34 |
|
|
35 |
;;; Code: |
;;; Code: |
36 |
|
|
37 |
|
;;; Remarks |
38 |
|
|
39 |
;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/. |
;; The ISO-IR registry is at http://www.itscj.ipsj.or.jp/ISO-IR/. |
40 |
;; Standards docs equivalent to iso-2022 and iso-8859 are at |
;; Standards docs equivalent to iso-2022 and iso-8859 are at |
41 |
;; http://www.ecma.ch/. |
;; http://www.ecma.ch/. |
42 |
|
|
43 |
|
;; FWIW, :http://www.microsoft.com/globaldev/reference/ lists the |
44 |
|
;; following for MS Windows, which are presumbaly the only charsets we |
45 |
|
;; really need to worry about on such systems: |
46 |
|
;; `OEM codepages': 437, 720, 737, 775, 850, 852, 855, 857, 858, 862, 866 |
47 |
|
;; `Windows codepages': 1250, 1251, 1252, 1253, 1254, 1255, 1256, 1257, |
48 |
|
;; 1258, 874, 932, 936, 949, 950 |
49 |
|
|
50 |
;;; Definitions of character sets. |
;;; Definitions of character sets. |
51 |
|
|
52 |
;; The charsets `ascii' and `unicode' are already defined in charset.c |
;; The charsets `ascii' and `unicode' are already defined in charset.c |
243 |
:code-space [#x40 #xFE #x81 #xFE] |
:code-space [#x40 #xFE #x81 #xFE] |
244 |
:code-offset #x150000 |
:code-offset #x150000 |
245 |
:unify-map "gbk") |
:unify-map "gbk") |
246 |
|
(define-charset-alias 'cp936 'chinese-gbk) |
247 |
|
|
248 |
(define-charset 'chinese-cns11643-1 |
(define-charset 'chinese-cns11643-1 |
249 |
"CNS11643 Plane 1 Chinese traditional: ISO-IR-171" |
"CNS11643 Plane 1 Chinese traditional: ISO-IR-171" |
316 |
:code-space [#x40 #xFE #xA1 #xFE] |
:code-space [#x40 #xFE #xA1 #xFE] |
317 |
:code-offset #x130000 |
:code-offset #x130000 |
318 |
:unify-map "big5") |
:unify-map "big5") |
319 |
|
;; Fixme: AKA cp950 according to |
320 |
|
;; <URL:http://www.microsoft.com/globaldev/reference/WinCP.asp>. Is |
321 |
|
;; that correct? |
322 |
|
|
323 |
(define-charset 'chinese-big5-1 |
(define-charset 'chinese-big5-1 |
324 |
"Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
"Frequently used part (A141-C67E) of Big5 (Chinese traditional)" |
395 |
:code-space [33 126 33 126] |
:code-space [33 126 33 126] |
396 |
:map "ksc5601-1987") |
:map "ksc5601-1987") |
397 |
|
|
398 |
|
;; Fixme: Korean cp949/UHC |
399 |
|
|
400 |
(define-charset 'chinese-sisheng |
(define-charset 'chinese-sisheng |
401 |
"SiSheng characters for PinYin/ZhuYin" |
"SiSheng characters for PinYin/ZhuYin" |
402 |
:short-name "SiSheng" |
:short-name "SiSheng" |
495 |
(define-charset-alias 'cp1250 'windows-1250) |
(define-charset-alias 'cp1250 'windows-1250) |
496 |
|
|
497 |
(define-charset 'windows-1251 |
(define-charset 'windows-1251 |
498 |
"WINDOWS-1251" |
"WINDOWS-1251 (Cyrillic)" |
499 |
:short-name "WINDOWS-1251" |
:short-name "WINDOWS-1251" |
500 |
:ascii-compatible-p t |
:ascii-compatible-p t |
501 |
:code-space [0 255] |
:code-space [0 255] |
503 |
(define-charset-alias 'cp1251 'windows-1251) |
(define-charset-alias 'cp1251 'windows-1251) |
504 |
|
|
505 |
(define-charset 'windows-1252 |
(define-charset 'windows-1252 |
506 |
"WINDOWS-1252 (Greek)" |
"WINDOWS-1252 (Latin I)" |
507 |
:short-name "WINDOWS-1252" |
:short-name "WINDOWS-1252" |
508 |
:ascii-compatible-p t |
:ascii-compatible-p t |
509 |
:code-space [0 255] |
:code-space [0 255] |
511 |
(define-charset-alias 'cp1252 'windows-1252) |
(define-charset-alias 'cp1252 'windows-1252) |
512 |
|
|
513 |
(define-charset 'windows-1253 |
(define-charset 'windows-1253 |
514 |
"WINDOWS-1253" |
"WINDOWS-1253 (Greek)" |
515 |
:short-name "WINDOWS-1253" |
:short-name "WINDOWS-1253" |
516 |
:ascii-compatible-p t |
:ascii-compatible-p t |
517 |
:code-space [0 255] |
:code-space [0 255] |
519 |
(define-charset-alias 'cp1253 'windows-1253) |
(define-charset-alias 'cp1253 'windows-1253) |
520 |
|
|
521 |
(define-charset 'windows-1254 |
(define-charset 'windows-1254 |
522 |
"WINDOWS-1254" |
"WINDOWS-1254 (Turkish)" |
523 |
:short-name "WINDOWS-1254" |
:short-name "WINDOWS-1254" |
524 |
:ascii-compatible-p t |
:ascii-compatible-p t |
525 |
:code-space [0 255] |
:code-space [0 255] |
551 |
(define-charset-alias 'cp1257 'windows-1257) |
(define-charset-alias 'cp1257 'windows-1257) |
552 |
|
|
553 |
(define-charset 'windows-1258 |
(define-charset 'windows-1258 |
554 |
"WINDOWS-1258" |
"WINDOWS-1258 (Viet Nam)" |
555 |
:short-name "WINDOWS-1258" |
:short-name "WINDOWS-1258" |
556 |
:ascii-compatible-p t |
:ascii-compatible-p t |
557 |
:code-space [0 255] |
:code-space [0 255] |
575 |
(define-charset-alias 'cp866u 'cp1125) |
(define-charset-alias 'cp866u 'cp1125) |
576 |
|
|
577 |
(define-charset 'cp437 |
(define-charset 'cp437 |
578 |
"CP437" |
"CP437 (US)" |
579 |
:short-name "CP437" |
:short-name "CP437" |
580 |
:code-space [0 255] |
:code-space [0 255] |
581 |
:ascii-compatible-p t |
:ascii-compatible-p t |
582 |
:map "cp437") |
:map "cp437") |
583 |
|
|
584 |
|
(define-charset 'cp720 |
585 |
|
"CP720 (Arabic)" |
586 |
|
:short-name "CP720" |
587 |
|
:code-space [0 255] |
588 |
|
:ascii-compatible-p t |
589 |
|
:map "cp720") |
590 |
|
|
591 |
(define-charset 'cp737 |
(define-charset 'cp737 |
592 |
"CP737" |
"CP737 (Greek)" |
593 |
:short-name "CP737" |
:short-name "CP737" |
594 |
:code-space [0 255] |
:code-space [0 255] |
595 |
:ascii-compatible-p t |
:ascii-compatible-p t |
610 |
:map "cp851") |
:map "cp851") |
611 |
|
|
612 |
(define-charset 'cp852 |
(define-charset 'cp852 |
613 |
"CP852" |
"CP852 (Latin II)" |
614 |
:short-name "CP852" |
:short-name "CP852" |
615 |
:code-space [0 255] |
:code-space [0 255] |
616 |
:ascii-compatible-p t |
:ascii-compatible-p t |
617 |
:map "cp852") |
:map "cp852") |
618 |
|
|
619 |
(define-charset 'cp855 |
(define-charset 'cp855 |
620 |
"CP855" |
"CP855 (Cyrillic)" |
621 |
:short-name "CP855" |
:short-name "CP855" |
622 |
:code-space [0 255] |
:code-space [0 255] |
623 |
:ascii-compatible-p t |
:ascii-compatible-p t |
624 |
:map "cp855") |
:map "cp855") |
625 |
|
|
626 |
(define-charset 'cp857 |
(define-charset 'cp857 |
627 |
"CP857" |
"CP857 (Turkish)" |
628 |
:short-name "CP857" |
:short-name "CP857" |
629 |
:code-space [0 255] |
:code-space [0 255] |
630 |
:ascii-compatible-p t |
:ascii-compatible-p t |
631 |
:map "cp857") |
:map "cp857") |
632 |
|
|
633 |
|
(define-charset 'cp858 |
634 |
|
"CP858 (Multilingual Latin I + Euro)" |
635 |
|
:short-name "CP858" |
636 |
|
:code-space [0 255] |
637 |
|
:ascii-compatible-p t |
638 |
|
:map "cp858") |
639 |
|
|
640 |
(define-charset 'cp860 |
(define-charset 'cp860 |
641 |
"CP860" |
"CP860" |
642 |
:short-name "CP860" |
:short-name "CP860" |
652 |
:map "cp861") |
:map "cp861") |
653 |
|
|
654 |
(define-charset 'cp862 |
(define-charset 'cp862 |
655 |
"CP862" |
"CP862 (Hebrew)" |
656 |
:short-name "CP862" |
:short-name "CP862" |
657 |
:code-space [0 255] |
:code-space [0 255] |
658 |
:ascii-compatible-p t |
:ascii-compatible-p t |
687 |
:map "cp869") |
:map "cp869") |
688 |
|
|
689 |
(define-charset 'cp874 |
(define-charset 'cp874 |
690 |
"CP874" |
"CP874 (Thai)" |
691 |
:short-name "CP874" |
:short-name "CP874" |
692 |
:code-space [0 255] |
:code-space [0 255] |
693 |
:ascii-compatible-p t |
:ascii-compatible-p t |