view lisp/mule/cyrillic.el @ 3767:6b2ef948e140

[xemacs-hg @ 2006-12-29 18:09:38 by aidan] etc/ChangeLog addition: 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * unicode/unicode-consortium/8859-7.TXT: Update the mapping to the 2003 version of ISO 8859-7. lisp/ChangeLog addition: 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * mule/cyrillic.el: * mule/cyrillic.el (iso-8859-5): * mule/cyrillic.el (cyrillic-koi8-r-encode-table): Add syntax, case support for Cyrillic; make some parentheses more Lispy. * mule/european.el: Content moved to latin.el, file deleted. * mule/general-late.el: If Unicode tables are to be loaded at dump time, do it here, not in loadup.el. * mule/greek.el: Add syntax, case support for Greek. * mule/latin.el: Move the content of european.el here. Change the case table mappings to use hexadecimal codes, to make cross reference to the standards easier. In all cases, take character syntax from similar characters in Latin-1 , rather than deciding separately what syntax they should take. Add (incomplete) support for case with Turkish. Remove description of the character sets used from the language environments' doc strings, since now that we create variant language environments on the fly, such descriptions will often be inaccurate. Set the native-coding-system language info property while setting the other coding-system properties of the language. * mule/misc-lang.el (ipa): Remove the language environment. The International Phonetic _Alphabet_ is not a language, it's inane to have a corresponding language environment in XEmacs. * mule/mule-cmds.el (create-variant-language-environment): Also modify the coding-priority when creating a new language environment; document that. * mule/mule-cmds.el (get-language-environment-from-locale): Recognise that the 'native-coding-system language-info property can be a list, interpret it correctly when it is one. 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * coding.el (coding-system-category): Use the new 'unicode-type property for finding what sort of Unicode coding system subtype a coding system is, instead of the overshadowed 'type property. * dumped-lisp.el (preloaded-file-list): mule/european.el has been removed. * loadup.el (really-early-error-handler): Unicode tables loaded at dump time are now in mule/general-late.el. * simple.el (count-lines): Add some backslashes to to parentheses in docstrings to help fontification along. * simple.el (what-cursor-position): Wrap a line to fit in 80 characters. * unicode.el: Use the 'unicode-type property, not 'type, for setting the Unicode coding-system subtype. src/ChangeLog addition: 2006-12-21 Aidan Kehoe <kehoea@parhasard.net> * file-coding.c: Update the make-coding-system docstring to reflect unicode-type * general-slots.h: New symbol, unicode-type, since 'type was being overridden when accessing a coding system's Unicode subtype. * intl-win32.c: Backslash a few parentheses, to help fontification along. * intl-win32.c (complex_vars_of_intl_win32): Use the 'unicode-type symbol, not 'type, when creating the Microsoft Unicode coding system. * unicode.c (unicode_putprop): * unicode.c (unicode_getprop): * unicode.c (unicode_print): Using 'type as the property name when working out what Unicode subtype a given coding system is was broken, since there's a general coding system property called 'type. Change the former to use 'unicode-type instead.
author aidan
date Fri, 29 Dec 2006 18:09:51 +0000
parents f37a5923ceba
children fbf54025c136
line wrap: on
line source

;;; cyrillic.el --- Support for Cyrillic -*- coding: iso-2022-7bit; -*-

;; Copyright (C) 1995,1999 Electrotechnical Laboratory, JAPAN.
;; Licensed to the Free Software Foundation.
;; Copyright (C) 1997 MORIOKA Tomohiko
;; Copyright (C) 2001, 2002 Ben Wing.

;; Keywords: multilingual, Cyrillic

;; This file is part of XEmacs.

;; XEmacs 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 2, or (at your option)
;; any later version.

;; XEmacs 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 XEmacs; see the file COPYING.  If not, write to the Free
;; Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA
;; 02111-1307, USA.

;;; Commentary:

;; The character set ISO8859-5 is supported.  KOI-8 and ALTERNATIVNYJ are
;; converted to ISO8859-5 internally.

;; [Windows-1251 support deleted because XEmacs has automatic support.]

;; #### We only have automatic support on Windows; that needs to be put
;; back. Also, the Russian Wikipedia articles on KOI-8 list several other
;; related encodings--KOI8-U (Ukrainian), KOI8-RU (simultaneous support for
;; Russian, Belorussian, and Ukrainian), KOI8-C (for languages of the
;; Caucasus), KOI8-O (Old Church Slavonic)--and it would be nice to have
;; them. Beyond that, we're currently trashing lots of code points with
;; KOI-8 R; it would be nice to leverage the Unicode support to not do that. 

;;; Code:

;; Case table:
(loop
  for (upper lower)
  in '((#xcf #xef) ; YA
       (#xce #xee) ; YU
       (#xcd #xed) ; E
       (#xcc #xec) ; SOFT SIGN
       (#xcb #xeb) ; YERU
       (#xca #xea) ; HARD SIGN
       (#xc9 #xe9) ; SHCHA
       (#xc8 #xe8) ; SHA
       (#xc7 #xe7) ; CHE
       (#xc6 #xe6) ; TSE
       (#xc5 #xe5) ; HA
       (#xc4 #xe4) ; EF
       (#xc3 #xe3) ; U
       (#xc2 #xe2) ; TE
       (#xc1 #xe1) ; ES
       (#xc0 #xe0) ; ER
       (#xbf #xdf) ; PE
       (#xbe #xde) ; O
       (#xbd #xdd) ; EN
       (#xbc #xdc) ; EM
       (#xbb #xdb) ; EL
       (#xba #xda) ; KA
       (#xb9 #xd9) ; SHORT I
       (#xb8 #xd8) ; I
       (#xb7 #xd7) ; ZE
       (#xb6 #xd6) ; ZHE
       (#xb5 #xd5) ; IE
       (#xb4 #xd4) ; DE
       (#xb3 #xd3) ; GHE
       (#xb2 #xd2) ; VE
       (#xb1 #xd1) ; BE
       (#xb0 #xd0) ; A
       (#xaf #xff) ; DZHE
       (#xae #xfe) ; SHORT U
       (#xac #xfc) ; KJE
       (#xab #xfb) ; TSHE
       (#xaa #xfa) ; NJE
       (#xa9 #xf9) ; LJE
       (#xa8 #xf8) ; JE
       (#xa7 #xf7) ; YI
       (#xa6 #xf6) ; BYELORUSSIAN-UKRAINIAN I
       (#xa5 #xf5) ; DZE
       (#xa4 #xf4) ; UKRAINIAN IE
       (#xa3 #xf3) ; GJE
       (#xa2 #xf2) ; DJE
       (#xa1 #xf1)) ; IO
  with case-table = (standard-case-table)
  do
  (put-case-table-pair (make-char 'cyrillic-iso8859-5 upper)
		       (make-char 'cyrillic-iso8859-5 lower)
		       case-table))

;; The default character syntax is now word. Pay attention to the
;; exceptions in ISO-8859-5, copying them from ISO-8859-1. 
(loop
  for (latin-1 cyrillic) 
  in '((#xAD #xAD)  ;; SOFT HYPHEN
       (#xA7 #xFD)  ;; SECTION SIGN
       (#xA0 #xA0)) ;; NO BREAK SPACE
  with syntax-table = (standard-syntax-table)
  do (modify-syntax-entry
      (make-char 'cyrillic-iso8859-5 cyrillic)
      (string (char-syntax (make-char 'latin-iso8859-1 latin-1)))
      syntax-table))
  
;; Take NUMERO SIGN's syntax from #. 
(modify-syntax-entry (make-char 'cyrillic-iso8859-5 #xF0)
                     (string (char-syntax ?\# (standard-syntax-table)))
                     (standard-syntax-table))

(make-coding-system
 'iso-8859-5 'iso2022
 "ISO-8859-5 (Cyrillic)"
 '(charset-g0 ascii
   charset-g1 cyrillic-iso8859-5
   charset-g2 t
   charset-g3 t
   mnemonic "ISO8/Cyr"))

(set-language-info-alist
 "Cyrillic-ISO" '((charset cyrillic-iso8859-5)
		  (tutorial . "TUTORIAL.ru")
		  (coding-system iso-8859-5)
		  (coding-priority iso-8859-5)
		  (input-method . "cyrillic-yawerty")
		  (features cyril-util)
		  (sample-text . "Russian (,L@caaZXY(B)	,L7T`PRabRcYbU(B!")
		  (documentation . "Support for Cyrillic ISO-8859-5."))
 '("Cyrillic"))

;; KOI-8

(eval-and-compile

(defvar cyrillic-koi8-r-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
   ?$B(!(B ?$B("(B ?$B(#(B ?$B($(B ?$B(&(B ?$B(%(B ?$B('(B ?$B()(B ?$B(((B ?$B(*(B ?$B(+(B 32  ?$(G#'(B ?$(G#+(B ?$(G#/(B 32
   32  ?$(C"F(B 32  32  ?$B"#(B 32  ?$B"e(B ?$A!V(B ?$A!\(B ?$A!](B ?,L (B  32  ?,A0(B  ?,A2(B  ?,A7(B  ?,Aw(B
   ?$(G#D(B 32  32  ?,Lq(B  32  32  32  32  32  32  32  32  32  32  32  ?$(G#E(B
   32  32  ?$(G#G(B ?,L!(B  32  32  32  32  32  32  32  32  ?$(G#F(B 32  32  ?,A)(B
   ?,Ln(B  ?,LP(B  ?,LQ(B  ?,Lf(B  ?,LT(B  ?,LU(B  ?,Ld(B  ?,LS(B  ?,Le(B  ?,LX(B  ?,LY(B  ?,LZ(B  ?,L[(B  ?,L\(B  ?,L](B  ?,L^(B 
   ?,L_(B  ?,Lo(B  ?,L`(B  ?,La(B  ?,Lb(B  ?,Lc(B  ?,LV(B  ?,LR(B  ?,Ll(B  ?,Lk(B  ?,LW(B  ?,Lh(B  ?,Lm(B  ?,Li(B  ?,Lg(B  ?,Lj(B 
   ?,LN(B  ?,L0(B  ?,L1(B  ?,LF(B  ?,L4(B  ?,L5(B  ?,LD(B  ?,L3(B  ?,LE(B  ?,L8(B  ?,L9(B  ?,L:(B  ?,L;(B  ?,L<(B  ?,L=(B  ?,L>(B 
   ?,L?(B  ?,LO(B  ?,L@(B  ?,LA(B  ?,LB(B  ?,LC(B  ?,L6(B  ?,L2(B  ?,LL(B  ?,LK(B  ?,L7(B  ?,LH(B  ?,LM(B  ?,LI(B  ?,LG(B  ?,LJ(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)))
	(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 KOI8-R encoding 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.")

(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.")

;; (define-coding-system-alias 'koi8-r 'cyrillic-koi8)
;; (define-coding-system-alias 'koi8 'cyrillic-koi8)

(make-coding-system
 'koi8-r 'ccl
 "KOI8-R (Cyrillic)"
 '(decode ccl-decode-koi8
   encode ccl-encode-koi8
   mnemonic "KOI8"))

;; `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.")

;; (setq font-ccl-encoder-alist
;;       (cons (cons "koi8" ccl-encode-koi8-font) font-ccl-encoder-alist))

(defvar cyrillic-koi8-r-to-external-code-table
  (let ((table (make-char-table 'generic))
	(i 0)
	(len (length cyrillic-koi8-r-decode-table)))
    (while (< i len)
      (let ((ch (aref cyrillic-koi8-r-decode-table i)))
	(if (characterp ch)
	    (put-char-table ch i table)))
      (incf i)))
  "Table to convert from characters to their Koi8-R code.")

(set-language-info-alist
 "Cyrillic-KOI8" '((charset cyrillic-iso8859-5)
		   (coding-system koi8-r)
		   (native-coding-system koi8-r)
		   (coding-priority koi8-r)
		   (input-method . "cyrillic-yawerty")
		   (features cyril-util)
		   (locale "ru")
		   (mswindows-locale . "RUSSIAN")
		   (tutorial . "TUTORIAL.ru")
		   (sample-text . "Russian (,L@caaZXY(B)	,L7T`PRabRcYbU(B!")
		   (documentation . "Support for Cyrillic KOI8-R."))
 '("Cyrillic"))

;;; WINDOWS-1251 deleted; we support it automatically in XEmacs

;;; ALTERNATIVNYJ

(eval-and-compile

(defvar cyrillic-alternativnyj-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
   ?,L0(B  ?,L1(B  ?,L2(B  ?,L3(B  ?,L4(B  ?,L5(B  ?,L6(B  ?,L7(B  ?,L8(B  ?,L9(B  ?,L:(B  ?,L;(B  ?,L<(B  ?,L=(B  ?,L>(B  ?,L?(B
   ?,L@(B  ?,LA(B  ?,LB(B  ?,LC(B  ?,LD(B  ?,LE(B  ?,LF(B  ?,LG(B  ?,LH(B  ?,LI(B  ?,LJ(B  ?,LK(B  ?,LL(B  ?,LM(B  ?,LN(B  ?,LO(B
   ?,LP(B  ?,LQ(B  ?,LR(B  ?,LS(B  ?,LT(B  ?,LU(B  ?,LV(B  ?,LW(B  ?,LX(B  ?,LY(B  ?,LZ(B  ?,L[(B  ?,L\(B  ?,L](B  ?,L^(B  ?,L_(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
   ?,L`(B  ?,La(B  ?,Lb(B  ?,Lc(B  ?,Ld(B  ?,Le(B  ?,Lf(B  ?,Lg(B  ?,Lh(B  ?,Li(B  ?,Lj(B  ?,Lk(B  ?,Ll(B  ?,Lm(B  ?,Ln(B  ?,Lo(B
   ?,L!(B  ?,Lq(B   32  32  32  32  32  32  32  32  32  32  32  32  32 ?,Lp(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 (logior (nth 1 split) 128) i)
	  (if (/= ch 32)
	      (aset table ch i))))
      (setq i (1+ i)))
    table)
  "Cyrillic ALTERNATIVNYJ encoding table.")
  
)


(define-ccl-program ccl-decode-alternativnyj
  `(3
    ((read r0)
     (loop
      (write-read-repeat r0 ,cyrillic-alternativnyj-decode-table))))
  "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))))))
  "CCL program to encode Alternativnyj.")

;; (define-coding-system-alias 'alternativnyj 'cyrillic-alternativnyj)

(make-coding-system
 'alternativnyj 'ccl
 "Alternativnyj (Cyrillic)"
 '(decode ccl-decode-alternativnyj
   encode ccl-encode-alternativnyj
   mnemonic "Cy.Alt"))

;; `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
;;   '(0
;;     ((r1 |= 128)
;;      (r1 = r1 ,cyrillic-alternativnyj-encode-table)))
;;   "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-to-external-code-table
  (let ((table (make-char-table 'generic))
	(i 0)
	(len (length cyrillic-alternativnyj-decode-table)))
    (while (< i len)
      (let ((ch (aref cyrillic-alternativnyj-decode-table i)))
	(if (characterp ch)
	    (put-char-table ch i table)))
      (incf i)))
  "Table to convert from characters to their Alternativnyj code.")

(set-language-info-alist
 "Cyrillic-ALT" '((charset cyrillic-iso8859-5)
		  (coding-system alternativnyj)
		  (native-coding-system alternativnyj)
		  (coding-priority alternativnyj)
		  (input-method . "cyrillic-yawerty")
		  (features cyril-util)
		  (tutorial . "TUTORIAL.ru")
		  (sample-text . "Russian (,L@caaZXY(B)	,L7T`PRabRcYbU(B!")
		  (documentation . "Support for Cyrillic ALTERNATIVNYJ."))
 '("Cyrillic"))

;;; cyrillic.el ends here