diff --exclude='*.orig' -duNr emacs-21.2.orig/lisp/faces.el emacs-21.2/lisp/faces.el

--- emacs-21.2.orig/lisp/faces.el	2002-01-28 19:32:36 +0300

+++ emacs-21.2/lisp/faces.el	2003-02-10 19:15:27 +0300

@@ -88,7 +90,8 @@

     '(("gb2312.1980" "gb2312.80&gb8565.88" "gbk*")

       ("jisx0208.1990" "jisx0208.1983" "jisx0208.1978")

       ("ksc5601.1989" "ksx1001.1992" "ksc5601.1987")

-      ("muletibetan-2" "muletibetan-0")))

+      ("muletibetan-2" "muletibetan-0")

+      ("iso8859-5" "microsoft-cp1251" "koi8-u" "koi8")))

   "*Alist of alternative font registry names.

 Each element has the the form (REGISTRY ALTERNATIVE1 ALTERNATIVE2 ...).

 If fonts of registry REGISTRY can be loaded, font selection

diff --exclude='*.orig' -duNr emacs-21.2.orig/lisp/international/cyrillic-codepages-setup.el emacs-21.2/lisp/international/cyrillic-codepages-setup.el

--- emacs-21.2.orig/lisp/international/cyrillic-codepages-setup.el	1970-01-01 03:00:00 +0300

+++ emacs-21.2/lisp/international/cyrillic-codepages-setup.el	2003-02-10 21:12:24 +0300

@@ -0,0 +1,98 @@

+; Setup cyrillic codepages and aliases for their coding-systems.

+;

+; This feature is for setting the corresponding Cyrillic language environments

+; seamlessly (without writing any special commands before).

+;

+;

+; Based on some my ideas and the postings in sisyphus@altlinux.ru mailing list, 

+; particularly from Alexander Bokovoy and Serhii Hlodin.

+; Added MIME charset names according to http://www.iana.org/assignments/character-sets.

+;

+; February 2002

+; Ivan Zakharyaschev <imz@altlinux.ru>

+;

+; Copyright (C) ALT Linux Team 2002

+; (This file is not a part of the original GNU Emacs.)

+;

+; This code 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.

+

+(codepage-setup 1251)

+(coding-system-put 'cp1251 'mime-charset 'windows-1251)

+(define-coding-system-alias 'windows-1251 'cp1251)

+(define-coding-system-alias 'cyrillic-cp1251 'cp1251)

+

+(codepage-setup 1125)

+(define-coding-system-alias 'cp866u 'cp1125)

+(define-coding-system-alias 'cyrillic-cp1125 'cp1125)

+

+(codepage-setup 866)

+(coding-system-put 'cp866 'mime-charset 'cp866)

+(define-coding-system-alias 'ibm-866 'cp866)

+(define-coding-system-alias 'ibm866 'cp866)

+(define-coding-system-alias 'cyrillic-cp866 'cp866)

+

+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

+; A piece of code to correct the list of valid codes for the three codepage-based

+; coding systems: the new ``more reasonable'' values fix Emacs looping infinitely

+; on some encoded input:

+

+(defun cp-detect-valid-codes(codepage) "List valid codes for cpCODEPAGE coding-sytem

+in a format suitable for coding-system's `valid-codes' property.

+The result always has the range (0 . 127) as the first element,

+other elements are extracted from the corresponding codepage decode table

+and sorted.

+

+This function was not present in the original GNU Emacs, rather it has been added

+by ALT mainly to set reasonable `valid-codes' property of cp1251 coding-system

+(otherwise Emacs sometimes looped infinitely trying to process some odd input in

+encoded-kbd mode)."

+  (let* ((decode-table (intern (format "%s-decode-table" codepage))))

+    (cons

+     (cons 0 127)

+     (sort (delq nil (mapcar 'identity (symbol-value decode-table))) '<))))

+

+

+(defun cp-correct-valid-codes(codepage) "Try to set more reasonable values

+for the `valid-codes' property of cpCODEPAGE coding-system than the default 

+single full range ((0. 255)). The ``more reasonable'' values are acquired

+by calling `cp-detect-valid-codes' on CODEPAGE (it lists the codes really 

+present in the decode-table).

+

+This function was not present in the original GNU Emacs, rather it has been added

+by ALT mainly to set reasonable `valid-codes' property of cp1251 coding-system 

+(otherwise Emacs sometimes looped infinitely trying to process some odd input in

+encoded-kbd mode)."

+(coding-system-put codepage 'valid-codes (cp-detect-valid-codes codepage)))

+

+(mapc 'cp-correct-valid-codes '(cp1251 cp866 cp1125))

+

+; And now

+;;(coding-system-get 'cp1251 'valid-codes)

+; will return a much more detailed list of valid codes.

+

+; Valid codes lists fixed.

+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

+

+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

+; Add information about recoding X fonts in these charset/encodings.

+

+(define-ccl-program ccl-encode-cp1251-font

+  `(0

+    ((translate-character cp1251-encode-translation-table r0 r1)))

+  "CCL program to encode Cyrillic chars to CP1251 font.")

+

+;; (setq font-ccl-encoder-alist

+;;       (cons '("microsoft-cp1251" . ccl-encode-cp1251-font) font-ccl-encoder-alist))

+

+(setq font-ccl-encoder-alist

+      (cons '(".*1251" . ccl-encode-cp1251-font) font-ccl-encoder-alist))

+

+; X font data setup end.

+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;

+

+(provide 'cyrillic-codepages-setup)

+

+; End of cyrillic-codepages-setup

diff --exclude='*.orig' -duNr emacs-21.2.orig/lisp/international/fontset.el emacs-21.2/lisp/international/fontset.el

--- emacs-21.2.orig/lisp/international/fontset.el	2001-10-24 15:07:58 +0400

+++ emacs-21.2/lisp/international/fontset.el	2003-02-10 18:22:12 +0300

@@ -27,6 +27,10 @@

 ;;; Code:

+; Require the setup of cp1251 support, otherwise

+; it might be too late. (imz@altlinux.ru)

+(require 'cyrillic-codepages-setup)

+

 ;; Set standard fontname specification of characters in the default

 ;; fontset to find an appropriate font for each charset.  This is used

 ;; to generate a font name for a fontset if the fontset doesn't

@@ -50,7 +54,12 @@

 	   (hebrew-iso8859-8 . ("*" . "ISO8859-8"))

 	   (katakana-jisx0201 . ("*" . "JISX0201"))

 	   (latin-jisx0201 . (nil . "JISX0201"))

-	   (cyrillic-iso8859-5 . ("*" . "ISO8859-5"))

+	   (cyrillic-iso8859-5 . (nil . "ISO8859-5"))

+; These are the other possibilities (alternatives);

+; We don't need to use them here (face-font-registry-alternatives 

+; will help us to use all the available Cyrillic fonts):

+;	   (cyrillic-iso8859-5 . (nil . "*-*1251"))

+;	   (cyrillic-iso8859-5 . (nil . "KOI8"))

 	   (latin-iso8859-9 . (nil . "ISO8859-9"))

 	   (japanese-jisx0208-1978 . ("*" . "JISX0208.1978"))

 	   (chinese-gb2312 . ("*" . "GB2312.1980"))

@@ -111,6 +120,7 @@

 (set-font-encoding "ISO8859-1" 'ascii 0)

 (set-font-encoding "JISX0201" 'latin-jisx0201 0)

+;(set-font-encoding "MICROSOFT-CP1251" 'cp1251 0)

 (define-ccl-program ccl-encode-unicode-font

   `(0

@@ -164,6 +174,7 @@

     ("iso8859-15" ascii latin-iso8859-15)

     ("tis620" ascii thai-tis620)

     ("koi8" ascii cyrillic-iso8859-5)

+    (".*1251" ascii cyrillic-iso8859-5)

     ("viscii" ascii vietnamese-viscii-upper vietnamese-viscii-lower)

     ("vscii" ascii vietnamese-viscii-upper vietnamese-viscii-lower)

     ("mulelao-1" ascii lao)

diff --exclude='*.orig' -duNr emacs-21.2.orig/lisp/international/mule-conf.el emacs-21.2/lisp/international/mule-conf.el

--- emacs-21.2.orig/lisp/international/mule-conf.el	2002-03-13 22:51:55 +0300

+++ emacs-21.2/lisp/international/mule-conf.el	2003-02-10 21:12:24 +0300

@@ -425,9 +425,12 @@

   '(("ISO8859-15" . latin-iso8859-15)

     ("ISO8859-14" . latin-iso8859-14)

     ("KOI8-R" . koi8-r)

+    ("KOI8-U" . koi8-u)

+    ("MICROSOFT-CP1251" . cp1251)

     ("BIG5-0" . big5))

   "Alist of font charset names defined by XLFD, and the corresponding Emacs

-charsets or coding systems.")

+charsets or coding systems. 

+(koi8-u and microsoft-cp1251 added by ALT Linux Team.)")

 ;; Functions to support "Non-Standard Character Set Encodings" defined

 ;; by the ICCCM spec.  We support that by converting the leading

diff --exclude='*.orig' -duNr emacs-21.2.orig/lisp/language/cyrillic.el emacs-21.2/lisp/language/cyrillic.el

--- emacs-21.2.orig/lisp/language/cyrillic.el	2003-02-10 21:08:57 +0300

+++ emacs-21.2/lisp/language/cyrillic.el	2003-02-10 21:32:05 +0300

@@ -221,7 +221,9 @@

   "CCL program to encode Cyrillic chars to KOI font.")

 (setq font-ccl-encoder-alist

-      (cons '("koi8" . ccl-encode-koi8-font) font-ccl-encoder-alist))

+      (cons '("koi8-r" . ccl-encode-koi8-font) font-ccl-encoder-alist))

+; We need a finer (than just "koi8") regexp in order

+; to encode & display Ukrainian correctly (with koi8-u).

 (set-language-info-alist

  "Cyrillic-KOI8" `((charset cyrillic-iso8859-5)

@@ -329,6 +331,113 @@

 		  (documentation . "Support for Cyrillic ALTERNATIVNYJ."))

  '("Cyrillic"))

+(define-coding-system-alias 'koi8-ru 'koi8-u)

+

+; Several CP1251, CP866 and CP1125 based environments. 

+;

+; They can be chosen without taking care

+; of (codepage-setup 1251) -- it is done automatically by pre-requiring the feature

+; cyrillic-codepages-setup. (The source for it is in cyrillic-codepages-setup.el.)

+;

+; Based on the postings in sisyphus@altlinux.ru mailing list, particularly

+; from Alexander Bokovoy and Serhii Hlodin.

+;

+; CP1251 support in not complete because it is based on iso-8859-5 (and there

+; are not all the letters, e.g. no "Ghe with upturn").

+;

+; The new language-environments descriptions added by this patch

+; make use of the key "prereq-features" of the language-info structure.

+; This key is not present in original GNU Emacs 21, the support for it

+; is added by another patch (or hack): emacs-21.1-lang-env-prereqs.patch.

+; The descriptions in this form can exist and work even if there is no support

+; for the new key -- then you have to manually require 'cyrillic-codepages-setup

+; or to evaluate a corresponding (codepage-setup ...) before you use them.

+; 

+; February 2002

+; imz@altlinux.ru

+

+(set-language-info-alist

+ "Cyrillic-CP1251" `((charset cyrillic-iso8859-5)

+		   (prereq-features cyrillic-codepages-setup)

+                   (coding-system cp1251)

+                   (coding-priority cp1251)

+                   (input-method . "cyrillic-jcuken")

+		   (nonascii-translation . cp1251-nonascii-translation-table)

+                   (unibyte-display . cp1251)

+		   (features cyril-util)

+                   (sample-text . "Russian (,L@caaZXY(B)       ,L7T`PRabRcYbU(B!")

+                   (documentation . "Support for Cyrillic CP1251. Added in ALT's distribution."))

+ '("Cyrillic"))

+

+(set-language-info-alist

+ "Belarusian" `((charset cyrillic-iso8859-5)

+		   (prereq-features cyrillic-codepages-setup)

+		 (coding-system cp1251)

+		 (coding-priority cp1251)

+		 (nonascii-translation . cp1251-nonascii-translation-table)

+		 (input-method . "cyrillic-belarusian")

+		 (unibyte-display . cp1251)

+		   (features cyril-util)

+                   (sample-text . "Belarusian (,L1U[P`caZPo(B ,L\^RP(B)   ,L4WU]l(B ,LT^Q`k(B!")

+		 (documentation . "Support for Belarusian language (with CP1251 coding system). Suggests an input method from additional `leim' package. Added in ALT's distribution."))

+ '("Cyrillic"))

+

+(set-language-info-alist

+ "Ukrainian-CP1251" `((charset cyrillic-iso8859-5)

+		   (prereq-features cyrillic-codepages-setup)

+		      (coding-system cp1251)

+		      (coding-priority cp1251)

+		      (nonascii-translation . cp1251-nonascii-translation-table)

+		      (input-method . "cyrillic-ukrainian")

+		      (unibyte-display . cp1251)

+		   (features cyril-util)

+		   (sample-text . "Ukrainian (,LCZ`Pw]alZP(B)	,L4^Q`^S^(B ,LT]o(B!")

+		      (documentation . "Support for Ukrainian language (with CP1251 coding system; incomplete). Suggests an input method from additional `leim' package. Added in ALT's distribution."))

+ '("Cyrillic"))

+

+

+(set-language-info-alist

+ "Cyrillic-CP866" `((charset cyrillic-iso8859-5)

+		   (prereq-features cyrillic-codepages-setup)

+                   (coding-system cp866)

+                   (coding-priority cp866)

+                   (input-method . "cyrillic-jcuken")

+		   (nonascii-translation . cp866-nonascii-translation-table)

+                   (unibyte-display . cp866)

+		   (features cyril-util)

+                   (sample-text . "Russian (,L@caaZXY(B)       ,L7T`PRabRcYbU(B!")

+                   (documentation . "Support for Cyrillic CP866. There is little difference between this one and Cyrillic-ALT. Added in ALT's distribution."))

+ '("Cyrillic"))

+

+(set-language-info-alist

+ "Ukrainian-CP1125" `((charset cyrillic-iso8859-5)

+		   (prereq-features cyrillic-codepages-setup)

+		      (coding-system cp1125)

+		      (coding-priority cp1125)

+		      (nonascii-translation . cp1125-nonascii-translation-table)

+		      (input-method . "cyrillic-ukrainian")

+		      (unibyte-display . cp1125)

+		   (features cyril-util)

+		   (sample-text . "Ukrainian (,LCZ`Pw]alZP(B)	,L4^Q`^S^(B ,LT]o(B!")

+		      (documentation . "Support for Ukrainian language (with CP1125 coding system). Suggests an input method from additional `leim' package. Added in ALT's distribution."))

+ '("Cyrillic"))

+

+; End of the block of CP1251, CP866 and CP1125 based language environments.

+

+; Some special X font encodings:

+

+(setq font-ccl-encoder-alist

+      (cons '("koi8-c" . ccl-encode-koi8-u-font) font-ccl-encoder-alist))

+; Apparantly, koi8-c is a coding for Extended (Old) Cyrillic which matches

+; koi8-u in all letter positions. Since we don't have a special coding-system

+; for it in Emacs, but there happen to be such X fonts (e.g., -val-*-koi8-c), we treat it

+; the same way as koi8-u.

+

+(setq font-ccl-encoder-alist

+      (cons '("koi8-1" . ccl-encode-koi8-font) font-ccl-encoder-alist))

+; koi8-1 was present in some older fonts.

+

+

 (provide 'cyrillic)

 ;;; cyrillic.el ends here

--- emacs-21.2.orig/lisp/textmodes/ispell.el	2003-02-10 21:08:57 +0300

+++ emacs-21.2/lisp/textmodes/ispell.el	2003-02-10 21:12:24 +0300

@@ -486,6 +486,7 @@

 		       (choice :tag "Character set"

 			       (const iso-8859-1)

 			       (const iso-8859-2)

+			       (const cp1251)

 			       (const koi8-u)

 			       (const koi8-r))))

   :group 'ispell)

--- emacs-21.3/man/gnus.texi.more-cyr	2003-03-24 23:15:53 +0300

+++ emacs-21.3/man/gnus.texi	2003-03-24 23:16:04 +0300

@@ -8020,6 +8020,7 @@

 encode using quoted-printable) or @code{t} (always use 8bit).

 @end table

+@cindex Ukrainian

 @cindex Russian

 @cindex koi8-r

 @cindex koi8-u

@@ -8040,14 +8041,14 @@

 This means that Russian will be encoded using @code{koi8-r} instead of

 the default @code{iso-8859-5} @sc{mime} charset.

-If you want to read messages in @code{koi8-u}, you can cheat and say

+If you want to write messages in @code{koi8-u}, you can say (no cheat:

+@code{koi8-u} is really supported now)

 @lisp

-(define-coding-system-alias 'koi8-u 'koi8-r)

+(put-charset-property 'cyrillic-iso8859-5

+                      'preferred-coding-system 'koi8-u)

 @end lisp

-This will almost do the right thing.

-

 And finally, to read charsets like @code{windows-1251}, you can say

 something like

--- emacs-21.3/man/mule.texi.more-cyr	2003-03-24 22:59:49 +0300

+++ emacs-21.3/man/mule.texi	2003-03-24 23:09:42 +0300

@@ -8,6 +8,7 @@

 @cindex multibyte characters

 @cindex encoding of characters

+@cindex Belarusian

 @cindex Celtic

 @cindex Chinese

 @cindex Cyrillic

@@ -25,6 +26,7 @@

 @cindex Lao

 @cindex Latin

 @cindex Polish

+@cindex Russian

 @cindex Romanian

 @cindex Slovak

 @cindex Slovenian

@@ -32,6 +34,7 @@

 @cindex Tibetan

 @cindex Turkish

 @cindex Vietnamese

+@cindex Ukrainian

 @cindex Dutch

 @cindex Spanish

   Emacs supports a wide variety of international character sets,

@@ -261,12 +264,13 @@

 @cindex Euro sign

 @quotation

-Chinese-BIG5, Chinese-CNS, Chinese-GB, Cyrillic-ALT, Cyrillic-ISO,

-Cyrillic-KOI8, Czech, Devanagari, Dutch, English, Ethiopic, German,

+Belarusian, Chinese-BIG5, Chinese-CNS, Chinese-GB, Cyrillic-ALT,

+Cyrillic-CP1251, Cyrillic-CP866, Cyrillic-ISO, Cyrillic-KOI8, 

+Cyrillic-KOI8-U, Czech, Devanagari, Dutch, English, Ethiopic, German,

 Greek, Hebrew, IPA, Japanese, Korean, Lao, Latin-1, Latin-2, Latin-3,

 Latin-4, Latin-5, Latin-8 (Celtic), Latin-9 (updated Latin-1, with the

 Euro sign), Polish, Romanian, Slovak, Slovenian, Spanish, Thai,

-Tibetan, Turkish, and Vietnamese.

+Tibetan, Turkish, Ukrainian-CP1125, Ukrainian-CP1251, and Vietnamese.

 @end quotation

 @cindex fonts for various scripts

@@ -367,7 +371,7 @@

   The simplest kind of input method works by mapping ASCII letters

 into another alphabet; this allows you to use one other alphabet

-instead of ASCII.  The Greek and Russian input methods

+instead of ASCII.  The Greek and Cyrillic (e.g. Russian) input methods

 work this way.

   A more powerful technique is composition: converting sequences of

--- emacs-21.1.orig/etc/HELLO	Sat Sep 29 14:13:44 2001

+++ emacs-21.1/etc/HELLO	Sat Feb 16 18:07:39 2002

@@ -4,6 +4,7 @@

 ---------------------------------------------------------

 Amharic	($(3"c!<!N"^(B)	$(3!A!,!>(B

 Arabic			(38R(47d(3T!JSa(4W(3W(B

+Belarusian (,L1U[P`caZPo(B ,L\^RP(B) ,L4WU]l(B ,LT^Q`k(B!

 Czech (,Bh(Besky)		Dobr,B}(B den

 Danish (Dansk)		Hej, Goddag

 English			Hello

@@ -31,6 +32,7 @@

 Tibetan (4$(7"7r'"]0"7"]14"20"21!;4%P0"G#!"Q14"20"21!;(B)	4$(7"70"714$P0"!#C"Q1!;4"Er'"S0"E"S14"G0"G1!;4"70"714"2r'"[0"2"[1!;4"Dr'"[0"D"[14"#0"#14"G0"G1!>(B

 Tigrigna ($(3"8#r!N"^(B)	$(3!Q!,!<"8(B

 Turkish (T,M|(Brk,Mg(Be)	Merhaba

+Ukrainian (,LCZ`Pw]alZP(B ,L\^RP(B) ,L?`XRvb(B!

 Vietnamese (Ti,1*(Bng Vi,1.(Bt)	Ch,1`(Bo b,1U(Bn

 Japanese ($BF|K\8l(B)		$B$3$s$K$A$O(B, (I:]FAJ(B

--- emacs-21.3/lisp/international/mule-cmds.el.more-cyr2	2003-03-25 00:12:53 +0300

+++ emacs-21.3/lisp/international/mule-cmds.el	2003-03-25 00:24:21 +0300

@@ -1669,7 +1669,8 @@

     ; ay Aymara

     ; az Azerbaijani

     ; ba Bashkir

-    ("be" . "Latin-5") ; Belarusian [Byelorussian until early 1990s]

+    ("be.*[_.]cp1251" . "Belarusian") ; Belarusian [Byelorussian until early 1990s]

+    ("be" . "Belarusian") ; Belarusian [Byelorussian until early 1990s]

     ("bg" . "Latin-5") ; Bulgarian

     ; bh Bihari

     ; bi Bislama

@@ -1754,7 +1755,11 @@

     ("rm" . "Latin-1") ; Rhaeto-Romanic

     ; rn Kirundi

     ("ro" . "Romanian")

+    ("ru[_.]ua[_.]cp1251" . "Ukrainian-CP1251") ; Russian in Ukraine

+    ("ru[_.]ua[_.]koi8-u" . "Cyrillic-KOI8-U") ; Russian in Ukraine

+    ("ru.*[_.]cp1251" . "Cyrillic-CP1251") ; Russian

     ("ru.*[_.]koi8-r" . "Cyrillic-KOI8") ; Russian

+    ; ru.*[_.]pt154 Russian

     ("ru" . "Cyrillic-ISO") ; Russian

     ; rw Kinyarwanda

     ("sa" . "Devanagari") ; Sanskrit

@@ -1788,7 +1793,10 @@

     ; tt Tatar

     ; tw Twi

     ; ug Uighur

-    ("uk" . "Cyrillic-ISO") ; Ukrainian

+    ("uk.*[_.]cp1251" . "Ukrainian-CP1251") ; Ukrainian

+    ("uk.*[_.]cp1125" . "Ukrainian-CP1125") ; Ukrainian

+    ("uk.*[_.]koi8-u" . "Cyrillic-KOI8-U") ; Ukrainian

+    ("uk" . "Cyrillic-KOI8-U") ; Ukrainian

     ; ur Urdu

     ; uz Uzbek

     ("vi" . "Vietnamese")

@@ -1832,6 +1840,7 @@

     (".*8859[-_]?2\\>" . "Latin-2")

     (".*8859[-_]?3\\>" . "Latin-3")

     (".*8859[-_]?4\\>" . "Latin-4")

+    (".*8859[-_]?5\\>" . "Cyrillic-ISO")

     (".*8859[-_]?9\\>" . "Latin-5")

     (".*8859[-_]?14\\>" . "Latin-8")

     (".*8859[-_]?15\\>" . "Latin-9")