1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
|
;;; ucs-normalize.el --- Unicode normalization NFC/NFD/NFKD/NFKC -*- lexical-binding: t; -*-
;; Copyright (C) 2009-2025 Free Software Foundation, Inc.
;; Author: Taichi Kawabata <kawabata.taichi@gmail.com>
;; Keywords: unicode, normalization
;; This file is part of GNU Emacs.
;; GNU Emacs is free software: you can redistribute it and/or modify
;; it under the terms of the GNU General Public License as published by
;; the Free Software Foundation, either version 3 of the License, or
;; (at your option) any later version.
;; GNU Emacs is distributed in the hope that it will be useful,
;; but WITHOUT ANY WARRANTY; without even the implied warranty of
;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
;; GNU General Public License for more details.
;; You should have received a copy of the GNU General Public License
;; along with GNU Emacs. If not, see <https://www.gnu.org/licenses/>.
;;; Commentary:
;;
;; This program has passed the NormalizationTest-5.2.0.txt.
;;
;; References:
;; https://www.unicode.org/reports/tr15/
;; https://www.unicode.org/review/pr-29.html
;;
;; HFS-Normalization:
;; Reference:
;; https://developer.apple.com/library/archive/technotes/tn/tn1150.html
;;
;; HFS Normalization excludes following area for decomposition.
;;
;; U+02000 .. U+02FFF :: Punctuation, symbols, dingbats, arrows, etc.
;; (Characters in this region will be composed.)
;; U+0F900 .. U+0FAFF :: CJK compatibility Ideographs.
;; U+2F800 .. U+2FFFF :: CJK compatibility Ideographs.
;;
;; HFS-Normalization is useful for normalizing text involving CJK Ideographs.
;;
;;;
;;; Implementation Notes on NFC/HFS-NFC.
;;;
;;
;; <Stages> Decomposition Composition
;; NFD: 'nfd nil
;; NFC: 'nfd t
;; NFKD: 'nfkd nil
;; NFKC: 'nfkd t
;; HFS-NFD: 'hfs-nfd 'hfs-nfd-comp-p
;; HFS-NFC: 'hfs-nfd t
;;
;; Algorithm for Normalization
;;
;; Before normalization, following data will be prepared.
;;
;; 1. quick-check-list
;;
;; `quick-check-list' consists of characters that will be decomposed
;; during normalization. It includes composition-exclusions,
;; singletons, non-starter-decompositions and decomposable
;; characters.
;;
;; `quick-check-regexp' will search the above characters plus
;; combining characters.
;;
;; 2. decomposition-translation
;;
;; `decomposition-translation' is a translation table that will be
;; used to decompose the characters.
;;
;;
;; Normalization Process
;;
;; A. Searching (`ucs-normalize-region')
;;
;; Region is searched for `quick-check-regexp' to find possibly
;; normalizable point.
;;
;; B. Identification of Normalization Block
;;
;; (1) start of the block
;; If the searched character is a starter and not combining
;; with previous character, then the beginning of the block is
;; the searched character. If searched character is combining
;; character, then previous character will be the target
;; character
;; (2) end of the block
;; Block ends at non-composable starter character.
;;
;; C. Decomposition (`ucs-normalize-block')
;;
;; The entire block will be decomposed by
;; `decomposition-translation' table.
;;
;; D. Sorting and Composition of Smaller Blocks (`ucs-normalize-block-compose-chars')
;;
;; The block will be split to multiple smaller blocks by starter
;; characters. Each block is sorted, and composed if necessary.
;;
;; E. Composition of Entire Block (`ucs-normalize-compose-chars')
;;
;; Composed blocks are collected and again composed.
;;; Code:
(defconst ucs-normalize-version "1.2")
(eval-when-compile
(require 'cl-lib)
(require 'regexp-opt))
(declare-function nfd "ucs-normalize" (char))
(eval-when-compile
(defconst ucs-normalize-composition-exclusions
'(#x0958 #x0959 #x095A #x095B #x095C #x095D #x095E #x095F
#x09DC #x09DD #x09DF #x0A33 #x0A36 #x0A59 #x0A5A #x0A5B
#x0A5E #x0B5C #x0B5D #x0F43 #x0F4D #x0F52 #x0F57 #x0F5C
#x0F69 #x0F76 #x0F78 #x0F93 #x0F9D #x0FA2 #x0FA7 #x0FAC
#x0FB9 #xFB1D #xFB1F #xFB2A #xFB2B #xFB2C #xFB2D #xFB2E
#xFB2F #xFB30 #xFB31 #xFB32 #xFB33 #xFB34 #xFB35 #xFB36
#xFB38 #xFB39 #xFB3A #xFB3B #xFB3C #xFB3E #xFB40 #xFB41
#xFB43 #xFB44 #xFB46 #xFB47 #xFB48 #xFB49 #xFB4A #xFB4B
#xFB4C #xFB4D #xFB4E #x2ADC #x1D15E #x1D15F #x1D160 #x1D161
#x1D162 #x1D163 #x1D164 #x1D1BB #x1D1BC #x1D1BD #x1D1BE
#x1D1BF #x1D1C0)
"Composition Exclusion List.
This list is taken from
https://www.unicode.org/Public/UNIDATA/15.0/CompositionExclusions.txt")
;; Unicode ranges where decompositions & combining characters are
;; defined. Find them by running the following Awk program on
;; UnicodeData.txt:
;;
;; gawk -F";" "$6 != \"\" {print $0}"
(defvar check-range nil)
(setq check-range
'((#x00A0 . #x3400) (#xA600 . #xAC00) (#xF900 . #x11100)
(#x11100 . #x11A00) (#x1D000 . #x1E100) (#x1EE00 . #x1F300)
(#x1FBF0 . #x1FC00) (#x2F800 . #x2FB00)))
;; Basic normalization functions
(defun nfd (char)
(let ((decomposition
(get-char-code-property char 'decomposition)))
(if (and decomposition (numberp (car decomposition))
(or (> (length decomposition) 1)
(/= (car decomposition) char)))
decomposition)))
(defun nfkd (char)
(let ((decomposition
(get-char-code-property char 'decomposition)))
(if (symbolp (car decomposition)) (cdr decomposition)
(if (or (> (length decomposition) 1)
(/= (car decomposition) char)) decomposition))))
(defun hfs-nfd (char)
(when (or (and (>= char 0) (< char #x2000))
(and (>= char #x3000) (< char #xf900))
(and (>= char #xfb00) (< char #x2f800))
(>= char #x30000))
(nfd char))))
(eval-and-compile
(defun ucs-normalize-hfs-nfd-comp-p (char)
(and (>= char #x2000) (< char #x3000)))
(defsubst ucs-normalize-ccc (char)
(get-char-code-property char 'canonical-combining-class))
)
;; Data common to all normalizations
(eval-when-compile
(defvar combining-chars nil)
(setq combining-chars nil)
(defvar decomposition-pair-to-composition nil)
(setq decomposition-pair-to-composition nil)
(defvar non-starter-decompositions nil)
(setq non-starter-decompositions nil)
;; This file needs to access these 2 Unicode properties, but when we
;; compile it during bootstrap, charprop.el was not built yet, and
;; therefore is not yet loaded into bootstrap-emacs, so
;; char-code-property-alist is nil, and get-char-code-property
;; always returns nil, something the code here doesn't like.
(define-char-code-property 'decomposition "uni-decomposition.el")
(define-char-code-property 'canonical-combining-class "uni-combining.el")
(let (ccc decomposition)
(mapc
(lambda (start-end)
(cl-do ((char (car start-end) (+ char 1))) ((> char (cdr start-end)))
(setq ccc (ucs-normalize-ccc char))
(setq decomposition (get-char-code-property
char 'decomposition))
(if (and (= (length decomposition) 1)
(= (car decomposition) char))
(setq decomposition nil))
(if (and ccc (/= 0 ccc)) (add-to-list 'combining-chars char))
(if (and (numberp (car decomposition))
(/= (ucs-normalize-ccc (car decomposition))
0))
(add-to-list 'non-starter-decompositions char))
(when (numberp (car decomposition))
(if (and (= 2 (length decomposition))
(null (memq char ucs-normalize-composition-exclusions))
(null (memq char non-starter-decompositions)))
(setq decomposition-pair-to-composition
(cons (cons decomposition char)
decomposition-pair-to-composition)))
;; If not singleton decomposition, second and later characters in
;; decomposition will be the subject of combining characters.
(if (cdr decomposition)
(dolist (char (cdr decomposition))
(add-to-list 'combining-chars char))))))
check-range))
(setq combining-chars
(append combining-chars
'(?ᅡ ?ᅢ ?ᅣ ?ᅤ ?ᅥ ?ᅦ ?ᅧ ?ᅨ ?ᅩ ?ᅪ
?ᅫ ?ᅬ ?ᅭ ?ᅮ ?ᅯ ?ᅰ ?ᅱ ?ᅲ ?ᅳ ?ᅴ ?ᅵ
?ᆨ ?ᆩ ?ᆪ ?ᆫ ?ᆬ ?ᆭ ?ᆮ ?ᆯ ?ᆰ ?ᆱ ?ᆲ ?ᆳ ?ᆴ
?ᆵ ?ᆶ ?ᆷ ?ᆸ ?ᆹ ?ᆺ ?ᆻ ?ᆼ ?ᆽ ?ᆾ ?ᆿ ?ᇀ ?ᇁ ?ᇂ)))
)
(eval-and-compile
(defun ucs-normalize-make-hash-table-from-alist (alist)
(let ((table (make-hash-table :test 'equal :size 2000)))
(mapc (lambda (x) (puthash (car x) (cdr x) table)) alist)
table))
(defvar ucs-normalize-decomposition-pair-to-primary-composite nil
"Hash table of decomposed pair to primary composite.
Note that Hangul are excluded.")
(setq ucs-normalize-decomposition-pair-to-primary-composite
(ucs-normalize-make-hash-table-from-alist
(eval-when-compile decomposition-pair-to-composition)))
(defun ucs-normalize-primary-composite (decomposition-pair composition-predicate)
"Convert DECOMPOSITION-PAIR to primary composite using COMPOSITION-PREDICATE."
(let ((char (or (gethash decomposition-pair
ucs-normalize-decomposition-pair-to-primary-composite)
(and (<= #x1100 (car decomposition-pair))
(< (car decomposition-pair) #x1113)
(<= #x1161 (cadr decomposition-pair))
(< (car decomposition-pair) #x1176)
(let ((lindex (- (car decomposition-pair) #x1100))
(vindex (- (cadr decomposition-pair) #x1161)))
(+ #xAC00 (* (+ (* lindex 21) vindex) 28))))
(and (<= #xac00 (car decomposition-pair))
(< (car decomposition-pair) #xd7a4)
(<= #x11a7 (cadr decomposition-pair))
(< (cadr decomposition-pair) #x11c3)
(= 0 (% (- (car decomposition-pair) #xac00) 28))
(let ((tindex (- (cadr decomposition-pair) #x11a7)))
(+ (car decomposition-pair) tindex))))))
(if (and char
(functionp composition-predicate)
(null (funcall composition-predicate char)))
nil char)))
)
(defvar ucs-normalize-combining-chars nil)
(setq ucs-normalize-combining-chars (eval-when-compile combining-chars))
(defvar ucs-normalize-combining-chars-regexp nil
"Regular expression to match sequence of combining characters.")
(setq ucs-normalize-combining-chars-regexp
(eval-when-compile (concat (regexp-opt-charset combining-chars) "+")))
(declare-function decomposition-translation-alist "ucs-normalize"
(decomposition-function))
(declare-function decomposition-char-recursively "ucs-normalize"
(char decomposition-function))
(declare-function alist-list-to-vector "ucs-normalize" (alist))
(eval-when-compile
(defun decomposition-translation-alist (decomposition-function)
(let (decomposition alist)
(mapc
(lambda (start-end)
(cl-do ((char (car start-end) (+ char 1))) ((> char (cdr start-end)))
(setq decomposition (funcall decomposition-function char))
(if decomposition
(setq alist (cons (cons char
(apply 'append
(mapcar (lambda (x)
(decomposition-char-recursively
x decomposition-function))
decomposition)))
alist)))))
check-range)
alist))
(defun decomposition-char-recursively (char decomposition-function)
(let ((decomposition (funcall decomposition-function char)))
(if decomposition
(apply 'append
(mapcar (lambda (x)
(decomposition-char-recursively x decomposition-function))
decomposition))
(list char))))
(defun alist-list-to-vector (alist)
(mapcar (lambda (x) (cons (car x) (apply 'vector (cdr x)))) alist))
(defvar nfd-alist nil)
(setq nfd-alist (alist-list-to-vector (decomposition-translation-alist 'nfd)))
(defvar nfkd-alist nil)
(setq nfkd-alist (alist-list-to-vector (decomposition-translation-alist 'nfkd)))
(defvar hfs-nfd-alist nil)
(setq hfs-nfd-alist (alist-list-to-vector (decomposition-translation-alist 'hfs-nfd)))
)
(eval-and-compile
(defvar ucs-normalize-hangul-translation-alist nil)
(setq ucs-normalize-hangul-translation-alist
(let ((i 0) entries)
(while (< i 11172)
(setq entries
(cons (cons (+ #xac00 i)
(if (= 0 (% i 28))
(vector (+ #x1100 (/ i 588))
(+ #x1161 (/ (% i 588) 28)))
(vector (+ #x1100 (/ i 588))
(+ #x1161 (/ (% i 588) 28))
(+ #x11a7 (% i 28)))))
entries)
i (1+ i))) entries))
(defun ucs-normalize-make-translation-table-from-alist (alist)
(make-translation-table-from-alist
(append alist ucs-normalize-hangul-translation-alist)))
(define-translation-table 'ucs-normalize-nfd-table
(ucs-normalize-make-translation-table-from-alist (eval-when-compile nfd-alist)))
(define-translation-table 'ucs-normalize-nfkd-table
(ucs-normalize-make-translation-table-from-alist (eval-when-compile nfkd-alist)))
(define-translation-table 'ucs-normalize-hfs-nfd-table
(ucs-normalize-make-translation-table-from-alist (eval-when-compile hfs-nfd-alist)))
(defun ucs-normalize-sort (chars)
"Sort by canonical combining class of CHARS."
(sort chars
(lambda (ch1 ch2)
(< (ucs-normalize-ccc ch1) (ucs-normalize-ccc ch2)))))
(defun ucs-normalize-compose-chars (chars composition-predicate)
"Compose CHARS by COMPOSITION-PREDICATE.
CHARS must be sorted and normalized in starter-combining pairs."
(if composition-predicate
(let* ((starter (car chars))
remain result prev-ccc
(target-chars (cdr chars))
target target-ccc
primary-composite)
(while target-chars
(setq target (car target-chars)
target-ccc (ucs-normalize-ccc target))
(if (and (or (null prev-ccc)
(< prev-ccc target-ccc))
(setq primary-composite
(ucs-normalize-primary-composite (list starter target)
composition-predicate)))
;; case 1: composable
(setq starter primary-composite
prev-ccc nil)
(if (= 0 target-ccc)
;; case 2: move starter
(setq result (nconc result (cons starter (nreverse remain)))
starter target
remain nil)
;; case 3: move target
(setq prev-ccc target-ccc
remain (cons target remain))))
(setq target-chars (cdr target-chars)))
(nconc result (cons starter (nreverse remain))))
chars))
(defun ucs-normalize-block-compose-chars (chars composition-predicate)
"Try composing CHARS by COMPOSITION-PREDICATE.
If COMPOSITION-PREDICATE is not given, then do nothing."
(let ((chars (ucs-normalize-sort chars)))
(if composition-predicate
(ucs-normalize-compose-chars chars composition-predicate)
chars)))
)
(declare-function quick-check-list "ucs-normalize"
(decomposition-translation &optional composition-predicate))
(declare-function quick-check-list-to-regexp "ucs-normalize" (quick-check-list))
(eval-when-compile
(defun quick-check-list (decomposition-translation
&optional composition-predicate)
"Quick-Check List for DECOMPOSITION-TRANSLATION and COMPOSITION-PREDICATE.
It includes Singletons, CompositionExclusions, and Non-Starter
decomposition."
(let (entries decomposition composition)
(with-temp-buffer
(mapc
(lambda (start-end)
(cl-do ((i (car start-end) (+ i 1))) ((> i (cdr start-end)))
(setq decomposition
(string-to-list
(progn
(erase-buffer)
(insert i)
(translate-region 1 2 decomposition-translation)
(buffer-string))))
(setq composition
(ucs-normalize-block-compose-chars decomposition composition-predicate))
(when (not (equal composition (list i)))
(setq entries (cons i entries)))))
check-range))
;;(remove-duplicates
(append entries
ucs-normalize-composition-exclusions
non-starter-decompositions)))
;;)
(defvar nfd-quick-check-list nil)
(setq nfd-quick-check-list (quick-check-list 'ucs-normalize-nfd-table ))
(defvar nfc-quick-check-list nil)
(setq nfc-quick-check-list (quick-check-list 'ucs-normalize-nfd-table t ))
(defvar nfkd-quick-check-list nil)
(setq nfkd-quick-check-list (quick-check-list 'ucs-normalize-nfkd-table ))
(defvar nfkc-quick-check-list nil)
(setq nfkc-quick-check-list (quick-check-list 'ucs-normalize-nfkd-table t ))
(defvar hfs-nfd-quick-check-list nil)
(setq hfs-nfd-quick-check-list (quick-check-list 'ucs-normalize-hfs-nfd-table
'ucs-normalize-hfs-nfd-comp-p))
(defvar hfs-nfc-quick-check-list nil)
(setq hfs-nfc-quick-check-list (quick-check-list 'ucs-normalize-hfs-nfd-table t ))
(defun quick-check-list-to-regexp (quick-check-list)
(regexp-opt-charset (append quick-check-list combining-chars)))
(defun quick-check-decomposition-list-to-regexp (quick-check-list)
(concat (quick-check-list-to-regexp quick-check-list) "\\|[가-힣]"))
(defun quick-check-composition-list-to-regexp (quick-check-list)
(quick-check-list-to-regexp quick-check-list))
)
;; NFD/NFC
(defvar ucs-normalize-nfd-quick-check-regexp nil)
(setq ucs-normalize-nfd-quick-check-regexp
(eval-when-compile (quick-check-decomposition-list-to-regexp nfd-quick-check-list)))
(defvar ucs-normalize-nfc-quick-check-regexp nil)
(setq ucs-normalize-nfc-quick-check-regexp
(eval-when-compile (quick-check-composition-list-to-regexp nfc-quick-check-list)))
;; NFKD/NFKC
(defvar ucs-normalize-nfkd-quick-check-regexp nil)
(setq ucs-normalize-nfkd-quick-check-regexp
(eval-when-compile (quick-check-decomposition-list-to-regexp nfkd-quick-check-list)))
(defvar ucs-normalize-nfkc-quick-check-regexp nil)
(setq ucs-normalize-nfkc-quick-check-regexp
(eval-when-compile (quick-check-composition-list-to-regexp nfkc-quick-check-list)))
;; HFS-NFD/HFS-NFC
(defvar ucs-normalize-hfs-nfd-quick-check-regexp nil)
(setq ucs-normalize-hfs-nfd-quick-check-regexp
(eval-when-compile (concat (quick-check-decomposition-list-to-regexp hfs-nfd-quick-check-list))))
(defvar ucs-normalize-hfs-nfc-quick-check-regexp nil)
(setq ucs-normalize-hfs-nfc-quick-check-regexp
(eval-when-compile (quick-check-composition-list-to-regexp hfs-nfc-quick-check-list)))
;;------------------------------------------------------------------------------------------
;; Normalize local region.
(defun ucs-normalize-block
(from to &optional decomposition-translation-table composition-predicate)
"Normalize region FROM TO, by sorting the region with canonical-cc.
If DECOMPOSITION-TRANSLATION-TABLE is given, translate region
before sorting. If COMPOSITION-PREDICATE is given, then compose
the region by using it."
(save-restriction
(narrow-to-region from to)
(goto-char (point-min))
(if decomposition-translation-table
(translate-region from to decomposition-translation-table))
(goto-char (point-min))
(let ((start (point)) chars); ccc)
(while (not (eobp))
(forward-char)
(when (or (eobp)
(= 0 (ucs-normalize-ccc (char-after (point)))))
(setq chars
(nconc chars
(ucs-normalize-block-compose-chars
(string-to-list (buffer-substring start (point)))
composition-predicate))
start (point)))
;;(unless ccc (error "Undefined character can not be normalized!"))
)
(delete-region (point-min) (point-max))
(apply 'insert
(ucs-normalize-compose-chars
chars composition-predicate)))))
(defun ucs-normalize-region
(from to quick-check-regexp translation-table composition-predicate)
"Normalize region from FROM to TO.
QUICK-CHECK-REGEXP is applied for searching the region.
TRANSLATION-TABLE will be used to decompose region.
COMPOSITION-PREDICATE will be used to compose region."
(save-excursion
(save-restriction
(narrow-to-region from to)
(goto-char (point-min))
(let (start-pos starter)
(while (re-search-forward quick-check-regexp nil t)
(setq starter (string-to-char (match-string 0)))
(setq start-pos (match-beginning 0))
(ucs-normalize-block
;; from
(if (or (= start-pos (point-min))
(and (= 0 (ucs-normalize-ccc starter))
(not (memq starter ucs-normalize-combining-chars))))
start-pos (1- start-pos))
;; to
(if (looking-at ucs-normalize-combining-chars-regexp)
(match-end 0) (1+ start-pos))
translation-table composition-predicate))))))
;; --------------------------------------------------------------------------------
(defmacro ucs-normalize-string (ucs-normalize-region)
"Normalize string STR using the function UCS-NORMALIZE-REGION."
`(with-temp-buffer
(insert str)
(,ucs-normalize-region (point-min) (point-max))
(buffer-string)))
(defun ucs-normalize-NFD-region (from to)
"Decompose the region between FROM and TO according to the Unicode NFD.
This replaces the text between FROM and TO with its canonical decomposition,
a.k.a. the \"Unicode Normalization Form D\"."
(interactive "r")
(ucs-normalize-region from to
ucs-normalize-nfd-quick-check-regexp
'ucs-normalize-nfd-table nil))
(defun ucs-normalize-NFD-string (str)
"Decompose the string STR according to the Unicode NFD.
This returns a new string that is the canonical decomposition of STR,
a.k.a. the \"Unicode Normalization Form D\" of STR. For instance:
(ucs-normalize-NFD-string \"Å\") => \"Å\""
(ucs-normalize-string ucs-normalize-NFD-region))
(defun ucs-normalize-NFC-region (from to)
"Compose the region between FROM and TO according to the Unicode NFC.
This replaces the text between FROM and TO with the result of its
canonical decomposition (see `ucs-normalize-NFD-region') followed by
canonical composition, a.k.a. the \"Unicode Normalization Form C\"."
(interactive "r")
(ucs-normalize-region from to
ucs-normalize-nfc-quick-check-regexp
'ucs-normalize-nfd-table t))
;;;###autoload
(defun string-glyph-compose (string)
"Compose STRING according to the Unicode NFC.
This returns a new string obtained by canonical decomposition
of STRING (see `ucs-normalize-NFC-string') followed by canonical
composition, a.k.a. the \"Unicode Normalization Form C\" of STRING.
For instance:
(string-glyph-compose \"Å\") => \"Å\""
(ucs-normalize-NFC-string string))
;;;###autoload
(defun string-glyph-decompose (string)
"Decompose STRING according to the Unicode NFD.
This returns a new string that is the canonical decomposition of STRING,
a.k.a. the \"Unicode Normalization Form D\" of STRING. For instance:
(ucs-normalize-NFD-string \"Å\") => \"Å\""
(ucs-normalize-NFD-string string))
(defun ucs-normalize-NFC-string (str)
"Compose STR according to the Unicode NFC.
This returns a new string obtained by canonical decomposition
of STR (see `ucs-normalize-NFC-string') followed by canonical
composition, a.k.a. the \"Unicode Normalization Form C\" of STR.
For instance:
(string-glyph-compose \"Å\") => \"Å\""
(ucs-normalize-string ucs-normalize-NFC-region))
(defun ucs-normalize-NFKD-region (from to)
"Decompose the region between FROM and TO according to the Unicode NFKD.
This replaces the text between FROM and TO with its compatibility
decomposition, a.k.a. \"Unicode Normalization Form KD\"."
(interactive "r")
(ucs-normalize-region from to
ucs-normalize-nfkd-quick-check-regexp
'ucs-normalize-nfkd-table nil))
(defun ucs-normalize-NFKD-string (str)
"Decompose the string STR according to the Unicode NFKD.
This returns a new string obtained by compatibility decomposition
of STR. This is much like the NFD (canonical decomposition) form,
see `ucs-normalize-NFD-string', but mainly differs for precomposed
characters. For instance:
(ucs-normalize-NFD-string \"fi\") => \"fi\"
(ucs-normalize-NFKD-string \"fi\") = \"fi\""
(ucs-normalize-string ucs-normalize-NFKD-region))
(defun ucs-normalize-NFKC-region (from to)
"Compose the region between FROM and TO according to the Unicode NFKC.
This replaces the text between FROM and TO with the result of its
compatibility decomposition (see `ucs-normalize-NFC-region') followed by
canonical composition, a.k.a. the \"Unicode Normalization Form KC\"."
(interactive "r")
(ucs-normalize-region from to
ucs-normalize-nfkc-quick-check-regexp
'ucs-normalize-nfkd-table t))
(defun ucs-normalize-NFKC-string (str)
"Compose STR according to the Unicode NFC.
This returns a new string obtained by compatibility decomposition
of STR (see `ucs-normalize-NFKD-string') followed by canonical
composition, a.k.a. the \"Unicode Normalization Form KC\" of STR.
This is much like the NFC (canonical composition) form, but mainly
differs for precomposed characters. For instance:
(ucs-normalize-NFC-string \"fi\") => \"fi\"
(ucs-normalize-NFKC-string \"fi\") = \"fi\""
(ucs-normalize-string ucs-normalize-NFKC-region))
(defun ucs-normalize-HFS-NFD-region (from to)
"Normalize region between FROM and TO by Unicode NFD and Mac OS's HFS Plus."
(interactive "r")
(ucs-normalize-region from to
ucs-normalize-hfs-nfd-quick-check-regexp
'ucs-normalize-hfs-nfd-table
'ucs-normalize-hfs-nfd-comp-p))
(defun ucs-normalize-HFS-NFD-string (str)
"Normalize the string STR by the Unicode NFD and Mac OS's HFS Plus."
(ucs-normalize-string ucs-normalize-HFS-NFD-region))
(defun ucs-normalize-HFS-NFC-region (from to)
"Normalize region between FROM and TO by Unicode NFC and Mac OS's HFS Plus."
(interactive "r")
(ucs-normalize-region from to
ucs-normalize-hfs-nfc-quick-check-regexp
'ucs-normalize-hfs-nfd-table t))
(defun ucs-normalize-HFS-NFC-string (str)
"Normalize the string STR by the Unicode NFC and Mac OS's HFS Plus."
(ucs-normalize-string ucs-normalize-HFS-NFC-region))
;; Post-read-conversion function for `utf-8-hfs'.
(defun ucs-normalize-hfs-nfd-post-read-conversion (len)
(save-excursion
(save-restriction
(save-match-data
(narrow-to-region (point) (+ (point) len))
(ucs-normalize-HFS-NFC-region (point-min) (point-max))
(- (point-max) (point-min))))))
;; Pre-write conversion for `utf-8-hfs'.
;; _from and _to are legacy arguments (see `define-coding-system').
(defun ucs-normalize-hfs-nfd-pre-write-conversion (_from _to)
(save-match-data
(ucs-normalize-HFS-NFD-region (point-min) (point-max))))
;;; coding-system definition
(define-coding-system 'utf-8-hfs
"UTF-8 based coding system for macOS HFS file names.
The singleton characters in HFS normalization exclusion will not
be decomposed."
:coding-type 'utf-8
:mnemonic ?U
:charset-list '(unicode)
:post-read-conversion 'ucs-normalize-hfs-nfd-post-read-conversion
:pre-write-conversion 'ucs-normalize-hfs-nfd-pre-write-conversion
)
;; This is tested in dired.c:file_name_completion in order to reject
;; false positives due to comparison of encoded file names.
(coding-system-put 'utf-8-hfs 'decomposed-characters 't)
(provide 'ucs-normalize)
;; Local Variables:
;; coding: utf-8
;; End:
;;; ucs-normalize.el ends here
|