-;;; cyrillic.el --- Support for languages which use Cyrillic characters
+;;; cyrillic.el --- support for Cyrillic -*- coding: iso-2022-7bit; -*-
;; Copyright (C) 1995 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
+;; Copyright (C) 2001, 2002, 2003 Free Software Foundation, Inc.
-;; Keywords: multilingual, Cyrillic
+;; Author: Kenichi Handa <handa@etl.go.jp>
+;; Keywords: multilingual, Cyrillic, i18n
;; This file is part of GNU Emacs.
;;; Commentary:
;; The character set ISO8859-5 is supported. KOI-8 and ALTERNATIVNYJ
-;; are converted to ISO8859-5 internally.
+;; are converted to Unicode internally. See
+;; <URL:http://www.ecma.ch/ecma1/STAND/ECMA-113.HTM>. For more info
+;; on Cyrillic charsets, see
+;; <URL:http://czyborra.com/charsets/cyrillic.html>. The KOI and
+;; Alternativnyj coding systems should live in code-pages.el, but
+;; they've always been preloaded and the coding system autoload
+;; mechanism didn't get accepted, so they have to stay here and
+;; duplicate code-pages stuff.
+
+;; Note that 8859-5 maps directly onto the Unicode Cyrillic block,
+;; apart from codepoints 160 (NBSP, c.f. U+0400), 173 (soft hyphen,
+;; c.f. U+04OD) and 253 (section sign, c.f U+045D). The KOI-8 and
+;; Alternativnyj coding systems encode both 8859-5 and Unicode.
+;; ucs-tables.el provides unification for cyrillic-iso-8bit.
+
+;; Customizing `utf-fragment-on-decoding' allows decoding characters
+;; from KOI and Alternativnyj into 8859-5 where that's possible.
+;; cyrillic-iso8859-5 characters take half as much space in the buffer
+;; as the mule-unicode-0100-24ff equivalents, though that's probably
+;; not normally a big deal.
;;; Code:
;; Cyrillic (general)
-;; ISO-8859-5 staff
+;; ISO-8859-5 stuff
(make-coding-system
'cyrillic-iso-8bit 2 ?5
- "ISO 2022 based 8-bit encoding for Cyrillic script (MIME:ISO-8859-5)"
+ "ISO 2022 based 8-bit encoding for Cyrillic script (MIME:ISO-8859-5)."
'(ascii cyrillic-iso8859-5 nil nil
- nil nil nil nil nil nil nil)
+ nil nil nil nil nil nil nil nil nil nil nil t)
'((safe-charsets ascii cyrillic-iso8859-5)
(mime-charset . iso-8859-5)))
"Cyrillic-ISO" '((charset cyrillic-iso8859-5)
(coding-system cyrillic-iso-8bit)
(coding-priority cyrillic-iso-8bit)
- (input-method . "cyrillic-yawerty")
+ (input-method . "cyrillic-yawerty") ; fixme
(nonascii-translation . cyrillic-iso8859-5)
(unibyte-display . cyrillic-iso-8bit)
(features cyril-util)
(documentation . "Support for Cyrillic ISO-8859-5."))
'("Cyrillic"))
-;; KOI-8 staff
-
-(eval-and-compile
+;; KOI-8R stuff
+;; The mule-unicode portion of this is from
+;; http://www.unicode.org/Public/MAPPINGS/VENDORS/MISC/KOI8-R.TXT,
+;; which references RFC 1489.
(defvar cyrillic-koi8-r-decode-table
[
0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
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
- 32 32 32 ?\e,Lq\e(B 32 32 32 32 32 32 32 32 32 32 32 32
- 32 32 32 ?\e,L!\e(B 32 32 32 32 32 32 32 32 32 32 32 32
- ?\e,Ln\e(B ?\e,LP\e(B ?\e,LQ\e(B ?\e,Lf\e(B ?\e,LT\e(B ?\e,LU\e(B ?\e,Ld\e(B ?\e,LS\e(B ?\e,Le\e(B ?\e,LX\e(B ?\e,LY\e(B ?\e,LZ\e(B ?\e,L[\e(B ?\e,L\\e(B ?\e,L]\e(B ?\e,L^\e(B
- ?\e,L_\e(B ?\e,Lo\e(B ?\e,L`\e(B ?\e,La\e(B ?\e,Lb\e(B ?\e,Lc\e(B ?\e,LV\e(B ?\e,LR\e(B ?\e,Ll\e(B ?\e,Lk\e(B ?\e,LW\e(B ?\e,Lh\e(B ?\e,Lm\e(B ?\e,Li\e(B ?\e,Lg\e(B ?\e,Lj\e(B
- ?\e,LN\e(B ?\e,L0\e(B ?\e,L1\e(B ?\e,LF\e(B ?\e,L4\e(B ?\e,L5\e(B ?\e,LD\e(B ?\e,L3\e(B ?\e,LE\e(B ?\e,L8\e(B ?\e,L9\e(B ?\e,L:\e(B ?\e,L;\e(B ?\e,L<\e(B ?\e,L=\e(B ?\e,L>\e(B
- ?\e,L?\e(B ?\e,LO\e(B ?\e,L@\e(B ?\e,LA\e(B ?\e,LB\e(B ?\e,LC\e(B ?\e,L6\e(B ?\e,L2\e(B ?\e,LL\e(B ?\e,LK\e(B ?\e,L7\e(B ?\e,LH\e(B ?\e,LM\e(B ?\e,LI\e(B ?\e,LG\e(B ?\e,LJ\e(B ]
+ ;; 8859-5 plus Unicode
+ ?\e$,2 \e(B ?\e$,2 "\e(B ?\e$,2 ,\e(B ?\e$,2 0\e(B ?\e$,2 4\e(B ?\e$,2 8\e(B ?\e$,2 <\e(B ?\e$,2 D\e(B ?\e$,2 L\e(B ?\e$,2 T\e(B ?\e$,2 \\e(B ?\e$,2!@\e(B ?\e$,2!D\e(B ?\e$,2!H\e(B ?\e$,2!L\e(B ?\e$,2!P\e(B
+ ?\e$,2!Q\e(B ?\e$,2!R\e(B ?\e$,2!S\e(B ?\e$,1{ \e(B ?\e$,2!`\e(B ?\e$,1s"\e(B ?\e$,1x:\e(B ?\e$,1xh\e(B ?\e$,1y$\e(B ?\e$,1y%\e(B ?\e,L \e(B ?\e$,1{!\e(B ?\e,A0\e(B ?\e,A2\e(B ?\e,A7\e(B ?\e,Aw\e(B
+ ?\e$,2 p\e(B ?\e$,2 q\e(B ?\e$,2 r\e(B ?\e,Lq\e(B ?\e$,2 s\e(B ?\e$,2 t\e(B ?\e$,2 u\e(B ?\e$,2 v\e(B ?\e$,2 w\e(B ?\e$,2 x\e(B ?\e$,2 y\e(B ?\e$,2 z\e(B ?\e$,2 {\e(B ?\e$,2 |\e(B ?\e$,2 }\e(B ?\e$,2 ~\e(B
+ ?\e$,2 \7f\e(B ?\e$,2! \e(B ?\e$,2!!\e(B ?\e,L!\e(B ?\e$,2!"\e(B ?\e$,2!#\e(B ?\e$,2!$\e(B ?\e$,2!%\e(B ?\e$,2!&\e(B ?\e$,2!'\e(B ?\e$,2!(\e(B ?\e$,2!)\e(B ?\e$,2!*\e(B ?\e$,2!+\e(B ?\e$,2!,\e(B ?\e,A)\e(B
+ ?\e,Ln\e(B ?\e,LP\e(B ?\e,LQ\e(B ?\e,Lf\e(B ?\e,LT\e(B ?\e,LU\e(B ?\e,Ld\e(B ?\e,LS\e(B ?\e,Le\e(B ?\e,LX\e(B ?\e,LY\e(B ?\e,LZ\e(B ?\e,L[\e(B ?\e,L\\e(B ?\e,L]\e(B ?\e,L^\e(B
+ ?\e,L_\e(B ?\e,Lo\e(B ?\e,L`\e(B ?\e,La\e(B ?\e,Lb\e(B ?\e,Lc\e(B ?\e,LV\e(B ?\e,LR\e(B ?\e,Ll\e(B ?\e,Lk\e(B ?\e,LW\e(B ?\e,Lh\e(B ?\e,Lm\e(B ?\e,Li\e(B ?\e,Lg\e(B ?\e,Lj\e(B
+ ?\e,LN\e(B ?\e,L0\e(B ?\e,L1\e(B ?\e,LF\e(B ?\e,L4\e(B ?\e,L5\e(B ?\e,LD\e(B ?\e,L3\e(B ?\e,LE\e(B ?\e,L8\e(B ?\e,L9\e(B ?\e,L:\e(B ?\e,L;\e(B ?\e,L<\e(B ?\e,L=\e(B ?\e,L>\e(B
+ ?\e,L?\e(B ?\e,LO\e(B ?\e,L@\e(B ?\e,LA\e(B ?\e,LB\e(B ?\e,LC\e(B ?\e,L6\e(B ?\e,L2\e(B ?\e,LL\e(B ?\e,LK\e(B ?\e,L7\e(B ?\e,LH\e(B ?\e,LM\e(B ?\e,LI\e(B ?\e,LG\e(B ?\e,LJ\e(B
+ ;; All Unicode:
+;; ?\e$,2 \e(B ?\e$,2 "\e(B ?\e$,2 ,\e(B ?\e$,2 0\e(B ?\e$,2 4\e(B ?\e$,2 8\e(B ?\e$,2 <\e(B ?\e$,2 D\e(B ?\e$,2 L\e(B ?\e$,2 T\e(B ?\e$,2 \\e(B ?\e$,2!@\e(B ?\e$,2!D\e(B ?\e$,2!H\e(B ?\e$,2!L\e(B ?\e$,2!P\e(B
+;; ?\e$,2!Q\e(B ?\e$,2!R\e(B ?\e$,2!S\e(B ?\e$,1{ \e(B ?\e$,2!`\e(B ?\e$,1s"\e(B ?\e$,1x:\e(B ?\e$,1xh\e(B ?\e$,1y$\e(B ?\e$,1y%\e(B ?\e,A \e(B ?\e$,1{!\e(B ?\e,A0\e(B ?\e,A2\e(B ?\e,A7\e(B ?\e,Aw\e(B
+;; ?\e$,2 p\e(B ?\e$,2 q\e(B ?\e$,2 r\e(B ?\e$,1(q\e(B ?\e$,2 s\e(B ?\e$,2 t\e(B ?\e$,2 u\e(B ?\e$,2 v\e(B ?\e$,2 w\e(B ?\e$,2 x\e(B ?\e$,2 y\e(B ?\e$,2 z\e(B ?\e$,2 {\e(B ?\e$,2 |\e(B ?\e$,2 }\e(B ?\e$,2 ~\e(B
+;; ?\e$,2 \7f\e(B ?\e$,2! \e(B ?\e$,2!!\e(B ?\e$,1(!\e(B ?\e$,2!"\e(B ?\e$,2!#\e(B ?\e$,2!$\e(B ?\e$,2!%\e(B ?\e$,2!&\e(B ?\e$,2!'\e(B ?\e$,2!(\e(B ?\e$,2!)\e(B ?\e$,2!*\e(B ?\e$,2!+\e(B ?\e$,2!,\e(B ?\e,A)\e(B
+;; ?\e$,1(n\e(B ?\e$,1(P\e(B ?\e$,1(Q\e(B ?\e$,1(f\e(B ?\e$,1(T\e(B ?\e$,1(U\e(B ?\e$,1(d\e(B ?\e$,1(S\e(B ?\e$,1(e\e(B ?\e$,1(X\e(B ?\e$,1(Y\e(B ?\e$,1(Z\e(B ?\e$,1([\e(B ?\e$,1(\\e(B ?\e$,1(]\e(B ?\e$,1(^\e(B
+;; ?\e$,1(_\e(B ?\e$,1(o\e(B ?\e$,1(`\e(B ?\e$,1(a\e(B ?\e$,1(b\e(B ?\e$,1(c\e(B ?\e$,1(V\e(B ?\e$,1(R\e(B ?\e$,1(l\e(B ?\e$,1(k\e(B ?\e$,1(W\e(B ?\e$,1(h\e(B ?\e$,1(m\e(B ?\e$,1(i\e(B ?\e$,1(g\e(B ?\e$,1(j\e(B
+;; ?\e$,1(N\e(B ?\e$,1(0\e(B ?\e$,1(1\e(B ?\e$,1(F\e(B ?\e$,1(4\e(B ?\e$,1(5\e(B ?\e$,1(D\e(B ?\e$,1(3\e(B ?\e$,1(E\e(B ?\e$,1(8\e(B ?\e$,1(9\e(B ?\e$,1(:\e(B ?\e$,1(;\e(B ?\e$,1(<\e(B ?\e$,1(=\e(B ?\e$,1(>\e(B
+;; ?\e$,1(?\e(B ?\e$,1(O\e(B ?\e$,1(@\e(B ?\e$,1(A\e(B ?\e$,1(B\e(B ?\e$,1(C\e(B ?\e$,1(6\e(B ?\e$,1(2\e(B ?\e$,1(L\e(B ?\e$,1(K\e(B ?\e$,1(7\e(B ?\e$,1(H\e(B ?\e$,1(M\e(B ?\e$,1(I\e(B ?\e$,1(G\e(B ?\e$,1(J\e(B
+ ]
"Cyrillic KOI8-R decoding table.")
-(defvar cyrillic-koi8-r-encode-table
- (let ((table (make-vector 256 32))
- (i 0))
- (while (< i 256)
- (let* ((ch (aref cyrillic-koi8-r-decode-table i))
- (split (split-char ch)))
- (if (eq (car split) 'cyrillic-iso8859-5)
- (aset table (logior (nth 1 split) 128) i)
- (if (/= ch 32)
- (aset table ch i))))
- (setq i (1+ i)))
- table)
- "Cyrillic KOI8-R encoding table.")
-
-)
+(let ((table (make-translation-table-from-vector
+ cyrillic-koi8-r-decode-table)))
+ (define-translation-table 'cyrillic-koi8-r-nonascii-translation-table table)
+ (define-translation-table 'cyrillic-koi8-r-encode-table
+ (char-table-extra-slot table 0)))
+
+;; No point in keeping it around. (It can't be let-bound, since it's
+;; needed for macro expansion.)
+(makunbound 'cyrillic-koi8-r-decode-table)
(define-ccl-program ccl-decode-koi8
- `(3
- ((read r0)
- (loop
- (write-read-repeat r0 ,cyrillic-koi8-r-decode-table))))
- "CCL program to decode KOI8.")
+ `(4
+ ((loop
+ (r0 = 0)
+ (read r1)
+ (if (r1 < 128)
+ (write-repeat r1)
+ ((translate-character cyrillic-koi8-r-nonascii-translation-table r0 r1)
+ (translate-character ucs-translation-table-for-decode r0 r1)
+ (write-multibyte-character r0 r1)
+ (repeat))))))
+ "CCL program to decode KOI8-R.")
(define-ccl-program ccl-encode-koi8
`(1
- ((read r0)
- (loop
- (if (r0 != ,(charset-id 'cyrillic-iso8859-5))
- (write-read-repeat r0)
- ((read r0)
- (write-read-repeat r0 , cyrillic-koi8-r-encode-table))))))
- "CCL program to encode KOI8.")
-
+ ((loop
+ (read-multibyte-character r0 r1)
+ (translate-character cyrillic-koi8-r-encode-table r0 r1)
+ (if (r0 != ,(charset-id 'ascii))
+ (if (r0 != ,(charset-id 'eight-bit-graphic))
+ (if (r0 != ,(charset-id 'eight-bit-control))
+ (r1 = ??))))
+ (write-repeat r1))))
+ "CCL program to encode KOI8-R.")
+
+(defun cyrillic-unify-encoding (table)
+ "Set up equivalent characters in the encoding TABLE.
+This works whether or not the table is Unicode-based or
+8859-5-based. (Only appropriate for Cyrillic.)"
+ (let ((table (get table 'translation-table)))
+ (dotimes (i 96)
+ (let* ((c (make-char 'cyrillic-iso8859-5 (+ i 32)))
+ (u ; equivalent Unicode char
+ (cond ((eq c ?\e,L \e(B) ?\e,A \e(B)
+ ((eq c ?\e,L-\e(B) ?\e,A-\e(B)
+ ((eq c ?\e,L}\e(B) ?\e,A'\e(B)
+ (t (decode-char 'ucs (+ #x400 i)))))
+ (ec (aref table c)) ; encoding of 8859-5
+ (uc (aref table u))) ; encoding of Unicode
+ (unless (memq c '(?\e,L \e(B ?\e,L-\e(B ?\e,L}\e(B)) ; 8859-5 exceptions
+ (unless uc
+ (aset table u ec))
+ (unless ec
+ (aset table c uc)))))))
+
+(cyrillic-unify-encoding 'cyrillic-koi8-r-encode-table)
+
(make-coding-system
'cyrillic-koi8 4
;; We used to use ?K. It is true that ?K is more strictly correct,
;; but it is also used for Korean.
;; So people who use koi8 for languages other than Russian
;; will have to forgive us.
- ?R "KOI8 8-bit encoding for Cyrillic (MIME: KOI8-R)"
+ ?R "KOI8-R 8-bit encoding for Cyrillic (MIME: KOI8-R)."
'(ccl-decode-koi8 . ccl-encode-koi8)
- '((safe-charsets ascii cyrillic-iso8859-5)
+ `((safe-chars . cyrillic-koi8-r-encode-table)
(mime-charset . koi8-r)
- (valid-codes (0 127) 163 179 (192 255))))
+ (valid-codes (0 . 255))
+ (dependency unify-8859-on-encoding-mode unify-8859-on-decoding-mode)))
(define-coding-system-alias 'koi8-r 'cyrillic-koi8)
(define-coding-system-alias 'koi8 'cyrillic-koi8)
+(define-coding-system-alias 'cp878 'cyrillic-koi8)
+
+;; Allow displaying some of KOI & al with an 8859-5-encoded font. We
+;; won't bother about the exceptions when encoding the font, since
+;; NBSP will fall through below and work anyhow, and we'll have
+;; avoided setting the fontset for the other two to 8859-5 -- they're
+;; not in KOI and Alternativnyj anyhow.
+(define-ccl-program ccl-encode-8859-5-font
+ `(0
+ ((if (r0 == ,(charset-id 'cyrillic-iso8859-5))
+ (r1 += 128)
+ (if (r0 == ,(charset-id 'mule-unicode-0100-24ff))
+ (r1 = (r2 + 128))))))
+ "Encode ISO 8859-5 and Cyrillic Unicode chars to 8859-5 font.")
+(add-to-list 'font-ccl-encoder-alist '("iso8859-5" . ccl-encode-8859-5-font))
+
+;; The table is set up later to encode both Unicode and 8859-5.
(define-ccl-program ccl-encode-koi8-font
`(0
- ((r1 |= 128)
- (r1 = r1 ,cyrillic-koi8-r-encode-table)))
+ (translate-character cyrillic-koi8-r-encode-table r0 r1))
"CCL program to encode Cyrillic chars to KOI font.")
-(setq font-ccl-encoder-alist
- (cons (cons "koi8" ccl-encode-koi8-font) font-ccl-encoder-alist))
-
-(defvar cyrillic-koi8-r-nonascii-translation-table
- (make-translation-table-from-vector cyrillic-koi8-r-decode-table)
- "Value of `nonascii-translation-table' in Cyrillic-KOI8 language environment..")
+(add-to-list 'font-ccl-encoder-alist '("koi8" . ccl-encode-koi8-font))
(set-language-info-alist
"Cyrillic-KOI8" `((charset cyrillic-iso8859-5)
(nonascii-translation
- . ,cyrillic-koi8-r-nonascii-translation-table)
- (charset-origin-alist
- (cyrillic-iso8859-5 "KOI8-R" cyrillic-encode-koi8-r-char))
+ . ,(get 'cyrillic-koi8-r-nonascii-translation-table
+ 'translation-table))
(coding-system cyrillic-koi8)
- (coding-priority cyrillic-koi8)
- (input-method . "cyrillic-yawerty")
+ (coding-priority cyrillic-koi8 cyrillic-iso-8bit)
+ (input-method . "russian-typewriter")
(features cyril-util)
(unibyte-display . cyrillic-koi8)
(sample-text . "Russian (\e,L@caaZXY\e(B) \e,L7T`PRabRcYbU\e(B!")
(documentation . "Support for Cyrillic KOI8-R."))
'("Cyrillic"))
-;;; ALTERNATIVNYJ staff
+(set-language-info-alist
+ "Russian" `((charset cyrillic-iso8859-5)
+ (nonascii-translation
+ . ,(get 'cyrillic-koi8-r-nonascii-translation-table
+ 'translation-table))
+ (coding-system cyrillic-koi8)
+ (coding-priority cyrillic-koi8 cyrillic-iso-8bit)
+ (input-method . "russian-computer")
+ (features cyril-util)
+ (unibyte-display . cyrillic-koi8)
+ (sample-text . "Russian (\e,L@caaZXY\e(B) \e,L7T`PRabRcYbU\e(B!")
+ (documentation . "\
+Support for Russian using koi8-r and the russian-computer input method.")
+ (tutorial . "TUTORIAL.ru"))
+ '("Cyrillic"))
+
+
+(defvar cyrillic-koi8-u-decode-table
+ [
+ 0 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
+ ;; All Unicode:
+;; ?\e$,2 \e(B ?\e$,2 "\e(B ?\e$,2 ,\e(B ?\e$,2 0\e(B ?\e$,2 4\e(B ?\e$,2 8\e(B ?\e$,2 <\e(B ?\e$,2 D\e(B ?\e$,2 L\e(B ?\e$,2 T\e(B ?\e$,2 \\e(B ?\e$,2!@\e(B ?\e$,2!D\e(B ?\e$,2!H\e(B ?\e$,2!L\e(B ?\e$,2!P\e(B
+;; ?\e$,2!Q\e(B ?\e$,2!R\e(B ?\e$,2!S\e(B ?\e$,1{ \e(B ?\e$,2!`\e(B ?\e$,1x9\e(B ?\e$,1x:\e(B ?\e$,1xh\e(B ?\e$,1y$\e(B ?\e$,1y%\e(B ?\e,L \e(B ?\e$,1{!\e(B ?\e,A0\e(B ?\e,A2\e(B ?\e,A7\e(B ?\e,Aw\e(B
+;; ?\e$,2 p\e(B ?\e$,2 q\e(B ?\e$,2 r\e(B ?\e$,1(q\e(B ?\e$,1(t\e(B ?\e$,2 t\e(B ?\e$,1(v\e(B ?\e$,1(w\e(B ?\e$,2 w\e(B ?\e$,2 x\e(B ?\e$,2 y\e(B ?\e$,2 z\e(B ?\e$,2 {\e(B ?\e$,1)Q\e(B ?\e$,2 }\e(B ?\e$,2 ~\e(B
+;; ?\e$,2 \7f\e(B ?\e$,2! \e(B ?\e$,2!!\e(B ?\e$,1(!\e(B ?\e$,1($\e(B ?\e$,2!#\e(B ?\e$,1(&\e(B ?\e$,1('\e(B ?\e$,2!&\e(B ?\e$,2!'\e(B ?\e$,2!(\e(B ?\e$,2!)\e(B ?\e$,2!*\e(B ?\e$,1)P\e(B ?\e$,2!,\e(B ?\e,A)\e(B
+;; ?\e$,1(n\e(B ?\e$,1(P\e(B ?\e$,1(Q\e(B ?\e$,1(f\e(B ?\e$,1(T\e(B ?\e$,1(U\e(B ?\e$,1(d\e(B ?\e$,1(S\e(B ?\e$,1(e\e(B ?\e$,1(X\e(B ?\e$,1(Y\e(B ?\e$,1(Z\e(B ?\e$,1([\e(B ?\e$,1(\\e(B ?\e$,1(]\e(B ?\e$,1(^\e(B
+;; ?\e$,1(_\e(B ?\e$,1(o\e(B ?\e$,1(`\e(B ?\e$,1(a\e(B ?\e$,1(b\e(B ?\e$,1(c\e(B ?\e$,1(V\e(B ?\e$,1(R\e(B ?\e$,1(l\e(B ?\e$,1(k\e(B ?\e$,1(W\e(B ?\e$,1(h\e(B ?\e$,1(m\e(B ?\e$,1(i\e(B ?\e$,1(g\e(B ?\e$,1(j\e(B
+;; ?\e$,1(N\e(B ?\e$,1(0\e(B ?\e$,1(1\e(B ?\e$,1(F\e(B ?\e$,1(4\e(B ?\e$,1(5\e(B ?\e$,1(D\e(B ?\e$,1(3\e(B ?\e$,1(E\e(B ?\e$,1(8\e(B ?\e$,1(9\e(B ?\e$,1(:\e(B ?\e$,1(;\e(B ?\e$,1(<\e(B ?\e$,1(=\e(B ?\e$,1(>\e(B
+;; ?\e$,1(?\e(B ?\e$,1(O\e(B ?\e$,1(@\e(B ?\e$,1(A\e(B ?\e$,1(B\e(B ?\e$,1(C\e(B ?\e$,1(6\e(B ?\e$,1(2\e(B ?\e$,1(L\e(B ?\e$,1(K\e(B ?\e$,1(7\e(B ?\e$,1(H\e(B ?\e$,1(M\e(B ?\e$,1(I\e(B ?\e$,1(G\e(B ?\e$,1(J\e(B
+;; 8859-5 plus Unicode:
+ ?\e$,2 \e(B ?\e$,2 "\e(B ?\e$,2 ,\e(B ?\e$,2 0\e(B ?\e$,2 4\e(B ?\e$,2 8\e(B ?\e$,2 <\e(B ?\e$,2 D\e(B ?\e$,2 L\e(B ?\e$,2 T\e(B ?\e$,2 \\e(B ?\e$,2!@\e(B ?\e$,2!D\e(B ?\e$,2!H\e(B ?\e$,2!L\e(B ?\e$,2!P\e(B
+ ?\e$,2!Q\e(B ?\e$,2!R\e(B ?\e$,2!S\e(B ?\e$,1{ \e(B ?\e$,2!`\e(B ?\e$,1x9\e(B ?\e$,1x:\e(B ?\e$,1xh\e(B ?\e$,1y$\e(B ?\e$,1y%\e(B ?\e,L \e(B ?\e$,1{!\e(B ?\e,A0\e(B ?\e,A2\e(B ?\e,A7\e(B ?\e,Aw\e(B
+ ?\e$,2 p\e(B ?\e$,2 q\e(B ?\e$,2 r\e(B ?\e,Lq\e(B ?\e,Lt\e(B ?\e$,2 t\e(B ?\e,Lv\e(B ?\e,Lw\e(B ?\e$,2 w\e(B ?\e$,2 x\e(B ?\e$,2 y\e(B ?\e$,2 z\e(B ?\e$,2 {\e(B ?\e$,1)Q\e(B ?\e$,2 }\e(B ?\e$,2 ~\e(B
+ ?\e$,2 \7f\e(B ?\e$,2! \e(B ?\e$,2!!\e(B ?\e,L!\e(B ?\e,L$\e(B ?\e$,2!#\e(B ?\e,L&\e(B ?\e,L'\e(B ?\e$,2!&\e(B ?\e$,2!'\e(B ?\e$,2!(\e(B ?\e$,2!)\e(B ?\e$,2!*\e(B ?\e$,1)P\e(B ?\e$,2!,\e(B ?\e,A)\e(B
+ ?\e,Ln\e(B ?\e,LP\e(B ?\e,LQ\e(B ?\e,Lf\e(B ?\e,LT\e(B ?\e,LU\e(B ?\e,Ld\e(B ?\e,LS\e(B ?\e,Le\e(B ?\e,LX\e(B ?\e,LY\e(B ?\e,LZ\e(B ?\e,L[\e(B ?\e,L\\e(B ?\e,L]\e(B ?\e,L^\e(B
+ ?\e,L_\e(B ?\e,Lo\e(B ?\e,L`\e(B ?\e,La\e(B ?\e,Lb\e(B ?\e,Lc\e(B ?\e,LV\e(B ?\e,LR\e(B ?\e,Ll\e(B ?\e,Lk\e(B ?\e,LW\e(B ?\e,Lh\e(B ?\e,Lm\e(B ?\e,Li\e(B ?\e,Lg\e(B ?\e,Lj\e(B
+ ?\e,LN\e(B ?\e,L0\e(B ?\e,L1\e(B ?\e,LF\e(B ?\e,L4\e(B ?\e,L5\e(B ?\e,LD\e(B ?\e,L3\e(B ?\e,LE\e(B ?\e,L8\e(B ?\e,L9\e(B ?\e,L:\e(B ?\e,L;\e(B ?\e,L<\e(B ?\e,L=\e(B ?\e,L>\e(B
+ ?\e,L?\e(B ?\e,LO\e(B ?\e,L@\e(B ?\e,LA\e(B ?\e,LB\e(B ?\e,LC\e(B ?\e,L6\e(B ?\e,L2\e(B ?\e,LL\e(B ?\e,LK\e(B ?\e,L7\e(B ?\e,LH\e(B ?\e,LM\e(B ?\e,LI\e(B ?\e,LG\e(B ?\e,LJ\e(B
+ ]
+ "Cyrillic KOI8-U decoding table.")
+
+(let ((table (make-translation-table-from-vector
+ cyrillic-koi8-u-decode-table)))
+ (define-translation-table 'cyrillic-koi8-u-nonascii-translation-table table)
+ (define-translation-table 'cyrillic-koi8-u-encode-table
+ (char-table-extra-slot table 0)))
+
+(makunbound 'cyrillic-koi8-u-decode-table)
+
+(define-ccl-program ccl-decode-koi8-u
+ `(4
+ ((loop
+ (r0 = 0)
+ (read r1)
+ (if (r1 < 128)
+ (write-repeat r1)
+ ((translate-character cyrillic-koi8-u-nonascii-translation-table r0 r1)
+ (translate-character ucs-translation-table-for-decode r0 r1)
+ (write-multibyte-character r0 r1)
+ (repeat))))))
+ "CCL program to decode KOI8-U.")
+
+(define-ccl-program ccl-encode-koi8-u
+ `(1
+ ((loop
+ (read-multibyte-character r0 r1)
+ (translate-character cyrillic-koi8-u-encode-table r0 r1)
+ (if (r0 != ,(charset-id 'ascii))
+ (if (r0 != ,(charset-id 'eight-bit-graphic))
+ (if (r0 != ,(charset-id 'eight-bit-control))
+ (r1 = ??))))
+ (write-repeat r1))))
+ "CCL program to encode KOI8-U.")
+
+(cyrillic-unify-encoding 'cyrillic-koi8-u-encode-table)
+
+(make-coding-system
+ 'koi8-u 4
+ ?U "KOI8-U 8-bit encoding for Cyrillic (MIME: KOI8-U)"
+ '(ccl-decode-koi8-u . ccl-encode-koi8-u)
+ `((safe-chars . cyrillic-koi8-u-encode-table)
+ (mime-charset . koi8-u)
+ (valid-codes (0 . 255))
+ (dependency unify-8859-on-encoding-mode unify-8859-on-decoding-mode)))
+
+(define-ccl-program ccl-encode-koi8-u-font
+ `(0
+ (translate-character cyrillic-koi8-u-encode-table r0 r1))
+ "CCL program to encode Cyrillic chars to KOI-U font.")
+
+(add-to-list 'font-ccl-encoder-alist '("koi8-u" . ccl-encode-koi8-u-font))
+
+(set-language-info-alist
+ "Ukrainian" `((coding-system koi8-u)
+ (coding-priority koi8-u)
+ (nonascii-translation
+ . ,(get 'cyrillic-koi8-u-nonascii-translation-table
+ 'translation-table))
+ (input-method . "ukrainian-computer")
+ (features code-pages)
+ (documentation
+ . "Support for Ukrainian with KOI8-U character set."))
+ '("Cyrillic"))
-(eval-and-compile
+;;; ALTERNATIVNYJ stuff
+;; Fixme: It's unclear what's the correct table. I've found
+;; statements both that it's the same as cp866 and somewhat different,
+;; but nothing that looks really definitive.
(defvar cyrillic-alternativnyj-decode-table
[
0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15
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
+;; ?\e$,1(0\e(B ?\e$,1(1\e(B ?\e$,1(2\e(B ?\e$,1(3\e(B ?\e$,1(4\e(B ?\e$,1(5\e(B ?\e$,1(6\e(B ?\e$,1(7\e(B ?\e$,1(8\e(B ?\e$,1(9\e(B ?\e$,1(:\e(B ?\e$,1(;\e(B ?\e$,1(<\e(B ?\e$,1(=\e(B ?\e$,1(>\e(B ?\e$,1(?\e(B
+;; ?\e$,1(@\e(B ?\e$,1(A\e(B ?\e$,1(B\e(B ?\e$,1(C\e(B ?\e$,1(D\e(B ?\e$,1(E\e(B ?\e$,1(F\e(B ?\e$,1(G\e(B ?\e$,1(H\e(B ?\e$,1(I\e(B ?\e$,1(J\e(B ?\e$,1(K\e(B ?\e$,1(L\e(B ?\e$,1(M\e(B ?\e$,1(N\e(B ?\e$,1(O\e(B
+;; ?\e$,1(P\e(B ?\e$,1(Q\e(B ?\e$,1(R\e(B ?\e$,1(S\e(B ?\e$,1(T\e(B ?\e$,1(U\e(B ?\e$,1(V\e(B ?\e$,1(W\e(B ?\e$,1(X\e(B ?\e$,1(Y\e(B ?\e$,1(Z\e(B ?\e$,1([\e(B ?\e$,1(\\e(B ?\e$,1(]\e(B ?\e$,1(^\e(B ?\e$,1(_\e(B
+;; ?\e$,2!Q\e(B ?\e$,2!R\e(B ?\e$,2!S\e(B ?\e$,2 "\e(B ?\e$,2 D\e(B ?\e$,2!!\e(B ?\e$,2!"\e(B ?\e$,2 v\e(B ?\e$,2 u\e(B ?\e$,2!#\e(B ?\e$,2 q\e(B ?\e$,2 w\e(B ?\e$,2 }\e(B ?\e$,2 |\e(B ?\e$,2 {\e(B ?\e$,2 0\e(B
+;; ?\e$,2 4\e(B ?\e$,2 T\e(B ?\e$,2 L\e(B ?\e$,2 <\e(B ?\e$,2 \e(B ?\e$,2 \\e(B ?\e$,2 ~\e(B ?\e$,2 \7f\e(B ?\e$,2 z\e(B ?\e$,2 t\e(B ?\e$,2!)\e(B ?\e$,2!&\e(B ?\e$,2! \e(B ?\e$,2 p\e(B ?\e$,2!,\e(B ?\e$,2!'\e(B
+;; ?\e$,2!(\e(B ?\e$,2!$\e(B ?\e$,2!%\e(B ?\e$,2 y\e(B ?\e$,2 x\e(B ?\e$,2 r\e(B ?\e$,2 s\e(B ?\e$,2!+\e(B ?\e$,2!*\e(B ?\e$,2 8\e(B ?\e$,2 ,\e(B ?\e$,2!H\e(B ?\e$,2!D\e(B ?\e$,2!L\e(B ?\e$,2!P\e(B ?\e$,2!@\e(B
+;; ?\e$,1(`\e(B ?\e$,1(a\e(B ?\e$,1(b\e(B ?\e$,1(c\e(B ?\e$,1(d\e(B ?\e$,1(e\e(B ?\e$,1(f\e(B ?\e$,1(g\e(B ?\e$,1(h\e(B ?\e$,1(i\e(B ?\e$,1(j\e(B ?\e$,1(k\e(B ?\e$,1(l\e(B ?\e$,1(m\e(B ?\e$,1(n\e(B ?\e$,1(o\e(B
+;; ?\e$,1(!\e(B ?\e$,1(q\e(B ?\e$,1ry\e(B ?\e$,1rx\e(B ?\e$,1%A\e(B ?\e$,1%@\e(B ?\e$,1s:\e(B ?\e$,1s9\e(B ?\e$,1vq\e(B ?\e$,1vs\e(B ?\e,A1\e(B ?\e,Aw\e(B ?\e$,1uV\e(B ?\e,A$\e(B ?\e$,2!`\e(B ?\e,A \e(B ;
+;; 8859+Unicode
?\e,L0\e(B ?\e,L1\e(B ?\e,L2\e(B ?\e,L3\e(B ?\e,L4\e(B ?\e,L5\e(B ?\e,L6\e(B ?\e,L7\e(B ?\e,L8\e(B ?\e,L9\e(B ?\e,L:\e(B ?\e,L;\e(B ?\e,L<\e(B ?\e,L=\e(B ?\e,L>\e(B ?\e,L?\e(B
?\e,L@\e(B ?\e,LA\e(B ?\e,LB\e(B ?\e,LC\e(B ?\e,LD\e(B ?\e,LE\e(B ?\e,LF\e(B ?\e,LG\e(B ?\e,LH\e(B ?\e,LI\e(B ?\e,LJ\e(B ?\e,LK\e(B ?\e,LL\e(B ?\e,LM\e(B ?\e,LN\e(B ?\e,LO\e(B
?\e,LP\e(B ?\e,LQ\e(B ?\e,LR\e(B ?\e,LS\e(B ?\e,LT\e(B ?\e,LU\e(B ?\e,LV\e(B ?\e,LW\e(B ?\e,LX\e(B ?\e,LY\e(B ?\e,LZ\e(B ?\e,L[\e(B ?\e,L\\e(B ?\e,L]\e(B ?\e,L^\e(B ?\e,L_\e(B
- 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
- 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
- 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
+ ?\e$,2!Q\e(B ?\e$,2!R\e(B ?\e$,2!S\e(B ?\e$,2 "\e(B ?\e$,2 D\e(B ?\e$,2!!\e(B ?\e$,2!"\e(B ?\e$,2 v\e(B ?\e$,2 u\e(B ?\e$,2!#\e(B ?\e$,2 q\e(B ?\e$,2 w\e(B ?\e$,2 }\e(B ?\e$,2 |\e(B ?\e$,2 {\e(B ?\e$,2 0\e(B
+ ?\e$,2 4\e(B ?\e$,2 T\e(B ?\e$,2 L\e(B ?\e$,2 <\e(B ?\e$,2 \e(B ?\e$,2 \\e(B ?\e$,2 ~\e(B ?\e$,2 \7f\e(B ?\e$,2 z\e(B ?\e$,2 t\e(B ?\e$,2!)\e(B ?\e$,2!&\e(B ?\e$,2! \e(B ?\e$,2 p\e(B ?\e$,2!,\e(B ?\e$,2!'\e(B
+ ?\e$,2!(\e(B ?\e$,2!$\e(B ?\e$,2!%\e(B ?\e$,2 y\e(B ?\e$,2 x\e(B ?\e$,2 r\e(B ?\e$,2 s\e(B ?\e$,2!+\e(B ?\e$,2!*\e(B ?\e$,2 8\e(B ?\e$,2 ,\e(B ?\e$,2!H\e(B ?\e$,2!D\e(B ?\e$,2!L\e(B ?\e$,2!P\e(B ?\e$,2!@\e(B
?\e,L`\e(B ?\e,La\e(B ?\e,Lb\e(B ?\e,Lc\e(B ?\e,Ld\e(B ?\e,Le\e(B ?\e,Lf\e(B ?\e,Lg\e(B ?\e,Lh\e(B ?\e,Li\e(B ?\e,Lj\e(B ?\e,Lk\e(B ?\e,Ll\e(B ?\e,Lm\e(B ?\e,Ln\e(B ?\e,Lo\e(B
- ?\e,L!\e(B ?\e,Lq\e(B 32 32 32 32 32 32 32 32 32 32 32 32 32 ?\e,Lp\e(B]
+ ;; Taken from http://www.cyrillic.com/ref/cyrillic/koi-8alt.html
+ ;; with guesses for the Unicodes of the glyphs in the absence of a
+ ;; table.
+ ?\e,L!\e(B ?\e,Lq\e(B ?\e$,1ry\e(B ?\e$,1rx\e(B ?\e$,1%A\e(B ?\e$,1%@\e(B ?\e$,1s:\e(B ?\e$,1s9\e(B ?\e$,1vq\e(B ?\e$,1vs\e(B ?\e,A1\e(B ?\e,Aw\e(B ?\e,Lp\e(B ?\e,A$\e(B ?\e$,2!`\e(B ?\e,L \e(B]
"Cyrillic ALTERNATIVNYJ decoding table.")
-(defvar cyrillic-alternativnyj-encode-table
- (let ((table (make-vector 256 32))
- (i 0))
- (while (< i 256)
- (let* ((ch (aref cyrillic-alternativnyj-decode-table i))
- (split (split-char ch)))
- (if (eq (car split) 'cyrillic-iso8859-5)
- (aset table (nth 1 split) i)
- (if (/= ch 32)
- (aset table ch i))))
- (setq i (1+ i)))
+(let ((table (make-translation-table-from-vector
+ cyrillic-alternativnyj-decode-table)))
+ (define-translation-table 'cyrillic-alternativnyj-nonascii-translation-table
table)
- "Cyrillic ALTERNATIVNYJ encoding table.")
-
-)
+ (define-translation-table 'cyrillic-alternativnyj-encode-table
+ (char-table-extra-slot table 0)))
+(makunbound 'cyrillic-alternativnyj-decode-table)
(define-ccl-program ccl-decode-alternativnyj
- `(3
- ((read r0)
- (loop
- (write-read-repeat r0 ,cyrillic-alternativnyj-decode-table))))
+ `(4
+ ((loop
+ (r0 = 0)
+ (read r1)
+ (if (r1 < 128)
+ (write-repeat r1)
+ ((translate-character cyrillic-alternativnyj-nonascii-translation-table
+ r0 r1)
+ (translate-character ucs-translation-table-for-decode r0 r1)
+ (write-multibyte-character r0 r1)
+ (repeat))))))
"CCL program to decode Alternativnyj.")
(define-ccl-program ccl-encode-alternativnyj
`(1
- ((read r0)
- (loop
- (if (r0 != ,(charset-id 'cyrillic-iso8859-5))
- (write-read-repeat r0)
- ((read r0)
- (write-read-repeat r0 ,cyrillic-alternativnyj-encode-table))))))
+ ((loop
+ (read-multibyte-character r0 r1)
+ (translate-character cyrillic-alternativnyj-encode-table r0 r1)
+ (if (r0 != ,(charset-id 'ascii))
+ (if (r0 != ,(charset-id 'eight-bit-graphic))
+ (if (r0 != ,(charset-id 'eight-bit-control))
+ (r1 = ??))))
+ (write-repeat r1))))
"CCL program to encode Alternativnyj.")
-
+
+(cyrillic-unify-encoding 'cyrillic-alternativnyj-encode-table)
+
(make-coding-system
'cyrillic-alternativnyj 4 ?A
- "ALTERNATIVNYJ 8-bit encoding for Cyrillic"
+ "ALTERNATIVNYJ 8-bit encoding for Cyrillic."
'(ccl-decode-alternativnyj . ccl-encode-alternativnyj)
- '((safe-charsets ascii cyrillic-iso8859-5)
- (valid-codes (0 175) (224 241) 255)))
+ `((safe-chars . cyrillic-alternativnyj-encode-table)
+ (valid-codes (0 . 255))
+ (dependency unify-8859-on-encoding-mode unify-8859-on-decoding-mode)))
(define-coding-system-alias 'alternativnyj 'cyrillic-alternativnyj)
(define-ccl-program ccl-encode-alternativnyj-font
- '(0
- ((r1 |= 128)
- (r1 = r1 ,cyrillic-alternativnyj-encode-table)))
+ `(0
+ (translate-character cyrillic-alternativnyj-encode-table r0 r1))
"CCL program to encode Cyrillic chars to Alternativnyj font.")
-(setq font-ccl-encoder-alist
- (cons (cons "alternativnyj" ccl-encode-alternativnyj-font)
- font-ccl-encoder-alist))
-
-(defvar cyrillic-alternativnyj-nonascii-translation-table
- (make-translation-table-from-vector cyrillic-alternativnyj-decode-table)
- "Value of `nonascii-translation-table' in Cyrillic-ALT language environment.")
+(add-to-list 'font-ccl-encoder-alist
+ '("alternativnyj" . ccl-encode-alternativnyj-font))
(set-language-info-alist
"Cyrillic-ALT" `((charset cyrillic-iso8859-5)
(nonascii-translation
- . ,cyrillic-alternativnyj-nonascii-translation-table)
- (charset-origin-alist
- (cyrillic-iso8859-5 "ALTERNATIVNYJ"
- cyrillic-encode-koi8-r-char))
+ . ,(get 'cyrillic-alternativnyj-nonascii-translation-table
+ 'translation-table))
(coding-system cyrillic-alternativnyj)
(coding-priority cyrillic-alternativnyj)
- (input-method . "cyrillic-yawerty")
+ (input-method . "russian-typewriter")
(features cyril-util)
(unibyte-display . cyrillic-alternativnyj)
(sample-text . "Russian (\e,L@caaZXY\e(B) \e,L7T`PRabRcYbU\e(B!")
(documentation . "Support for Cyrillic ALTERNATIVNYJ."))
'("Cyrillic"))
+(set-language-info-alist
+ "Windows-1251" `((coding-system windows-1251)
+ (coding-priority windows-1251)
+ (nonascii-translation
+ . ,(get 'decode-windows-1252 'translation-table))
+ (input-method . "russian-typewriter") ; fixme?
+ (features code-pages)
+ (documentation . "Support for windows-1251 character set."))
+ '("Cyrillic"))
+
+(set-language-info-alist
+ "Tajik" `((coding-system cyrillic-koi8-t)
+ (coding-priority cyrillic-koi8-t)
+ (nonascii-translation
+ . ,(get 'decode-koi8-t 'translation-table))
+ (input-method . "russian-typewriter") ; fixme?
+ (features code-pages)
+ (documentation . "Support for Tajik using KOI8-T."))
+ '("Cyrillic"))
+
+(set-language-info-alist
+ "Bulgarian" `((coding-system windows-1251)
+ (coding-priority windows-1251)
+ (nonascii-translation
+ . ,(get 'decode-windows-1251 'translation-table))
+ (input-method . "bulgarian-bds")
+ (features code-pages)
+ (documentation
+ . "Support for Bulgarian with windows-1251 character set.")
+ (tutorial . "TUTORIAL.bg"))
+ '("Cyrillic"))
+
+(set-language-info-alist
+ "Belarusian" `((coding-system windows-1251)
+ (coding-priority windows-1251)
+ (nonascii-translation
+ . ,(get 'decode-windows-1251 'translation-table))
+ (input-method . "belarusian")
+ (features code-pages)
+ (documentation
+ . "Support for Belarusian with windows-1251 character set.
+\(The name Belarusian replaced Byelorussian in the early 1990s.)"))
+ '("Cyrillic"))
+
+(provide 'cyrillic)
+
+;;; arch-tag: bda71ae0-ba41-4cb6-a6e0-1dff542313d3
;;; cyrillic.el ends here
HCoop / bpt / emacs.git / blobdiff