)
 983            (#x0CBC . #x0CBC)
 984            (#x0CBF . #x0CBF)
 985            (#x0CC6 . #x0CC6)
 986            (#x0CCC . #x0CCD)
 987            (#x0CE2 . #x0CE3)
 988            (#x0D41 . #x0D43)
 989            (#x0D4D . #x0D4D)
 990            (#x0DCA . #x0DCA)
 991            (#x0DD2 . #x0DD6)
 992            (#x0E31 . #x0E31)
 993            (#x0E34 . #x0E3A)
 994            (#x0E47 . #x0E4E)
 995            (#x0EB1 . #x0EB1)
 996            (#x0EB4 . #x0EBC)
 997            (#x0EC8 . #x0ECD)
 998            (#x0F18 . #x0F19)
 999            (#x0F35 . #x0F35)
1000            (#x0F37 . #x0F37)
1001            (#x0F39 . #x0F39)
1002            (#x0F71 . #x0F7E)
1003            (#x0F80 . #x0F84)
1004            (#x0F86 . #x0F87)
1005            (#x0F90 . #x0FBC)
1006            (#x0FC6 . #x0FC6)
1007            (#x102D . #x1030)
1008            (#x1032 . #x1037)
1009            (#x1039 . #x1039)
1010            (#x1058 . #x1059)
1011            (#x1160 . #x11FF)
1012            (#x135F . #x135F)
1013            (#x1712 . #x1714)
1014            (#x1732 . #x1734)
1015            (#x1752 . #x1753)
1016            (#x1772 . #x1773)
1017            (#x17B4 . #x17B5)
1018            (#x17B7 . #x17BD)
1019            (#x17C6 . #x17C6)
1020            (#x17C9 . #x17D3)
1021            (#x17DD . #x17DD)
1022            (#x180B . #x180D)
1023            (#x18A9 . #x18A9)
1024            (#x1920 . #x1922)
1025            (#x1927 . #x1928)
1026            (#x1932 . #x1932)
1027            (#x1939 . #x193B)
1028            (#x1A17 . #x1A18)
1029            (#x1B00 . #x1B03)
1030            (#x1B34 . #x1B34)
1031            (#x1B36 . #x1B3A)
1032            (#x1B3C . #x1B3C)
1033            (#x1B42 . #x1B42)
1034            (#x1B6B . #x1B73)
1035            (#x1DC0 . #x1DFF)
1036            (#x200B . #x200F)
1037            (#x202A . #x202E)
1038            (#x2060 . #x206F)
1039            (#x20D0 . #x20EF)
1040            (#x302A . #x302F)
1041            (#x3099 . #x309A)
1042            (#xA806 . #xA806)
1043            (#xA80B . #xA80B)
1044            (#xA825 . #xA826)
1045            (#xFB1E . #xFB1E)
1046            (#xFE00 . #xFE0F)
1047            (#xFE20 . #xFE23)
1048            (#xFEFF . #xFEFF)
1049            (#xFFF9 . #xFFFB)
1050            (#x10A01 . #x10A0F)
1051            (#x10A38 . #x10A3F)
1052            (#x1D167 . #x1D169)
1053            (#x1D173 . #x1D182)
1054            (#x1D185 . #x1D18B)
1055            (#x1D1AA . #x1D1AD)
1056            (#x1D242 . #x1D244)
1057            (#xE0001 . #xE01EF))))
1058   (dolist (elt l)
1059     (set-char-table-range char-width-table elt 0)))
1060
1061 ;; 2: East Asian Wide and Full-width characters.
1062 (let ((l '((#x1100 . #x115F)
1063            (#x2329 . #x232A)
1064            (#x2E80 . #x303E)
1065            (#x3040 . #xA4CF)
1066            (#xAC00 . #xD7A3)
1067            (#xF900 . #xFAFF)
1068            (#xFE30 . #xFE6F)
1069            (#xFF01 . #xFF60)
1070            (#xFFE0 . #xFFE6)
1071            (#x20000 . #x2FFFF)
1072            (#x30000 . #x3FFFF))))
1073   (dolist (elt l)
1074     (set-char-table-range char-width-table elt 2)))
1075
1076 ;; Other double width
1077 ;;(map-charset-chars
1078 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1079 ;; 'ethiopic)
1080 ;; (map-charset-chars
1081 ;;  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1082 ;; 'tibetan)
1083 (map-charset-chars
1084  (lambda (range _ignore) (set-char-table-range char-width-table range 2))
1085  'indian-2-column)
1086 (map-charset-chars
1087  (lambda (range _ignore) (set-char-table-range char-width-table range 2))
1088  'arabic-2-column)
1089
1090 ;; Internal use only.
1091 ;; Alist of locale symbol vs charsets.  In a language environment
1092 ;; corresponding to the locale, width of characters in the charsets is
1093 ;; set to 2.  Each element has the form:
1094 ;;   (LOCALE TABLE (CHARSET (FROM-CODE . TO-CODE) ...) ...)
1095 ;; LOCALE: locale symbol
1096 ;; TABLE: char-table used for char-width-table, initially nil.
1097 ;; CAHRSET: character set
1098 ;; FROM-CODE, TO-CODE: range of code-points in CHARSET
1099
1100 (defvar cjk-char-width-table-list
1101   '((ja_JP nil (japanese-jisx0208 (#x2121 . #x287E))
1102                (cp932-2-byte (#x8140 . #x879F)))
1103     (zh_CN nil (chinese-gb2312 (#x2121 . #x297E)))
1104     (zh_HK nil (big5-hkscs (#xA140 . #xA3FE) (#xC6A0 . #xC8FE)))
1105     (zh_TW nil (big5 (#xA140 . #xA3FE))
1106                (chinese-cns11643-1 (#x2121 . #x427E)))
1107     (ko_KR nil (korean-ksc5601 (#x2121 . #x2C7E)))))
1108
1109 ;; Internal use only.
1110 ;; Setup char-width-table appropriate for a language environment
1111 ;; corresponding to LOCALE-NAME (symbol).
1112
1113 (defun use-cjk-char-width-table (locale-name)
1114   (while (char-table-parent char-width-table)
1115     (setq char-width-table (char-table-parent char-width-table)))
1116   (let ((slot (assq locale-name cjk-char-width-table-list)))
1117     (or slot (error "Unknown locale for CJK language environment: %s"
1118                     locale-name))
1119     (unless (nth 1 slot)
1120       (let ((table (make-char-table nil)))
1121         (dolist (charset-info (nthcdr 2 slot))
1122           (let ((charset (car charset-info)))
1123             (dolist (code-range (cdr charset-info))
1124               (map-charset-chars #'(lambda (range _arg)
1125                                      (set-char-table-range table range 2))
1126                                  charset nil
1127                                  (car code-range) (cdr code-range)))))
1128         (optimize-char-table table)
1129         (set-char-table-parent table char-width-table)
1130         (setcar (cdr slot) table)))
1131     (setq char-width-table (nth 1 slot))))
1132
1133 (defun use-default-char-width-table ()
1134   "Internal use only.
1135 Setup char-width-table appropriate for non-CJK language environment."
1136   (while (char-table-parent char-width-table)
1137     (setq char-width-table (char-table-parent char-width-table))))
1138
1139 (optimize-char-table (standard-case-table))
1140 (optimize-char-table (standard-syntax-table))
1141
1142 \f
1143 ;; Setting char-script-table.
1144
1145 ;; The data is compiled from Blocks.txt and Scripts.txt in the
1146 ;; "Unicode Character Database", simplified to lump together all the
1147 ;; blocks belonging to the same language.  E.g., "Basic Latin",
1148 ;; "Latin-1 Supplement", "Latin Extended-A", etc. are all lumped
1149 ;; together under "latin".
1150 ;;
1151 ;; The Unicode blocks actually extend past some of these ranges with
1152 ;; undefined codepoints.
1153 (let ((script-list nil))
1154   (dolist
1155       (elt
1156        '((#x0000 #x007F latin)
1157          (#x00A0 #x024F latin)
1158          (#x0250 #x02AF phonetic)
1159          (#x02B0 #x036F latin)
1160          (#x0370 #x03E1 greek)
1161          (#x03E2 #x03EF coptic)
1162          (#x03F0 #x03F3 greek)
1163          (#x0400 #x052F cyrillic)
1164          (#x0530 #x058F armenian)
1165          (#x0590 #x05FF hebrew)
1166          (#x0600 #x06FF arabic)
1167          (#x0700 #x074F syriac)
1168          (#x0750 #x077F arabic)
1169          (#x0780 #x07BF thaana)
1170          (#x07C0 #x07FF nko)
1171          (#x0800 #x083F samaritan)
1172          (#x0840 #x085F mandaic)
1173          (#x08A0 #x08FF arabic)
1174          (#x0900 #x097F devanagari)
1175          (#x0980 #x09FF bengali)
1176          (#x0A00 #x0A7F gurmukhi)
1177          (#x0A80 #x0AFF gujarati)
1178          (#x0B00 #x0B7F oriya)
1179          (#x0B80 #x0BFF tamil)
1180          (#x0C00 #x0C7F telugu)
1181          (#x0C80 #x0CFF kannada)
1182          (#x0D00 #x0D7F malayalam)
1183          (#x0D80 #x0DFF sinhala)
1184          (#x0E00 #x0E7F thai)
1185          (#x0E80 #x0EFF lao)
1186          (#x0F00 #x0FFF tibetan)
1187          (#x1000 #x109F burmese) ; according to Unicode 6.1, should be "myanmar"
1188          (#x10A0 #x10FF georgian)
1189          (#x1100 #x11FF hangul)
1190          (#x1200 #x139F ethiopic)
1191          (#x13A0 #x13FF cherokee)
1192          (#x1400 #x167F canadian-aboriginal)
1193          (#x1680 #x169F ogham)
1194          (#x16A0 #x16FF runic)
1195          (#x1700 #x171F tagalog)
1196          (#x1720 #x173F hanunoo)
1197          (#x1740 #x175F buhid)
1198          (#x1760 #x177F tagbanwa)
1199          (#x1780 #x17FF khmer)
1200          (#x1800 #x18AF mongolian)
1201          (#x18B0 #x18FF canadian-aboriginal)
1202          (#x1900 #x194F limbu)
1203          (#x1950 #x197F tai-le)
1204          (#x1980 #x19DF tai-lue)
1205          (#x19E0 #x19FF khmer)
1206          (#x1A00 #x1A00 buginese)
1207          (#x1A20 #x1AAF tai-tham)
1208          (#x1B00 #x1B7F balinese)
1209          (#x1B80 #x1BBF sundanese)
1210          (#x1BC0 #x1BFF batak)
1211          (#x1C00 #x1C4F lepcha)
1212          (#x1C50 #x1C7F ol-chiki)
1213          (#x1CC0 #x1CCF sundanese)
1214          (#x1CD0 #x1CFF vedic)
1215          (#x1D00 #x1DBF phonetic)
1216          (#x1DC0 #x1EFF latin)
1217          (#x1F00 #x1FFF greek)
1218          (#x2000 #x27FF symbol)
1219          (#x2800 #x28FF braille)
1220          (#x2900 #x2BFF symbol)
1221          (#x2C00 #x2C5F glagolitic)
1222          (#x2C60 #x2C7F latin)
1223          (#x2C80 #x2CFF coptic)
1224          (#x2D00 #x2D2F georgian)
1225          (#x2D30 #x2D7F tifinagh)
1226          (#x2D80 #x2DDF ethiopic)
1227          (#x2DE0 #x2DFF cyrillic)
1228          (#x2E00 #x2E7F symbol)
1229          (#x2E80 #x2FDF han)
1230          (#x2FF0 #x2FFF ideographic-description)
1231          (#x3000 #x303F cjk-misc)
1232          (#x3040 #x30FF kana)
1233          (#x3100 #x312F bopomofo)
1234          (#x3130 #x318F hangul)
1235          (#x3190 #x319F kanbun)
1236          (#x31A0 #x31BF bopomofo)
1237          (#x31C0 #x31EF cjk-misc)
1238          (#x31F0 #x31FF kana)
1239          (#x3200 #x9FAF han)
1240          (#xA000 #xA4CF yi)
1241          (#xA4D0 #xA4FF lisu)
1242          (#xA500 #xA63F vai)
1243          (#xA640 #xA69F cyrillic)
1244          (#xA6A0 #xA6FF bamum)
1245          (#xA700 #xA7FF latin)
1246          (#xA800 #xA82F syloti-nagri)
1247          (#xA830 #xA83F north-indic-number)
1248          (#xA840 #xA87F phags-pa)
1249          (#xA880 #xA8DF saurashtra)
1250          (#xA8E0 #xA8FF devanagari)
1251          (#xA900 #xA92F kayah-li)
1252          (#xA930 #xA95F rejang)
1253          (#xA960 #xA97F hangul)
1254          (#xA980 #xA9DF javanese)
1255          (#xAA00 #xAA5F cham)
1256          (#xAA60 #xAA7B burmese)        ; Unicode 6.1: "myanmar"
1257          (#xAA80 #xAADF tai-viet)
1258          (#xAAE0 #xAAFF meetei-mayek)
1259          (#xAB00 #xAB2F ethiopic)
1260          (#xABC0 #xABFF meetei-mayek)
1261          (#xAC00 #xD7FF hangul)
1262          (#xF900 #xFAFF han)
1263          (#xFB1D #xFB4F hebrew)
1264          (#xFB50 #xFDFF arabic)
1265          (#xFE30 #xFE4F han)
1266          (#xFE70 #xFEFF arabic)
1267          (#xFF00 #xFF5F cjk-misc)
1268          (#xFF61 #xFF9F kana)
1269          (#xFFE0 #xFFE6 cjk-misc)
1270          (#x10000 #x100FF linear-b)
1271          (#x10100 #x1013F aegean-number)
1272          (#x10140 #x1018F ancient-greek-number)
1273          (#x10190 #x101CF ancient-symbol)
1274          (#x101D0 #x101FF phaistos-disc)
1275          (#x10280 #x1029F lycian)
1276          (#x102A0 #x102DF carian)
1277          (#x10300 #x1032F olt-italic)
1278          (#x10330 #x1034F gothic)
1279          (#x10380 #x1039F ugaritic)
1280          (#x103A0 #x103DF old-persian)
1281          (#x10400 #x1044F deseret)
1282          (#x10450 #x1047F shavian)
1283          (#x10480 #x104AF osmanya)
1284          (#x10800 #x1083F cypriot-syllabary)
1285          (#x10840 #x1085F aramaic)
1286          (#x10900 #x1091F phoenician)
1287          (#x10920 #x1093F lydian)
1288          (#x10980 #x109FF meroitic)
1289          (#x10A00 #x10A5F kharoshthi)
1290          (#x10A60 #x10A7F old-south-arabian)
1291          (#x10B00 #x10B3F avestan)
1292          (#x10B40 #x10B5F inscriptional-parthian)
1293          (#x10B60 #x10B7F inscriptional-pahlavi)
1294          (#x10C00 #x10C4F old-turkic)
1295          (#x10E60 #x10E7F rumi-number)
1296          (#x11000 #x1107F brahmi)
1297          (#x11080 #x110CF kaithi)
1298          (#x110D0 #x110FF sora-sompeng)
1299          (#x11100 #x1114F chakma)
1300          (#x11180 #x111DF sharada)
1301          (#x11680 #x116CF takri)
1302          (#x12000 #x123FF cuneiform)
1303          (#x12400 #x1247F cuneiform-numbers-and-punctuation)
1304          (#x13000 #x1342F egyptian)
1305          (#x16800 #x16A3F bamum)
1306          (#x16F00 #x16F9F miao)
1307          (#x1B000 #x1B0FF kana)
1308          (#x1D000 #x1D0FF byzantine-musical-symbol)
1309          (#x1D100 #x1D1FF musical-symbol)
1310          (#x1D200 #x1D24F ancient-greek-musical-notation)
1311          (#x1D300 #x1D35F tai-xuan-jing-symbol)
1312          (#x1D360 #x1D37F counting-rod-numeral)
1313          (#x1D400 #x1D7FF mathematical)
1314          (#x1EE00 #x1EEFF arabic)
1315          (#x1F000 #x1F02F mahjong-tile)
1316          (#x1F030 #x1F09F domino-tile)
1317          (#x1F0A0 #x1F0FF playing-cards)
1318          (#x1F100 #x1F1FF symbol)
1319          (#x1F200 #x1F2FF han)
1320          (#x1F300 #x1F64F symbol)
1321          (#x1F680 #x1F77F symbol)
1322          (#x20000 #x2B81F han)
1323          (#x2F800 #x2FFFF han)))
1324     (set-char-table-range char-script-table
1325                           (cons (car elt) (nth 1 elt)) (nth 2 elt))
1326     (or (memq (nth 2 elt) script-list)
1327         (setq script-list (cons (nth 2 elt) script-list))))
1328   (set-char-table-extra-slot char-script-table 0 (nreverse script-list)))
1329
1330 (map-charset-chars
1331  #'(lambda (range _ignore)
1332      (set-char-table-range char-script-table range 'tibetan))
1333  'tibetan)
1334
1335 \f
1336 ;;; Setting unicode-category-table.
1337
1338 (when (setq unicode-category-table
1339             (unicode-property-table-internal 'general-category))
1340   (map-char-table #'(lambda (key val)
1341                       (if (and val
1342                                (or (and (/= (aref (symbol-name val) 0) ?M)
1343                                         (/= (aref (symbol-name val) 0) ?C))
1344                                    (eq val 'Zs)))
1345                           (modify-category-entry key ?.)))
1346                   unicode-category-table))
1347
1348 (optimize-char-table (standard-category-table))
1349
1350 \f
1351 ;; Display of glyphless characters.
1352
1353 (defvar char-acronym-table
1354   (make-char-table 'char-acronym-table nil)
1355   "Char table of acronyms for non-graphic characters.")
1356
1357 (let ((c0-acronyms '("NUL" "SOH" "STX" "ETX" "EOT" "ENQ" "ACK" "BEL"
1358                      "BS"   nil   nil  "VT"  "FF"  "CR"  "SO"  "SI"
1359                      "DLE" "DC1" "DC2" "DC3" "DC4" "NAK" "SYN" "ETB"
1360                      "CAN" "EM"  "SUB" "ESC" "FC"  "GS"  "RS"  "US")))
1361   (dotimes (i 32)
1362     (aset char-acronym-table i (car c0-acronyms))
1363     (setq c0-acronyms (cdr c0-acronyms))))
1364
1365 (let ((c1-acronyms '("XXX" "XXX" "BPH" "NBH" "IND" "NEL" "SSA" "ESA"
1366                      "HTS" "HTJ" "VTS" "PLD" "PLU" "R1"  "SS2" "SS1"
1367                      "DCS" "PU1" "PU2" "STS" "CCH" "MW"  "SPA" "EPA"
1368                      "SOS" "XXX" "SC1" "CSI" "ST"  "OSC" "PM"  "APC")))
1369   (dotimes (i 32)
1370     (aset char-acronym-table (+ #x0080 i) (car c1-acronyms))
1371     (setq c1-acronyms (cdr c1-acronyms))))
1372
1373 (aset char-acronym-table #x17B4 "KIVAQ")   ; KHMER VOWEL INHERENT AQ
1374 (aset char-acronym-table #x17B5 "KIVAA")   ; KHMER VOWEL INHERENT AA
1375 (aset char-acronym-table #x200B "ZWSP")    ; ZERO WIDTH SPACE
1376 (aset char-acronym-table #x200C "ZWNJ")    ; ZERO WIDTH NON-JOINER
1377 (aset char-acronym-table #x200D "ZWJ")     ; ZERO WIDTH JOINER
1378 (aset char-acronym-table #x200E "LRM")     ; LEFT-TO-RIGHT MARK
1379 (aset char-acronym-table #x200F "RLM")     ; RIGHT-TO-LEFT MARK
1380 (aset char-acronym-table #x202A "LRE")     ; LEFT-TO-RIGHT EMBEDDING
1381 (aset char-acronym-table #x202B "RLE")     ; RIGHT-TO-LEFT EMBEDDING
1382 (aset char-acronym-table #x202C "PDF")     ; POP DIRECTIONAL FORMATTING
1383 (aset char-acronym-table #x202D "LRO")     ; LEFT-TO-RIGHT OVERRIDE
1384 (aset char-acronym-table #x202E "RLO")     ; RIGHT-TO-LEFT OVERRIDE
1385 (aset char-acronym-table #x2060 "WJ")      ; WORD JOINER
1386 (aset char-acronym-table #x206A "ISS")     ; INHIBIT SYMMETRIC SWAPPING
1387 (aset char-acronym-table #x206B "ASS")     ; ACTIVATE SYMMETRIC SWAPPING
1388 (aset char-acronym-table #x206C "IAFS")    ; INHIBIT ARABIC FORM SHAPING
1389 (aset char-acronym-table #x206D "AAFS")    ; ACTIVATE ARABIC FORM SHAPING
1390 (aset char-acronym-table #x206E "NADS")    ; NATIONAL DIGIT SHAPES
1391 (aset char-acronym-table #x206F "NODS")    ; NOMINAL DIGIT SHAPES
1392 (aset char-acronym-table #xFEFF "ZWNBSP")  ; ZERO WIDTH NO-BREAK SPACE
1393 (aset char-acronym-table #xFFF9 "IAA")     ; INTERLINEAR ANNOTATION ANCHOR
1394 (aset char-acronym-table #xFFFA "IAS")     ; INTERLINEAR ANNOTATION SEPARATOR
1395 (aset char-acronym-table #xFFFB "IAT")     ; INTERLINEAR ANNOTATION TERMINATOR
1396 (aset char-acronym-table #x1D173 "BEGBM")  ; MUSICAL SYMBOL BEGIN BEAM
1397 (aset char-acronym-table #x1D174 "ENDBM")  ; MUSICAL SYMBOL END BEAM
1398 (aset char-acronym-table #x1D175 "BEGTIE") ; MUSICAL SYMBOL BEGIN TIE
1399 (aset char-acronym-table #x1D176 "END")    ; MUSICAL SYMBOL END TIE
1400 (aset char-acronym-table #x1D177 "BEGSLR") ; MUSICAL SYMBOL BEGIN SLUR
1401 (aset char-acronym-table #x1D178 "ENDSLR") ; MUSICAL SYMBOL END SLUR
1402 (aset char-acronym-table #x1D179 "BEGPHR") ; MUSICAL SYMBOL BEGIN PHRASE
1403 (aset char-acronym-table #x1D17A "ENDPHR") ; MUSICAL SYMBOL END PHRASE
1404 (aset char-acronym-table #xE0001 "|->TAG") ; LANGUAGE TAG
1405 (aset char-acronym-table #xE0020 "SP TAG") ; TAG SPACE
1406 (dotimes (i 94)
1407   (aset char-acronym-table (+ #xE0021 i) (format " %c TAG" (+ 33 i))))
1408 (aset char-acronym-table #xE007F "->|TAG") ; CANCEL TAG
1409
1410 (defun update-glyphless-char-display (&optional variable value)
1411   "Make the setting of `glyphless-char-display-control' take effect.
1412 This function updates the char-table `glyphless-char-display'."
1413   (when value
1414     (set-default variable value))
1415   (dolist (elt value)
1416     (let ((target (car elt))
1417           (method (cdr elt)))
1418       (or (memq method '(zero-width thin-space empty-box acronym hex-code))
1419           (error "Invalid glyphless character display method: %s" method))
1420       (cond ((eq target 'c0-control)
1421              (glyphless-set-char-table-range glyphless-char-display
1422                                              #x00 #x1F method)
1423              ;; Users will not expect their newlines and TABs be
1424              ;; displayed as anything but themselves, so exempt those
1425              ;; two characters from c0-control.
1426              (set-char-table-range glyphless-char-display #x9 nil)
1427              (set-char-table-range glyphless-char-display #xa nil))
1428             ((eq target 'c1-control)
1429              (glyphless-set-char-table-range glyphless-char-display
1430                                              #x80 #x9F method))
1431             ((eq target 'format-control)
1432              (when unicode-category-table
1433                (map-char-table
1434                 #'(lambda (char category)
1435                     (if (eq category 'Cf)
1436                         (let ((this-method method)
1437                               from to)
1438                           (if (consp char)
1439                               (setq from (car char) to (cdr char))
1440                             (setq from char to char))
1441                           (while (<= from to)
1442                             (when (/= from #xAD)
1443                               (if (eq method 'acronym)
1444                                   (setq this-method
1445                                         (aref char-acronym-table from)))
1446                               (set-char-table-range glyphless-char-display
1447                                                     from this-method))
1448                             (setq from (1+ from))))))
1449                 unicode-category-table)))
1450             ((eq target 'no-font)
1451              (set-char-table-extra-slot glyphless-char-display 0 method))
1452             (t
1453              (error "Invalid glyphless character group: %s" target))))))
1454
1455 (defun glyphless-set-char-table-range (chartable from to method)
1456   (if (eq method 'acronym)
1457       (let ((i from))
1458         (while (<= i to)
1459           (set-char-table-range chartable i (aref char-acronym-table i))
1460           (setq i (1+ i))))
1461     (set-char-table-range chartable (cons from to) method)))
1462
1463 ;;; Control of displaying glyphless characters.
1464 (defcustom glyphless-char-display-control
1465   '((format-control . thin-space)
1466     (no-font . hex-code))
1467   "List of directives to control display of glyphless characters.
1468
1469 Each element has the form (GROUP . METHOD), where GROUP is a
1470 symbol specifying the character group, and METHOD is a symbol
1471 specifying the method of displaying characters belonging to that
1472 group.
1473
1474 GROUP must be one of these symbols:
1475   `c0-control':     U+0000..U+001F, but excluding newline and TAB.
1476   `c1-control':     U+0080..U+009F.
1477   `format-control': Characters of Unicode General Category `Cf',
1478                     such as U+200C (ZWNJ), U+200E (LRM), but
1479                     excluding characters that have graphic images,
1480                     such as U+00AD (SHY).
1481   `no-font':        characters for which no suitable font is found.
1482                     For character terminals, characters that cannot
1483                     be encoded by `terminal-coding-system'.
1484
1485 METHOD must be one of these symbols:
1486   `zero-width': don't display.
1487   `thin-space': display a thin (1-pixel width) space.  On character
1488                 terminals, display as 1-character space.
1489   `empty-box':  display an empty box.
1490   `acronym':    display an acronym of the character in a box.  The
1491                 acronym is taken from `char-acronym-table', which see.
1492   `hex-code':   display the hexadecimal character code in a box.
1493
1494 Do not set its value directly from Lisp; the value takes effect
1495 only via a custom `:set'
1496 function (`update-glyphless-char-display'), which updates
1497 `glyphless-char-display'."
1498   :version "24.1"
1499   :type '(alist :key-type (symbol :tag "Character Group")
1500                 :value-type (symbol :tag "Display Method"))
1501   :options '((c0-control
1502               (choice (const :tag "Don't display" zero-width)
1503                       (const :tag "Display as thin space" thin-space)
1504                       (const :tag "Display as empty box" empty-box)
1505                       (const :tag "Display acronym" acronym)
1506                       (const :tag "Display hex code in a box" hex-code)))
1507              (c1-control
1508               (choice (const :tag "Don't display" zero-width)
1509                       (const :tag "Display as thin space" thin-space)
1510                       (const :tag "Display as empty box" empty-box)
1511                       (const :tag "Display acronym" acronym)
1512                       (const :tag "Display hex code in a box" hex-code)))
1513              (format-control
1514               (choice (const :tag "Don't display" zero-width)
1515                       (const :tag "Display as thin space" thin-space)
1516                       (const :tag "Display as empty box" empty-box)
1517                       (const :tag "Display acronym" acronym)
1518                       (const :tag "Display hex code in a box" hex-code)))
1519              (no-font
1520               (choice (const :tag "Don't display" zero-width)
1521                       (const :tag "Display as thin space" thin-space)
1522                       (const :tag "Display as empty box" empty-box)
1523                       (const :tag "Display acronym" acronym)
1524                       (const :tag "Display hex code in a box" hex-code))))
1525   :set 'update-glyphless-char-display
1526   :group 'display)
1527
1528 \f
1529 ;;; Setting word boundary.
1530
1531 (setq word-combining-categories
1532       '((nil . ?^)
1533         (?^ . nil)
1534         (?C . ?H)
1535         (?C . ?K)))
1536
1537 (setq word-separating-categories        ;  (2-byte character sets)
1538       '((?H . ?K)                       ; Hiragana - Katakana
1539         ))
1540
1541 ;; Local Variables:
1542 ;; coding: utf-8
1543 ;; End:
1544
1545 ;;; characters.el ends here