diff options
Diffstat (limited to 'Master/texmf-dist/tex/csplain/base/csenc-u.tex')
-rw-r--r-- | Master/texmf-dist/tex/csplain/base/csenc-u.tex | 54 |
1 files changed, 49 insertions, 5 deletions
diff --git a/Master/texmf-dist/tex/csplain/base/csenc-u.tex b/Master/texmf-dist/tex/csplain/base/csenc-u.tex index da8b8d58139..0a6794d0091 100644 --- a/Master/texmf-dist/tex/csplain/base/csenc-u.tex +++ b/Master/texmf-dist/tex/csplain/base/csenc-u.tex @@ -5,10 +5,8 @@ %%% example: tex -ini -enc \let\enc=u \input csplain.ini % This is very simple setting of Czech and Slovak alphabet only. -% No special characters (such as dash, quotes etc.) used in UTF8 are -% declared here. No "UTF8 unknown code checking" is implemented here. -% The force is in the simplicity. The \mubyteout is set to 1 only. % User can reset this value and add his own declaration. +% For more information see cstexman.pdf. \ifx\mubyte\undefined \errhelp={You has specified \let\enc=u but this works only with encTeX @@ -62,10 +60,56 @@ \mubyte ^^c0 ^^c5^^94\endmubyte % \' R \mubyte ^^e0 ^^c5^^95\endmubyte % \' r +\def\setcsucode #1 #2 #3 #4 #5{} % to skip the data form utf8lat1.tex + % and utf8lata.tex + +% There exist some character-like control sequences defined in plainTeX. +% It seems to be usable to interpret their corresponding UTF-8 codes: + +\mubyte \S ^^c2^^a7\endmubyte % section sign +\mubyte \P ^^c2^^b6\endmubyte % paragraph (pilcrow) sign +\mubyte \ss ^^c3^^9f\endmubyte % german sharp s +\mubyte \l ^^c5^^82\endmubyte % l slashed +\mubyte \L ^^c5^^81\endmubyte % L slashed +\mubyte \ae ^^c3^^a6\endmubyte % ae ligature +\mubyte \oe ^^c5^^93\endmubyte % oe ligature +\mubyte \o ^^c3^^b8\endmubyte % o slash +\mubyte \AE ^^c3^^86\endmubyte % AE ligature +\mubyte \OE ^^c5^^92\endmubyte % OE ligature +\mubyte \O ^^c3^^98\endmubyte % O slash +\mubyte \i ^^c4^^b1\endmubyte % dotless i +\mubyte \j ^^c8^^b7\endmubyte % dotless j +\mubyte \aa ^^c3^^a5\endmubyte % a with ring +\mubyte \AA ^^c3^^85\endmubyte % A with ring +\mubyte \copyright ^^c2^^a9\endmubyte % copyright +\mubyte \dots ^^e2^^80^^a6\endmubyte % ellipsis +\mubyte \dag ^^e2^^80^^a0\endmubyte % single dagger +\mubyte \ddag ^^e2^^80^^a1\endmubyte % double dagger + +% The character-like control sequences defined in csplain: + +\mubyte \clqq ^^e2^^80^^9e\endmubyte % czech left double quote +\mubyte \crqq ^^e2^^80^^9c\endmubyte % czech right double quote +\mubyte \flqq ^^c2^^ab\endmubyte % french left (czech right) double guillquote +\mubyte \frqq ^^c2^^bb\endmubyte % french right (czech left) double quillquote +\mubyte \promile ^^e2^^80^^b0\endmubyte % per mille sign + +% everyjob message: + +\ifx\baseutfencoding\undefined \else \expandafter\endinput\fi + +\let\baseutfencoding\relax + \global\everyjob=\expandafter{\the\everyjob - \message{The UTF8->ISO-8859-2 re-encoding of Czech+Slovak alphabet activated by encTeX}} + \message{The utf8->iso8859-2 re-encoding of Czech+Slovak alphabet activated by encTeX}} + +% Warnings about UTF-8 unknown codes are set by default: + +\input utf8unkn + +% UTF-8 input / output is active by default: -\mubytein=1 \mubyteout=1 \mubytelog=1 +\mubytein=1 \mubyteout=3 \mubytelog=1 \xprncodes=0 \endinput |