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

   1 ;;; characters.el --- set syntax and category for multibyte characters
   2
   3 ;; Copyright (C) 1997, 2000-2015 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 ;; Load uni-mirrored.el and uni-brackets.el if available, so that they
 499 ;; get dumped into Emacs.  This allows to start Emacs with
 500 ;; force-load-messages in ~/.emacs, and avoid infinite recursion in
 501 ;; bidi_initialize, which needs to load uni-mirrored.el and
 502 ;; uni-brackets.el in order to display the "Loading" messages.
 503 (unicode-property-table-internal 'mirroring)
 504 (unicode-property-table-internal 'bracket-type)
 505
 506 ;; Latin
 507
 508 (modify-category-entry '(#x80 . #x024F) ?l)
 509
 510 (let ((tbl (standard-case-table)) c)
 511
 512   ;; Latin-1
 513
 514   ;; Fixme: Some of the non-word syntaxes here perhaps should be
 515   ;; reviewed.  (Note that the following all implicitly have word
 516   ;; syntax: ¢£¤¥¨ª¯²³´¶¸¹º.)  There should be a well-defined way of
 517   ;; relating Unicode categories to Emacs syntax codes.
 518
 519   ;; NBSP isn't semantically interchangeable with other whitespace chars,
 520   ;; so it's more like punctuation.
 521   (set-case-syntax ?  "." tbl)
 522   (set-case-syntax ?¡ "." tbl)
 523   (set-case-syntax ?¦ "_" tbl)
 524   (set-case-syntax ?§ "." tbl)
 525   (set-case-syntax ?© "_" tbl)
 526   ;; French wants
 527   ;;   (set-case-syntax-delims ?« ?» tbl)
 528   ;; And German wants
 529   ;;   (set-case-syntax-delims ?» ?« tbl)
 530   ;; So let's stay neutral and let users set these up if/when they want to.
 531   (set-case-syntax ?« "." tbl)
 532   (set-case-syntax ?» "." tbl)
 533   (set-case-syntax ?¬ "_" tbl)
 534   (set-case-syntax ? "_" tbl)
 535   (set-case-syntax ?® "_" tbl)
 536   (set-case-syntax ?° "_" tbl)
 537   (set-case-syntax ?± "_" tbl)
 538   (set-case-syntax ?µ "_" tbl)
 539   (set-case-syntax ?· "_" tbl)
 540   (set-case-syntax ?¼ "_" tbl)
 541   (set-case-syntax ?½ "_" tbl)
 542   (set-case-syntax ?¾ "_" tbl)
 543   (set-case-syntax ?¿ "." tbl)
 544   (let ((c 192))
 545     (while (<= c 222)
 546       (set-case-syntax-pair c (+ c 32) tbl)
 547       (setq c (1+ c))))
 548   (set-case-syntax ?× "_" tbl)
 549   (set-case-syntax ?ß "w" tbl)
 550   (set-case-syntax ?÷ "_" tbl)
 551   ;; See below for ÿ.
 552
 553   ;; Latin Extended-A, Latin Extended-B
 554   (setq c #x0100)
 555   (while (<= c #x02B8)
 556     (modify-category-entry c ?l)
 557     (setq c (1+ c)))
 558
 559   (let ((pair-ranges '((#x0100 . #x012F)
 560                        (#x0132 . #x0137)
 561                        (#x0139 . #x0148)
 562                        (#x014a . #x0177)
 563                        (#x0179 . #x017E)
 564                        (#x0182 . #x0185)
 565                        (#x0187 . #x0188)
 566                        (#x018B . #x018C)
 567                        (#x0191 . #x0192)
 568                        (#x0198 . #x0199)
 569                        (#x01A0 . #x01A5)
 570                        (#x01A7 . #x01A8)
 571                        (#x01AC . #x01AD)
 572                        (#x01AF . #x01B0)
 573                        (#x01B3 . #x01B6)
 574                        (#x01B8 . #x01B9)
 575                        (#x01BC . #x01BD)
 576                        (#x01CD . #x01DC)
 577                        (#x01DE . #x01EF)
 578                        (#x01F4 . #x01F5)
 579                        (#x01F8 . #x021F)
 580                        (#x0222 . #x0233)
 581                        (#x023B . #x023C)
 582                        (#x0241 . #x0242)
 583                        (#x0246 . #x024F))))
 584     (dolist (elt pair-ranges)
 585       (let ((from (car elt)) (to (cdr elt)))
 586         (while (< from to)
 587           (set-case-syntax-pair from (1+ from) tbl)
 588           (setq from (+ from 2))))))
 589
 590   (set-case-syntax-pair ?Ÿ ?ÿ tbl)
 591
 592   ;; In some languages, such as Turkish, U+0049 LATIN CAPITAL LETTER I
 593   ;; and U+0131 LATIN SMALL LETTER DOTLESS I make a case pair, and so
 594   ;; do U+0130 LATIN CAPITAL LETTER I WITH DOT ABOVE and U+0069 LATIN
 595   ;; SMALL LETTER I.
 596
 597   ;; We used to set up half of those correspondence unconditionally,
 598   ;; but that makes searches slow.  So now we don't set up either half
 599   ;; of these correspondences by default.
 600
 601   ;; (set-downcase-syntax  ?İ ?i tbl)
 602   ;; (set-upcase-syntax    ?I ?ı tbl)
 603
 604   (set-case-syntax-pair ?Ɓ ?ɓ tbl)
 605   (set-case-syntax-pair ?Ɔ ?ɔ tbl)
 606   (set-case-syntax-pair ?Ɖ ?ɖ tbl)
 607   (set-case-syntax-pair ?Ɗ ?ɗ tbl)
 608   (set-case-syntax-pair ?Ǝ ?ǝ tbl)
 609   (set-case-syntax-pair ?Ə ?ə tbl)
 610   (set-case-syntax-pair ?Ɛ ?ɛ tbl)
 611   (set-case-syntax-pair ?Ɠ ?ɠ tbl)
 612   (set-case-syntax-pair ?Ɣ ?ɣ tbl)
 613   (set-case-syntax-pair ?Ɩ ?ɩ tbl)
 614   (set-case-syntax-pair ?Ɨ ?ɨ tbl)
 615   (set-case-syntax-pair ?Ɯ ?ɯ tbl)
 616   (set-case-syntax-pair ?Ɲ ?ɲ tbl)
 617   (set-case-syntax-pair ?Ɵ ?ɵ tbl)
 618   (set-case-syntax-pair ?Ʀ ?ʀ tbl)
 619   (set-case-syntax-pair ?Ʃ ?ʃ tbl)
 620   (set-case-syntax-pair ?Ʈ ?ʈ tbl)
 621   (set-case-syntax-pair ?Ʊ ?ʊ tbl)
 622   (set-case-syntax-pair ?Ʋ ?ʋ tbl)
 623   (set-case-syntax-pair ?Ʒ ?ʒ tbl)
 624   (set-case-syntax-pair ?Ǆ ?ǆ tbl)
 625   (set-case-syntax-pair ?ǅ ?ǆ tbl)
 626   (set-case-syntax-pair ?Ǉ ?ǉ tbl)
 627   (set-case-syntax-pair ?ǈ ?ǉ tbl)
 628   (set-case-syntax-pair ?Ǌ ?ǌ tbl)
 629   (set-case-syntax-pair ?ǋ ?ǌ tbl)
 630
 631   ;; 01F0; F; 006A 030C; # LATIN SMALL LETTER J WITH CARON
 632   (set-case-syntax-pair ?Ǳ ?ǳ tbl)
 633   (set-case-syntax-pair ?ǲ ?ǳ tbl)
 634   (set-case-syntax-pair ?Ƕ ?ƕ tbl)
 635   (set-case-syntax-pair ?Ƿ ?ƿ tbl)
 636   (set-case-syntax-pair ?Ⱥ ?ⱥ tbl)
 637   (set-case-syntax-pair ?Ƚ ?ƚ tbl)
 638   (set-case-syntax-pair ?Ⱦ ?ⱦ tbl)
 639   (set-case-syntax-pair ?Ƀ ?ƀ tbl)
 640   (set-case-syntax-pair ?Ʉ ?ʉ tbl)
 641   (set-case-syntax-pair ?Ʌ ?ʌ tbl)
 642
 643   ;; Latin Extended Additional
 644   (modify-category-entry '(#x1e00 . #x1ef9) ?l)
 645   (setq c #x1e00)
 646   (while (<= c #x1ef9)
 647     (and (zerop (% c 2))
 648          (or (<= c #x1e94) (>= c #x1ea0))
 649          (set-case-syntax-pair c (1+ c) tbl))
 650     (setq c (1+ c)))
 651
 652   ;; Greek
 653   (modify-category-entry '(#x0370 . #x03ff) ?g)
 654   (setq c #x0370)
 655   (while (<= c #x03ff)
 656     (if (or (and (>= c #x0391) (<= c #x03a1))
 657             (and (>= c #x03a3) (<= c #x03ab)))
 658         (set-case-syntax-pair c (+ c 32) tbl))
 659     (and (>= c #x03da)
 660          (<= c #x03ee)
 661          (zerop (% c 2))
 662          (set-case-syntax-pair c (1+ c) tbl))
 663     (setq c (1+ c)))
 664   (set-case-syntax-pair ?Ά ?ά tbl)
 665   (set-case-syntax-pair ?Έ ?έ tbl)
 666   (set-case-syntax-pair ?Ή ?ή tbl)
 667   (set-case-syntax-pair ?Ί ?ί tbl)
 668   (set-case-syntax-pair ?Ό ?ό tbl)
 669   (set-case-syntax-pair ?Ύ ?ύ tbl)
 670   (set-case-syntax-pair ?Ώ ?ώ tbl)
 671
 672   ;; Armenian
 673   (setq c #x531)
 674   (while (<= c #x556)
 675     (set-case-syntax-pair c (+ c #x30) tbl)
 676     (setq c (1+ c)))
 677
 678   ;; Greek Extended
 679   (modify-category-entry '(#x1f00 . #x1fff) ?g)
 680   (setq c #x1f00)
 681   (while (<= c #x1fff)
 682     (and (<= (logand c #x000f) 7)
 683          (<= c #x1fa7)
 684          (not (memq c '(#x1f16 #x1f17 #x1f56 #x1f57
 685                                #x1f50 #x1f52 #x1f54 #x1f56)))
 686          (/= (logand c #x00f0) #x70)
 687          (set-case-syntax-pair (+ c 8) c tbl))
 688     (setq c (1+ c)))
 689   (set-case-syntax-pair ?Ᾰ ?ᾰ tbl)
 690   (set-case-syntax-pair ?Ᾱ ?ᾱ tbl)
 691   (set-case-syntax-pair ?Ὰ ?ὰ tbl)
 692   (set-case-syntax-pair ?Ά ?ά tbl)
 693   (set-case-syntax-pair ?ᾼ ?ᾳ tbl)
 694   (set-case-syntax-pair ?Ὲ ?ὲ tbl)
 695   (set-case-syntax-pair ?Έ ?έ tbl)
 696   (set-case-syntax-pair ?Ὴ ?ὴ tbl)
 697   (set-case-syntax-pair ?Ή ?ή tbl)
 698   (set-case-syntax-pair ?ῌ ?ῃ tbl)
 699   (set-case-syntax-pair ?Ῐ ?ῐ tbl)
 700   (set-case-syntax-pair ?Ῑ ?ῑ tbl)
 701   (set-case-syntax-pair ?Ὶ ?ὶ tbl)
 702   (set-case-syntax-pair ?Ί ?ί tbl)
 703   (set-case-syntax-pair ?Ῠ ?ῠ tbl)
 704   (set-case-syntax-pair ?Ῡ ?ῡ tbl)
 705   (set-case-syntax-pair ?Ὺ ?ὺ tbl)
 706   (set-case-syntax-pair ?Ύ ?ύ tbl)
 707   (set-case-syntax-pair ?Ῥ ?ῥ tbl)
 708   (set-case-syntax-pair ?Ὸ ?ὸ tbl)
 709   (set-case-syntax-pair ?Ό ?ό tbl)
 710   (set-case-syntax-pair ?Ὼ ?ὼ tbl)
 711   (set-case-syntax-pair ?Ώ ?ώ tbl)
 712   (set-case-syntax-pair ?ῼ ?ῳ tbl)
 713
 714   ;; cyrillic
 715   (modify-category-entry '(#x0400 . #x04FF) ?y)
 716   (setq c #x0400)
 717   (while (<= c #x04ff)
 718     (and (>= c #x0400)
 719          (<= c #x040f)
 720          (set-case-syntax-pair c (+ c 80) tbl))
 721     (and (>= c #x0410)
 722          (<= c #x042f)
 723          (set-case-syntax-pair c (+ c 32) tbl))
 724     (and (zerop (% c 2))
 725          (or (and (>= c #x0460) (<= c #x0480))
 726              (and (>= c #x048c) (<= c #x04be))
 727              (and (>= c #x04d0) (<= c #x04f4)))
 728          (set-case-syntax-pair c (1+ c) tbl))
 729     (setq c (1+ c)))
 730   (set-case-syntax-pair ?Ӂ ?ӂ tbl)
 731   (set-case-syntax-pair ?Ӄ ?ӄ tbl)
 732   (set-case-syntax-pair ?Ӈ ?ӈ tbl)
 733   (set-case-syntax-pair ?Ӌ ?ӌ tbl)
 734   (set-case-syntax-pair ?Ӹ ?ӹ tbl)
 735
 736   ;; general punctuation
 737   (setq c #x2000)
 738   (while (<= c #x200b)
 739     (set-case-syntax c " " tbl)
 740     (setq c (1+ c)))
 741   (while (<= c #x200F)
 742     (set-case-syntax c "." tbl)
 743     (setq c (1+ c)))
 744   ;; Fixme: These aren't all right:
 745   (setq c #x2010)
 746   (while (<= c #x2016)
 747     (set-case-syntax c "_" tbl)
 748     (setq c (1+ c)))
 749   ;; Punctuation syntax for quotation marks (like `)
 750   (while (<= c #x201f)
 751     (set-case-syntax  c "." tbl)
 752     (setq c (1+ c)))
 753   ;; Fixme: These aren't all right:
 754   (while (<= c #x2027)
 755     (set-case-syntax c "_" tbl)
 756     (setq c (1+ c)))
 757   (while (<= c #x206F)
 758     (set-case-syntax c "." tbl)
 759     (setq c (1+ c)))
 760
 761   ;; Roman numerals
 762   (setq c #x2160)
 763   (while (<= c #x216f)
 764     (set-case-syntax-pair c (+ c #x10) tbl)
 765     (setq c (1+ c)))
 766
 767   ;; Fixme: The following blocks might be better as symbol rather than
 768   ;; punctuation.
 769   ;; Arrows
 770   (setq c #x2190)
 771   (while (<= c #x21FF)
 772     (set-case-syntax c "." tbl)
 773     (setq c (1+ c)))
 774   ;; Mathematical Operators
 775   (while (<= c #x22FF)
 776     (set-case-syntax c "." tbl)
 777     (setq c (1+ c)))
 778   ;; Miscellaneous Technical
 779   (while (<= c #x23FF)
 780     (set-case-syntax c "." tbl)
 781     (setq c (1+ c)))
 782   ;; Control Pictures
 783   (while (<= c #x243F)
 784     (set-case-syntax c "_" tbl)
 785     (setq c (1+ c)))
 786
 787   ;; Circled Latin
 788   (setq c #x24b6)
 789   (while (<= c #x24cf)
 790     (set-case-syntax-pair c (+ c 26) tbl)
 791     (modify-category-entry c ?l)
 792     (modify-category-entry (+ c 26) ?l)
 793     (setq c (1+ c)))
 794
 795   ;; Coptic
 796   (let ((pair-ranges '((#x2C80 . #x2CE2)
 797                        (#x2CEB . #x2CF2))))
 798     (dolist (elt pair-ranges)
 799       (let ((from (car elt)) (to (cdr elt)))
 800         (while (< from to)
 801           (set-case-syntax-pair from (1+ from) tbl)
 802           (setq from (+ from 2))))))
 803   ;; There's no Coptic category.  However, Coptic letters that are
 804   ;; part of the Greek block above get the Greek category, and those
 805   ;; in this block are derived from Greek letters, so let's be
 806   ;; consistent about their category.
 807   (modify-category-entry '(#x2C80 . #x2CFF) ?g)
 808
 809   ;; Fullwidth Latin
 810   (setq c #xff21)
 811   (while (<= c #xff3a)
 812     (set-case-syntax-pair c (+ c #x20) tbl)
 813     (modify-category-entry c ?l)
 814     (modify-category-entry (+ c #x20) ?l)
 815     (setq c (1+ c)))
 816
 817   ;; Combining diacritics
 818   (modify-category-entry '(#x300 . #x362) ?^)
 819   ;; Combining marks
 820   (modify-category-entry '(#x20d0 . #x20ff) ?^)
 821
 822   ;; Fixme: syntax for symbols &c
 823   )
 824
 825 (let ((pairs
 826        '("⁅⁆"                               ; U+2045 U+2046
 827          "⁽⁾"                               ; U+207D U+207E
 828          "₍₎"                               ; U+208D U+208E
 829          "〈〉"                               ; U+2329 U+232A
 830          "⎴⎵"                               ; U+23B4 U+23B5
 831          "❨❩"                               ; U+2768 U+2769
 832          "❪❫"                               ; U+276A U+276B
 833          "❬❭"                               ; U+276C U+276D
 834          "❰❱"                               ; U+2770 U+2771
 835          "❲❳"                               ; U+2772 U+2773
 836          "❴❵"                               ; U+2774 U+2775
 837          "⟦⟧"                               ; U+27E6 U+27E7
 838          "⟨⟩"                               ; U+27E8 U+27E9
 839          "⟪⟫"                               ; U+27EA U+27EB
 840          "⦃⦄"                               ; U+2983 U+2984
 841          "⦅⦆"                               ; U+2985 U+2986
 842          "⦇⦈"                               ; U+2987 U+2988
 843          "⦉⦊"                               ; U+2989 U+298A
 844          "⦋⦌"                               ; U+298B U+298C
 845          "⦍⦎"                               ; U+298D U+298E
 846          "⦏⦐"                               ; U+298F U+2990
 847          "⦑⦒"                               ; U+2991 U+2992
 848          "⦓⦔"                               ; U+2993 U+2994
 849          "⦕⦖"                               ; U+2995 U+2996
 850          "⦗⦘"                               ; U+2997 U+2998
 851          "⧼⧽"                               ; U+29FC U+29FD
 852          "〈〉"                               ; U+3008 U+3009
 853          "《》"                               ; U+300A U+300B
 854          "「」"                               ; U+300C U+300D
 855          "『』"                               ; U+300E U+300F
 856          "【】"                               ; U+3010 U+3011
 857          "〔〕"                               ; U+3014 U+3015
 858          "〖〗"                               ; U+3016 U+3017
 859          "〘〙"                               ; U+3018 U+3019
 860          "〚〛"                               ; U+301A U+301B
 861          "﴾﴿"                               ; U+FD3E U+FD3F
 862          "︵︶"                               ; U+FE35 U+FE36
 863          "︷︸"                               ; U+FE37 U+FE38
 864          "︹︺"                               ; U+FE39 U+FE3A
 865          "︻︼"                               ; U+FE3B U+FE3C
 866          "︽︾"                               ; U+FE3D U+FE3E
 867          "︿﹀"                               ; U+FE3F U+FE40
 868          "﹁﹂"                               ; U+FE41 U+FE42
 869          "﹃﹄"                               ; U+FE43 U+FE44
 870          "﹙﹚"                               ; U+FE59 U+FE5A
 871          "﹛﹜"                               ; U+FE5B U+FE5C
 872          "﹝﹞"                               ; U+FE5D U+FE5E
 873          "（）"                               ; U+FF08 U+FF09
 874          "［］"                               ; U+FF3B U+FF3D
 875          "｛｝"                               ; U+FF5B U+FF5D
 876          "｟｠"                               ; U+FF5F U+FF60
 877          "｢｣"                               ; U+FF62 U+FF63
 878          )))
 879   (dolist (elt pairs)
 880     (modify-syntax-entry (aref elt 0) (string ?\( (aref elt 1)))
 881     (modify-syntax-entry (aref elt 1) (string ?\) (aref elt 0)))))
 882
 883 \f
 884 ;; For each character set, put the information of the most proper
 885 ;; coding system to encode it by `preferred-coding-system' property.
 886
 887 ;; Fixme: should this be junked?
 888 (let ((l '((latin-iso8859-1     . iso-latin-1)
 889            (latin-iso8859-2     . iso-latin-2)
 890            (latin-iso8859-3     . iso-latin-3)
 891            (latin-iso8859-4     . iso-latin-4)
 892            (thai-tis620         . thai-tis620)
 893            (greek-iso8859-7     . greek-iso-8bit)
 894            (arabic-iso8859-6    . iso-2022-7bit)
 895            (hebrew-iso8859-8    . hebrew-iso-8bit)
 896            (katakana-jisx0201   . japanese-shift-jis)
 897            (latin-jisx0201      . japanese-shift-jis)
 898            (cyrillic-iso8859-5  . cyrillic-iso-8bit)
 899            (latin-iso8859-9     . iso-latin-5)
 900            (japanese-jisx0208-1978 . iso-2022-jp)
 901            (chinese-gb2312      . chinese-iso-8bit)
 902            (chinese-gbk         . chinese-gbk)
 903            (gb18030-2-byte      . chinese-gb18030)
 904            (gb18030-4-byte-bmp  . chinese-gb18030)
 905            (gb18030-4-byte-smp  . chinese-gb18030)
 906            (gb18030-4-byte-ext-1 . chinese-gb18030)
 907            (gb18030-4-byte-ext-2 . chinese-gb18030)
 908            (japanese-jisx0208   . iso-2022-jp)
 909            (korean-ksc5601      . iso-2022-kr)
 910            (japanese-jisx0212   . iso-2022-jp)
 911            (chinese-big5-1      . chinese-big5)
 912            (chinese-big5-2      . chinese-big5)
 913            (chinese-sisheng     . iso-2022-7bit)
 914            (ipa                 . iso-2022-7bit)
 915            (vietnamese-viscii-lower . vietnamese-viscii)
 916            (vietnamese-viscii-upper . vietnamese-viscii)
 917            (arabic-digit        . iso-2022-7bit)
 918            (arabic-1-column     . iso-2022-7bit)
 919            (lao                 . lao)
 920            (arabic-2-column     . iso-2022-7bit)
 921            (indian-is13194      . devanagari)
 922            (indian-glyph        . devanagari)
 923            (tibetan-1-column    . tibetan)
 924            (ethiopic            . iso-2022-7bit)
 925            (chinese-cns11643-1  . iso-2022-cn)
 926            (chinese-cns11643-2  . iso-2022-cn)
 927            (chinese-cns11643-3  . iso-2022-cn)
 928            (chinese-cns11643-4  . iso-2022-cn)
 929            (chinese-cns11643-5  . iso-2022-cn)
 930            (chinese-cns11643-6  . iso-2022-cn)
 931            (chinese-cns11643-7  . iso-2022-cn)
 932            (indian-2-column     . devanagari)
 933            (tibetan             . tibetan)
 934            (latin-iso8859-14    . iso-latin-8)
 935            (latin-iso8859-15    . iso-latin-9))))
 936   (while l
 937     (put-charset-property (car (car l)) 'preferred-coding-system (cdr (car l)))
 938     (setq l (cdr l))))
 939
 940 \f
 941 ;; Setup auto-fill-chars for charsets that should invoke auto-filling.
 942 ;; SPACE and NEWLINE are already set.
 943
 944 (set-char-table-range auto-fill-chars '(#x3041 . #x30FF) t)
 945 (set-char-table-range auto-fill-chars '(#x3400 . #x4DB5) t)
 946 (set-char-table-range auto-fill-chars '(#x4e00 . #x9fbb) t)
 947 (set-char-table-range auto-fill-chars '(#xF900 . #xFAFF) t)
 948 (set-char-table-range auto-fill-chars '(#xFF00 . #xFF9F) t)
 949 (set-char-table-range auto-fill-chars '(#x20000 . #x2FFFF) t)
 950
 951 \f
 952 ;;; Setting char-width-table.  The default is 1.
 953
 954 ;; 0: non-spacing, enclosing combining, formatting, Hangul Jamo medial
 955 ;;    and final characters.
 956 (let ((l '((#x0300 . #x036F)
 957            (#x0483 . #x0489)
 958            (#x0591 . #x05BD)
 959            (#x05BF . #x05BF)
 960            (#x05C1 . #x05C2)
 961            (#x05C4 . #x05C5)
 962            (#x05C7 . #x05C7)
 963            (#x0600 . #x0603)
 964            (#x0610 . #x0615)
 965            (#x064B . #x065E)
 966            (#x0670 . #x0670)
 967            (#x06D6 . #x06E4)
 968            (#x06E7 . #x06E8)
 969            (#x06EA . #x06ED)
 970            (#x070F . #x070F)
 971            (#x0711 . #x0711)
 972            (#x0730 . #x074A)
 973            (#x07A6 . #x07B0)
 974            (#x07EB . #x07F3)
 975            (#x0901 . #x0902)
 976            (#x093C . #x093C)
 977            (#x0941 . #x0948)
 978            (#x094D . #x094D)
 979            (#x0951 . #x0954)
 980            (#x0962 . #x0963)
 981            (#x0981 . #x0981)
 982            (#x09BC . #x09BC)
 983            (#x09C1 . #x09C4)
 984            (#x09CD . #x09CD)
 985            (#x09E2 . #x09E3)
 986            (#x0A01 . #x0A02)
 987            (#x0A3C . #x0A3C)
 988            (#x0A41 . #x0A4D)
 989            (#x0A70 . #x0A71)
 990            (#x0A81 . #x0A82)
 991            (#x0ABC . #x0ABC)
 992            (#x0AC1 . #x0AC8)
 993            (#x0ACD . #x0ACD)
 994            (#x0AE2 . #x0AE3)
 995            (#x0B01 . #x0B01)
 996            (#x0B3C . #x0B3C)
 997            (#x0B3F . #x0B3F)
 998            (#x0B41 . #x0B43)
 999            (#x0B4D . #x0B56)
1000            (#x0B82 . #x0B82)
1001            (#x0BC0 . #x0BC0)
1002            (#x0BCD . #x0BCD)
1003            (#x0C3E . #x0C40)
1004            (#x0C46 . #x0C56)
1005            (#x0CBC . #x0CBC)
1006            (#x0CBF . #x0CBF)
1007            (#x0CC6 . #x0CC6)
1008            (#x0CCC . #x0CCD)
1009            (#x0CE2 . #x0CE3)
1010            (#x0D41 . #x0D43)
1011            (#x0D4D . #x0D4D)
1012            (#x0DCA . #x0DCA)
1013            (#x0DD2 . #x0DD6)
1014            (#x0E31 . #x0E31)
1015            (#x0E34 . #x0E3A)
1016            (#x0E47 . #x0E4E)
1017            (#x0EB1 . #x0EB1)
1018            (#x0EB4 . #x0EBC)
1019            (#x0EC8 . #x0ECD)
1020            (#x0F18 . #x0F19)
1021            (#x0F35 . #x0F35)
1022            (#x0F37 . #x0F37)
1023            (#x0F39 . #x0F39)
1024            (#x0F71 . #x0F7E)
1025            (#x0F80 . #x0F84)
1026            (#x0F86 . #x0F87)
1027            (#x0F90 . #x0FBC)
1028            (#x0FC6 . #x0FC6)
1029            (#x102D . #x1030)
1030            (#x1032 . #x1037)
1031            (#x1039 . #x1039)
1032            (#x1058 . #x1059)
1033            (#x1160 . #x11FF)
1034            (#x135F . #x135F)
1035            (#x1712 . #x1714)
1036            (#x1732 . #x1734)
1037            (#x1752 . #x1753)
1038            (#x1772 . #x1773)
1039            (#x17B4 . #x17B5)
1040            (#x17B7 . #x17BD)
1041            (#x17C6 . #x17C6)
1042            (#x17C9 . #x17D3)
1043            (#x17DD . #x17DD)
1044            (#x180B . #x180D)
1045            (#x18A9 . #x18A9)
1046            (#x1920 . #x1922)
1047            (#x1927 . #x1928)
1048            (#x1932 . #x1932)
1049            (#x1939 . #x193B)
1050            (#x1A17 . #x1A18)
1051            (#x1B00 . #x1B03)
1052            (#x1B34 . #x1B34)
1053            (#x1B36 . #x1B3A)
1054            (#x1B3C . #x1B3C)
1055            (#x1B42 . #x1B42)
1056            (#x1B6B . #x1B73)
1057            (#x1DC0 . #x1DFF)
1058            (#x200B . #x200F)
1059            (#x202A . #x202E)
1060            (#x2060 . #x206F)
1061            (#x20D0 . #x20EF)
1062            (#x302A . #x302F)
1063            (#x3099 . #x309A)
1064            (#xA806 . #xA806)
1065            (#xA80B . #xA80B)
1066            (#xA825 . #xA826)
1067            (#xFB1E . #xFB1E)
1068            (#xFE00 . #xFE0F)
1069            (#xFE20 . #xFE23)
1070            (#xFEFF . #xFEFF)
1071            (#xFFF9 . #xFFFB)
1072            (#x10A01 . #x10A0F)
1073            (#x10A38 . #x10A3F)
1074            (#x1D167 . #x1D169)
1075            (#x1D173 . #x1D182)
1076            (#x1D185 . #x1D18B)
1077            (#x1D1AA . #x1D1AD)
1078            (#x1D242 . #x1D244)
1079            (#xE0001 . #xE01EF))))
1080   (dolist (elt l)
1081     (set-char-table-range char-width-table elt 0)))
1082
1083 ;; 2: East Asian Wide and Full-width characters.
1084 (let ((l '((#x1100 . #x115F)
1085            (#x2329 . #x232A)
1086            (#x2E80 . #x303E)
1087            (#x3040 . #xA4CF)
1088            (#xAC00 . #xD7A3)
1089            (#xF900 . #xFAFF)
1090            (#xFE30 . #xFE6F)
1091            (#xFF01 . #xFF60)
1092            (#xFFE0 . #xFFE6)
1093            (#x20000 . #x2FFFF)
1094            (#x30000 . #x3FFFF))))
1095   (dolist (elt l)
1096     (set-char-table-range char-width-table elt 2)))
1097
1098 ;; Other double width
1099 ;;(map-charset-chars
1100 ;; (lambda (range ignore) (set-char-table-range char-width-table range 2))
1101 ;; 'ethiopic)
1102 ;; (map-charset-chars
1103 ;;  (lambda (range ignore) (set-char-table-range char-width-table range 2))
1104 ;; 'tibetan)
1105 (map-charset-chars
1106  (lambda (range _ignore) (set-char-table-range char-width-table range 2))
1107  'indian-2-column)
1108 (map-charset-chars
1109  (lambda (range _ignore) (set-char-table-range char-width-table range 2))
1110  'arabic-2-column)
1111
1112 ;; Internal use only.
1113 ;; Alist of locale symbol vs charsets.  In a language environment
1114 ;; corresponding to the locale, width of characters in the charsets is
1115 ;; set to 2.  Each element has the form:
1116 ;;   (LOCALE TABLE (CHARSET (FROM-CODE . TO-CODE) ...) ...)
1117 ;; LOCALE: locale symbol
1118 ;; TABLE: char-table used for char-width-table, initially nil.
1119 ;; CHARSET: character set
1120 ;; FROM-CODE, TO-CODE: range of code-points in CHARSET
1121
1122 (defvar cjk-char-width-table-list
1123   '((ja_JP nil (japanese-jisx0208 (#x2121 . #x287E))
1124                (cp932-2-byte (#x8140 . #x879F)))
1125     (zh_CN nil (chinese-gb2312 (#x2121 . #x297E)))
1126     (zh_HK nil (big5-hkscs (#xA140 . #xA3FE) (#xC6A0 . #xC8FE)))
1127     (zh_TW nil (big5 (#xA140 . #xA3FE))
1128                (chinese-cns11643-1 (#x2121 . #x427E)))
1129     (ko_KR nil (korean-ksc5601 (#x2121 . #x2C7E)))))
1130
1131 ;; Internal use only.
1132 ;; Setup char-width-table appropriate for a language environment
1133 ;; corresponding to LOCALE-NAME (symbol).
1134
1135 (defun use-cjk-char-width-table (locale-name)
1136   (while (char-table-parent char-width-table)
1137     (setq char-width-table (char-table-parent char-width-table)))
1138   (let ((slot (assq locale-name cjk-char-width-table-list)))
1139     (or slot (error "Unknown locale for CJK language environment: %s"
1140                     locale-name))
1141     (unless (nth 1 slot)
1142       (let ((table (make-char-table nil)))
1143         (dolist (charset-info (nthcdr 2 slot))
1144           (let ((charset (car charset-info)))
1145             (dolist (code-range (cdr charset-info))
1146               (map-charset-chars #'(lambda (range _arg)
1147                                      (set-char-table-range table range 2))
1148                                  charset nil
1149                                  (car code-range) (cdr code-range)))))
1150         (optimize-char-table table)
1151         (set-char-table-parent table char-width-table)
1152         (setcar (cdr slot) table)))
1153     (setq char-width-table (nth 1 slot))))
1154
1155 (defun use-default-char-width-table ()
1156   "Internal use only.
1157 Setup char-width-table appropriate for non-CJK language environment."
1158   (while (char-table-parent char-width-table)
1159     (setq char-width-table (char-table-parent char-width-table))))
1160
1161 (optimize-char-table (standard-case-table))
1162 (optimize-char-table (standard-syntax-table))
1163
1164 \f
1165 ;; Setting char-script-table.
1166
1167 ;; The data is compiled from Blocks.txt and Scripts.txt in the
1168 ;; "Unicode Character Database", simplified to lump together all the
1169 ;; blocks belonging to the same language.  E.g., "Basic Latin",
1170 ;; "Latin-1 Supplement", "Latin Extended-A", etc. are all lumped
1171 ;; together under "latin".
1172 ;;
1173 ;; The Unicode blocks actually extend past some of these ranges with
1174 ;; undefined codepoints.
1175 ;;
1176 ;; Last update: http://www.unicode.org/Public/8.0.0/ucd/Blocks-8.0.0d3.txt
1177 (let ((script-list nil))
1178   (dolist
1179       (elt
1180        '((#x0000 #x007F latin)
1181          (#x00A0 #x024F latin)
1182          (#x0250 #x02AF phonetic)       ; IPA Extensions
1183          (#x02B0 #x036F latin)          ; Spacing Modifiers and Diacriticals
1184          (#x0370 #x03E1 greek)
1185          (#x03E2 #x03EF coptic)
1186          (#x03F0 #x03FF greek)
1187          (#x0400 #x052F cyrillic)
1188          (#x0530 #x058F armenian)
1189          (#x0590 #x05FF hebrew)
1190          (#x0600 #x06FF arabic)
1191          (#x0700 #x074F syriac)
1192          (#x0750 #x077F arabic)         ; Arabic Supplement
1193          (#x0780 #x07BF thaana)
1194          (#x07C0 #x07FF nko)
1195          (#x0800 #x083F samaritan)
1196          (#x0840 #x085F mandaic)
1197          (#x08A0 #x08FF arabic)         ; Arabic Extended-A
1198          (#x0900 #x097F devanagari)
1199          (#x0980 #x09FF bengali)
1200          (#x0A00 #x0A7F gurmukhi)
1201          (#x0A80 #x0AFF gujarati)
1202          (#x0B00 #x0B7F oriya)
1203          (#x0B80 #x0BFF tamil)
1204          (#x0C00 #x0C7F telugu)
1205          (#x0C80 #x0CFF kannada)
1206          (#x0D00 #x0D7F malayalam)
1207          (#x0D80 #x0DFF sinhala)
1208          (#x0E00 #x0E7F thai)
1209          (#x0E80 #x0EFF lao)
1210          (#x0F00 #x0FFF tibetan)
1211          (#x1000 #x109F burmese)        ; Myanmar
1212          (#x10A0 #x10FF georgian)
1213          (#x1100 #x11FF hangul)
1214          (#x1200 #x139F ethiopic)       ; Ethiopic and Ethiopic Supplement
1215          (#x13A0 #x13FF cherokee)
1216          (#x1400 #x167F canadian-aboriginal)
1217          (#x1680 #x169F ogham)
1218          (#x16A0 #x16FF runic)
1219          (#x1700 #x171F tagalog)
1220          (#x1720 #x173F hanunoo)
1221          (#x1740 #x175F buhid)
1222          (#x1760 #x177F tagbanwa)
1223          (#x1780 #x17FF khmer)
1224          (#x1800 #x18AF mongolian)
1225          (#x18B0 #x18FF canadian-aboriginal) ; Canadian Aboriginal Syllabics Extended
1226          (#x1900 #x194F limbu)
1227          (#x1950 #x197F tai-le)
1228          (#x1980 #x19DF tai-lue)        ; New Tai Lue
1229          (#x19E0 #x19FF khmer)          ; Khmer Symbols
1230          (#x1A00 #x1A1F buginese)
1231          (#x1A20 #x1AAF tai-tham)
1232          (#x1AB0 #x1AFF latin)          ; Combining Diacritical Marks Extended
1233          (#x1B00 #x1B7F balinese)
1234          (#x1B80 #x1BBF sundanese)
1235          (#x1BC0 #x1BFF batak)
1236          (#x1C00 #x1C4F lepcha)
1237          (#x1C50 #x1C7F ol-chiki)
1238          (#x1CC0 #x1CCF sundanese)
1239          (#x1CD0 #x1CFF vedic)
1240          (#x1D00 #x1DBF phonetic)       ; Phonetic Extensions & Supplement
1241          (#x1DC0 #x1EFF latin)          ; Latin Extended Additional
1242          (#x1F00 #x1FFF greek)          ; Greek Extended
1243          (#x2000 #x27FF symbol)
1244          (#x2800 #x28FF braille)
1245          (#x2900 #x2BFF symbol)
1246          (#x2C00 #x2C5F glagolitic)
1247          (#x2C60 #x2C7F latin)          ; Latin Extended-C
1248          (#x2C80 #x2CFF coptic)
1249          (#x2D00 #x2D2F georgian)       ; Georgian Supplement
1250          (#x2D30 #x2D7F tifinagh)
1251          (#x2D80 #x2DDF ethiopic)       ; Ethiopic Extended
1252          (#x2DE0 #x2DFF cyrillic)       ; Cyrillic Extended-A
1253          (#x2E00 #x2E7F symbol)
1254          (#x2E80 #x2FDF han)
1255          (#x2FF0 #x2FFF ideographic-description)
1256          (#x3000 #x303F cjk-misc)
1257          (#x3040 #x30FF kana)           ; Hiragana and Katakana
1258          (#x3100 #x312F bopomofo)
1259          (#x3130 #x318F hangul)         ; Hangul Compatibility Jamo
1260          (#x3190 #x319F kanbun)
1261          (#x31A0 #x31BF bopomofo)       ; Bopomofo Extended
1262          (#x31C0 #x31EF cjk-misc)       ; CJK Strokes
1263          (#x31F0 #x31FF kana)           ; Katakana Phonetic Extensions
1264          (#x3200 #x9FFF han)
1265          (#xA000 #xA4CF yi)
1266          (#xA4D0 #xA4FF lisu)
1267          (#xA500 #xA63F vai)
1268          (#xA640 #xA69F cyrillic)       ; Cyrillic Extended-B
1269          (#xA6A0 #xA6FF bamum)
1270          (#xA700 #xA7FF latin)
1271          (#xA800 #xA82F syloti-nagri)
1272          (#xA830 #xA83F north-indic-number)
1273          (#xA840 #xA87F phags-pa)
1274          (#xA880 #xA8DF saurashtra)
1275          (#xA8E0 #xA8FF devanagari)     ; Devanagari Extended
1276          (#xA900 #xA92F kayah-li)
1277          (#xA930 #xA95F rejang)
1278          (#xA960 #xA97F hangul)         ; Hangul Jamo Extended
1279          (#xA980 #xA9DF javanese)
1280          (#xA9E0 #xA9FF burmese)        ; Myanmar Extended-B
1281          (#xAA00 #xAA5F cham)
1282          (#xAA60 #xAA7F burmese)        ; Myanmar Extended-A
1283          (#xAA80 #xAADF tai-viet)
1284          (#xAAE0 #xAAFF meetei-mayek)   ; Meetei Mayek Extensions
1285          (#xAB00 #xAB2F ethiopic)       ; Ethiopic Extended-A
1286          (#xAB30 #xAB6F latin)          ; Latin Extended-E
1287          (#xAB70 #xABBF cherokee)       ; Cherokee Supplement
1288          (#xABC0 #xABFF meetei-mayek)
1289          (#xAC00 #xD7FF hangul)
1290          (#xF900 #xFAFF han)
1291          (#xFB00 #xFB06 latin)          ; Latin ligatures
1292          (#xFB13 #xFB17 armenian)       ; Armenian ligatures
1293          (#xFB1D #xFB4F hebrew)         ; Alphabetic Presentation Forms
1294          (#xFB50 #xFDFF arabic)         ; Arabic Presentation Forms-A
1295          (#xFE10 #xFE1F vertical-form)
1296          (#xFE20 #xFE2F latin)          ; Combining Half Marks
1297          (#xFE30 #xFE4F han)
1298          (#xFE50 #xFE6F symbol)         ; Small Form Variants
1299          (#xFE70 #xFEFF arabic)         ; Arabic Presentation Forms-B
1300          (#xFF00 #xFF60 cjk-misc)
1301          (#xFF61 #xFF9F kana)
1302          (#xFFA0 #xFFDF hangul)
1303          (#xFFE0 #xFFEF cjk-misc)
1304          (#x10000 #x100FF linear-b)
1305          (#x10100 #x1013F aegean-number)
1306          (#x10140 #x1018F ancient-greek-number)
1307          (#x10190 #x101CF ancient-symbol)
1308          (#x101D0 #x101FF phaistos-disc)
1309          (#x10280 #x1029F lycian)
1310          (#x102A0 #x102DF carian)
1311          (#x102E0 #x102FF coptic)       ; Coptic Epact Numbers
1312          (#x10300 #x1032F old-italic)
1313          (#x10330 #x1034F gothic)
1314          (#x10350 #x1037F old-permic)
1315          (#x10380 #x1039F ugaritic)
1316          (#x103A0 #x103DF old-persian)
1317          (#x10400 #x1044F deseret)
1318          (#x10450 #x1047F shavian)
1319          (#x10480 #x104AF osmanya)
1320          (#x10500 #x1052F elbasan)
1321          (#x10530 #x1056F caucasian-albanian)
1322          (#x10600 #x1077F linear-a)
1323          (#x10800 #x1083F cypriot-syllabary)
1324          (#x10840 #x1085F aramaic)
1325          (#x10860 #x1087F palmyrene)
1326          (#x10880 #x108AF nabataean)
1327          (#x108E0 #x108FF hatran)
1328          (#x10900 #x1091F phoenician)
1329          (#x10920 #x1093F lydian)
1330          (#x10980 #x109FF meroitic)
1331          (#x10A00 #x10A5F kharoshthi)
1332          (#x10A60 #x10A7F old-south-arabian)
1333          (#x10A80 #x10A9F old-north-arabian)
1334          (#x10AC0 #x10AFF manichaean)
1335          (#x10B00 #x10B3F avestan)
1336          (#x10B40 #x10B5F inscriptional-parthian)
1337          (#x10B60 #x10B7F inscriptional-pahlavi)
1338          (#x10B80 #x10BAF psalter-pahlavi)
1339          (#x10C00 #x10C4F old-turkic)
1340          (#x10C80 #x10CFF old-hungarian)
1341          (#x10E60 #x10E7F rumi-number)
1342          (#x11000 #x1107F brahmi)
1343          (#x11080 #x110CF kaithi)
1344          (#x110D0 #x110FF sora-sompeng)
1345          (#x11100 #x1114F chakma)
1346          (#x11150 #x1117F mahajani)
1347          (#x11180 #x111DF sharada)
1348          (#x111E0 #x111FF sinhala-archaic-number)
1349          (#x11200 #x1124F khojki)
1350          (#x11280 #x112AF multani)
1351          (#x112B0 #x112FF khudawadi)
1352          (#x11300 #x1137F grantha)
1353          (#x11480 #x114DF tirhuta)
1354          (#x11580 #x115FF siddham)
1355          (#x11600 #x1165F modi)
1356          (#x11680 #x116CF takri)
1357          (#x11700 #x1173F ahom)
1358          (#x118A0 #x118FF warang-citi)
1359          (#x11AC0 #x11AFF pau-cin-hau)
1360          (#x12000 #x123FF cuneiform)
1361          (#x12400 #x1247F cuneiform-numbers-and-punctuation)
1362          (#x12480 #x1254F cuneiform)    ; Early Dynastic Cuneiform
1363          (#x13000 #x1342F egyptian)
1364          (#x14400 #x1467F anatolian)
1365          (#x16800 #x16A3F bamum)
1366          (#x16A40 #x16A6F mro)
1367          (#x16AD0 #x16AFF bassa-vah)
1368          (#x16B00 #x16B8F pahawh-hmong)
1369          (#x16F00 #x16F9F miao)
1370          (#x1B000 #x1B0FF kana)         ; Kana Supplement
1371          (#x1BC00 #x1BCAF duployan-shorthand)
1372          (#x1D000 #x1D0FF byzantine-musical-symbol)
1373          (#x1D100 #x1D1FF musical-symbol)
1374          (#x1D200 #x1D24F ancient-greek-musical-notation)
1375          (#x1D300 #x1D35F tai-xuan-jing-symbol)
1376          (#x1D360 #x1D37F counting-rod-numeral)
1377          (#x1D400 #x1D7FF mathematical)
1378          (#x1D800 #x1DAAF sutton-sign-writing)
1379          (#x1E800 #x1E8DF mende-kikakui)
1380          (#x1EE00 #x1EEFF arabic)       ; Arabic Mathematical Alphabetic Symbols
1381          (#x1F000 #x1F02F mahjong-tile)
1382          (#x1F030 #x1F09F domino-tile)
1383          (#x1F0A0 #x1F0FF playing-cards)
1384          (#x1F100 #x1F1FF symbol)       ; Enclosed Alphanumeric Supplement
1385          (#x1F200 #x1F2FF han)          ; Enclosed Ideographic Supplement
1386          (#x1F300 #x1F9FF symbol)
1387          (#x20000 #x2A6DF han)
1388          (#x2A700 #x2CEAF han)
1389          (#x2F800 #x2FA1F han)))
1390     (set-char-table-range char-script-table
1391                           (cons (car elt) (nth 1 elt)) (nth 2 elt))
1392     (or (memq (nth 2 elt) script-list)
1393         (setq script-list (cons (nth 2 elt) script-list))))
1394   (set-char-table-extra-slot char-script-table 0 (nreverse script-list)))
1395
1396 (map-charset-chars
1397  #'(lambda (range _ignore)
1398      (set-char-table-range char-script-table range 'tibetan))
1399  'tibetan)
1400
1401 \f
1402 ;;; Setting unicode-category-table.
1403
1404 (when (setq unicode-category-table
1405             (unicode-property-table-internal 'general-category))
1406   (map-char-table #'(lambda (key val)
1407                       (if val
1408                           (cond ((or (and (/= (aref (symbol-name val) 0) ?M)
1409                                           (/= (aref (symbol-name val) 0) ?C))
1410                                      (eq val 'Zs))
1411                                  (modify-category-entry key ?.))
1412                                 ((eq val 'Mn)
1413                                  (modify-category-entry key ?^)))))
1414                   unicode-category-table))
1415
1416 (optimize-char-table (standard-category-table))
1417
1418 \f
1419 ;; Display of glyphless characters.
1420
1421 (defvar char-acronym-table
1422   (make-char-table 'char-acronym-table nil)
1423   "Char table of acronyms for non-graphic characters.")
1424
1425 (let ((c0-acronyms '("NUL" "SOH" "STX" "ETX" "EOT" "ENQ" "ACK" "BEL"
1426                      "BS"   nil   nil  "VT"  "FF"  "CR"  "SO"  "SI"
1427                      "DLE" "DC1" "DC2" "DC3" "DC4" "NAK" "SYN" "ETB"
1428                      "CAN" "EM"  "SUB" "ESC" "FC"  "GS"  "RS"  "US")))
1429   (dotimes (i 32)
1430     (aset char-acronym-table i (car c0-acronyms))
1431     (setq c0-acronyms (cdr c0-acronyms))))
1432
1433 (let ((c1-acronyms '("XXX" "XXX" "BPH" "NBH" "IND" "NEL" "SSA" "ESA"
1434                      "HTS" "HTJ" "VTS" "PLD" "PLU" "R1"  "SS2" "SS1"
1435                      "DCS" "PU1" "PU2" "STS" "CCH" "MW"  "SPA" "EPA"
1436                      "SOS" "XXX" "SC1" "CSI" "ST"  "OSC" "PM"  "APC")))
1437   (dotimes (i 32)
1438     (aset char-acronym-table (+ #x0080 i) (car c1-acronyms))
1439     (setq c1-acronyms (cdr c1-acronyms))))
1440
1441 (aset char-acronym-table #x17B4 "KIVAQ")   ; KHMER VOWEL INHERENT AQ
1442 (aset char-acronym-table #x17B5 "KIVAA")   ; KHMER VOWEL INHERENT AA
1443 (aset char-acronym-table #x200B "ZWSP")    ; ZERO WIDTH SPACE
1444 (aset char-acronym-table #x200C "ZWNJ")    ; ZERO WIDTH NON-JOINER
1445 (aset char-acronym-table #x200D "ZWJ")     ; ZERO WIDTH JOINER
1446 (aset char-acronym-table #x200E "LRM")     ; LEFT-TO-RIGHT MARK
1447 (aset char-acronym-table #x200F "RLM")     ; RIGHT-TO-LEFT MARK
1448 (aset char-acronym-table #x202A "LRE")     ; LEFT-TO-RIGHT EMBEDDING
1449 (aset char-acronym-table #x202B "RLE")     ; RIGHT-TO-LEFT EMBEDDING
1450 (aset char-acronym-table #x202C "PDF")     ; POP DIRECTIONAL FORMATTING
1451 (aset char-acronym-table #x202D "LRO")     ; LEFT-TO-RIGHT OVERRIDE
1452 (aset char-acronym-table #x202E "RLO")     ; RIGHT-TO-LEFT OVERRIDE
1453 (aset char-acronym-table #x2060 "WJ")      ; WORD JOINER
1454 (aset char-acronym-table #x206A "ISS")     ; INHIBIT SYMMETRIC SWAPPING
1455 (aset char-acronym-table #x206B "ASS")     ; ACTIVATE SYMMETRIC SWAPPING
1456 (aset char-acronym-table #x206C "IAFS")    ; INHIBIT ARABIC FORM SHAPING
1457 (aset char-acronym-table #x206D "AAFS")    ; ACTIVATE ARABIC FORM SHAPING
1458 (aset char-acronym-table #x206E "NADS")    ; NATIONAL DIGIT SHAPES
1459 (aset char-acronym-table #x206F "NODS")    ; NOMINAL DIGIT SHAPES
1460 (aset char-acronym-table #xFEFF "ZWNBSP")  ; ZERO WIDTH NO-BREAK SPACE
1461 (aset char-acronym-table #xFFF9 "IAA")     ; INTERLINEAR ANNOTATION ANCHOR
1462 (aset char-acronym-table #xFFFA "IAS")     ; INTERLINEAR ANNOTATION SEPARATOR
1463 (aset char-acronym-table #xFFFB "IAT")     ; INTERLINEAR ANNOTATION TERMINATOR
1464 (aset char-acronym-table #x1D173 "BEGBM")  ; MUSICAL SYMBOL BEGIN BEAM
1465 (aset char-acronym-table #x1D174 "ENDBM")  ; MUSICAL SYMBOL END BEAM
1466 (aset char-acronym-table #x1D175 "BEGTIE") ; MUSICAL SYMBOL BEGIN TIE
1467 (aset char-acronym-table #x1D176 "END")    ; MUSICAL SYMBOL END TIE
1468 (aset char-acronym-table #x1D177 "BEGSLR") ; MUSICAL SYMBOL BEGIN SLUR
1469 (aset char-acronym-table #x1D178 "ENDSLR") ; MUSICAL SYMBOL END SLUR
1470 (aset char-acronym-table #x1D179 "BEGPHR") ; MUSICAL SYMBOL BEGIN PHRASE
1471 (aset char-acronym-table #x1D17A "ENDPHR") ; MUSICAL SYMBOL END PHRASE
1472 (aset char-acronym-table #xE0001 "|->TAG") ; LANGUAGE TAG
1473 (aset char-acronym-table #xE0020 "SP TAG") ; TAG SPACE
1474 (dotimes (i 94)
1475   (aset char-acronym-table (+ #xE0021 i) (format " %c TAG" (+ 33 i))))
1476 (aset char-acronym-table #xE007F "->|TAG") ; CANCEL TAG
1477
1478 (defun update-glyphless-char-display (&optional variable value)
1479   "Make the setting of `glyphless-char-display-control' take effect.
1480 This function updates the char-table `glyphless-char-display'."
1481   (when value
1482     (set-default variable value))
1483   (dolist (elt value)
1484     (let ((target (car elt))
1485           (method (cdr elt)))
1486       (or (memq method '(zero-width thin-space empty-box acronym hex-code))
1487           (error "Invalid glyphless character display method: %s" method))
1488       (cond ((eq target 'c0-control)
1489              (glyphless-set-char-table-range glyphless-char-display
1490                                              #x00 #x1F method)
1491              ;; Users will not expect their newlines and TABs be
1492              ;; displayed as anything but themselves, so exempt those
1493              ;; two characters from c0-control.
1494              (set-char-table-range glyphless-char-display #x9 nil)
1495              (set-char-table-range glyphless-char-display #xa nil))
1496             ((eq target 'c1-control)
1497              (glyphless-set-char-table-range glyphless-char-display
1498                                              #x80 #x9F method))
1499             ((eq target 'format-control)
1500              (when unicode-category-table
1501                (map-char-table
1502                 #'(lambda (char category)
1503                     (if (eq category 'Cf)
1504                         (let ((this-method method)
1505                               from to)
1506                           (if (consp char)
1507                               (setq from (car char) to (cdr char))
1508                             (setq from char to char))
1509                           (while (<= from to)
1510                             (when (/= from #xAD)
1511                               (if (eq method 'acronym)
1512                                   (setq this-method
1513                                         (aref char-acronym-table from)))
1514                               (set-char-table-range glyphless-char-display
1515                                                     from this-method))
1516                             (setq from (1+ from))))))
1517                 unicode-category-table)))
1518             ((eq target 'no-font)
1519              (set-char-table-extra-slot glyphless-char-display 0 method))
1520             (t
1521              (error "Invalid glyphless character group: %s" target))))))
1522
1523 (defun glyphless-set-char-table-range (chartable from to method)
1524   (if (eq method 'acronym)
1525       (let ((i from))
1526         (while (<= i to)
1527           (set-char-table-range chartable i (aref char-acronym-table i))
1528           (setq i (1+ i))))
1529     (set-char-table-range chartable (cons from to) method)))
1530
1531 ;;; Control of displaying glyphless characters.
1532 (defcustom glyphless-char-display-control
1533   '((format-control . thin-space)
1534     (no-font . hex-code))
1535   "List of directives to control display of glyphless characters.
1536
1537 Each element has the form (GROUP . METHOD), where GROUP is a
1538 symbol specifying the character group, and METHOD is a symbol
1539 specifying the method of displaying characters belonging to that
1540 group.
1541
1542 GROUP must be one of these symbols:
1543   `c0-control':     U+0000..U+001F, but excluding newline and TAB.
1544   `c1-control':     U+0080..U+009F.
1545   `format-control': Characters of Unicode General Category `Cf',
1546                     such as U+200C (ZWNJ), U+200E (LRM), but
1547                     excluding characters that have graphic images,
1548                     such as U+00AD (SHY).
1549   `no-font':        characters for which no suitable font is found.
1550                     For character terminals, characters that cannot
1551                     be encoded by `terminal-coding-system'.
1552
1553 METHOD must be one of these symbols:
1554   `zero-width': don't display.
1555   `thin-space': display a thin (1-pixel width) space.  On character
1556                 terminals, display as 1-character space.
1557   `empty-box':  display an empty box.
1558   `acronym':    display an acronym of the character in a box.  The
1559                 acronym is taken from `char-acronym-table', which see.
1560   `hex-code':   display the hexadecimal character code in a box.
1561
1562 Do not set its value directly from Lisp; the value takes effect
1563 only via a custom `:set'
1564 function (`update-glyphless-char-display'), which updates
1565 `glyphless-char-display'."
1566   :version "24.1"
1567   :type '(alist :key-type (symbol :tag "Character Group")
1568                 :value-type (symbol :tag "Display Method"))
1569   :options '((c0-control
1570               (choice (const :tag "Don't display" zero-width)
1571                       (const :tag "Display as thin space" thin-space)
1572                       (const :tag "Display as empty box" empty-box)
1573                       (const :tag "Display acronym" acronym)
1574                       (const :tag "Display hex code in a box" hex-code)))
1575              (c1-control
1576               (choice (const :tag "Don't display" zero-width)
1577                       (const :tag "Display as thin space" thin-space)
1578                       (const :tag "Display as empty box" empty-box)
1579                       (const :tag "Display acronym" acronym)
1580                       (const :tag "Display hex code in a box" hex-code)))
1581              (format-control
1582               (choice (const :tag "Don't display" zero-width)
1583                       (const :tag "Display as thin space" thin-space)
1584                       (const :tag "Display as empty box" empty-box)
1585                       (const :tag "Display acronym" acronym)
1586                       (const :tag "Display hex code in a box" hex-code)))
1587              (no-font
1588               (choice (const :tag "Don't display" zero-width)
1589                       (const :tag "Display as thin space" thin-space)
1590                       (const :tag "Display as empty box" empty-box)
1591                       (const :tag "Display acronym" acronym)
1592                       (const :tag "Display hex code in a box" hex-code))))
1593   :set 'update-glyphless-char-display
1594   :group 'display)
1595
1596 \f
1597 ;;; Setting word boundary.
1598
1599 (setq word-combining-categories
1600       '((nil . ?^)
1601         (?^ . nil)
1602         (?C . ?H)
1603         (?C . ?K)))
1604
1605 (setq word-separating-categories        ;  (2-byte character sets)
1606       '((?H . ?K)                       ; Hiragana - Katakana
1607         ))
1608
1609 ;; Local Variables:
1610 ;; coding: utf-8
1611 ;; End:
1612
1613 ;;; characters.el ends here