%%%% email-ru.tex
%% Author: Laurent Siebenmann,
%% Math B^at 425, Univ. Paris-Sud, 91405-Orsay
%% Email addresses: (use several)
[email protected],
%%
[email protected],
[email protected]
%%
%% Version 2001.02.06 of Feb 2001 (**beta**)
%%
http://topo.math.u-psud.fr/~lcs/ASCII-Cyrillic/
%% Look for future versions on CTAN archives.
%%
%% Copyright conditions according to Gnu Public Licence.
%%
%% This utility converts a new *lossless* ASCII
%% transcription of Russian/Ukrainian text
%% -- called ASCII-Cyrillic --
%% to and from the 5 most used 8-bit Cyrillic
%% text file encodings. (Others can be introduced.)
%%
%% "email-ru.tex" is particularly useful for
%% persons outside of Russia obliged to use
%% a non-Cyrillic keyboard for typing Russian.
%%
%% It is also good for viewing Cyrillic
%% text files (including ".tex" files)
%% when one has no suitable Cyrillic screen font.
%%
%% It allows Cyrillic 8-bit text files to be sent
%% in the body of any email message.
%% This feature inspired the name "email-ru.tex".
%%
%% Launch "Plain TeX" of D. Knuth on this file.
%% The usual command line is simply:
%% tex email-ru <return>
%% Then follow instructions given on screen.
%% Documentation follows the last \endinput.
%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%% Params and Tools %%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\catcode`\@=11
\catcode`\/=13
\catcode`\|=13
\chardef\CatOne@=\catcode1\relax %% storage
\catcode1=13 % A syntactical trick for AccIN
%% \HiOctetsCat@{13} will be in force for assimilation
\errorcontextlines=20
\let\ex@\expandafter
\let\cs@\csname
\let\ecs@\endcsname
\let\ne@\noexpand
\def\@e{}
\endlinechar=-1
\def\Sharp@{\string##}
%%temporarily suppress Plain's logging of allocations
\let\wlog@ld\wlog
\def\wlog#1{\relax}
\newif \ifGoodOptions@
\def\empty{}
\def\Line@{}
\ex@\def\cs@ email-ru-version\ecs@{v2001.02.06}
%% Will use loops with fuller syntax
\def\Loop@#1\Repeat@{%
\def\Iterate@{#1\expandafter\Iterate@\fi}%
\Iterate@}
\def\iwr@{\immediate\write16}%
\def\wr@{\immediate\write\MainStreamOut@}%
%\def\Wr@#1{\iwr@{#1}\wr@{#1}} %% for tests
\let\Wr@\wr@ %% for tests
%\def\@EndLine{}%
\def\Gobble@#1{}%
\edef\OtherBacksl@{\ex@\Gobble@\string\\}%
\def\ExpTwiceAfter@{\ex@\ex@\ex@}%
\def\ExpThriceAfter@{\ex@\ExpTwiceAfter@\ex@}%
\def\ExpFourTimesAfter@{\ex@\ExpThriceAfter@\ex@}%
\ifx\undefined\@@end
\let\End\end
\else
\def\End{\cs@ @@end\ecs@}
\fi
%%%% WORD-PROCESSING MACROS from boxedeps.tex
%% %% \long was evicted for email-ru
%%% \IN@0#1@#2@ : Is 1st exp of #1 in 1st exp of #2 ??
%% Answer in \ifIN@
%\let\ex@\expandafter
\newif\ifIN@\def\IN@{\ex@\INN@\ex@}
\def\INN@0#1@#2@{\def\NI@##1#1##2##3\ENDNI@
{\ifx\m@rker##2\IN@false\else\IN@true\fi}%
\ex@\NI@#2@@#1\m@rker\ENDNI@}
\def\m@rker{\m@@rker}
%%% \SPLIT@0#1@#2@ : Split 1st exp of #2 at 1st exp of #1
%% \Initialtoks@ , \Terminaltoks@ will contain pieces
\newtoks\Initialtoks@ \newtoks\Terminaltoks@
\def\SPLIT@{\ex@\SPLITT@\ex@}
\def\SPLITT@0#1@#2@{\def\TTILPS@##1#1##2@{%
\Initialtoks@{##1}\Terminaltoks@{##2}}\ex@\TTILPS@#2@}
%%% \CHAIN@
\newtoks\Chaintoks@
\newtoks\Linktoks@
\def\CHAIN@{%
\edef\Chainholder@{\the\Chaintoks@\the\Linktoks@}%
\Chaintoks@\ex@{\Chainholder@}%
}
\newlinechar=`\^^J
\def\ChainLine@{\Linktoks@\ex@{\ex@^^J\Line@}\CHAIN@}
%%%%% ARITHMETIC MACRO \SetCharValue@#1
%% Supposing #1 has 1st expansion a character cat 11 ot 12
%% assign the octet to byte register \Char@
\def\SetCharValue@#1{\ex@\chardef\ex@\Char@\ex@`#1\relax}
%% \def\mac{a}\SetCharValue@{a}
%% \show\Char@\end
%%%%% \HiOctetsCat@#1
%%%
\def\HiOctetsCat@#1{%
\count255=128\relax
\Loop@
\catcode\count255=#1\relax
\advance\count255 by 1\relax
\ifnum
\count255<256\relax
\Repeat@
}
%%%%% \LowOctetsCat@#1
%%%
\def\LowOctetsCat@#1{%
\count255=0\relax
\Loop@
\catcode\count255=#1\relax
\advance\count255 by 1\relax
\ifnum
\count255<32\relax
\Repeat@
\catcode127=#1\relax
}
%%%%% \ASCIIOctetsCat@#1
%%%
\def\ASCIIOctetsCat@#1{%
\count255=32\relax
\Loop@
\catcode\count255=#1\relax
\advance\count255 by 1\relax
\ifnum
\count255<126\relax
\Repeat@
}
\def\MakeSlantPct@{\lccode`\~=`\%
\lowercase{\edef/{\string ~}}}%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%% Tables %%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%% \@LigShorts...: Ru and Ukr variants
%% was \@HiOctetLigOutEncoding
\def\@LigShortsRu{%
/A A /B B /V V /G G /D D /E E /ZH ZH /Z Z %
/I I /ISHRT J /K K /L L /M M /N N /O O /P P %
/R R /S S /T T /U U /F F /H X /C TS /CH CH %
/SH SH /SHCH SHCH /HRDSN " %
/ERY Y /SFTSN ' /EREV E /YU JU /YA JA /YO E %
/a a /b b /v v /g g /d d /e e /zh zh /z z %
/i i /ishrt j /k k /l l /m m /n n /o o /p p %
/r r /s s /t t /u u /f f /h x /c ts /ch ch %
/sh sh /shch shch /hrdsn " %
/ery y /sftsn ' /erev e /yu ju /ya ja /yo e %
/USHRT U /ushrt u %% Byelorussian
/II II /ii ii %% Byelorussian (& Ukr)
%/textnumero No %
%/guillemotleft << %
%/guillemotright >> %
}
%%%%%% \@LigShortsUkr
%%% program also treats word-beginning phenomena:
%%% '{IE} => Ye, '{YI} => Yi, '{ISHRT} => Y
%%% '{YU} => Yu, '{YA} => Ya; also lower case
\def\@LigShortsUkr{\let\temp@=\0 \def\0{}%
/A A /B B /V V /G H /GUP G /D D /E E /IE IE /ZH ZH /Z Z %
/I Y /II I /YI I /ISHRT I /K K /L L /M M /N N /O O /P P %
/R R /S S /T T /U U /F F /H KH /C TS /CH Ch %
/SH Sh /SHCH Shch %% /HRDSN gone!
/APOS ' %
/SFTSN \0 /YU Iu /YA Ia %% avoid missing space problem
/a a /b b /v v /g h /gup g /d d /e e /ie ie /zh zh /z z %
/i y /ii i /yi i /ishrt i /k k /l l /m m /n n /o o /p p %
/r r /s s /t t /u u /f f /h kh /c ts /ch ch %
/sh sh /shch shch %% /hrdsn gone!
/sftsn \0 /yu iu /ya ia %% avoid missing space problem
/apos ' %
%/textnumero No %
%/guillemotleft << %
%/guillemotright >> %
\let\0=\temp@
}
%%%%% \@SetLigShorts: %% 8 to 7
%% s_ means short as function of LaTeX Tag
\def\@SetLigShorts{%
\def/##1 ##2 {\ex@\edef\cs@ ts_##1\ecs@{##2}%
}
\@TheLigShorts
}
%%%%%% \@AccShortsRu \@AccShortsUkr
\def\@AccShortsRu{%
/A A /B B /V V /G G /D D /E E /ZH 'G /ZH 'Z /Z Z %
/I I /ISHRT J /K K /L L /M M /N N /O O /P P %
/R R /S S /T T /U U /F F /H 'K /H X /C C /C 'T %% last dominates
/CH 'C /SH 'S /SH W /SHCH 'W /HRDSN Q %
/ERY Y /SFTSN H /EREV 'E /YU 'U /YA 'A /YO 'O %
/a a /b b /v v /g g /d d /e e /zh 'g /zh 'z /z z %
/i i /ishrt j /k k /l l /m m /n n /o o /p p %
/r r /s s /t t /u u /f f /h 'k /h x /c c /c 't /ch 'c %
/sh 's /sh w /shch 'w /hrdsn q %
/ery y /sftsn h /erev 'e /yu 'u /ya 'a /yo 'o %
%% Byelorussian
/USHRT 'V /ushrt 'v %% Byelorussian only
/II 'I /ii 'i %% Byelorussian (& Ukr but then I,i)
%% Following of questionable benefit
%/textnumero 'N %
%/guillemotleft '< %
%/guillemotright '> %
}
\def\@AccShortsUkr{%
/A A /B B /V V /G H /G G % preferred last
/GUP 'G /D D /E E /IE 'E /ZH 'Z /Z Z %
/I Y /II I /YI 'I /ISHRT J /K K /L L /M M /N N /O O /P P %
/R R /S S /T T /U U /F F /H 'K /H X /C C /C 'T /CH 'C %
/SH 'S /SH W /SHCH 'W %% HRDSN not Ukr
/YA 'A /YU 'U /SFTSN Q %% /YO 'O
/APOS '* %
%
/a a /b b /v v /g h /g g % preferred last
/gup 'g /d d /e e /ie 'e /zh 'z /z z %
/i y /ii i /yi 'i /ishrt j /k k /l l /m m /n n /o o /p p %
/r r /s s /t t /u u /f f /h 'k /h x /c c /c 't /ch 'c %
/sh 's /sh w /shch 'w %% hrdsn not ukr
/ya 'a /yu 'u /sftsn q %% /yo 'o
%
/apos '* %
}
\def\@SetAccOutShorts{%
\def/##1 ##2 {\ex@\def\cs@ ts_##1\ecs@{##2}}%
\@TheAccShorts
}
\def\@SetAccInShortsA{%
\def/##1 ##2 {\ex@\def\cs@ ts_##1\ecs@{##2}%
\ex@\edef\cs@ to_##1\ecs@{'\lbrace@##1\rbrace@}%% prelim background
}
\@TheAccShorts
}
\def\@SetAccInShortsB{%
\def/##1 ##2 {\ex@\edef\cs@ so_##2\ecs@{\cs@ to_##1\ecs@}}%
\@TheAccShorts
}
%%%%%%% \@LetterTags
%% list of all Cyrillic letter alphabetic tags used
%\def\@LetterTags{%
% %% Russian
% /A A /B B /V V /G G /D D /E E /ZH 'Z /Z Z %
% /I I /ISHRT J /K K /L L /M M /N N /O O /P P %
% /R R /S S /T T /U U /F F /H X /C 'T /CH C %
% /SH W /SHCH 'W /HRDSN Q %
% /ERY Y /SFTSN H /EREV 'E /YU 'U /YA 'A /YO 'O %
% %% + for Ukr, Byelorussian, Yug, Macedonian
% /DJE /DZE /DZHE /GJE /GUP /GUP /IE /II %
% /JE /KJE /LJE /NJE /TSJE /USHRT /YI %
% /APOS %
% %% + for Tatar and other
% /CHVCRS /KBEAK /NDSC /OTLD /SCHWA /SHHA /VCRS
% /Y /ZHDSC
% }
%%%%%% \@IdentifyAccInLetterTags
% %% \te_<tag> --> \@e if abstract letter exists else \relax
%\def\@IdentifyAccInLetterTags{%
% \def/##1 {\ex@\def\cs@ te_##1\ecs@{}}%
% \@LetterTags}
%%%%%%% \@DiacriticStrings
%% table with 3 columns, / active three arg
%% #1 = LaTeX tag if known, #2 = short in letters,
%% #3 short in freestyle.%
%% | gives syntactical workaround
%% to be '[<thestring>]
\def\@DiacriticStrings{%
/Delta,Delta,Delta.%
|{quotedblbase}{LLQ}{,,}%
|{quotesinglbase}{llq}{,}%
/textquotedblleft,LQ,``.%
/textquotedblright,RQ,".
%%/textquotedblright,RQ,''.% omit?????????????
%% double fails to define '["] last one wins
%% simply because only the map T --> S tag
%% to short tag currently used
/textquoteleft,lq,`.%
/textquoteright,rq,'.%
/textnumero,No,No.%
/textblacksquare,blacksquare,blacksquare.%
/paragraph,par,P.%
/section,section,S.%
/approx,approx,\string~\string~.%
/textbullet,bullet,**.%
/textperiodcentered,cdot,cdot.%
/textbrokenbar,bbar,bbar.%
/textcent,cent,cent.%
/copyright,cp,copyright.%
/textcurrency,coin,currency.%
/dagger,dag,dag.%
/ddagger,ddag,ddag.%
/degree,deg,deg.%
/divide,divide,div.%
|{dots}{dots}{...}%
/euro,euro,euro.
/florin,florin,florin.%
/lnot,lnot,neg.%
/lessequal,leq,<=.%
/greaterequal,geq,>=.%
/guillemotleft,LG,<<.%
/guillemotright,RG,>>.%
/guilsinglleft,lg,<.%
/guilsinglright,rg,>.%
/infinity,infty,infty.%
/mu,mu,mu.%
/nobreakspace,nbsp,nbsp.%
/textemdash,emdash,---.%
/textendash,endash,--.%
|{notequal}{neq}{\string/=}%
/perthousand,perK,perK.%
/partialdiff,partial,partial.%
/pounds,pounds,pounds.%
/plusminus,pm,+-.%
/textregistered,reg,registered.%
/softhyphen,shy,\string\-.
/solidus,solidus,solidus.
/radical,surd,surd.%
/texttrademark,tm,trademark.%
%/ukrhard,rq,'.%
}
%%%%% \@SetDiacShorts defines some \TS_<tag> --> <7short>
%% Caps for diacritics, T for my tex tag, S for short
%% Extracts info from \@DiacriticStrings
\def\@SetDiacShorts{%
\def/##1,##2,##3.{\ex@\edef\cs@ TS_##2\ecs@{##3}}%
\def|##1##2##3{\ex@\edef\cs@ TS_##2\ecs@{##3}}%
\@DiacriticStrings
}
%%%%%%%% Encoding Vectors
%% Each defines meanings for 128--255
%% /??. letter with tag ??
%% |??. non-letter with tag ??
%% /. undefined 'meaningless'
%% /apos. Cyrillic apostrophe if used by language
%% and otherwise equivalent to |rq. (right quote)
%%%%%%% DosEncoding
%% Creator: Microsoft DOS code page 866
%% LaTeX Tag: cp866nav
%% Comment: Covers Russian, Byelorussian, Ukrainian
%%+ Many variants exist.
%%+ This is the New Alternative Variant (NAV)
\def\DosEncodingVect@{%
/A./B./V./G./D./E./ZH./Z.%% "80--
/I./ISHRT./K./L./M./N./O./P.%% --"8F
/R./S./T./U./F./H./C./CH.%% "90--
/SH./SHCH./HRDSN./ERY./SFTSN./EREV./YU./YA.%% --"9F
/a./b./v./g./d./e./zh./z.%% "A0--
/i./ishrt./k./l./m./n./o./p.%% --"AF
\.\.\.\.\.\.\.\.%% "B0--
\.\.\.\.\.\.\.\.%% --"BF
\.\.\.\.\.\.\.\.%% "C0--
\.\.\.\.\.\.\.\.%% --"CF
\.\.\.\.\.\.\.\.%% "D0--
\.\.\.\.\.\.\.\.%% --"DF
/r./s./t./u./f./h./c./ch.%% "E0--
/sh./shch./hrdsn./ery./sftsn./erev./yu./ya.%% --"EF
/YO./yo./GUP./gup./IE./ie./II./ii.%% "F0--
/YI./yi./USHRT./ushrt.|No.|LG.|RG.|nbsp.%% --"FF
}
%%%%%%% MacEncoding
%% LaTeX Tag: macukr
%% Comment: Covers Russian, Byelorussian, Ukrainian
\def\MacEncodingVect@{%
/A./B./V./G./D./E./ZH./Z.%% "80--
/I./ISHRT./K./L./M./N./O./P.%% --"8F
/R./S./T./U./F./H./C./CH.%% "90--
/SH./SHCH./HRDSN./ERY./SFTSN./EREV./YU./YA.%% --"9F
|dag.|deg./GUP.|pounds.|section.|cdot.|par./II.%% "A0--
|reg.|cp.|tm./TSJE./tsje.|neq./GJE./gje.%% --"AF
|infty.|pm.|leq.|geq./ii.|mu./gup./JE.%% "B0--
/IE./ie./YI./yi./LJE./lje./NJE./nje.%% --"BF
/je./DZE.|lnot.|surd.|florin.|approx.|Delta.|LG.%% "C0--
|RG.|dots.|nbsp./DJE./dje./KJE./kje./dze.%% --"CF
|endash.|emdash.|LQ.|RQ.|lq.\apos.|divide.|LLQ.%% "D0--
/USHRT./ushrt./DZHE./dzhe.|No./YO./yo./ya.%% --"DF
/a./b./v./g./d./e./zh./z.%% "E0--
/i./ishrt./k./l./m./n./o./p.%% --"EF
/r./s./t./u./f./h./c./ch.%% "F0--
/sh./shch./hrdsn./ery./sftsn./erev./yu.|coin.%% --"FF
}
%%%%%%% IsoEncoding
%% LaTeX Tag: ISO88595
%% Comment: ISO~8859-5 also called ISO-IR-144
%% Covers Russian, Byelorussian
%%+ but letter GUP gup of Ukrainian is missing
\def\IsoEncodingVect@{%
\.\.\.\.\.\.\.\.%% "80--
\.\.\.\.\.\.\.\.%% --"8F
\.\.\.\.\.\.\.\.%% "90--
\.\.\.\.\.\.\.\.%% --"9F
|nbsp./YO./TSJE./GJE./IE./DZE./II./YI.%% "A0--
/JE./LJE./NJE./DJE./KJE.|shy./USHRT./DZHE.%% --"AF
/A./B./V./G./D./E./ZH./Z.%% "B0--
/I./ISHRT./K./L./M./N./O./P.%% --"BF
/R./S./T./U./F./H./C./CH.%% "C0--
/SH./SHCH./HRDSN./ERY./SFTSN./EREV./YU./YA.%% --"CF
/a./b./v./g./d./e./zh./z.%% "D0--
/i./ishrt./k./l./m./n./o./p.%% --"DF
/r./s./t./u./f./h./c./ch.%% "E0--
/sh./shch./hrdsn./ery./sftsn./erev./yu./ya.%% --"EF
|No./yo./tsje./gje./ie./dze./ii./yi.%% "F0--
/je./lje./nje./dje./kje.|section./ushrt./dzhe.%% --"FF
}
%%
%%%%%%% WinEncoding
%% LaTeX Tag: cp1251
%% Comment: Microsoft Windows Cyrillic encoding
%%+ covers Russian, Byelorussian, Ukrainian
\def\WinEncodingVect@{%
/TSJE./GJE.|llq./gje.|LLQ.|dots.|dag.|ddag.%% "80--
|euro.|perK./LJE.|lg./NJE./KJE./DJE./DZHE.%% --"8F
/tsje.|lq.\apos.|LQ.|RQ.|bullet.|endash.|emdash.%% "90--
|solidus.|tm./lje.|rg./nje./kje./dje./dzhe.%% --"9F
|nbsp./USHRT./ushrt./JE.|coin./GUP.|bbar.|section.%% "A0--
/YO.|cp./IE.|LG.|lnot.|shy.|reg./YI.%% --"AF
|deg.|pm./II./ii./gup.|mu.|par.|cdot.%% "B0--
/yo.|No./ie.|RG./je./DZE./dze./yi.%% --"BF
/A./B./V./G./D./E./ZH./Z.%% "C0--
/I./ISHRT./K./L./M./N./O./P.%% --"CF
/R./S./T./U./F./H./C./CH.%% "D0--
/SH./SHCH./HRDSN./ERY./SFTSN./EREV./YU./YA.%% --"DF
/a./b./v./g./d./e./zh./z.%% "E0--
/i./ishrt./k./l./m./n./o./p.%% --"EF
/r./s./t./u./f./h./c./ch.%% "F0--
/sh./shch./hrdsn./ery./sftsn./erev./yu./ya.%% --"FF
}
%
%%%%%%% KoiEncoding "universal version"
%% LaTeX Tag: koi8-u
%% Comment: Russian, Byelorussian, Ukrainian
%%+ Devised for Internet use, 1993.
%%+ -u means 'unified'(?)
\def\KoiEncodingVect@{%
\.\.\.\.\.\.\.\.%% "80--
\.\.\.\.\.\.\.\.%% --"8F
\.|lq.\apos.|LQ.|RQ.|bullet.|endash.|emdash.%% "90--
|cp.|tm.|nbsp.|RG.|reg.|LG.|cdot.|coin.%% --"9F
|nbsp./tsje./gup./yo./ie./dze./ii./yi.%% "A0--
/je./lje./nje./dje./kje./gup./ushrt./dzhe.%% --"AF
|No./TSJE./GUP./YO./IE./DZE./II./YI.%% "B0--
/JE./LJE./NJE./DJE./KJE./GUP./USHRT./DZHE.%% --"BF
/yu./a./b./c./d./e./f./g.%% "C0--
/h./i./ishrt./k./l./m./n./o.%% --"CF
/p./ya./r./s./t./u./zh./v.%% "D0--
/sftsn./ery./z./sh./erev./shch./ch./hrdsn.%% --"DF
/YU./A./B./C./D./E./F./G.%% "E0--
/H./I./ISHRT./K./L./M./N./O.%% --"EF
/P./YA./R./S./T./U./ZH./V.%% "F0--
/SFTSN./ERY./Z./SH./EREV./SHCH./CH./HRDSN.%% --"FF
}
%%%%%%% NullEncoding
%%
\def\NullEncodingVect@{%
\.\.\.\.\.\.\.\.%% "80--
\.\.\.\.\.\.\.\.%% --"8F
\.\.\.\.\.\.\.\.%% "90--
\.\.\.\.\.\.\.\.%% --"9F
\.\.\.\.\.\.\.\.%% "A0--
\.\.\.\.\.\.\.\.%% --"AF
\.\.\.\.\.\.\.\.%% "B0--
\.\.\.\.\.\.\.\.%% --"BF
\.\.\.\.\.\.\.\.%% "C0--
\.\.\.\.\.\.\.\.%% --"CF
\.\.\.\.\.\.\.\.%% "D0--
\.\.\.\.\.\.\.\.%% --"DF
\.\.\.\.\.\.\.\.%% "E0--
\.\.\.\.\.\.\.\.%% --"EF
\.\.\.\.\.\.\.\.%% "F0--
\.\.\.\.\.\.\.\.%% --"FF
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\HiOctetsCat@{13}
\def\HighActiveOctetsHolder@{%
/^^80 80 /^^81 81 /^^82 82 /^^83 83 /^^84 84 /^^85 85 /^^86 86 %
/^^87 87 /^^88 88 /^^89 89 /^^8a 8a /^^8b 8b /^^8c 8c /^^8d 8d %
/^^8e 8e /^^8f 8f /^^90 90 /^^91 91 /^^92 92 /^^93 93 /^^94 94 %
/^^95 95 /^^96 96 /^^97 97 /^^98 98 /^^99 99 /^^9a 9a /^^9b 9b %
/^^9c 9c /^^9d 9d /^^9e 9e /^^9f 9f /^^a0 a0 /^^a1 a1 /^^a2 a2 %
/^^a3 a3 /^^a4 a4 /^^a5 a5 /^^a6 a6 /^^a7 a7 /^^a8 a8 /^^a9 a9 %
/^^aa aa /^^ab ab /^^ac ac /^^ad ad /^^ae ae /^^af af /^^b0 b0 %
/^^b1 b1 /^^b2 b2 /^^b3 b3 /^^b4 b4 /^^b5 b5 /^^b6 b6 /^^b7 b7 %
/^^b8 b8 /^^b9 b9 /^^ba ba /^^bb bb /^^bc bc /^^bd bd /^^be be %
/^^bf bf /^^c0 c0 /^^c1 c1 /^^c2 c2 /^^c3 c3 /^^c4 c4 /^^c5 c5 %
/^^c6 c6 /^^c7 c7 /^^c8 c8 /^^c9 c9 /^^ca ca /^^cb cb /^^cc cc %
/^^cd cd /^^ce ce /^^cf cf /^^d0 d0 /^^d1 d1 /^^d2 d2 /^^d3 d3 %
/^^d4 d4 /^^d5 d5 /^^d6 d6 /^^d7 d7 /^^d8 d8 /^^d9 d9 /^^da da %
/^^db db /^^dc dc /^^dd dd /^^de de /^^df df /^^e0 e0 /^^e1 e1 %
/^^e2 e2 /^^e3 e3 /^^e4 e4 /^^e5 e5 /^^e6 e6 /^^e7 e7 /^^e8 e8 %
/^^e9 e9 /^^ea ea /^^eb eb /^^ec ec /^^ed ed /^^ee ee /^^ef ef %
/^^f0 f0 /^^f1 f1 /^^f2 f2 /^^f3 f3 /^^f4 f4 /^^f5 f5 /^^f6 f6 %
/^^f7 f7 /^^f8 f8 /^^f9 f9 /^^fa fa /^^fb fb /^^fc fc /^^fd fd %
/^^fe fe /^^ff ff }%% watch space before brace
%%% (what about CR and linefeed?)
\begingroup
\LowOctetsCat@{13}%% localized
%\global\let^^0c=\relax %% Textures? Plain?; poluting??
\let^^0c=\relax %% localized
\gdef\LowActiveOctetsHolder@{%% watch gdef; will cleanup after
/^^00 00 /^^01 01 /^^02 02 /^^03 03 /^^04 04 /^^05 05 /^^06 06 %
/^^07 07 /^^08 08 /^^09 09 /^^0a 0a /^^0b 0b /^^0c 0c /^^0d 0d %
/^^0e 0e /^^0f 0f /^^10 10 /^^11 11 /^^12 12 /^^13 13 /^^14 14 %
/^^15 15 /^^16 16 /^^17 17 /^^18 18 /^^19 19 /^^1a 1a /^^1b 1b %
/^^1c 1c /^^1d 1d /^^1e 1e /^^1f 1f /^^7f 7f }
\endgroup
\let^^0c=\relax %% was \par for Textures
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% TRANSLATION MACROS %%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% Make sure chars >= 127 are ordinary (lccodes = 0)
%%%% This is default maybe to be changed
\def\HiOctetsZeroLCcodes@{%
\count255=128\relax
\Loop@
\lccode\count255=0\relax
\advance\count255 by 1\relax
\ifnum
\count255<256\relax
\Repeat@
}
%%%%% \PrepMoreLiveAccIn@
%% is one of two:
\def\PrepMoreLiveAccIn@{% maybe < and >
%%% \maybe@excl##1 : is tag active-alpha ??
\def\maybe@excl##1{%
\ifnum \lccode`##1>0 \@e
\ex@\@excl\ex@##1%% DON'T put tracer (...) on this line!
\else
\ex@##1%% nor this line --- because of macro soiling
\fi}
%
\lccode`.=`\}%
%%% \CyrLetter@##1: <diactag> --> \TO_ or puke
\lowercase{\def\CyrLetter@##1.{%
\ex@\ifx\cs@ to_\maybe@excl##1^^A\ecs@\relax
\(CyrLetter@_cont)'\lbrace@\CyrUniv@@##1.%
\else
\(CyrLetter@_bingo)\ex@\ex@\cs@ to_\maybe@excl##1^^A\ecs@
%% \(CyrDiac@_bingo)
\fi}}%%
\lccode`.=0%
%\show\CyrLetter@
%
%%% \CyrDiac@##1: <diactag> --> \TO_ or puke
\def\CyrDiac@##1]{%
\ex@\ifx\cs@ TO_\maybe@excl##1^^A\ecs@\relax
\(CyrDiac@_cont)'[\CyrUniv@@##1]%
\else
\(CyrDiac@_bingo)\ex@\ex@\cs@ TO_\maybe@excl##1^^A\ecs@
%% \(CyrDiac@_bingo)
\fi}%
%
%%% \CyrUniv@@##1 : second depth
\def\CyrUniv@@##1{%
\ifnum \lccode`##1>0 \@e
\(CyrUniv@@_lc)\string##1\ex@\@c@excl %%
\else
\ifx##1\@Excl
\(CyrUniv@@_e)\ex@\ex@\ex@\CyrUniv@@excl
\else
\(CyrUniv@@_o)\ex@\ex@\ex@##1%
\fi
\fi}
%
%%% \CyrUniv@@excl##1 : third depth
\def\CyrUniv@@excl##1{%
\ifnum \lccode`##1>0 \@e
\(CyrUniv@@excl_lc)\ex@ ##1%% do buggerall%%
\else
\ifx##1\@Excl
\(CyrUniv@@excl_Excl)\string!%% (@bs@excl_Excl)
\else
\if\noexpand ##1\string_%
\(CyrUniv@@excl_h)\ExpThriceAfter@\@@UlnCheck %%
\else
\(CyrUniv@@excl_o)\string!\ExpThriceAfter@ ##1%%
\fi
\fi
\fi
}%
%
\uccode`<=`<
\ex@\edef\cs@ so_'<\ecs@{\cs@ TO_LG\ecs@}%
\uccode`>=`>
\ex@\edef\cs@ so_'>\ecs@{\cs@ TO_RG\ecs@}%
\uccode`N=`N
\ex@\edef\cs@ so_'N\ecs@{\cs@ TO_No\ecs@}%
%
%%% Define \TO_"
%% Wanted the '["] --> (exp of) \TO_RQ, but table
%% only gave TS_
\ex@\ifx\cs@ TO_RQ\ecs@\relax
\ex@\edef\cs@ TO_"\ecs@{'["]}%
\else
\ex@\edef\cs@ TO_"\ecs@{\cs@ TO_RQ\ecs@}%
\fi
%\ex@\show\cs@ TO_"\ecs@
%
%%% Following are crucial and delicate matters
\uccode`\{=`\{
\ex@\let\cs@ so_'\lbrace@\ecs@\CyrLetter@
%% \so_<lbrace>#1=\CyrLetter@#1
\uccode`\[=`\[
\ex@\let\cs@ so_'[\ecs@\CyrDiac@ %
\ex@\def\cs@ so_''\ecs@{'}%
%
}%
\def\PrepMoreLiveRuAccIn@{%
\PrepMoreLiveAccIn@
%%% Following for rq-APOS confluence (Russian)
%% Here we know APOS has no short form
%\ex@\show\cs@ to_APOS\ecs@
%\ex@\show\cs@ TO_rq\ecs@
\ex@
\ifx\cs@ TO_rq\ecs@\relax
\else\ex@
\ifx\cs@ to_APOS\ecs@\relax %% is def needed?
\ex@\edef\cs@ to_APOS\ecs@{\cs@ TO_rq\ecs@}%
\ex@\edef\cs@ to_apos\ecs@{\cs@ TO_rq\ecs@}%
\fi
\fi
%\ex@\show\cs@ to_APOS\ecs@
%\ex@\show\cs@ to_apos\ecs@
}
%\iwr@{}%
%\iwr@{ temp@=\temp@}%
%\iwr@{temp@@=\temp@@}%
%\iwr@{}%
%\show\temp@
%\show\temp@@
%\read16 to \Junk
%\def\temp@@{'[rq]}%
\def\PrepMoreLiveUkrAccIn@{%
\PrepMoreLiveAccIn@
\uccode`*=`*
%%% Following for rq-APOS confluence (Ukr)
%\ex@\show\cs@ to_APOS\ecs@
%\ex@\show\cs@ TO_rq\ecs@
\ex@\let\ex@\temp@\cs@ TO_rq\ecs@
\ifx\temp@\relax
\else %%
\ex@\let\ex@\temp@\cs@ to_APOS\ecs@
\edef\temp@@{'\lbrace@ APOS\rbrace@}
\ifx\temp@\temp@@
\ex@\edef\cs@ to_APOS\ecs@{\cs@ TO_rq\ecs@}%
\ex@\edef\cs@ to_apos\ecs@{\cs@ TO_rq\ecs@}%
\fi
\fi
%\ex@\show\cs@ to_APOS\ecs@
%\ex@\show\cs@ to_apos\ecs@
%%%%% Set \so_'*, \to_apos, \to_APOS, to \TO_rq
%% when nothing better available
%% \so_'* --> \to_apos by \@SetAccInShorts
%\ex@\show\cs@ so_'*\ecs@
\ex@\edef\cs@ so_'*\ecs@{\cs@ to_apos\ecs@}%
}%
%%%%% Define category 12 braces
\lccode `\.=123\relax\lowercase{\def\lbrace@{.}}%
\lccode `\.=125\relax\lowercase{\def\rbrace@{.}}%
\lccode `\.=0\relax
%%%%% \@SetHighAccess
%% \c_128 etc. will be the ACTIVE char
%% \h_128 etc. will be lc hex value thereof
\def\@SetHighAccess{%
\def/##1 ##2 {\chardef\byte=`##1\relax
\let##1\relax %% preliminary for edef protection
\edef\temp@{\the\byte}%
\ex@\def\cs@ da_\temp@\ecs@{##1}%%
%% da_ for \the\byte ==> active character
\ex@\def\cs@ do_\temp@\ecs@{\string##1}%%
%% do_ for \the\byte ==> cat 12 char
\ex@\def\cs@ dh_\temp@\ecs@{##2}}%%
%% dh_ for \the\byte ==> lc hex string
\HighActiveOctetsHolder@
}
%%%%% \@HiOctetUkrLigOutDefs %% 8 to 7
%% \TheEightbitEncodingVect@ is typically \DosEncodingVect@
\def\@HiOctetUkrLigOutDefs{%
%%% Auxilliary tools for high octets:
\@SetLigShorts
%% \ts_<LaTeX letter Tag> --> short ASCII %% r-to-s
%% sets some \cs@ ts_<tag>\ecs@ to ASCII char, or ' and that
%% for example \_shch --> 'w
\@SetHighAccess %% \da_<decimal> --> active high octet
\@SetDiacShorts
%%% Defs of active char values '{...} '[...] !__xy and Acc shorts
%% /##1. %% where ##1 is LaTeX letter Tag
%% letter high active octet code \the\count255 -->
%% \ts_<LaTeX letter Tag> if it exists or '{<LaTeX letter Tag>}
%%% for letters
%% \ta_<LaTeX letter Tag> --> active high octet %% r-to-a
%% \ot_<other high octet> --> <LaTeX letter Tag> %% o-to-r
%
\def/##1.{\ex@\let\ex@\temp@\cs@ ts_##1\ecs@
\ifx\temp@\relax
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\lbrace@ ##1\rbrace@}%
\else
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\temp@}%
%% Here we know we have letter
%% with a short form \ts_<LaTeX letter Tag>
%% For Ukr context modif preps
%% need ability to access active octets of
%% \CYRIE,\cyrie,\CYRYI,\cyryi,\CYRISHRT,\cyrishrt
%% for example \ta_IE --> the active octet giving IE
%% so prepare this access for all shorts:
\edef\temp@{\ex@\ex@\ex@\ne@\cs@ da_\the\count255\ecs@}%
%\show\temp@
\ex@\let\cs@ ta_##1\ecs@\temp@ %%% defines \ta_<LaTeX letter Tag>
\edef\temp@{\ex@\string\temp@}%% the cat other octet
%\show\temp@
%% Want LaTeX letter Tag of octet when it exists, else \relax
\ex@\edef\cs@ ot_\temp@\ecs@{##1}%
%\ex@\show\cs@ ot_\temp@\ecs@
\fi
\advance\count255 by 1\relax}
%% |##1. %% where ##1 is my short tex diacritic tag for email-ru.tex
%% defines \da_<\the\count255> = <active high octet> --> or Acc short
\def|##1.{%
%% Here we know we have diacritic with a short form \TS_##1
%% For Ukr context modif preps need ability to
%% define active octets of these
%% for example \TA_LQ --> (the active octet '[LQ])
%% so prepare this access for all high diacritics:
\edef\temp@{\cs@ da_\the\count255\ecs@}
%% value is active high octet, still equal \relax
\ex@\edef\cs@ TA_##1\ecs@{\temp@}%% defines \TA_<my diac tag>
\ex@\edef\cs@ OT_\ex@\string\temp@\ecs@{##1}%
%% defines \OT_<my diac other octet>
%%%% *finally* the active high octet
%% value changes from \relax to [\TS_##1]
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@
{[\cs@ TS_##1\ecs@]\ne@\UkrWB@}%
\advance\count255 by 1\relax}
%% \. sets the active high octet equal to !__xy where "XY=\count255
\def\.{\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{%
!\string_\string_\cs@ dh_\the\count255\ecs@}%%
%% in short \def ^^xy{the string !__xy}
\advance\count255 by 1\relax}
%
%%%% \apos. just means |rq. as far as Ukr Translit concerned
%\def\APOS.{|rq.}%
\def\apos.{|rq.}%
%
\count 255=128\relax
%\show\TheEightbitEncodingVect@
\TheEightbitEncodingVect@
%% finally prevent softhyphen catalyzing:
\ex@\ex@\ex@\edef\cs@ TA_shy\ecs@{[\cs@ TS_shy\ecs@]}
}
%%%%% \@HiOctetRuLigOutDefs %% 8 to 7 %% use comments for Ukr
\def\@HiOctetRuLigOutDefs{%
%%%% Auxilliary tools for high octets:
\@SetLigShorts
\@SetHighAccess %% \da_<decimal> --> active high octet
\@SetDiacShorts
%%%% /##1.
\def/##1.{\ex@\let\ex@\temp@\cs@ ts_##1\ecs@
\ifx\temp@\relax
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\lbrace@ ##1\rbrace@}%
\else
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\temp@}%
\fi
\advance\count255 by 1\relax}
%%%% |##1.
%% defines \da_<\the\count255> = <active high octet> --> or Acc short
\def|##1.{%
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{[\cs@ TS_##1\ecs@]}%
\advance\count255 by 1\relax}
%%%% \. sets the active high octet equal to !__xy where "XY=\count255
\def\.{\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{%
!\string_\string_\cs@ dh_\the\count255\ecs@}%%
%% in short \def ^^xy{the string !__xy}
\advance\count255 by 1\relax}
%
%%%% \apos. just means |rq. for now 26-11-00
\def\apos.{|rq.}
%
\count 255=128\relax
\TheEightbitEncodingVect@
}
%%%%% \@HiOctetAccOutDefs %% 8 to 7
%% \TheEightbitEncodingVect@ is typically \DosEncodingVect@
\def\@HiOctetAccOutDefs{%
%%% Auxilliary tools for high octets:
\@SetAccOutShorts
%% sets some \cs@ ts_<tag>\ecs@ to ASCII char, or ' and that
%% for example \_shch --> 'w
\@SetHighAccess
\@SetDiacShorts
%\ex@\show\cs@[lg]\ecs@
%%%% Defs of active char values '{...} '[...] !__xy and Acc shorts
%%% /##1. sets the active high octet equal to '{##1} or Acc short
\def/##1.{\ex@\let\ex@\temp@\cs@ ts_##1\ecs@
\ifx\temp@\relax
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@
{'\lbrace@ ##1\rbrace@}%
\else
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\temp@}%
\fi
\advance\count255 by 1\relax}%
%%% |##1. active high octet --> '[\TS_##1] or Acc short
\def|##1.{\ex@\let\ex@\temp@\cs@ ts_##1\ecs@ %% why this 24-11-00?
\ifx\temp@\relax
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@
{'[\cs@ TS_##1\ecs@]}%
\else
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\temp@}%
\fi
\advance\count255 by 1\relax}%
%%% \. sets the active high octet equal to !__xy where "XY=\count255
\def\.{\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{%
'\string_\string_\cs@ dh_\the\count255\ecs@}%
%% in short \def ^^xy{'__xy}
\advance\count255 by 1\relax}
%%% \apos. sets the active high octet equal to '* for Ukr
%% and otherwise to '[']
\def\apos.{%
\ex@\let\ex@\temp@\cs@ ts_apos\ecs@%
%\show\temp@ % normally '* (Ukr) or \relax (Ru)
\ifx\temp@\relax
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{'[\cs@ TS_rq\ecs@]}%
\else
\ex@\ex@\ex@\edef\cs@ da_\the\count255\ecs@{\temp@}%
\fi
\advance\count255 by 1\relax}%
\count 255=128\relax
\TheEightbitEncodingVect@
}
%%%%%% \@HiOctetsAccInDefs %% 7 to 8
%% extracts all useful info from the
%% \TheEightbitEncodingVect@ which is typically \DosEncodingVect@
%% it will be (other high octet) valued functions:
%% \so_<7short>, \to_<latextag>,
%% \TO_<7short>, \TO_<mydiactag>, \ho_<hextag>
\def\@HiOctetsAccInDefs{%
%%%%% Extract info from \TheEightbitEncodingVect@
%%%% Auxilliary tools for high octets: (all are used)
\@SetHighAccess
%% \do_<decimal> --> <8other> **, \dh_<decimal> --> <hex> **
\@SetAccInShortsA %% \so_<tag> --> '{<tag>} as default
%% \ts_<tag> --> <7short>, eg. \ts_shch --> 'w **
\@SetDiacShorts %% \TS_<tag> --> <7short> **
%\@IdentifyAccInLetterTags %% \te_<tag> --> \@e when char "known"
%\ex@\show\cs@ te_gje\ecs@
%%%% \Set@ho and \The@o used thrice below,
%% defines \ho_<hex> --> cat 12 octet
\def\The@o{\cs@ do_\the\count255\ecs@}%
\def\Set@ho{\edef\The@hex{\cs@ dh_\the\count255\ecs@}%
\ex@\edef\cs@ ho_\The@hex\ecs@{\The@o}}%
%%%% \. Surely \ho_xy --> ^^xy where "XY=\count255
\def\.{\Set@ho \advance\count255 by 1\relax}%
%%%% /##1. where ##1 is <tag> = LaTeX cyrillic letter tag
\def/##1.{\Set@ho
%%% maybe \so_<7short> --> other high octet
\ex@\ifx\cs@ ts_##1\ecs@\relax
\else
\edef\temp@{\cs@ ts_##1\ecs@}
\ex@\edef\cs@ so_\temp@\ecs@{\The@o}%
\fi
%%% surely \to_<tag> --> other high octet
\ex@\edef\cs@ to_##1\ecs@{\The@o}%
\advance\count255 by 1\relax}%
%%%% |##1. where ##1 is <tag> = my tex diac tag
%%%xxx REVISE to elim TS_ and \@SetDiacShorts
%%%xxx and also diac table anomaly re '["]
\def|##1.{\Set@ho
%%% surely \TO_<7short> --> other high octet
\ex@\edef\cs@ TO_##1\ecs@{\The@o}%
\edef\temp@{\cs@ TS_##1\ecs@}
\ex@\edef\cs@ TO_\temp@\ecs@{\The@o}%
%%% surely \TO_<tag> --> other high octet
\ex@\edef\cs@ TO_##1\ecs@{\The@o}%
\advance\count255 by 1\relax }%
%
%%%% \apos. just means |rq. for now 26-11-00
\def\apos.{|rq.}
%
\count255=128\relax
\TheEightbitEncodingVect@
%
%%%%% Define active English letter A --> \so_A
%% and 'A --> '\so_A if nothing better
\def/##1{\lccode`\~=`##1
\lowercase{\edef~}{\cs@ so_##1\ecs@}%
\ex@\ifx\cs@ so_'##1\ecs@\relax
\ex@\edef\cs@ so_'##1\ecs@{'\cs@ so_##1\ecs@}%
\fi}
\LatinLettersholder@
\@SetAccInShortsB %% \so_'g ==> edef exp of \to_gup etc
}
%%%%%% \StrangeLowOctetsToCaskets@ %%%%% correct for CR & LF??
%
\edef\OctetCasket@#1 #2 {\edef#1{\string!\string_\string_#2}}%
%%\OctetCasket@^^ff ff --> {the string !__ff}
\def\StrangeLowOctetsToCaskets@{%
\let/\OctetCasket@
\LowActiveOctetsHolder@
%% \HighActiveOctetsHolder@ handled otherwise
}
%%%%%% \StrangeOctetResurections@ %%%%% correct for CR & LF??
%% unnecessary now
%%%% \cs@!xy\ecs@ gives resurected octet __xy
\def\OctetResurection@#1 #2 {%
\ex@\edef\cs@ ho_#2\ecs@{\string#1}%
%\ex@\show\cs@ ho_#2\ecs@
}
\def\StrangeOctetResurections@{%
\let/\OctetResurection@
\LowActiveOctetsHolder@
}
%%%%%% \@IsDigitHolder \@IsDigitDefs
%
\def\HexDigitsHolder@{/0/1/2/3/4/5/6/7/8/9/a/b/c/d/e/f}
%
\def\@IsDigit{0}%
\def\@IsDigitDefs{%
\def/##1{\ex@\def\cs@ x_##1\ecs@{0}}% %% 0 is sign of digit
\HexDigitsHolder@}
\def\LatinLettersholder@{%% cat is *letter* here
/A/B/C/D/E/F/G/H/I/J/K/L/M/N/O/P/Q/R/S/T/U/V/W/X/Y/Z%
/a/b/c/d/e/f/g/h/i/j/k/l/m/n/o/p/q/r/s/t/u/v/w/x/y/z%
}%
%%%%%% \LatinLetterActiveAccOutDefs@
%%% for AccOut currently
\let\pEng@=\relax %% initial
\def\LatinLetterActiveAccOutDef@#1{%
\lccode`\~=`#1\relax\lccode`a=`#1\relax
\lowercase{\edef~{\pEng@ a}}}%
%
\def\LatinLetterActiveAccOutDefs@{%
\let/\LatinLetterActiveAccOutDef@
\LatinLettersholder@
\lccode`\~=0 \lccode`a=`a%% restorative measure
}%
%%%%%% \ActiveUkrLigOutDefs@
%%% for context sensitive, official Ukr lig transliteration
\def\ActiveUkrLigOutDefs@{%
\lccode`\~=13\relax
\lowercase{\let~\UkrLigOutEndLine@}%% it edefs to empty
%%%% \UkrWB@ Word-Beginning catalysis
%% High diacritics have \UkrWB@ catalytic
%% postfix by \@HiOctetUkrLigOutDefs
%%% ASCII chars 32--126 will have
%% \UkrWB@ catalytic postfix iff active
%% But just some diacritics will be activated by
%\lccode`\~=`\-\relax
%\lowercase{\def~{-\UkrWB@}}%
\count255=32\relax
\Loop@
\lccode`\~=\count255\relax
\lowercase{\edef~{\string~\ne@\UkrWB@}}%
\advance\count255 by 1\relax
\ifnum\count255>126\relax\else
\Repeat@
\lccode`\~=0\relax %% restorative
%%% \UkrWBShift@{##1}{##2}%
%% {LaTeX Tag}{Word Beginning transliteration}
\def\UkrWBShift@##1##2{%
\edef\temp@{\ex@\ex@\ex@\string\cs@ ta_##1\ecs@}%
%% cat other, high octet
%\show\temp@
\ex@\edef\cs@ wb_\temp@\ecs@{##2}%
%% ##2 is the catalyzed character(s), cat other, ASCII
%\ex@\show\cs@ wb_\temp@\ecs@
%% It serves in place of \ts_##1
}%
\UkrWBShift@{IE}{Ye}%
\UkrWBShift@{ie}{ye}%
\UkrWBShift@{YI}{Yi}%
\UkrWBShift@{yi}{yi}%
\UkrWBShift@{ISHRT}{Y}%
\UkrWBShift@{ishrt}{y}%
\UkrWBShift@{YU}{Yu}%
\UkrWBShift@{yu}{yu}%
\UkrWBShift@{YA}{Ya}%
\UkrWBShift@{ya}{ya}%
\def\UkrWB@##1{%
%% ##1 is a token and the interesting case is when it is
%% one of the 8 active chars \c_IE,...,\c_ya
\ex@\ifx\cs@ wb_\string##1\ecs@ \relax
%% if a context transformation is NOT defined
\ex@##1%
\else
\cs@ wb_\string##1\ecs@ %% dangerous but OK?
\fi
}%
%%% Post-Z catalysis:
%% \CYRZ\CYRG ==> ZGH, \CYRZ\cyrg ==> Zgh, \cyrz\cyrg ==> zgh
%%
\edef\temp@{\let\ne@\Ukr@G=\ex@\ex@\ex@\ne@\cs@ ta_G\ecs@}\temp@
\edef\temp@{\let\ne@\Ukr@g=\ex@\ex@\ex@\ne@\cs@ ta_g\ecs@}\temp@
%%\Ukr@G is expansion of \ta_G
%%\Ukr@g is expansion of \ta_g
\def\AfterUkrZorz@ ##1{%% checks for G,g ==> GH, gh
%(AfterUkrZorz@)
\ifx##1\Ukr@G
GH%
\else
\ifx##1\Ukr@g
gh%
\else
%(neither ta_G nor ta_g)%
\ex@\ex@\ex@##1%
\fi
\fi
}%
\ex@\ex@\ex@\def\cs@ ta_Z\ecs@{Z\AfterUkrZorz@}%
\ex@\ex@\ex@\def\cs@ ta_z\ecs@{z\AfterUkrZorz@}%
}
%%%%%% \ActiveRuLigOutDefs@
\let\ActiveRuLigOutDefs@\relax%
%%%%%% \PrimableTestPrep@
%% to help decide whether prime in 8-bit file should double
%% depends on whether following char (when char)
%% decision in \def\pr@
%%% N.B. More than Latin letters are primable
\def\PrimableTestPrep@{%
\def/##1{\uccode`##1=1}%
%% uccode=1 means *potentially* primable to us
\LatinLettersholder@/</>/*/[\ex@/\lbrace@ %
%% < > * cause all the fuss; others later??
}
%%%%%% \PrepFlagsAccOut@
%
\def\PrepFlagsAccOut@{%
\let\pEng@=\relax
%% English letter flag from \LatinLetterActiveAccOutDefs@
\let\pExcl@=\relax %% from active !
\let\pBs@=\relax %% from active \
\let\pPr@=\relax %% from active '
\let\pCR@=\relax %% from active ^^M as \endlinechar
%% initial
\lccode`\~=`\\\relax%% makes active \ --> \pBs@
\lowercase{\def~{\pBs@}}%
\lccode`\~=`!\relax%% makes active ! --> \pExcl@
\lowercase{\def~{\pExcl@}}%
\lccode`\~=`\'\relax%% makes active ' --> \pPr@
\lowercase{\def~{\pPr@}}%
\lccode`\~=9\relax%% makes active ^^09 --> !^^09 (string)
\lowercase{\edef~{\string!\string_\string_09}}%
\lccode`\~=13\relax%% makes active ^^0d = !^^0d (string)
\lowercase{\def~{\pCR@}}%
}%
%%%%%% \PrepFlagsAccIn@ for
%
\def\PrepFlagsAccIn@{%
\lccode`\~=`\\\relax%% makes active \ --> \@Bs
\lowercase{\let~\@Bs}%
\lccode`\~=`!\relax%% makes active ! --> \@Excl
\lowercase{\let~\@Excl}%
\lccode`\~=`\'\relax%% makes active ' --> \@Acc
\lowercase{\let~\@Acc}%
\lccode`\~=13\relax%% makes active ^^0d = \@EndLine (string)
\lowercase{\let~\@e}%
\let ^^A=\@e
}%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% TransSetup %%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%% \TransSetupAccIn@ (8 out)
\def\TransSetupAccIn@{%
\HiOctetsZeroLCcodes@ %% default to change
\@HiOctetsAccInDefs
\ThePrepMoreLiveAccIn@
%% This one is \PrepMoreLiveRuAccIn@ or \PrepMoreLiveUkrAccIn@
\StrangeOctetResurections@
\PrepFlagsAccIn@
\endlinechar=13
%\show^^A
}
%%%%% \TransSetupAccOut@ (7 out)
\def\TransSetupAccOut@{%
\StrangeLowOctetsToCaskets@
\@HiOctetAccOutDefs
%% high octet to tag short or '{??} or '[??] or !__xy
%%\ex@\show\cs@ ts_APOS\ecs@
\LatinLetterActiveAccOutDefs@
\PrimableTestPrep@ %% to make \IFnextprimable@ work
\PrepFlagsAccOut@
\endlinechar=13 % will change later
}
%%%%% \TransSetupLigOut@
\def\TransSetupLigOut@{%
\StrangeLowOctetsToCaskets@
\@HiOctetLigOutDefs
%% is \@HiOctetRuLigOutDefs or \@HiOctetUkrLigOutDefs
\ActiveLigOutDefs@ %% \relax or \ActiveUkrLigOutDefs@
\endlinechar=-1\relax
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% CategorySetup %%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%% \CategorySetup@ best done as a predefined macro
%% to avoid self-ref problems
%%%%%% \ActivateLatinLetters@
\def\ActivateLatinLetters@{%
%\showthe\catcode`\/
\def/##1{\catcode`##1=13\relax}%
\LatinLettersholder@
}
%%%%% \MakeSpecialsOther@
%% Dangerous/exotic lower ascii become "other"
\def\MakeSpecialsOther@{%
\catcode9=13 %% tab
%%\catcode13=12 %% CR, just char absorb file at once? No
\catcode32=12 %% space to preserve multiple spaces
\catcode`\#=12
\catcode`\$=12
\catcode`\%=12
\catcode`\&=12
\catcode`\'=12 %% will often undo this
\catcode`\/=12
\catcode`\@=12
\catcode`\\=12 %% will often undo this
\catcode`\^=12
\catcode`\_=12
\catcode`\`=12
\catcode`\{=12
\catcode`\|=12
\catcode`\}=12
\catcode`\~=12
}
%%%% \MakeAsciiOther@
\def\MakeAsciiOther@{%
\count255=0 %
\Loop@
\catcode\count255=12\relax
\advance\count255 by 1\relax
\ifnum \count255< 128\relax
\Repeat@
}
%%%% \ActivateFlagChars@
\def\ActivateFlagChars@{%
\catcode`\'=13
\catcode`\!=13
\catcode`\\=13
\catcode13=13
}
%%%% \UkrLigContextActivations@
%% space, - and other non-letters
\def\UkrLigContextActivations@{%
\catcode13=13 %% CR
%\showthe\lccode`\.%
\count255=32\relax
\Loop@
\ifnum\lccode\count255=0\relax %% nonletters activated
\catcode\count255=13\relax
\fi
\advance\count255 by 1\relax
\ifnum\count255>126\relax\else
\Repeat@
%\def/##1{\catcode`##1=12\relax}\LatinLettersholder@
}
%%%% \RuLigContextActivations@
\let\RuLigContextActivations@\relax
\def\CategorySetupAccIn@{%
\LowOctetsCat@{15}%%
\catcode9=12\catcode10=12\relax %\catcode13=12 %% moderates above
\HiOctetsCat@{15}% %% to prevent disasters.
\MakeSpecialsOther@
\ActivateLatinLetters@ %% also done in AccOut direction
\ActivateFlagChars@ %% catcode 13 becomes 13
}
\def\CategorySetupAccOut@{%
\HiOctetsCat@{13}%
\LowOctetsCat@{13}%% includes controls; may work as input
\MakeSpecialsOther@
\ActivateLatinLetters@ %% but but < > still cat 12
\ActivateFlagChars@
}
\def\CategorySetupLigOut@{%
\HiOctetsCat@{13}%
\LowOctetsCat@{13}%% includes controls; may work as input
\MakeSpecialsOther@
\LigContextActivations@
%% \RuLigContextActivations@ or \UkrLigContextActivations@
%% initially ^^M=\relax
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% SecondPassPrepAccOut %%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\def\IFnextprimable@{\ifnum\uccode`##1=1\relax}
%%%%% \SecondPassPrepAccOut@ preps :
%%% AccOut is 2-pass process; see Eng.tex fo 2nd alone
%%%% First come a lot of definitions
\def\Gobble@#1{}%
\edef\OtherBacksl@{\ex@\Gobble@\string\\}%
\def\ExpTwiceAfter@{\ex@\ex@\ex@}%
\def\ExpThriceAfter@{\ex@\ExpTwiceAfter@\ex@}%
\def\ExpFourTimesAfter@{\ex@\ExpThriceAfter@\ex@}%
%%%%% \SecondPassPrepAccOut@
%%%% The p-versions are \relax outside SecondPass group
\def \SecondPassPrepAccOut@{%
\let\pEng@=\Eng@ %% Begin English Letterwise mark
\let\pExcl@=\Excl@ %% escaping exclamation marks
\let\pPr@=\Pr@ %% escaping prime
\let\pBs@=\Bs@ %% smart backslash
\let\pCR@=\AccOutEndLine@
}
%%%% \Eng@ meaning Begin English; will be let equal to \?
%%% \? will be prelim flag for English
\def\Eng@{\eng@}
%%%% \eng@#1 meaning begin English with argument
\def\eng@#1{!#1\c@eng@}
%%%% \c@eng@ continue English, first lap
\def\c@eng@#1{%
\ifx#1\Eng@
%\message{Is Eng@:\noexpand#1}%
\ex@\cc@eng@
\else
%\message{Not Eng@:\noexpand#1}%
\ifcat\noexpand#1a%% means Russian naked letter
!#1%% 8 then continue naked
\else
\ExpTwiceAfter@#1% after \ex@ removed here#1
%% just continue naked
\fi
\fi
}
%%%% \cc@eng@ continuing begin English, since
%%% letter here guaranteed, as at \eng@
\def\cc@eng@#1{%
#1\c@eng@ %% this time do not deposit a \string!
}
%%%% \Bs@ Backslash macro, will be \let equal to active \
%%%
\def\Bs@{\bs@}
\def\bs@#1{%
\ifx#1\Eng@
%\message{Is Eng@:\noexpand#1}%
\OtherBacksl@\ex@\cc@eng@
\else
%\message{Not Eng@:\noexpand#1}%
\ifx\Bs@#1%
%\message{Is Bs@:\noexpand#1}%
\OtherBacksl@\OtherBacksl@
\else
\ifcat\noexpand#1a%
\OtherBacksl@!#1
\else
\OtherBacksl@\ExpThriceAfter@#1%
\fi
\fi
\fi}
%%%% \Pr@ Prime macro, will be \let equal to active '
%%% Is the preconverted character ' not yet doubled
%%% Beware that primes for "accented" Russian letters
%%% are already ' (cat 12) at this intermediate stage
\def\Pr@{\pr@}%
%
\def\pr@#1{%
\ifcat\noexpand#1\noexpand\Pr@ %% test for flag \Pr@ and friends
\(pr@_flag)''\ex@#1%
\else
\ifnum\uccode`#1=1 \@e
%% not flag but primable \IFnextprimable@
\(pr@_primable@)''#1%
\else
\if\noexpand#1'%% is it ' from ya and friends
\(pr@_prime)''#1%
\else
\(pr@_p)'\ExpThriceAfter@#1% finally sure one prime will do
\fi
\fi
\fi
}%
%%%% \Excl@ Exclamation macro, will be \let equal to active !
%%% Is the preconverted character ! not yet doubled.
%%% Watch for interaction with \?=\Eng@.
\def\Excl@{\excl@}%
\def\excl@#1{%
\ifx#1\Excl@
!!\ex@\excl@
\else
\ifx#1\Eng@%%
%\message{Is Eng@:\string#1}%
!!\ex@\ex@\ex@\Eng@%
\else
\ifcat\noexpand#1a%
!!#1%
\else
\if\noexpand#1!%
%\message{Is !:\string#1}%
!!!%
\else
%\message{Not !:\string#1}%
!\ExpFourTimesAfter@#1%
\fi
\fi
\fi
\fi
}%
%%%% \EmptyEndLine@@ \UkrLigOutEndLine@ \AccOutEndLine@
%%% \endlinechar will be 13 and active and equal to:
\def\EmptyEndLine@@{}%
%%% but ALSO
\def\UkrLigOutEndLine@{\EmptyEndLine@@}%
%%% AND
\let\AccOutEndLine@\EmptyEndLine@@
%%% AND
\edef\AccInEndLine@{%
\ne@\Wobble@]\ne@\Wobble@\rbrace@\ne@\Gobble@\relax}%
%%% \Wobble@#1 is an end-of-line test
%% for AccIn mode and '[] '{} syntaxes
%%
\def\Wobble@#1{\cs@ W_#1\ecs@}
\ex@\edef\cs@ W_]\ecs@{}%
\ex@\edef\cs@ W_\rbrace@\ecs@{}%
\ex@\edef\cs@ W_\ecs@{Wobble}%% value must be string (not \relax)
%% since it will enter a \cs@ ... \ecs@
%% \AccInEndLine@ normally ultimately
%% vanishes if simply \edef expanded.
%% It's a \write that adds a CR in output
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%% AccIn ' ! \ %%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\def\(#1){}
\def\@Acc{\@acc}
% \def\@acc#1{%
% \ifnum \uccode`#1>0 \@e
% %(@acc_uccode)%
% %\cs@'\string#1\ecs@
% \ex@\ex@\cs@ so_'\string#1\ecs@
% \else
% \ifx#1\@Acc
% \(@acc_@Acc)%
% \ex@'%
% \else
% \(@acc_puke)%
% '\ex@\ex@\ex@#1%
% \fi
% \fi}
\def\@acc#1{%
\ex@\ifx\cs@ so_'\string#1\ecs@\relax
%\(@acc_puke for \cs@ so_'\string#1\ecs@)%
%% above tracer fails when #1 is )
'\ex@#1%
\else
%\(@acc_so_)%
\ex@\ex@\cs@ so_'\string#1\ecs@
\fi
}
\def\@Excl{\@excl}
\def\@excl#1{%
\ifnum \lccode`#1>0 \@e
\(@excl_c)\string#1\ex@\@c@excl %%(@excl_c)
\else
\ifx#1\@Excl
\(@excl_!)\string!%% (@excl_!)
\else
\(@excl_@@excl)\ex@\ex@\ex@ \@@excl \ex@\ex@\ex@#1%
%% quiery continues with \@@excl
\fi
\fi
}
\def\@@excl#1{%% handle _ and reliquat
\if\noexpand#1\string_%
%% \string!\string_ held back
\(@@excl_h)\ex@\@@UlnCheck %%(@@excl_h)
\else
\(@@excl_p)\string!\ex@#1%% (@@excl_p)
\fi
}
\def\@c@excl#1{%
\ifnum \lccode`#1>0 \@e
\(@c@excl_a)\string#1\ex@\@c@excl %%(@c@excl_a)
\else
\ifx#1\@Excl
\(@c@excl_@Excl)\ex@\ex@\ex@ \@eexcl %%\@UlnCheck
%% \@eexcl an "anti exclam"
%% \string! held back %%(@c@excl_!)
\else
\if\noexpand#1\string_%
%% \string!\string_ held back
\(@c@excl_hat)\ExpThriceAfter@\@@@UlnCheck %%(@c@excl_hat)
\else
\(@c@excl_p)\ExpThriceAfter@#1%% (@c@excl_p)
\fi
\fi
\fi
}
%%% an "anti exclam or exit exclam"
\def\@eexcl#1{%
\ifnum \lccode`#1>0 \@e
\(@eexcl_x)\ex@#1%% (@eexcl_x)
\else
\if\noexpand#1\string_%
%% \string!\string_ held back
\(@eexcl_hat)\ex@\ex@\ex@\@@@UlnCheck %%(@eexcl_hat)
\else
\(@eexcl_p)\ex@\ex@\ex@#1%% (@eexcl_p)
\fi
\fi
}
%%% past ! occurring in Eng look for first _ for case of !__xy
\def\@UlnCheck#1{%
\if\noexpand#1\string_%
%% retain first \string_
\(@UlnCheck_h)\ex@\@@UlnCheck %%(@UlnCheck_h)
\else
\(@UlnCheck_p)\ex@#1%% (@UlnCheck_p)
\fi
}
%%% past !_ look for second _ for case of !__xy
\def\@@UlnCheck#1{%
\if\noexpand#1\string_%
%% retain second \string_
\(@@UlnCheck_d)\ex@\@DigitCheck %%(@@UlnCheck_d)
\else
\(@@UlnCheck_p)\string!\string_\ex@#1%% (@@UlnCheck_p)
\fi
}
%%% past end-of-english _ look for second _ for case of !__xy
\def\@@@UlnCheck#1{%
\if\noexpand#1\string_%
%% retain second \string_
\(@@@UlnCheck_d)\ex@\@DigitCheck %%(@@@UlnCheck_d)
\else
\(@@@UlnCheck_p)\string_\ex@#1%% (@@UlnCheck_p)
\fi
}
%%% \@DigitCheck
%%% past !__ look for hex digit
%%% Prudent approach avoids line overrun; speed OK?
\def\@DigitCheck#1{%
\ex@\ifx\cs@ x_\string#1\ecs@\@IsDigit
\ex@\@DigitAll\ex@#1%% (@DigitCheck_d)
%% replace #1 as only storage device available
\else
\string!\string_\string_\ex@#1 %%(@DigitCheck_p)
\fi
}
%%% \@DigitAll
%%% past !__<digit> look for second hex digit #2
%%% Prudent approach avoids line overrun; speed OK?
\def\@DigitAll#1#2{%
\ex@\ifx\cs@ x_\string#2\ecs@\@IsDigit
%% x for hex%% (@DigitAll_d)
%\cs@!\string#1\string#2\ecs@ %% one octet replaces 5!
\cs@ ho_\string#1\string#2\ecs@
\else
\string!\string_\string_\ex@#1\ex@#2%
%% puke up five %% (@DigitAll_p)
\fi
}
%%%%%% \HexDigitsHolder@ \@IsDigitDefs
%
\def\HexDigitsHolder@{/0/1/2/3/4/5/6/7/8/9/a/b/c/d/e/f}
%
\def\@IsDigit{\@@IsDigit}%
\def\@IsDigitDefs{%% x_ for hex
\def/##1{\ex@\def\cs@ x_##1\ecs@{\@@IsDigit}}%
%% \@@IsDigit is sign of digit
\HexDigitsHolder@}
\@IsDigitDefs
%%% \@Bs and \@bs#1
\def\@Bs{\@bs}
\def\@bs#1{\OtherBacksl@
\ifnum \lccode`#1>0 \@e
\(@Bs_a)\string#1\ex@\@c@excl %%(@Bs_a)
\else
\ifx#1\@Bs
\(@Bs_bs)\OtherBacksl@ %%(@Bs_bs)
\else
\ifx#1\@Excl
\(@Bs_bs!)\ExpThriceAfter@\@bs@excl %%(@Bs_bs!)
\else
\(@Bs_o)\ExpThriceAfter@#1%% (@Bs_o)
\fi
\fi
\fi
}
\def\@bs@excl#1{%
\ifnum \lccode`#1>0 \@e
\(@bs@excl_lc)\ex@ #1%% do buggerall%% (@bs@excl_lc)
\else
\ifx#1\@Excl
\(@bs@excl_Excl)\string!%% (@bs@excl_Excl)
\else
\if\noexpand #1\string_%
\(@bs@excl_h)\ExpThriceAfter@\@@UlnCheck %%(@bs@excl_h)
\else
\(@bs@excl_o)\string!\ExpThriceAfter@ #1%% (@bs@excl_o)
\fi
\fi
\fi
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% MainConversionLoop %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\def\MainConversionLoop@{%
\message{\Sharp@}
\count255=0
\Loop@ %%
\advance\count255 1\relax
\ifnum\count255>40\relax
\count255=0\relax
\message{\Sharp@}%
\fi
\ifeof\MainStreamIn@
\else
\read\MainStreamIn@ to \Line@
\TheTreatLine@
\Repeat@
}
%%%%% \TreatLine... Macros
%
%%%% AccIn
\def\TreatLineAccIn@{%
%\show\Line@
%\show\AccInEndLine@
%\def\temp@{\ex@\Line@\AccInEndLine@}
%\show\temp@
%\tracingmacros=1
%\show ^^A
%\ex@\show\cs@ W_^^A\ecs@
\Wr@{\ex@\Line@\AccInEndLine@}% provisional?
}
%%%% AccOut
\def\TreatLineAccOut@{% new 25 Aug
\edef\Line@{\Line@}%% maybe add \EmptyEndLine@
\begingroup
\SecondPassPrepAccOut@
\Wr@{\Line@\AccOutEndLine@}%
\endgroup
}
%%%% LigOut \TreatLineLigOut@
%% is \TreatLineUkrLigOut@ or \TreatLineRuLigOut@
\def\TreatLineUkrLigOut@{% new 1 Nov
\Wr@{\ex@\UkrWB@\Line@\UkrLigOutEndLine@}
}% provisional?
\def\TreatLineRuLigOut@{% new 7 Sept
\Wr@{\Line@}}%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% I / O %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\newread\MainStreamIn@
\newwrite\MainStreamOut@
\def\MainFileIn@{IN.txt}%
\def\MainFileOut@{OUT.txt}%
\def\AuxFileOut@{OUT.txt}%% this time, so not really needed
\def\AuxEncodingFile@{\cs@ \Encodingtag@ EncodingFile@\ecs@}
\def\ExtraEncodingFile@{extraenc.tex}
\def\HeadEncodingFile@{IN.txt}
%%%%% \SetupLineReads@ uses \TheStreamIn@ and
%% \TheFileIn@ which must be specified
\def\SetupLineReads@{%
\openin\TheStreamIn@\TheFileIn@\relax
\ifeof\TheStreamIn@
\closein\TheStreamIn@
\def\Decision@{\iwr@{}%
\iwr@{ * Sorry, "\TheFileIn@" is absent\string/busy; quitting.}
\cs@ end\ecs@}
\else
\let\Decision@\relax
\fi
\Decision@
}
\def\SetupModifLineReads@{%% for Extra or Head
\let\TheFileIn@\AuxEncodingFile@ %% alternative here!
\let\TheStreamIn@\MainStreamIn@
\SetupLineReads@
}
\def\SetupMainLineReads@{%% for Extra or Head
\let\TheStreamIn@\MainStreamIn@
\let\TheFileIn@\MainFileIn@ %% alternative here!
\SetupLineReads@
}
%%%%% \SetupWriteOuts@
\def\SetupWriteOuts@{%
\immediate\openout\TheStreamOut@\TheFileOut@\relax
}
\def\SetupMainWriteOuts@{%
\let\TheStreamOut@\MainStreamOut@
\let\TheFileOut@\MainFileOut@
\SetupWriteOuts@
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% INTERVIEW %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% This can serve as a table of contents for this section
%
\def\InterviewUser@{%
\GetPrevOptions@
\Splash@
\SetupMainLineReads@
\GetUserChanges@
\InscribeUserChanges@
\AbortLossyInput@
\SetupMainWriteOuts@
%\WriteProlog@
}
\def\ReservedPrevOptions@{7ARW}
\let\PrevOptions@\ReservedPrevOptions@
%%%% \GetPrevOptions@
\def\GetPrevOptions@{%
\openin\MainStreamIn@ email-ru.opn \relax
\ifeof\MainStreamIn@
\else
\read\MainStreamIn@ to \PrevOptions@
\fi
\closein\MainStreamIn@
%\show\PrevOptions@
\TestOptions@\PrevOptions@
\ifGoodOptions@
%\iwr@{Good PrevOptions.}
\PreImplant@\PrevOptions@ %% includes format test
%% then preimplantation done and atoms defined
\else
%\iwr@{Bad PrevOptions.}
\let\PrevOptions@\ReservedPrevOptions@ %% \TestOptions@ not needed
\PreImplant@\PrevOptions@ %% so that atoms defined
\fi
}
%%%% \PreImplant@ #1; 1st exp of #1 is some sifted options like 8SW
%%% Sets atomic tags \Direction@, \ACtype@,
%% \LangGroup@, \Encoding@, for these options
\def\PreImplant@#1{ %% for reuse
\ex@\PreImplant@@#1\endPreImplant@@} % 4 \relax for insurance
\def\PreImplant@@#1#2#3#4#5\endPreImplant@@{%
\def\Direction@{#1}
\def\ACtype@{#2}
\def\LangGroup@{#3}%\show\LangGroup@
\def\Encoding@{#4}%\show\Encoding@
}
%%%% \TestOptions@ for \PrevOptions from possibly damaged file
\def\TestOptions@@#1#2#3#4#5\endTestOptions@@{%
\IN@0#1@78@
\ifIN@
\IN@0#2@LA@
\ifIN@
\IN@0#3@RU@
\ifIN@
\IN@0#4@DEHMIWK@
\ifIN@
\def\ttemp{#5}%\show\ttemp
\ifx\ttemp\empty
\GoodOptions@true
%\message{GoodOptions@true}%
\fi
\fi
\fi
\fi
\fi
}
%
\def\TestOptions@#1{%
%\edef\temp{#1}\show\temp
\GoodOptions@false
\ex@\TestOptions@@#1\endTestOptions@@}
%%%% \SetModetag@ sets \Modetag@ to AccIn, AccOut, or LigOut
%% \LangGroup@ does not affect this
\def\SetModetag@{%
\if\Direction@ 8%
\def\Modetag@{AccIn}%
\else
\if\ACtype@ L%
\def\Modetag@{LigOut}%
\else
\def\Modetag@{AccOut}%
\fi
\fi}
%%%% \PrepOptionTags@
%%% Uses \Direction@, \ACtype@, \LangGroup@, \Encoding@.
%%% Sets Long tags \Modetag@,
%% \ACtypetag@, \LangGrouptag@, \Encodingtag@,
%
\def\Ltag@{Lig}
\def\Atag@{Acc}
%
\def\Dtag@{Dos}
\def\Mtag@{Mac}
\def\Itag@{Iso}
\def\Wtag@{Win}
\def\Ktag@{Koi}
\def\Etag@{Extra}
\def\Htag@{Head}
%
\def\Rtag@{Ru}\def\Rlongtag@{Russian}
\def\Utag@{Ukr}\def\Ulongtag@{Ukrainian}
%
\def\PrepOptionTags@{%
\SetModetag@ %% sets \Modetag@
\edef\ACtypetag@{\cs@\ACtype@ tag@\ecs@}%
\edef\Encodingtag@{\cs@\Encoding@ tag@\ecs@}%
\edef\LangGrouptag@{%
\cs@\LangGroup@ tag@\ecs@}% short name Ru or Ukr or ...
\edef\TheLangGroup@{%
\cs@\LangGroup@ longtag@\ecs@}%% full name; for dialog
\edef\LangAlphabetA@{\cs@\LangGrouptag@ AlphabetA@\ecs@}
\edef\LangAlphabetZ@{\cs@\LangGrouptag@ AlphabetZ@\ecs@}
}
\def\iwr@{\immediate\write16}%
\def\wr@{\immediate\write\MainStreamOut@}%
\def\MainFileIn@{IN.txt}%
\def\MainFileOut@{OUT.txt}%
%{\cs@ OUT-\
[email protected]\ecs@}%
\def\ExtraEncodingFile@{extraenc.tex}
\def\batchindirname@{IN_BAT}%
\def\batchoutdirname@{OUT_BAT}%
\def\batchfilename@{batch}%
\def\DosBlurb@{DOS New Alternative Cyrillic encoding cp866nav}%
\def\MacBlurb@{Apple Macintosh Cyrillic}%
\def\IsoBlurb@{ISO8859-5 of 1988 for Sun,DEC,HP,Linux... }%
\def\WinBlurb@{Windows Cyrillic encoding, MicroSoft cp1251}%
\def\KoiBlurb@{KOI8 Internet Cyrillic (RFC-1489 of 1993)}%
\def\HeadBlurb@{Header encoding, placed near top of input}%
\def\ExtraBlurb@{Extra encoding from your own "\ExtraEncodingFile@"}%
\def\RuAlphabetA@{ a b v g d e 'o 'z z i j k l m n o p r s t}%
\def\RuAlphabetZ@{ u f x 't c w 'w q y h 'e 'u 'a }%
\def\UkrAlphabetA@{ a b v g(or h) 'g d e 'e 'z z y i 'i j k}%
\def\UkrAlphabetZ@{ l m n o p r s t u f x 't c w 'w q 'u 'a }%
\def\Rule@{ //////////////////////////////////////////////////////////}%
%%%%%% \Splash@
\def\Splash@ {%
\MakeSlantPct@
\iwr@{}%
\iwr@{\Rule@}%
\iwr@{ ///////////////////// email-ru.tex ///////////////////////}%
\iwr@{ // Converts Cyrillic text files between universal 7-bit}%
\iwr@{ // "ASCI-Cyrillic" and 8-bit Cyrillic text encodings.}%
\iwr@{ // Name input file "\MainFileIn@", alongside of "email-ru.tex".}%
\iwr@{ //// OPTIONS: Strike any option keys; then one <return>:-}%
\iwr@{ / X = abort now.}%
\iwr@{ / 8 = 8-bit output ; 7 = 7-bit output. }%
%\iwr@{ /// There are two routes for input:}%
%\iwr@{ / F = File ("\MainFileIn@", normally %
% alongside of this "email-ru.tex").}%
%\iwr@{ / B = Batch (files in directory %
% "\batchindirname@", in same location).}%
\iwr@{ /// There are two supported 7-bit formats:}%
\iwr@{ / L = Lossy transcription (using Ligatures);}%
\iwr@{ / A = ASCII-Cyrillic, using ' as accent and also ! \noexpand\ }%
\iwr@{ /// There are two supported language groups:}%
\iwr@{ / R = Russian (including Bulgarian and Byelorussian);}%
\iwr@{ / U = Ukrainian.}%
\iwr@{ /// There are many supported 8-bit Cyrillic encodings:}%
\iwr@{ / D = \DosBlurb@;}%
\iwr@{ / M = \MacBlurb@;}%
\iwr@{ / I = \IsoBlurb@;}%
\iwr@{ / W = \WinBlurb@;}%
\iwr@{ / K = \KoiBlurb@;}%
\iwr@{ / H = \HeadBlurb@;}%
\iwr@{ / E = \ExtraBlurb@.}%
\iwr@{ //// HELP: toward end of this %
macro file "email-ru.tex".}%
\iwr@{\Rule@}%
\iwr@{}%
}
%%% Subtle sanitization to see only ACDIKLMSTWX78
%%% Fails with case change alone; so use active too
\def \SeeOnlyACDEHIKLMRSTUWX78@{%
\count255=0\relax
\Loop@
\catcode\count255=9\relax
\advance\count255 by 1\relax
\ifnum
\count255<256\relax
\Repeat@
\catcode`7=12\relax
\catcode`8=12\relax
%% Undo above for 11 letters
\def/##1{\catcode`##1=11\relax}%
/A/C/D/E/H/I/K/L/M/R/S/T/U/W/X/a/c/d/e/h/i/k/l/m/r/s/t/u/w/x
\catcode`7=12\relax\catcode`8=12\relax
%% next make active a expand to letter A, etc.
\def/##1{\uccode`\~=`##1\relax\uppercase{\def~{##1}}}%
/a/c/d/e/h/i/k/l/m/s/r/t/u/w/x %% these are cat 11
%% then make these 11 letters active
\def/##1{\catcode`##1=13\relax}%
/a/c/d/e/h/i/k/l/m/r/s/t/u/w/x
}
\def\GetUserChanges@{%
\iwr@{ *** Default options: \PrevOptions@. }%
\iwr@{ *** Just type any change(s) and hit <return>.}%
\iwr@{ *** (Lowercase is OK.)}%
\begingroup
\SeeOnlyACDEHIKLMRSTUWX78@
\global\read16 to \YourChanges
\xdef\YourChanges{\YourChanges}
\endgroup
%\show\YourChanges
\let\UserChanges@\YourChanges
%\show\UserChanges@
\let\Reliquat@\UserChanges@
%\show\Reliquat@
\def\SiftedOptions@{}%
}
\def\Codify@#1{%
\IN@0#1@\Reliquat@ @%
\ifIN@\else
\edef\temp{#1}\message{Bug in \string\Codify@.}
\show\temp\show\Reliquat@
\show\Direction@
\fi
\SPLIT@0#1@\Reliquat@ @%
\edef\Reliquat@{\the\Initialtoks@\the\Terminaltoks@}%
\edef\SiftedOptions@{\SiftedOptions@#1}%
}
\def\CaseX@{%
\IN@0X@\UserChanges@ @%
\ifIN@
\def\Decision@{
\iwr@{ * Exit requested (by X).}
\endgroup\end}%
\else
\def\Decision@{}%
\fi
\Decision@}
\def\AdjustDirection@{%
%\show\UserChanges@
\IN@07@\UserChanges@ @%
\ifIN@
\Codify@{7}%
\else
\IN@08@\UserChanges@ @%
\ifIN@
\Codify@{8}%
\else
\edef\Reliquat@{\Reliquat@\Direction@}
\Codify@{\Direction@}%
\fi\fi
}
\def\AdjustACtype@{%
\IN@0L@\UserChanges@ @%
\ifIN@
\Codify@{L}%
\else
\IN@0A@\UserChanges@ @%
\ifIN@
\Codify@{A}%
\else
\edef\Reliquat@{\Reliquat@\ACtype@}
\Codify@{\ACtype@}%
\fi\fi
}
\def\AdjustLangGroup@{%
\IN@0R@\UserChanges@ @%
\ifIN@
\Codify@{R}%
\else
\IN@0U@\UserChanges@ @%
\ifIN@
\Codify@{U}%
\else
\edef\Reliquat@{\Reliquat@\LangGroup@}
\Codify@{\LangGroup@}%
\fi\fi
}
\def\AdjustEncoding@{%
\IN@0D@\UserChanges@ @%
\ifIN@
\Codify@{D}%
\else
\IN@0M@\UserChanges@ @%
\ifIN@
\Codify@{M}%
\else
\IN@0I@\UserChanges@ @%
\ifIN@
\Codify@{I}%
\else
\IN@0W@\UserChanges@ @%
\ifIN@
\Codify@{W}%
\else
\IN@0K@\UserChanges@ @%
\ifIN@
\Codify@{K}%
\else
\IN@0H@\UserChanges@ @%
\ifIN@
\Codify@{H}%
\else
\IN@0E@\UserChanges@ @%
\ifIN@
\Codify@{E}%
\else
\edef\Reliquat@{\Reliquat@\Encoding@}
\Codify@{\Encoding@}%
\fi\fi\fi\fi\fi\fi\fi
}
%%%% \InscribeUserChanges@
%%% Uses \PrevOptions@ in atomic form plus \UserChanges@
%%% Yields \SiftedOptions@ and \Reliquat@
%%% Yields full implementation of \SiftedOptions@
\def\InscribeUserChanges@{%
\CaseX@
\AdjustDirection@
\AdjustACtype@
\AdjustLangGroup@
\AdjustEncoding@
\PreImplant@\SiftedOptions@ % updates atomic options
\PrepOptionTags@
%\iwr@{ Direction@ = \Direction@}%
%\iwr@{ ACtype@ = \ACtype@}%
%\iwr@{ Encoding@ = \Encoding@}%
\iwr@{ Options keys being used: \SiftedOptions@}%
\iwr@{}%
\iwr@{ Modetag@ = \Modetag@}%
\iwr@{ ACtypetag@ = \ACtypetag@}%
\iwr@{ LangGrouptag@ = \LangGrouptag@}%
\iwr@{ Encodingtag@ = \Encodingtag@}%
\iwr@{}%
}
\def\AbortLossyInput@{%
%\message{AbortLossyInput@}%
\def\Decision@{}%
\if\ACtype@ L%
\if\Direction@ 8%
\iwr@{ !!! Sorry, type L (=Lossy) %
7-bit cannot be converted to 8-bit!}%
\def\Decision@{\read16 to \byebye \end}%
\fi
\fi
\Decision@}
\def\PrologRule@
{ /////////////////////////////////////////////////////////////////}%
\def\WritePrologOut@{%
\MakeSlantPct@
\Wr@{\PrologRule@}
%\show\SiftedOptions@
\Wr@{ //// Converted by "email-ru.tex", %
\cs@ email-ru-version\ecs@, options \SiftedOptions@, to}
\IN@07@\SiftedOptions@ @%
\ifIN@
\IN@0L@\SiftedOptions@ @%
\ifIN@
\Wr@{ //// \TheLangGroup@\space
text in a readable but lossy 7-bit ASCII format,}
\IN@0R@\SiftedOptions@ @%
\ifIN@
\Wr@{ //// namely the U.S. Lib. of Congress transcription scheme.}
\else
\Wr@{ //// namely the official Ukrainian one of 1996.}
\fi
\else
\Wr@{ //// \TheLangGroup@\space
text in faithful 7-bit ASCII-Cyrillic format.}
\Wr@{ //// The 33 letters of the modern \TheLangGroup@
\space alphabet are:}
\Wr@{ //// \LangAlphabetA@}
\Wr@{ //// \LangAlphabetZ@}
\Wr@{ //// For perfect restoration %
to many common 8-bit Cyrillic text}
\Wr@{ //// encodings, %
obtain the TeX utility "email-ru.tex" from CTAN.}
\fi
\else
\Wr@{ //// \TheLangGroup@\space
text in the 8-bit extended ASCII encoding:-}
\Wr@{ //// \cs@ \Encodingtag@ Blurb@\ecs@. For readable}
\Wr@{ //// ASCII transcriptions, %
use "email-ru.tex" available on CTAN.}
\fi
\Wr@{\PrologRule@}
\Wr@{}
\iwr@{ Processing (in 40 line units):-}\message{ }%
}
%%%%%%%%%%%%%%%%%%% <--------- END OF INTERVIEW
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% MODIFICATIONS %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\newif\ifExit@
\newif\ifModif@
\newif\ifAbortModif@
\newtoks\Modiftoks@
\newcount\Modifcount@
\newcount\EndModifcount@
%\newcount\Prologcount@
\def \MaybeAbortModif@{
\ifAbortModif@
\iwr@{}
\endgroup\endgroup
\iwr@{ !! Hit return to abort.}
\read-1 to \Junk@
\ex@\end
\fi
}
%%%%% \FindAndCopyModif@
%% Uses \AuxEncodingFile@, \AuxStreamIn@
%% provides \Modifcount@, \EndModifcount@
\def\FindAndCopyModif@{%
\SetupModifLineReads@
\count255=0
\Loop@ %%
\read\MainStreamIn@ to \Line@
% \iwr@{ Line@ = \Line@}%
\ifeof\MainStreamIn@
\AbortModif@true
\iwr@{}%
\iwr@{ !! At eof of \AuxEncodingFile@.}%
\iwr@{ !! Although modification was announced for input,}%
\iwr@{ !! the flag \ModifFlag@\space is missing.}%
\iwr@{ !! The input line number now is \the \count255.}%
\fi
\MaybeAbortModif@
\advance\count255 1\relax
\ifnum\count255>80\relax
\Exit@true
\global\AbortModif@true
\iwr@{}%
\iwr@{ !! Input limit.}%
\iwr@{ !! Although modification was announced for input,}%
\iwr@{ !! the flag \ModifFlag@\space is missing.}%
\iwr@{ !! The input line number now is \the \count255.}%
\iwr@{ Line@ = \Line@}%
\fi
\IN@0\ModifFlag@ @\Line@ @
\ifIN@
%\iwr@{}%
%\iwr@{ *** Bingo ***************}%
\Exit@true
\Modif@true
\global\Modifcount@=\count255
%\iwr@{}
%\iwr@{ ** Modification beginning at line \the\count255.}
%\iwr@{ ** Exit@ is true.}
\fi
\ifExit@
\else
\Repeat@
%
\MaybeAbortModif@
%
\Exit@false
\Chaintoks@{}%% clean slate
\ChainLine@ %% in reserve for keeps !!!!!!!!!!!
\Wr@{\Line@}%% temp for reading
\Loop@ %%
\read\TheStreamIn@ to \Line@
\ChainLine@ %% in reserve for keeps !!!!!!!!!!!
\Wr@{\Line@}%% temp for reading
\ifeof\MainStreamIn@
\Exit@true
\AbortModif@true
\iwr@{}%
\iwr@{ !! End of input file and the}%
\iwr@{ !! flag \EndModifFlag@\space is missing.}%
\iwr@{ !! The line number now is \the \count255 : }%
\fi
\MaybeAbortModif@
\advance\count255 1\relax
%\iwr@{}%
%\iwr@{ ** Count 255 advanced to \the\count255.}%
\ifnum\count255>220\relax
\Exit@true
\AbortModif@true
\iwr@{}%
\iwr@{ !! Runon modification. Aborting at line 220.}%
\iwr@{ !! Need a flag: }%
\iwr@{ !! "\EndModifFlag@"}%
\iwr@{ !! The line number now is \the \count255 : }%
\fi
\MaybeAbortModif@
\IN@0\EndModifFlag@ @\Line@ @%
\ifIN@
\Exit@true %\message{** Exit@true **}%
\global\EndModifcount@=\count255
%\iwr@{}%
%\iwr@{ ** Modification ending at line \the\count255.}%
%\iwr@{ ** Exit@ is true. }%
\fi
\ifExit@
\else
\Repeat@
%
\cs@ \Encodingtag@ StreamInAdjust@\ecs@
%% Explanation: If Extra is encoding tag, then closein
%% \ExtraEncodingFile@ and openin \MainFileIn@
%% But if it is Head then do nothing and continue input.
\immediate\closeout\MainStreamOut@
%\iwr@{}%
%\iwr@{ *** Both loops completed.}%
%\iwr@{ *** Modification began at line \the\Modifcount@.}%
%\iwr@{ *** Modification ended at line \the\EndModifcount@.}%
%\iwr@{ *** See modif in "\MainFileOut@". %
% Then hit <return> to continue.}%
%\read16 to \Junk@
}
\def\ExtraStreamInAdjust@{%
\immediate\closein\MainStreamIn@
\immediate\openin\MainStreamIn@\MainFileIn@\relax}
%% \HeadStreamInAdjust@ will be relax
\MakeSlantPct@
\uccode`!=`\%
\uccode`?=`\#
\uppercase{%
\edef\ModifFlag@{!?[<ASCII-CYRILLIC\string_MODIF>?]}%
\edef\EndModifFlag@{!?[<ASCII-CYRILLIC\string_ENDMODIF>?]}%
}
\uccode`!=0
\uccode`?=0
\def\CatsForCopying@{%
\LowOctetsCat@{12}%
\HiOctetsCat@{12}%
\MakeSpecialsOther@ }
\def\TransCodeTheRest@{%
\count255=0
\Loop@ %%
\advance\count255 by 1\relax
\ifnum\count255=40\relax
\count255=0\message{\Sharp@}%
\fi
\ifeof\MainStreamIn@
\else
\read\MainStreamIn@ to \Line@
\ex@\uppercase\ex@{\ex@\Wr@\ex@{\Line@}}%
%\iwr@{\Line@}%
\Repeat@
}
\def\DoConversion@{%
\iwr@{}%
\iwr@{ ** ExploitModifs@}%
%
\TransCodeTheRest@
\immediate\closein\MainStreamIn@
\immediate\closeout\MainStreamOut@
}
%%%%%%%%%%%%%%%%%%% <--------- END OF MODIFICATIONS
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% \ImplantCurrentOptions@ %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%% \ImplantCurrentOptions@
%% Is unique bridge between interview and converter parts
%%%%% Currently \Modetag@ (LigOut or AccOut )
%% and \Encodingtag@ determine \ACtypetag@
%% so last is confined to Interview.
%%%%% \Modetag@ \Encodingtag@ \LangGrouptag@ are all
%% that is currently used from Interview
\def \ImplantCurrentOptions@{%
%%%%% \CategorySetup@
\ex@\let\ex@\CategorySetup@
%%**** = formally indep of encoding and language
\cs@ CategorySetup\Modetag@ @\ecs@
%%%%% \TheTransSetup@
\ex@\let\ex@\TheTransSetup@ %%****
\cs@ TransSetup\Modetag@ @\ecs@
%%%%% \MainConversionLoop@ is formally invariant
%%%%% \TreatLineLigOut@ %%** means formally indep of encoding
\ex@\let\ex@\TreatLineLigOut@ %%
\cs@ TreatLine\LangGrouptag@ LigOut@\ecs@
%\show\TreatLineLigOut@
%%%%% \TheTreatLine@
\ex@\let\ex@\TheTreatLine@ %%****
\cs@ TreatLine\Modetag@ @\ecs@ %%
%\show\TheTreatLine@
%%%%% \TheEightbitEncodingVect@
\ex@\let\ex@\TheEightbitEncodingVect@ %% formally indep of language
\cs@ \Encodingtag@ EncodingVect@\ecs@
%\show\TheEightbitEncodingVect@
%\ex@\show\cs@ \Encodingtag@ EncodingVect@\ecs@
%%%%% \@TheModeShorts \@TheAccShorts or \@TheLigShorts
\ex@\let\ex@\@TheAccShorts %%**
\cs@ @AccShorts\LangGrouptag@\ecs@
\ex@\let\ex@\@TheLigShorts %%**
\cs@ @LigShorts\LangGrouptag@\ecs@
%%%%% \@HiOctetLigOutDefs
\ex@\let\ex@\@HiOctetLigOutDefs %%**
\cs@ @HiOctet\LangGrouptag@ LigOutDefs\ecs@
%%%%% \ActiveLigOutDefs@
\ex@\let\ex@\ActiveLigOutDefs@ %%**
\cs@ Active\LangGrouptag@ LigOutDefs@\ecs@
%%%%% \LigContextActivations@
\ex@\let\ex@\LigContextActivations@ %%**
\cs@ \LangGrouptag@ LigContextActivations@\ecs@
%%%%% \ThePrepMoreLiveAccIn@
\ex@\let\ex@\ThePrepMoreLiveAccIn@ %%**
\cs@ PrepMoreLive\LangGrouptag@ AccIn@\ecs@
%\show\PrepMoreLiveAccIn@
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% MAIN %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%
%% \Main@:- After \CategorySetup@ to \endgroup
%% must avoid space { } etc
\def\Main@{%
\begingroup
\InterviewUser@
\DoTheHeader@ %% hiatus "}{" , but here
%% \SiftedOptions@, \PrevOptions@ etc. etc. global
\ImplantCurrentOptions@
\TheTransSetup@
%\ex@\show\cs@'\string>\ecs@
\MaybeSetupLineReads@
\begingroup
\CategorySetup@
%\showthe\catcode`\-
%\showthe\catcode127
%\showthe\catcode32\relax
%\showthe\catcode`\\
\MainConversionLoop@
\endgroup
\Endgame@
\endgroup
\end
}
\def\MaybeSetupLineReads@{%
\def\temp@{E}%
\ifx\Encoding@\temp@
\SetupMainLineReads@
\fi}
\def\ProcessingReport@{}
\def\DoTheHeader@{%
\IN@0\Encoding@ @DMIWK@
\ifIN@
\ex@\DoOrdHeader@
\else
\ex@\DoAuxHeader@
\fi}
\def\DoOrdHeader@{%
\SetupMainWriteOuts@
\WritePrologOut@
}
\newtoks\temptoks@
\def\DoAuxHeader@{%
%\iwr@{ * \string\DoAuxHeader@}%
\SetupMainWriteOuts@
\CatsForCopying@
%\iwr@{}
\iwr@{ * \ne@\FindAndCopyModif@ :- %
Seeking modifs in "\AuxEncodingFile@".}%
\iwr@{}
\FindAndCopyModif@
\global\Chaintoks@\Chaintoks@
\global\let\SiftedOptions@\SiftedOptions@
\global\let\PrevOptions@\PrevOptions@
\global\let\Modetag@\Modetag@
\global\let\Encodingtag@\Encodingtag@
\global\let\LangGrouptag@\LangGrouptag@
\global\let\TheLangGroup@\TheLangGroup@
\global\let\LangAlphabetA@\LangAlphabetA@
\global\let\LangAlphabetZ@\LangAlphabetZ@
\endgroup %%%%%%%%%%%%% coming up for old categories
\let\AsciiCyrModif\relax %% to get by gate on encoding
%\iwr@{ * Now digesting the modifs in "\MainFileOut@".}%
%\iwr@{}%
\input\MainFileOut@ %% !!!!!!!!
\begingroup %%%%%%%%%%%%
\CatsForCopying@
%% Now wipe out \MainFileOut@
\SetupMainWriteOuts@
\WritePrologOut@
\Wr@{\the\Chaintoks@}\Wr@{}%
\global\Chaintoks@{}%% Cleanup
\temptoks@\ex@{\AuxEncodingVect@}%
%\showthe\temptoks@
%\iwr@{}%
%\iwr@{ ** Here is meaning of \string\AuxEncodingVect@:}%
%\iwr@{\the\temptoks@}%
%\iwr@{}%
%\iwr@{ ** Hit <return> to continue.}%
%\read16 to \Junk
\ex@\let\cs@\Encodingtag@ EncodingVect@\ecs@\AuxEncodingVect@
}%
%\let\ExtraEncodingVect@\NullEncodingVect@
%\let\HeadEncodingVect@\NullEncodingVect@
%%%%% \Closing@
\def\Closing@{%
\ProcessingReport@
\iwr@{}
\iwr@{ *** Finished! See \MainFileOut@\space
alongside of \MainFileIn@.}%
%\iwr@{ *** Hit <return> to exit.}%
%\read16 to \byebye
}
\def\WriteEpilog@{%
\MakeSlantPct@
%\Wr@{}%
\Wr@{\PrologRule@}%
\Wr@{ //// End of output by %
"email-ru.tex", with options \SiftedOptions@.}%
\Wr@{\PrologRule@}%
}
\def\WritePrevOptions@{%
\ifx\SiftedOptions@\PrevOptions@
\else
\immediate\openout\MainStreamOut@ email-ru.opn \relax
\immediate\write\MainStreamOut@{\SiftedOptions@}%
\immediate\closeout\MainStreamOut@
\fi
}%
\def\Endgame@{%
\WriteEpilog@
\immediate\closein\MainStreamIn@
\immediate\closeout\MainStreamOut@
\WritePrevOptions@
\Closing@
%%%%%%%% End of assimilation categories
%%
\catcode`\/=12 %% was 13
\catcode`\|=12 %% was 13
\catcode1=\CatOne@ %% syntactical trick for AccIN
\catcode`\@=12 %% was 11
}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%% EXECUTE MAIN %%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\Main@
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\endinput
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%% %%%%
%%% DOCUMENTATION FOR "email-ru.tex" %%%%
%%% %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Nota Bene: This documentation is mostly ASCII text. But it
requires a few lines of Cyrillic text. These are presented in
the MS Windows 8-bit encoding cp1251 for octets 128--255. As
cyrillic characters may not display correctly, all blocks of
one or more such lines are preceded by a warning line tagged
"%#Cy(" and followed by a line tagged "%#Cy)". GIF versions
are visible on the HTML home page at
http://topo.math.u-psud.fr/~lcs/ASCII-Cyrillic/ascii-cy.htm
CONTENTS
SECTION 1 Introduction
SECTION 2 Russian ASCII-Cyrillic
APPENDIX ASCII-Cyrillic for Bulgarian and Byellorussian
APPENDIX ASCII-Cyrillic for Ukrainian
APPENDIX Specifying a Cyrillic encoding vector in the input
APPENDIX Specifying an external Cyrillic encoding vector
APPENDIX The ^^xy pitfall
APPENDIX Email transfer checklist
SECTION 1
*** Introduction ***
This utility serves Russian and Ukrainian languages in
parallel. The documentation is initially for Russian and the
few modifications needed to adapt to the Ukrainian alphabet are
concentrated in an appendix.
Here is a fragment of Russian email in 8-bit Microsoft
Windows Russian text encoding. It can be typed and read on
any computer in any country where a Cyrillic alphabet is
indigenous --- but rarely beyond.
%#Cy(
�� �������� ���� Gardine ������� ���, ���
����� ��������� �� �����. � � ��� �������
���� ���� ���� ������. ��� ��� ��
��������� ����� ����, ��� � �������� �� ��
����. ��������� ����� �13A,
������������, ��� ������ -- ������� ����,
��� � ������. ����� � ��� �����, �� �����
����������. ����� �� � ������. � ����
��������� �����, � ��� �� ��� ����� ��
������.
%#Cy)
Even this degree of portability is hampered by the
frequent need to re-encode for another computer operating
system. If that problem is already bothering you here,
you may want to read the HTML or PDF formatted documentation
available at
http://topo.math.u-psud.fr/~lcs/ASCII-Cyrillic/
or on CTAN TeX archives.
The utility "email-ru.tex" serves primarily to quickly
convert this 8-bit text to and from a new 7-bit ASCII
transcription of Russian, called "ASCII-Cyrillic" which is is
both typeable and readable on every computer worldwide:
Na obratnom puti !Gardine obq'asnila mne, kak
delath peresadku na metro. My s nej proexali
bolhwu'u casth puti vmeste. Ona vywla na
ostanovke posle togo, kak my pereseli na mo'u
lini'u. Polhzovaths'a metro 'N13!A,
dejstvitelhno, ocenh prosto -- gorazdo pro'we,
cem v Moskve. Kogda 'a 'eto pon'ala, to srazu
uspokoilash. Sejcas vs'o v por'adke. 'A mogu
polhzovaths'a metro, i u'ze ne bo'ush xodith po
Pari'zu.
Well chosen English (Latin) letters stand for most Russian
letters. To distinguish the remaining handful of Russian
letters, a prefixed accent ' is used. Further, to introduce
English words, the exclamation mark ! appears. The whole
ASCII-Cyrillic system for Russian can hopefully be learned
in an hour.
Russian prose (8-bit encoded) is less than 4 percent
bulkier in 7-bit ASCII-Cyrillic form. Thus typing speed
for ASCII-Cyrillic on any computer keyboard can approach
that for a Cyrillic keyboard.
The bulk difference of 4 percent drops to less then 1
percent when modern "gzip" compression is applied to both.
Thus there is virtually no penalty for storing Cyrillic text
files in ASCII-Cyrillic form.
The 7-bit ASCII-Cyrillic form can be converted by
"email-ru.tex" back to any of the most used 8-bit encodings.
ASCII-Cyrillic is a cousin of existing transcriptions of
Russian which differ in using the concept of ligature -- i.e.
they use two or more English letters for certain Russian letters.
The utility "email-ru.tex" also converts Russian to one such
ligature-based transcription system established by the the USA
Library of Congress:
Na obratnom puti Gardine ob\jasnila mne, kak
delat' peresadku na metro. My s nej proexali
bol'shuju chast' puti vmeste. Ona vyshla na
ostanovke posle togo, kak my pereseli na moju
liniju. Pol'zovat'sja metro No13A,
dejstvitel'no, ochen' prosto -- gorazdo proshche,
chem v Moskve. Kogda ja eto ponjala, to srazu
uspokoilas'. Sejchas vse v porjadke. Ja mogu
pol'zovat'sja metro, i uzhe ne bojus' xodit' po
Parizhu.
Caveat: Accurate reconversion of existing ligature-based
transcriptions back to 8-bit format requires
a good deal of human intervention.
Although not more readable, the ASCII-Cyrillic
representation has the advantage that, for machines as well
as men, it is completely unambiguous as well as easily
readable. The "email-ru.tex" utility does the translation
*both* ways without human intervention, and the conversion
(8-bit) ==> (7-bit) ==> (8-bit) gives back *exactly* the
original 8-bit Russian text. (One minor oddity to remember:
terminal spaces on all lines are deleted.)
Thus, by ASCII Cyrillic encoding a Russian text file,
one can archive and transfer it and conveniently and safely.
The utility "email-ru.tex" provides the means for encoding
and decoding almost anywhere.
Outside of Russia, with no Russian keyboard available,
one can now accurately type and read Russian using
ASCII-Cyrillic.
The converter "email-ru.tex" is programmed as a macro
package for the widely (and even freely) available program
called TeX. It is widely installed, and even the most modest
installation of TeX (in version >=3 of 1989) should suffice.
It is fair here to think of TeX as a machine accepting
many attachments like "email-ru.tex", which permit one to do
a great variety jobs in the world of documentation.
Here is an internet address leading to many choices of
TeX implementation:
http://www.TUG.org
The simplest configuration or "format" of TeX called
"Plain" is best; but there is a good chance that
a randomly chosen format will also work.
Beginner's operating instructions for using
"email-ru.tex" once the TeX program is available are
simple:-
(i) put a copy of the file to convert, alongside of
email-ru.tex and give it the name "IN.txt".
(ii) process "email-ru.tex" (not "IN.txt") with Plain TeX. The
usual command line is:
tex email-ru.tex<return>
On computers with a graphical interface, one instead
usually just pushes the icon of "email-ru.tex" onto the
icon of the TeX program, indicating the format Plain if
the occasion offers itself.
(iii) follow the instructions offered by email-ru.tex. An
explanatory prolog and trailer will be added to the converted
output.
PITFALL: A few important TeX implementations, particularly
under the unix and Macintosh operating systems, cannot be
configured to \write true octets > 127 as "email-ru.tex"
expects in converting *from* ASCII-Cyrillic *to* 8-bit
Cyrillic text. Instead, octets >= 128 are represented by 4
ASCII character 'pseudo-octets' "^^xy" where "xy" is the
lowercase two digit hexadecimal notation for the octet. If
you encounter this in your announced 8-bit output from
"email-ru.tex", please refer to the appendix called "The ^^xy
pitfall" to learn how you can work around this difficulty.
SECTION 2
*** Russian ASCII-Cyrillic for email-ru.tex ***
This section is a practical introduction to
the new ASCII-Cyrillic system.
The 33 letters of the modern Russian alphabet, in
alphabetic order, are typed:
a b v g d e 'o 'z z i j k l m n o p r
s t u f x 't 'c w 'w q y h 'e 'u 'a
The letter 'o is an <e-dieresis> pronounced "yo", and in
principle it should be placed immediately after e. However,
most Russian dictionaries list it as an accented Russian e
and not as an autonomous letter like the other 32.
The MS Windows 8-bit version is:
%#Cy(
� � � � � � � � � � � � � � � � �
� � � � � � � � � � � � � � � �
%#Cy)
Similarly for capital letters:
A B V G D E 'O 'Z Z I J K L M N O P R
S T U F X 'T 'C W 'W Q Y H 'E 'U 'A
correspond to:
%#Cy(
� � � � � � � � � � � � � � � � � �
� � � � � � � � � � � � � � �
%#Cy)
Where there are several ergonomically "optimal" choices for
typing a Russian character, several may be admissible.
Thus:
'g='z 's=w c='t 'k=x
Incidentally, the strongest justification for typing "c" for a
letter consistently pronounced "ts" is the
traditional Russian recitation of the Latin alphabet:
ah beh tseh deh ...
For the Russian number character, which resembles in
shape the pair "No", ASCII-Cyrillic uses the notation '[No]
or alternatively 'N. A short list of important
representations for non-letter characters are:
'[No] Cyrillic number sign = 'N
'[<<] Cyrillic left quotes (left guillemets) = '<
'[>>] Cyrillic right quotes (right guillemets) = '>
'[,,] Cyrillic left inner double quotes ='[LQ]
'["] Cyrillic right inner double quotes ='[RQ] (*not* '[''])
'['] Single right quote ='[rq] (usually = '{apos})
'[`] Single left quote ='[lq]
'[---] long dash ='[emdash]
'[--] medium dash ='[endash]
'[...] dots (suspension) ='[dots]
'[<=] less than or equal ='[leq]
'[>=] greater than or equal ='[geq]
'[/=] not equal ='[neq]
'[nbsp] unbreakable space
'[\-] soft hyphen ='[shy]
'[^o] degree(s) ='[degree]
'[**] bullet ='[bullet]
'[~~] approx ='[approx]
Conventions established by TeX or PostScript or Unicode are
followed; however, additionally, some short forms with mnemonic
value are available as the above examples illustrate. An adequate
table of concordances of norms can be found by searching for the
word "currency" in this file.
[In TeX typescripts, many of the above diacritics already
have equally convenient ASCII representations as a TeX control
word beginning with "\" . Thus few of the above concern TeX
users.]
For the Cyrillic *letter* "gup" not in the modern Russian
alphabet of 33 letters, ASCII-Cyrillic uses '{gup} (and
'{GUP} for the uppercase form). Similarly for other Cyrillic
characters. The braces proclaim a Cyrillic letter.
The ASCII-Cyrillic expression for an octet >127 *not*
encoded to any normalized character, is !__xy where xy is the
two-digit hexadecimal representation of the octet. For example,
octet "8B, in the KOI8 encoding, is for non-text graphic
purposes and thus is rendered in ASCII-Cyrillic format as
!__8b. Conversion back to the 8-bit form will work. However,
although the 5 octet string "!__8b" is ASCII text, this text
is not independent of 8-bit encoding. Thus, it is best to
eliminate such "unencoded" or "meaningless" octets.
Beware that, if, in ASCII-Cyrillic, you type simply
"Coca-Cola", then you get:
%#Cy(
���-����
%#Cy)
ASCII-Cyrillic is not well designed for typing English
sentences, but occasional English words or letters are used
in Russian, so ASCII-Cyrillic allows one to type !U for an
isolated U and:
!Coca-!Cola for Coca-Cola
TeX is a powerful stable and portable formatting
system -- perhaps the most widely used for scientific and
technical documents. For a continental European language with
an accented Latin alphabet (French for example), a TeX
typescript is often created as an 8-bit text file that (just
as for Russian) depends on 8-bit encoding. However TeX itself
has always offered an alternative more prolix ASCII form for
such accented latin letters; and it has always served to provide
exchangeable ASCII typescripts that are readable and editable.
ASCII-Cyrillic seems to be the first ASCII scheme to offer
something similar for all Russian TeX typescripts.
To let TeX users more easily type in ASCII-Cyrillic, the
latter preserves TeX control sequences like \begin. The
familiar (La)TeX command
\begin{document}
is thus expressed as:
\begin{!document}
Here \ and ! have special roles, and are called escape characters
because they allow the letter sequences "begin" and "document"
to escape from routine conversion between English letters and
Russian Cyrillic letters.
Since the three ASCII characters ' ! \ do have special
powers to influence the interpretation of what follows, their
syntax in ASCII-Cyrillic typing has some eccentricities.
Fortunately, these occur only rarely. They will be discussed
in a file "email-ru.spc" (not yet available) that will contain
more formal specifications for ASCII-Cyrillic. In the
interim, curious users can probe the intricacies using
"email-ru.tex". (Please report inconsistencies and
infelicities to the author!)
The ASCII non-letter characters are all common to Russian
and English, namely:
<space>
! " # $ % & ' ( ) * + , - . /
0 1 2 3 4 5 6 7 8 9 : ; < = > ? @
[ \ ] ^ _ `
{ | } ~
It is worth remembering these, since you can then pretty well
identify ASCII text at sight. All of these, except on occasion
' ! \ , can be freely used in ASCII-Cyrillic typing of Russian
prose; they are not altered under conversion to an 8-bit
encoding.
One advantage of ASCII-Cyrillic representation is that it
appears the same on every computer in the world today. Indeed,
the ASCII encoding has for decades been a universally (but not
exclusively) used standard for computers. Its use by programmers
worldwide guarantees its validity for many future decades.
The MS Windows 8-bit Cyrillic encoding can be expected only in
Russia and under MS Windows operating systems. On the other hand,
the first 128 of 256 codes in it adhere to the universal ASCII
standard (which is also an ISO standard). The same inclusion of
ASCII holds for most other Cyrillic encodings in use today; at the
technical level, "email-ru.tex" relies heavily on this convenient
fact. Hopefully an overwhelming majority of Russian computer users
work with one of the five 8-bit encodings currently supported by
"email-ru.tex"; their tags for "email-ru.tex" are D,M,I,W,K
respectively (the order being historical). Deviations can be
handled by introducing an an auxiliary encoding, as indicated in
appendices, and using auxiliary keys H or E.
These tags are less discriminating than the conventional
tags fully identifying encodings used by Russian computer
screen fonts for text. There is in practice a one-to-many
correspondence from keys in the user dialog to encodings:
D (Dos) <=> cp866... MS DOS encodings
M (Mac) <=> mac... Apple Macintosh Cyrillic encodings
I (Iso) <=> iso88595 of 1988 for unix (Sun,DEC,HP,Linux,etc.)
W (Win) <=> cp1251 for Microsoft Windows
K (Koi) <=> koi8... Internet encodings, since RFC-1489 of 1993
H (Head) <=> encoding specified at the Head of the file
to be processed (see Appendix for syntax).
E (Extra)<=> Extra user-defined encoding -- same syntax but
located in (or via) the file "extraenc.tex".
The casual user of "email-ru.tex" should should just notice
which sort of computer environment he is using, and guess from
the above list which of the five tags D,M,I,W,K best applies.
Almost always, one of these five works perfectly:- because it is
the same as for the computer involved as regards all characters
actually used. (Deviations for unused characters are of no
practical significance!)
Technical comment: In the above list, ... stands for any
continuation yielding some valid LaTeX input encoding tag for
Cyrillic that you can find in the LaTeX file "cyinpenc.dtx".
The latter builds files named "<encodingtag>.def" directly
employed by LaTeX installations. Alternative references for
these Cyrillic encodings are:
--- russian.el, 1994 by Valery Alexeev <
[email protected]>
"Display, translate and edit buffers containing Russian
characters" an emacs editor macro package, LCD Archive Entry:
~/packages/russian.el.Z
--- nic.funet.fi:/pub/culture/russian/comp/characters
--- cyrillic.encoding.faq by Andras Kornai <
[email protected]>
--- lettermappings.gz by Dmitri Vulis <
[email protected]>
--- internet RFC 1489
---
http://www.fingertipsoft.com/ref/cyrillic
Conversion between different 8-bit encodings is possible
using "email-ru.tex". But one must do it in two steps, going via
the ASCII_Cyrillic 7-bit format. Beware that in case the target
encoding does not contain a certain character in the source file,
that character is left in a distinctive ASCII-Cyrillic form.
This, in practice, helps you see and repair the damage. Such
damage is neither exceptional nor avoidable since the characters
covered by the encodings vary somewhat with the encoding. But it
is usually minor and repairable.
Exercise: You know enough at this point to use ASCII-Cyrillic to
type or read any Russian email or any piece of Russian prose,
for example, that in the first section. Convert forth and back
between 7-bit and 8-bit forms using "email-ru.tex".
This version of "email-ru.tex" is preliminary; if a problem is
is encountered, please first check the most up-to-date version; then
please communicate bugs and suggestions to the author.
Possibilities for future development:
-- support for more Cyrillic alphabets
-- support for Unicode Cyrillic
-- support for the Mime protocol
-- batch mode
-- segmented files (e.g. just certain parts marked for conversion)
-- integration with TeX for rapid typesetting of ASCII-Cyrillic
text.
Thanks are due to the members of the Cyrillic TeX discussion
list (
[email protected]) for clarifying the problems a utility
such as this one should address. The list archives are available
at:
https://info.vsu.ru/Lists/CyrTeX-en/List.html
Advice from Maksym Polyakov <
[email protected]> was
essential in establishing the Ukrainian mode.
Laurent Siebenmann
[email protected]
[email protected]
[email protected]
ASCII-Cyrillic home page in December 2000:
http://topo.math.u-psud.fr/~lcs/ASCII-Cyrillic/ascii-cy.htm
Copyright Conditions: Gnu Public Licence
*** APPENDIX ASCII-Cyrillic for Bulgarian and Byelorussian ***
ASCII-Cyrillic for Bulgarian coincides with ASCII-Cyrillic
for Russian.
ASCII-Cyrillic for Byelorussian is fully compatible with
Russian, but uses two extra letters:
%#Cy(
� �
%#Cy)
<==> '{ii} '{ushrt} <==> 'i 'v
The short forms are currently available even in Russian mode, but
this may change in future versions.
*** APPENDIX ASCII-Cyrillic for Ukrainian ***
This is similar to but distinct from the Russian mode and is
*not* compatible with it.
The 33+1 letters of the modern Ukrainian alphabet, listed in
alphabetic order (MS Windows 8-bit encoding here) are:
%#Cy(
� � � � � � � � � � � � � � � � �
� � � � � � � � � � � � � � � � �
%#Cy)
and the preferred Ukrainian ASCII-Cyrillic (short) form is:
a b v g 'g d e 'e 'z z y i 'i j k l m n
o p r s t u f x 't 'c w 'w 'u 'a q '*
The 34th character is a Cyrillic apostrophe, a modifier letter that
has various roles, among them those of the hard sign of Russian. The
representation valid for all Cyrillic languages is '{apos}.
The following four letters do not occur in
Russian:
%#Cy(
� � � �
%#Cy)
<==> '{gup} '{ie} '{ii} '{yi} (for all Cyrillic)
<==> 'g 'e i 'i (for Ukrainian)
<==> (no Russian short forms)
The forms '{gup} etc. (in the second row) are the same for all
cyrillic languages.
Reciprocally, the following four Russian letters
do not occur in Ukrainian:
%#Cy(
� � � �
%#Cy)
<==> '{hrdsn} '{ery} '{erev} '{yo} (for all Cyrillic)
<==> (no Ukrainian short forms)
<==> q y 'e 'o (for Russian)
The following two letters are common to Ukrainian and Russian
but the ASCII-Cyrillic short forms are different.
%#Cy(
� �
%#Cy)
<==> '{i} '{sftsn} (for all Cyrillic)
<==> y q (for Ukrainian)
<==> i h (for Russian)
The use, in Ukrainian ASCII-Cyrillic, of q as a short form for
'{sftsn} is justified by the fact that the shape q rotated by 180
degrees is similar to that of '{sftsn}. But there is another
reason for this choice. It permits one to use h as an alternative
Ukrainian short form for '{g} --- which is natural since in many
cases '{g} is pronounced like the harsh German h in "Horst".
The full list of alternatives short forms is:
's=w
c='t
'k='x=x
h=g
Similarly for capital letters. In particular:
%#Cy(
� � � � � � � � � � � � � � � � � �
� � � � � � � � � � � � � � � �
%#Cy)
have the Ukrainian ASCII-Cyrillic representation:
A B V G 'G D E 'E 'Z Z Y I 'I J K L M N
O P R S T U F X 'T 'C W 'W 'U 'A Q '*
Long forms valid for all Cyrillic languages are:
'{A} '{B} '{V} '{G} '{GUP} '{D} '{E} '{IE} '{ZH} '{Z}
'{R} '{I} '{II} '{YI} '{J} '{K} '{L} '{M} '{N} '{O}
'{P} '{S} '{T} '{U} '{F} '{X} '{C} '{CH}
'{SH} '{SHCH} '{YU} '{YA} '{SFTSN} '{APOS}
Note that the Ukrainian apostrophe '{APOS} is a *letter*
and unlike '{SFTSN} it normally coincides with the lowercase
version: normally '{APOS}='{apos}. In case of a distinction
'* will be '{apos}.
There is an official lossy "Latin transliteration" for
Ukrainian using the ligature concept, and it is supported by
"email-ru.tex". See the Ukrainian national norm of 1996
summarized at:
http://www.rada.kiev.ua/translit.htm
Beware that the official transliterations of the six letters
'{g} '{ie} '{yi} '{ishrt} '{yu} '{ya}
are *context dependent*. This is a good reason for relying
on "email-ru.tex" to do the official transliteration.
The other aspects of ASCII-Cyrillic are the same for Ukrainian
and Russian.
*** APPENDIX Specifying a Cyrillic encoding vector in the input ***
The following is technical, but probably well within the reach
of confirmed TeX users.
The encoding option key "H" (for Header) in the main dialog
serves to request use of an encoding vector given in full near the top
of the input file.
Here is the appropriate syntax; it should be imitated quite
exactly. Beginning in the first 80 lines of the file to convert
(normally IN.txt), there should occur the following sort of
structure:
%#[<ASCII-CYRILLIC_MODIF>#]
\ifx\AsciiCyrModif\relax %%% TeX gateway
%%% Encoding to be used only if requested via the
%%% "H" encoding option key of the "email-ru.tex" dialog.
%%% LaTeX encoding Tag: cp866
\def\AuxEncodingVect@{%
/A./B./V./G./D./E./ZH./Z.%% "80--
/I./ISHRT./K./L./M./N./O./P.%% --"8F
/R./S./T./U./F./H./C./CH.%% "90--
/SH./SHCH./HRDSN./ERY./SFTSN./EREV./YU./YA.%% --"9F
/a./b./v./g./d./e./zh./z.%% "A0--
/i./ishrt./k./l./m./n./o./p.%% --"AF
\.\.\.\.\.\.\.\.%% "B0--
\.\.\.\.\.\.\.\.%% --"BF
\.\.\.\.\.\.\.\.%% "C0--
\.\.\.\.\.\.\.\.%% --"CF
\.\.\.\.\.\.\.\.%% "D0--
\.\.\.\.\.\.\.\.%% --"DF
/r./s./t./u./f./h./c./ch.%% "E0--
/sh./shch./hrdsn./ery./sftsn./erev./yu./ya.%% --"EF
/YO./yo./IE./ie./YI./yi./USHRT./ushrt.%% "F0--
|deg.|bullet.|cdot.|surd.|No.|coin.|blacksquare.|nbsp.%% --"FF
}
%%% This is the old "Standard" version of DOS encoding cp~866.
%%% Key D gave the New Alternative Variant" or "NAV" version
%%% The differences lie in the range "F2--"FE.
\fi
%#[<ASCII-CYRILLIC_ENDMODIF>#]
This provides an ordered list of 128 definitions for the encoding
positions 128="80 to 255="FF. There are, basically, three sorts of
definition and 8 definitions per row. For example:
--- "/SHCH." encodes position "9C as the Cyrillic *letter* whose TeX
name is \CYRSHCH. The truncated TeX name is always used.
--- "|nbsp." encodes position "FF as the unbreakable space. The "|"
indicates that this is a *diacritic* character. The names for
diacritical characters used here are the shorter alphabetical names
that one finds in the list of diacritics you can locate by searching
for the word "currency" in this file.
--- "\." encodes position "B0 as a *undefined*, and similarly for
"B1--"DF.
See also comments preceeding the internal encodings.
If there is no encoding definition set up in the above manner, then
"email-ru.tex" will abort.
Material on lines before:
%#[<ASCII-CYRILLIC_MODIF>#]
will be skipped. Then, lines up to and including:
%#[<ASCII-CYRILLIC_ENDMODIF>#]
will be copied verbatim and appear immediately after the usual
prologue for the output. Lines after that will be converted using the
designated encoding.
Beware: If the H option key is not used, then (in the present version)
the *whole* input file will be converted with another specified
encoding. Remove to safe storage unused encodings; they may confuse
inexperienced users.
*** APPENDIX Specifying an external Cyrillic encoding vector ***
In the main dialog the encoding option key "E" (for External) is
devoted to this. It requests an encoding via the *user-defined* file
"extraenc.tex". The simplest possibility for "extraenc.tex" is exactly
the sort of segment
%#[<ASCII-CYRILLIC_MODIF>#]
...
%#[<ASCII-CYRILLIC_ENDMODIF>#]
used with the "H" option key. The behavior commanded is the same
as with the "H" option key, except that the whole input file is
converted. In particular, the encoding vector will be inserted
into the output, below the usual prolog.
A TeX programmer would be able to provide access via a
dialog in "extraenc.tex" to an arbitrary number of encoding
vectors.
*** APPENDIX The ^^xy Pitfall ***
The pitfall to be discussed affects chiefly conversion
from 7-bit ASCII-Cyrillic text files to 8-bit Cyrillic text.
The author of TeX, Donald Knuth, provided, beginning with the
first 8-bit version 3 of 1989, a "pseudo-8-bit" mechanism allowing
octets > 127 being output via the TeX primitive command \write to
be written each as a sequence of four ASCII octets ^^xy
(called a "pseudo-octet") where xy is the the 2-digit lowercase
hexadecimal notation for the octet. For example, octet 128 becomes
^^80, and octet 255 becomes ^^ff.
The use of this mechanism seems to be standard TeX.
Presumably, it was intended to allow TeX to function on
operating systems that are unable to handle text files
containing octets >= 128. However, there are now virtually no
such operating systems, and the feature is a hinderance to many
users, in particular to users of email-ru.tex wishing to extract
true 8-bit text from ASCII-Cyrillic. Thus, *most* TeX
implementations now offer true 8-bit text output, at least
optionally -- thus enabling "email-ru.tex" to convert
ASCII-Cyrillic to true 8-bit text.
If your TeX writes only "pseudo-octets", try the following:
WORKAROUND (A) If (as is highly probable) you *know* that the
*intended* 8-bit output would contain no pseudo-octet ^^xy then you
can finish the conversion job by applying the tiny converter "Kto8"
to get rid of the "pseudo-octets". The name "Kto8" is a contraction
of the phrase "Knuthian-to-8-bit". "Kto8" currently scans once,
converting any Knuthian pseudo-octet ^^xy encountered to the
corresponding genuine octet. Further, it does something similar
for Knuth's representations of the form ^^X for the octets
0,1,..,31, and 127. It is self-documenting. Look for "Kto8" in the
ASCII-Cyrillic distribution directory; there will be binaries for
the Macintosh, Windows, and some unix operating systems.
WORKAROUND (B) Examine the operating options for your TeX
implementation (normally in documentation provided by the
implementor) to see if, by hook or by crook, you can get true
8-bit output. Many implementors, commercial or not, are extremely
responsive to user enquiries.
WORKAROUND (C) Ask yourself whether an 8-bit Cyrillic version is
strictly necessary. If the 8-bit output was really intended for
typographic composition by TeX, then you will probably find that
the "pseudo-8-bit" output will be equally acceptable to TeX,
albeit unreadable to human eyes.
WORKAROUND (D) Use one of the many fully 8-bit-capable TeX
installations.
Here is a list of TeX implementations for which the current
version is known to offer true 8-bit \write output, at least
optionally (see www.tug.org for other TeX implementations).
PLEASE CONTRIBUTE ADDITIONS TO THIS LIST!
** MS Windows Operating System, including DOS
-- BaKoMa TeX by B.K. Malyshev
-- emtex, for DOS, by E. Mattes
Comments: Create format file using option flag -o.
Octet 255 infortunately remains ^^ff.
-- fptex for Windows, by F. Popineau.
Comments: It is a Windows port of tetex.
-- miktex for Windows, by C. Schenk.
-- VTeX by MicroPress Inc.
Comments: 8-bit output is the default behavior for the
console-mode compilers [free versions on Linux and OS/2, as well
as Console mode on Win] but the 7-bit behaviour is the default
in GUI version which is integrated into the Vtex/Win IDE. In
either case, there is a switch to change the behaviour.
-- Y&Y TeX, by Y&Y Inc,
http://www.Y&Y.com
Comment: By default, output is 8-bit. Command line option -K
gives pseudo-8-bit output.
** Macintosh OS
-- Textures, by Blue Sky Research (since TeX 3)
-- OzTeX from v4 of 2001
Comment: To get true 8-bit output, you must set
write_8_bit = true in your configuration file and then
rebuild your format file(s).
** Unix OS and Linux OS
-- tetex for unix and linux, by T. Esser
It is based on web2C.
-- web2C maintained currently by Olaf Weber.
Comment: Specific compilations not included,
cf. tetex and fptex.
In case your default configuration is not OK,
try the tex command line option:
"--translate-file=cp8bit.tcx"
and learn about TCX files.
-- VTeX for Linux (see MS Widows listing).
---------------
Veteran TeX users should note one more subtle point
concerning pseudo-octets:- When in its usual *typesetting* mode
and reading a pseudo octet ^^xy, TeX will behave exactly as if
it has read the octet numbered xy (in lowercase hexadecimal
notation). In contrast, when running "email-ru.tex", TeX
regards an ^^xy in the input file as merely a sequence of 4
ASCII octets. This is because ^ then has TeX category 12
('other'). If you really truly want "email-ru.tex" to have the
more exotic behavior, you can, in effect, obtain it by
preliminary processing of the input with Kto8.
*** APPENDIX Email Transfer Checklist ***
ASCII-Cyrillic is a useful format for simplest email
transfers of Cyrillic text files. The universally accepted ASCII
text part of an email message can be used. This feature explains
the name "email-ru.tex".
For informal letters, it may be as good to use a
ligature-based ASCII representation (also generated by
"email-ru.tex"). But, if the typescript is "work in progress" (a
draft of work to be published later on), then a *faithful* system
like ASCII-Cyrillic is infinitely better.
As with any electronic transfer, care is required to avoid
mutilation and misinterpretation. Watch the following points.
(1) Be sure the ASCII-Cyrillic version has no "meaningless"
characters like !__ab. You may have to change your encoding or
revise the 8-bit source to get rid of these without real damage to
your typescript.
(2) Arrange that the file has no long lines (say >70 characters).
Many text editors, word processors, and web browsers allow
adjustment of text file line breaks; check out their text file I/O
features.
(3) Make sure the ASCII-Cyrillic version is indeed faithful.
First delete trailing spaces on all lines (as TeX ignores these).
Then take your 8-bit version, convert doubly 8 ==> 7 ==> 8, and
check that the resulting 8-bit version is restored 100% (using a
file comparison utility).
(4) Arrange that no "tilde" character "~" occurs at the beginning
of any line, for example, by inserting a space before each line.
(5) Be sure the recipient has TeX, and also "email-ru.tex".
Fortunately, the latter is ASCII text that can be sent by email
after precaution (4).
(6) If you know which 8-bit encoding your correspondent will be
using, then do that 7 ==> 8 bit conversion yourself, and verify
that his/her encoding includes all the characters you are using.
If not, in the 8-bit file, there will be some "unencoded" letters
or diacritics appearing in the form '{??} or '[??], for a suitable
tag ??.
(7) If your correspondent uses a mysterious 8-bit encoding, you
can learn what it is by examining his/her 8-bit typescripts. Then
include the mysterious encoding vector at the top of the
ASCII-Cyrillic version as indicated in another APPENDIX. Tell your
correspondent to select the "H" encoding option key in converting
the received email to 8-bit. The *whole* email can be processed;
just the part after the encoding vector will be output, and in the
mysterious 8-bit encoding.
(8) The following test may detect email ASCII text transmission
problems beyond those already mentioned. They were frequent in
early days but are now quite rare.
%%%%%%%%%%%% ASCII Character transmission test
%
% Upper case letters: ABCDEFGHIJKLMNOPQRSTUVWXYZ
% Lower case letters: abcdefghijklmnopqrstuvwxyz
% Digits: 0123456789
% Square, curly, angle braces, parentheses: [] {} <> ()
% Backslash, slash, vertical bar: \ / |
% Punctuation: . ? ! , : ;
% Underscore, hyphen, equals sign: _ - =
% Quotes--right left double: ' ` "
%"at", "number" "dollar", "percent", "and": @ # $ % &
% "hat", "star", "plus", "tilde": ^ * + ~
%
%%%%%%%%%%%%%%%%%%%%%%%%
%
% A single error can be disastrous in TeX files.
%
%%%%%%%%%%%%%%%%%%%%%%%%
