;;; Commentary:
-;; The character set ISO8859-5 is supported. KOI-8 and ALTERNATIVNYJ
-;; are converted to ISO8859-5 internally.
+;; The character set ISO8859-5 is supported.
+;; KOI-8, Windows-1251, and ALTERNATIVNYJ are converted to ISO8859-5
+;; internally.
;;; Code:
-;; For syntax of Cyrillic
+;; Cyrillic syntax
(modify-syntax-entry 'cyrillic-iso8859-5 "w")
(modify-syntax-entry ?\e,L-\e(B ".")
(modify-syntax-entry ?\e,Lp\e(B ".")
;;; CYRILLIC
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
-;; ISO-8859-5 staff
-
-;; (make-coding-system
-;; 'cyrillic-iso-8bit 2 ?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)
-;; '((safe-charsets ascii cyrillic-iso8859-5)
-;; (mime-charset . iso-8859-5)))
-
-;; (define-coding-system-alias 'iso-8859-5 'cyrillic-iso-8bit)
+;; ISO-8859-5
(make-coding-system
'iso-8859-5 'iso2022
- "MIME ISO-8859-5"
+ "ISO-8859-5 (ISO 2022 based 8-bit encoding for Cyrillic script)"
'(charset-g0 ascii
charset-g1 cyrillic-iso8859-5
charset-g2 t
(documentation . "Support for Cyrillic ISO-8859-5."))
'("Cyrillic"))
-;; KOI-8 staff
+;; KOI-8
(eval-and-compile
(write-read-repeat r0 , cyrillic-koi8-r-encode-table))))))
"CCL program to encode KOI8.")
-;; (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)"
-;; '(ccl-decode-koi8 . ccl-encode-koi8)
-;; '((safe-charsets ascii cyrillic-iso8859-5)
-;; (mime-charset . koi8-r)
-;; (valid-codes (0 . 127) 163 179 (192 . 255))
-;; (charset-origin-alist (cyrillic-iso8859-5 "KOI8-R"
-;; cyrillic-encode-koi8-r-char))))
-
;; (define-coding-system-alias 'koi8-r 'cyrillic-koi8)
;; (define-coding-system-alias 'koi8 'cyrillic-koi8)
(make-coding-system
'koi8-r 'ccl
- "Coding-system used for KOI8-R."
- `(decode ,ccl-decode-koi8
- encode ,ccl-encode-koi8
+ "KOI8-R 8-bit encoding for Cyrillic."
+ '(decode ccl-decode-koi8
+ encode ccl-encode-koi8
mnemonic "KOI8"))
-;; it is not correct, but XEmacs doesn't have `ccl' category...
+;; `iso-8-1' is not correct, but XEmacs doesn't have a `ccl' category
(coding-system-put 'koi8-r 'category 'iso-8-1)
-;; (define-ccl-program ccl-encode-koi8-font
-;; `(0
-;; ((r1 |= 128)
-;; (r1 = r1 ,cyrillic-koi8-r-encode-table)))
-;; "CCL program to encode Cyrillic chars to KOI font.")
+(define-ccl-program ccl-encode-koi8-r-font
+ `(0
+ ((r1 |= 128)
+ (r1 = r1 ,cyrillic-koi8-r-encode-table)))
+ "CCL program to encode Cyrillic chars to koi8-r font.")
;; (setq font-ccl-encoder-alist
;; (cons (cons "koi8" ccl-encode-koi8-font) font-ccl-encoder-alist))
(documentation . "Support for Cyrillic KOI8-R."))
'("Cyrillic"))
-;;; ALTERNATIVNYJ staff
+;;; WINDOWS-1251
+
+(eval-and-compile
+
+(defvar cyrillic-windows-1251-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
+ ?\e,L"\e(B ?\e,L#\e(B 32 ?\e,Ls\e(B 32 32 32 32 32 32 ?\e,L)\e(B 32 ?\e,L*\e(B ?\e,L,\e(B ?\e,L+\e(B ?\e,L/\e(B ;"
+ ?\e,Lr\e(B 32 32 32 32 32 32 32 32 32 ?\e,Ly\e(B 32 ?\e,Lz\e(B ?\e,L|\e(B ?\e,L{\e(B ?\e,L\7f\e(B
+ ?\e,L \e(B ?\e,L.\e(B ?\e,L~\e(B ?\e,L(\e(B ?\e,A$\e(B 32 ?\e,A&\e(B ?\e,L}\e(B ?\e,L!\e(B ?\e,A)\e(B ?\e,L$\e(B ?\e,A+\e(B ?\e,A,\e(B ?\e,L-\e(B ?\e,A.\e(B ?\e,L'\e(B
+ ?\e,A0\e(B ?\e,A1\e(B ?\e,L&\e(B ?\e,Lv\e(B 32 ?\e,A5\e(B ?\e,A6\e(B ?\e,A7\e(B ?\e,Lq\e(B ?\e,Lp\e(B ?\e,Lt\e(B ?\e,A;\e(B ?\e,Lx\e(B ?\e,L%\e(B ?\e,Lu\e(B ?\e,Lw\e(B
+ ?\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
+ ?\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 ]
+ "Cyrillic Windows-1251 decoding table.")
+
+(defvar cyrillic-windows-1251-encode-table
+ (let ((table (make-vector 256 32))
+ (i 0))
+ (while (< i 256)
+ (let* ((ch (aref cyrillic-windows-1251-decode-table i))
+ (split (split-char ch)))
+ (cond ((eq (car split) 'cyrillic-iso8859-5)
+ (aset table (logior (nth 1 split) 128) i)
+ )
+ ((eq ch 32))
+ ((eq (car split) 'ascii)
+ (aset table ch i)
+ )))
+ (setq i (1+ i)))
+ table)
+ "Cyrillic Windows-1251 encoding table.")
+
+)
+
+(define-ccl-program ccl-decode-windows1251
+ `(3
+ ((read r0)
+ (loop
+ (write-read-repeat r0 ,cyrillic-windows-1251-decode-table))))
+ "CCL program to decode Windows-1251.")
+
+(define-ccl-program ccl-encode-windows1251
+ `(1
+ ((read r0)
+ (loop
+ (if (r0 != ,(charset-id 'cyrillic-iso8859-5))
+ (write-read-repeat r0)
+ ((read r0)
+ (write-read-repeat r0 , cyrillic-windows-1251-encode-table))))))
+ "CCL program to encode Windows-1251.")
+
+(make-coding-system
+ 'windows-1251 'ccl
+ "Coding-system used for Windows-1251."
+ '(decode ccl-decode-windows1251
+ encode ccl-encode-windows1251
+ mnemonic "CyrW"))
+
+;; `iso-8-1' is not correct, but XEmacs doesn't have a `ccl' category
+(coding-system-put 'windows-1251 'category 'iso-8-1)
+
+(set-language-info-alist
+ "Cyrillic-Win" '((charset cyrillic-iso8859-5)
+ (coding-system windows-1251)
+ (coding-priority windows-1251)
+ (input-method . "cyrillic-yawerty")
+ (features cyril-util)
+ (tutorial . "TUTORIAL.ru")
+ (sample-text . "Russian (\e,L@caaZXY\e(B) \e,L7T`PRabRcYbU\e(B!")
+ (documentation . "Support for Cyrillic Windows-1251."))
+ '("Cyrillic"))
+
+;;; ALTERNATIVNYJ
(eval-and-compile
(write-read-repeat r0 ,cyrillic-alternativnyj-encode-table))))))
"CCL program to encode Alternativnyj.")
-;; (make-coding-system
-;; 'cyrillic-alternativnyj 4 ?A
-;; "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)
-;; (charset-origin-alist (cyrillic-iso8859-5 "ALTERNATIVNYJ"
-;; cyrillic-encode-koi8-r-char))))
-
-
;; (define-coding-system-alias 'alternativnyj 'cyrillic-alternativnyj)
(make-coding-system
'alternativnyj 'ccl
"Coding-system used for Alternativnyj"
- `(decode ,ccl-decode-alternativnyj
- encode ,ccl-encode-alternativnyj
+ '(decode ccl-decode-alternativnyj
+ encode ccl-encode-alternativnyj
mnemonic "Cy.Alt"))
-;; it is not correct, but XEmacs doesn't have `ccl' category...
+;; `iso-8-1' is not correct, but XEmacs doesn't have `ccl' category
(coding-system-put 'alternativnyj 'category 'iso-8-1)
;; (define-ccl-program ccl-encode-alternativnyj-font
(documentation . "Support for Cyrillic ALTERNATIVNYJ."))
'("Cyrillic"))
+;;
+;; Setup case table
+;;
+
+;; FIXME: this defun is cut-and-pasted from mule/latin.el
+(defun setup-case-pairs (charset pairs)
+ (let ((tbl (standard-case-table)))
+ (loop for (uc lc) in pairs do
+ (put-case-table-pair (make-char charset uc) (make-char charset lc) tbl))))
+
+(setup-case-pairs
+ 'cyrillic-iso8859-5
+ '(
+ (176 208) ;cyrillic letter a
+ (167 247) ;cyrillic letter yi
+ (205 237) ;cyrillic letter e
+ (174 254) ;cyrillic letter short u
+ (177 209) ;cyrillic letter be
+ (197 229) ;cyrillic letter ha
+ (184 216) ;cyrillic letter i
+ (180 212) ;cyrillic letter de
+ (198 230) ;cyrillic letter tse
+ (206 238) ;cyrillic letter yu
+ (190 222) ;cyrillic letter o
+ (168 248) ;cyrillic letter je
+ (202 234) ;cyrillic letter hard sign
+ (199 231) ;cyrillic letter che
+ (164 244) ;cyrillic letter ukrainian ie
+ (162 242) ;cyrillic letter dje
+ (179 211) ;cyrillic letter ghe
+ (195 227) ;cyrillic letter u
+ (191 223) ;cyrillic letter pe
+ (163 243) ;cyrillic letter gje
+ (194 226) ;cyrillic letter te
+ (172 252) ;cyrillic letter kje
+ (178 210) ;cyrillic letter ve
+ (169 249) ;cyrillic letter lje
+ (200 232) ;cyrillic letter sha
+ (170 250) ;cyrillic letter nje
+ (183 215) ;cyrillic letter ze
+ (165 245) ;cyrillic letter dze
+ (203 235) ;cyrillic letter yeru
+ (201 233) ;cyrillic letter shcha
+ (182 214) ;cyrillic letter zhe
+ (175 255) ;cyrillic letter dzhe
+ (196 228) ;cyrillic letter ef
+ (186 218) ;cyrillic letter ka
+ (204 236) ;cyrillic letter soft sign
+ (181 213) ;cyrillic letter ie
+ (187 219) ;cyrillic letter el
+ (188 220) ;cyrillic letter em
+ (189 221) ;cyrillic letter en
+ (171 251) ;cyrillic letter tshe
+ (192 224) ;cyrillic letter er
+ (161 241) ;cyrillic letter io
+ (166 246) ;cyrillic letter byelorussian-ukrainian i
+ (193 225) ;cyrillic letter es
+ (185 217) ;cyrillic letter short i
+ (207 239) ;cyrillic letter ya
+ ))
+
+;; This is our utility function; we don't want it in the dumped XEmacs.
+
+(fmakunbound 'setup-case-pairs)
+
;;; cyrillic.el ends here