| Current File : //usr/share/texlive/texmf-dist/tex/generic/enctex/utf8-t1.tex |
% utf8-t1.tex
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% This file implements the conversion from UTF8 to Cork
% encoding (used by DC (EC) fonts).
% The conversion is done by encTeX v. Dec 2002 or higher.
%
% Copyright (C) 2002-2003 Petr Olsak
% Copyright (C) 2003 David Necas (Yeti)
%
% This program is free software; you can redistribute it and/or modify
% it under the terms of the GNU General Public License as published by
% the Free Software Foundation; either version 2 of the License, or
% (at your option) any later version.
%
% This program is distributed in the hope that it will be useful,
% but WITHOUT ANY WARRANTY; without even the implied warranty of
% MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
% GNU General Public License for more details.
%
% You should have received a copy of the GNU General Public License
% along with this program; if not, write to the Free Software
% Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
\ifx\mubyte\undefined
\errhelp{Sorry, you can't use this file without encTeX ver. Jan. 2002.}
\errmessage{The encTeX extension of TeX is not found}
\endinput \fi
% first, we set the identity mapping in xord/xchr:
\bgroup
\ifx\xordcode\undefined
\errhelp{May be, you are using this file from csplain which disables
the \xordcode primitive. Use
initex \let\enc=u \input csplain.ini
for csplain generation instead this file.
If you are using ISO8859-2 input encoding in csplain,
you can skip this error message.}
\errmessage{I can't set the xord/xchr to identity mapping}
\def\xchrcode\count255=\count255{} \def\xordcode\count255=\count255{}
\fi
\count255=128
\loop \xordcode\count255=\count255
\xchrcode\count255=\count255
\advance\count255 by 1
\ifnum \count255<256 \repeat
\egroup
% we remove the current conversion table, if exists:
{\catcode`\^^@=12
\gdef\clearmubytes{\bgroup \count255=1
\loop \uccode`X=\count255
\uppercase{\mubyte XX\endmubyte}%
\advance\count255 by1
\ifnum\count255<256 \repeat
\mubyte ^^@^^@\endmubyte
\egroup}
}
\clearmubytes
% include these first, so we can redefine some characters better later here
\input utf8cseq
\input utf8math
\input utf8unkn
% now, the conversion table is created:
\mubyte ^^80 ^^c4^^82\endmubyte % latin capital letter a with breve
\mubyte ^^81 ^^c4^^84\endmubyte % latin capital letter a with ogonek
\mubyte ^^82 ^^c4^^86\endmubyte % latin capital letter c with acute
\mubyte ^^83 ^^c4^^8c\endmubyte % latin capital letter c with caron
\mubyte ^^84 ^^c4^^8e\endmubyte % latin capital letter d with caron
\mubyte ^^85 ^^c4^^9a\endmubyte % latin capital letter e with caron
\mubyte ^^86 ^^c4^^98\endmubyte % latin capital letter e with ogonek
\mubyte ^^87 ^^c4^^9e\endmubyte % latin capital letter g with breve
\mubyte ^^88 ^^c4^^b9\endmubyte % latin capital letter l with acute
\mubyte ^^89 ^^c4^^bd\endmubyte % latin capital letter l with caron
\mubyte ^^8a ^^c5^^81\endmubyte % latin capital letter l with stroke
\mubyte ^^8b ^^c5^^83\endmubyte % latin capital letter n with acute
\mubyte ^^8c ^^c5^^87\endmubyte % latin capital letter n with caron
\mubyte ^^8d ^^c5^^8a\endmubyte % latin capital letter eng (sami)
\mubyte ^^8e ^^c5^^90\endmubyte % latin capital letter o with double acute
\mubyte ^^8f ^^c5^^94\endmubyte % latin capital letter r with acute
\mubyte ^^90 ^^c5^^98\endmubyte % latin capital letter r with caron
\mubyte ^^91 ^^c5^^9a\endmubyte % latin capital letter s with acute
\mubyte ^^92 ^^c5^^a0\endmubyte % latin capital letter s with caron
\mubyte ^^93 ^^c5^^9e\endmubyte % latin capital letter s with cedilla
\mubyte ^^94 ^^c5^^a4\endmubyte % latin capital letter t with caron
\mubyte ^^95 ^^c5^^a2\endmubyte % latin capital letter t with cedilla
\mubyte ^^96 ^^c5^^b0\endmubyte % latin capital letter u with double acute
\mubyte ^^97 ^^c5^^ae\endmubyte % latin capital letter u with ring above
\mubyte ^^98 ^^c5^^b8\endmubyte % latin capital letter y with diaeresis
\mubyte ^^99 ^^c5^^b9\endmubyte % latin capital letter z with acute
\mubyte ^^9a ^^c5^^bd\endmubyte % latin capital letter z with caron
\mubyte ^^9b ^^c5^^bb\endmubyte % latin capital letter z with dot above
\mubyte ^^9c ^^c4^^b2\endmubyte % latin capital ligature ij
\mubyte ^^9d ^^c4^^b0\endmubyte % latin capital letter i with dot above
\mubyte ^^9e ^^c4^^91\endmubyte % latin small letter d with stroke
\mubyte ^^9f ^^c2^^a7\endmubyte % section sign
\mubyte ^^a0 ^^c4^^83\endmubyte % latin small letter a with breve
\mubyte ^^a1 ^^c4^^85\endmubyte % latin small letter a with ogonek
\mubyte ^^a2 ^^c4^^87\endmubyte % latin small letter c with acute
\mubyte ^^a3 ^^c4^^8d\endmubyte % latin small letter c with caron
\mubyte ^^a4 ^^c4^^8f\endmubyte % latin small letter d with caron
\mubyte ^^a5 ^^c4^^9b\endmubyte % latin small letter e with caron
\mubyte ^^a6 ^^c4^^99\endmubyte % latin small letter e with ogonek
\mubyte ^^a7 ^^c4^^9f\endmubyte % latin small letter g with breve
\mubyte ^^a8 ^^c4^^ba\endmubyte % latin small letter l with acute
\mubyte ^^a9 ^^c4^^be\endmubyte % latin small letter l with caron
\mubyte ^^aa ^^c5^^82\endmubyte % latin small letter l with stroke
\mubyte ^^ab ^^c5^^84\endmubyte % latin small letter n with acute
\mubyte ^^ac ^^c5^^88\endmubyte % latin small letter n with caron
\mubyte ^^ad ^^c5^^8b\endmubyte % latin small letter eng (sami)
\mubyte ^^ae ^^c5^^91\endmubyte % latin small letter o with double acute
\mubyte ^^af ^^c5^^95\endmubyte % latin small letter r with acute
\mubyte ^^b0 ^^c5^^99\endmubyte % latin small letter r with caron
\mubyte ^^b1 ^^c5^^9b\endmubyte % latin small letter s with acute
\mubyte ^^b2 ^^c5^^a1\endmubyte % latin small letter s with caron
\mubyte ^^b3 ^^c5^^9f\endmubyte % latin small letter s with cedilla
\mubyte ^^b4 ^^c5^^a5\endmubyte % latin small letter t with caron
\mubyte ^^b5 ^^c5^^a3\endmubyte % latin small letter t with cedilla
\mubyte ^^b6 ^^c5^^b1\endmubyte % latin small letter u with double acute
\mubyte ^^b7 ^^c5^^af\endmubyte % latin small letter u with ring above
\mubyte ^^b8 ^^c3^^bf\endmubyte % latin small letter y with diaeresis
\mubyte ^^b9 ^^c5^^ba\endmubyte % latin small letter z with acute
\mubyte ^^ba ^^c5^^be\endmubyte % latin small letter z with caron
\mubyte ^^bb ^^c5^^bc\endmubyte % latin small letter z with dot above
\mubyte ^^bc ^^c4^^b3\endmubyte % latin small ligature ij
\mubyte ^^bd ^^c2^^a1\endmubyte % inverted exclamation mark
\mubyte ^^be ^^c2^^bf\endmubyte % inverted question mark
\mubyte ^^bf ^^c2^^a3\endmubyte % pound sign
\mubyte ^^c0 ^^c3^^80\endmubyte % latin capital letter a with grave
\mubyte ^^c1 ^^c3^^81\endmubyte % latin capital letter a with acute
\mubyte ^^c2 ^^c3^^82\endmubyte % latin capital letter a with circumflex
\mubyte ^^c3 ^^c3^^83\endmubyte % latin capital letter a with tilde
\mubyte ^^c4 ^^c3^^84\endmubyte % latin capital letter a with diaeresis
\mubyte ^^c5 ^^c3^^85\endmubyte % latin capital letter a with ring above
\mubyte ^^c6 ^^c3^^86\endmubyte % latin capital letter ae (ash)
\mubyte ^^c7 ^^c3^^87\endmubyte % latin capital letter c with cedilla
\mubyte ^^c8 ^^c3^^88\endmubyte % latin capital letter e with grave
\mubyte ^^c9 ^^c3^^89\endmubyte % latin capital letter e with acute
\mubyte ^^ca ^^c3^^8a\endmubyte % latin capital letter e with circumflex
\mubyte ^^cb ^^c3^^8b\endmubyte % latin capital letter e with diaeresis
\mubyte ^^cc ^^c3^^8c\endmubyte % latin capital letter i with grave
\mubyte ^^cd ^^c3^^8d\endmubyte % latin capital letter i with acute
\mubyte ^^ce ^^c3^^8e\endmubyte % latin capital letter i with circumflex
\mubyte ^^cf ^^c3^^8f\endmubyte % latin capital letter i with diaeresis
\mubyte ^^d0 ^^c3^^90\endmubyte % latin capital letter eth (icelandic)
\mubyte ^^d1 ^^c3^^91\endmubyte % latin capital letter n with tilde
\mubyte ^^d2 ^^c3^^92\endmubyte % latin capital letter o with grave
\mubyte ^^d3 ^^c3^^93\endmubyte % latin capital letter o with acute
\mubyte ^^d4 ^^c3^^94\endmubyte % latin capital letter o with circumflex
\mubyte ^^d5 ^^c3^^95\endmubyte % latin capital letter o with tilde
\mubyte ^^d6 ^^c3^^96\endmubyte % latin capital letter o with diaeresis
\mubyte ^^d7 ^^c5^^92\endmubyte % latin capital ligature oe
\mubyte ^^d8 ^^c3^^98\endmubyte % latin capital letter o with stroke
\mubyte ^^d9 ^^c3^^99\endmubyte % latin capital letter u with grave
\mubyte ^^da ^^c3^^9a\endmubyte % latin capital letter u with acute
\mubyte ^^db ^^c3^^9b\endmubyte % latin capital letter u with circumflex
\mubyte ^^dc ^^c3^^9c\endmubyte % latin capital letter u with diaeresis
\mubyte ^^dd ^^c3^^9d\endmubyte % latin capital letter y with acute
\mubyte ^^de ^^c3^^9e\endmubyte % latin capital letter thorn (icelandic)
\mubyte ^^e0 ^^c3^^a0\endmubyte % latin small letter a with grave
\mubyte ^^e1 ^^c3^^a1\endmubyte % latin small letter a with acute
\mubyte ^^e2 ^^c3^^a2\endmubyte % latin small letter a with circumflex
\mubyte ^^e3 ^^c3^^a3\endmubyte % latin small letter a with tilde
\mubyte ^^e4 ^^c3^^a4\endmubyte % latin small letter a with diaeresis
\mubyte ^^e5 ^^c3^^a5\endmubyte % latin small letter a with ring above
\mubyte ^^e6 ^^c3^^a6\endmubyte % latin small letter ae (ash)
\mubyte ^^e7 ^^c3^^a7\endmubyte % latin small letter c with cedilla
\mubyte ^^e8 ^^c3^^a8\endmubyte % latin small letter e with grave
\mubyte ^^e9 ^^c3^^a9\endmubyte % latin small letter e with acute
\mubyte ^^ea ^^c3^^aa\endmubyte % latin small letter e with circumflex
\mubyte ^^eb ^^c3^^ab\endmubyte % latin small letter e with diaeresis
\mubyte ^^ec ^^c3^^ac\endmubyte % latin small letter i with grave
\mubyte ^^ed ^^c3^^ad\endmubyte % latin small letter i with acute
\mubyte ^^ee ^^c3^^ae\endmubyte % latin small letter i with circumflex
\mubyte ^^ef ^^c3^^af\endmubyte % latin small letter i with diaeresis
\mubyte ^^f0 ^^c3^^b0\endmubyte % latin small letter eth (icelandic)
\mubyte ^^f1 ^^c3^^b1\endmubyte % latin small letter n with tilde
\mubyte ^^f2 ^^c3^^b2\endmubyte % latin small letter o with grave
\mubyte ^^f3 ^^c3^^b3\endmubyte % latin small letter o with acute
\mubyte ^^f4 ^^c3^^b4\endmubyte % latin small letter o with circumflex
\mubyte ^^f5 ^^c3^^b5\endmubyte % latin small letter o with tilde
\mubyte ^^f6 ^^c3^^b6\endmubyte % latin small letter o with diaeresis
\mubyte ^^f7 ^^c5^^93\endmubyte % latin small ligature oe
\mubyte ^^f8 ^^c3^^b8\endmubyte % latin small letter o with stroke
\mubyte ^^f9 ^^c3^^b9\endmubyte % latin small letter u with grave
\mubyte ^^fa ^^c3^^ba\endmubyte % latin small letter u with acute
\mubyte ^^fb ^^c3^^bb\endmubyte % latin small letter u with circumflex
\mubyte ^^fc ^^c3^^bc\endmubyte % latin small letter u with diaeresis
\mubyte ^^fd ^^c3^^bd\endmubyte % latin small letter y with acute
\mubyte ^^fe ^^c3^^be\endmubyte % latin small letter thorn (icelandic)
\mubyte ^^ff ^^c3^^9f\endmubyte % latin small letter sharp s (german)
% Non-characters
\chardef\erqq="11
\mubyte \erqq ^^e2^^80^^9d\endmubyte % right double quotation mark
\chardef\erq="27
\mubyte \erq ^^e2^^80^^99\endmubyte % right single quotation mark
% there's no \elqq, it's the same Unicode character as \crqq
\chardef\flq="0E
\chardef\frq="0F
\mubyte \flq ^^e2^^80^^b9\endmubyte % single left-pointing angle quotation mark
\mubyte \frq ^^e2^^80^^ba\endmubyte % single right-pointing angle quotation mark
\chardef\endash="15
\chardef\emdash="16
\mubyte \endash ^^e2^^80^^93\endmubyte % en dash
\mubyte \emdash ^^e2^^80^^94\endmubyte % em dash
\chardef\utfligatureff="1B
\chardef\utfligaturefi="1C
\chardef\utfligaturefl="1D
\chardef\utfligatureffi="1E
\chardef\utfligatureffl="1F
\mubyte \utfligatureff ^^ef^^ac^^80\endmubyte % latin small ligature ff
\mubyte \utfligaturefi ^^ef^^ac^^81\endmubyte % latin small ligature fi
\mubyte \utfligaturefl ^^ef^^ac^^82\endmubyte % latin small ligature fl
\mubyte \utfligatureffi ^^ef^^ac^^83\endmubyte % latin small ligature ffi
\mubyte \utfligatureffl ^^ef^^ac^^84\endmubyte % latin small ligature ffl
% You can add more UTF-8 codes here. You can map these codes to
% control sequences (see encdoc.tex for more datails) so,
% the number of UTF-8 codes examined by TeX is unlimited.
% ...
\mubytein=1 \mubyteout=3
%% for compatibility with hyphen.lan file:
\let\csaccents=\relax \let\cmaccents=\relax
% now we still have to deal with accents
\input t1macro \input encmacro
% This needed for hyphenation patterns.
% (1) Czech/Slovak alphabet
% input TeX lc uc sf cat prn sequence
\setcharcode ? "C1 "E1 "C1 999 11 1 \texaccent \'A
\setcharcode ? "E1 "E1 "C1 1000 11 1 \texaccent \'a
\setcharcode ? "C4 "E4 "C4 999 11 1 \texaccent \"A
\setcharcode ? "E4 "E4 "C4 1000 11 1 \texaccent \"a
\setcharcode ? "83 "A3 "83 999 11 1 \texaccent \v C
\setcharcode ? "A3 "A3 "83 1000 11 1 \texaccent \v c
\setcharcode ? "84 "A4 "84 999 11 1 \texaccent \v D
\setcharcode ? "A4 "A4 "84 1000 11 1 \texaccent \v d
\setcharcode ? "C9 "E9 "C9 999 11 1 \texaccent \'E
\setcharcode ? "E9 "E9 "C9 1000 11 1 \texaccent \'e
\setcharcode ? "85 "A5 "85 999 11 1 \texaccent \v E
\setcharcode ? "A5 "A5 "85 1000 11 1 \texaccent \v e
\setcharcode ? "CD "ED "CD 999 11 1 \texaccent \'I
\setcharcode ? "ED "ED "CD 1000 11 1 \texaccent \'i \texaccent \'\i
\setcharcode ? "88 "A8 "88 999 11 1 \texaccent \'L
\setcharcode ? "A8 "A8 "88 1000 11 1 \texaccent \'l
\setcharcode ? "89 "A9 "89 999 11 1 \texaccent \v L
\setcharcode ? "A9 "A9 "89 1000 11 1 \texaccent \v l
\setcharcode ? "8C "AC "8C 999 11 1 \texaccent \v N
\setcharcode ? "AC "AC "8C 1000 11 1 \texaccent \v n
\setcharcode ? "D3 "F3 "D3 999 11 1 \texaccent \'O
\setcharcode ? "F3 "F3 "D3 1000 11 1 \texaccent \'o
\setcharcode ? "D4 "F4 "D4 999 11 1 \texaccent \^O
\setcharcode ? "F4 "F4 "D4 1000 11 1 \texaccent \^o
\setcharcode ? "D6 "F6 "D6 999 11 1 \texaccent \"O
\setcharcode ? "F6 "F6 "D6 1000 11 1 \texaccent \"o
\setcharcode ? "8F "AF "8F 999 11 1 \texaccent \'R
\setcharcode ? "AF "AF "8F 1000 11 1 \texaccent \'r
\setcharcode ? "90 "B0 "90 999 11 1 \texaccent \v R
\setcharcode ? "B0 "B0 "90 1000 11 1 \texaccent \v r
\setcharcode ? "92 "B2 "92 999 11 1 \texaccent \v S
\setcharcode ? "B2 "B2 "92 1000 11 1 \texaccent \v s
\setcharcode ? "94 "B4 "94 999 11 1 \texaccent \v T
\setcharcode ? "B4 "B4 "94 1000 11 1 \texaccent \v t
\setcharcode ? "DA "FA "DA 999 11 1 \texaccent \'U
\setcharcode ? "FA "FA "DA 1000 11 1 \texaccent \'u
\setcharcode ? "97 "B7 "97 999 11 1 \texaccent \r U
\setcharcode ? "B7 "B7 "97 1000 11 1 \texaccent \r u
\setcharcode ? "DC "FC "DC 999 11 1 \texaccent \"U
\setcharcode ? "FC "FC "DC 1000 11 1 \texaccent \"u
\setcharcode ? "DD "FD "DD 999 11 1 \texaccent \'Y
\setcharcode ? "FD "FD "DD 1000 11 1 \texaccent \'y
\setcharcode ? "9A "BA "9A 999 11 1 \texaccent \v Z
\setcharcode ? "BA "BA "9A 1000 11 1 \texaccent \v z
% (2) Non Czech/Slovak alphabet
% input TeX lc uc sf cat prn sequence
\setcharcode ? "81 "A1 "81 999 11 1 \texaccent \og A
\setcharcode ? "A1 "A1 "81 1000 11 1 \texaccent \og a
\setcharcode ? "8A "AA "8A 999 11 1 \texmacro \L
\setcharcode ? "AA "AA "8A 1000 11 1 \texmacro \l
\setcharcode ? "91 "B1 "91 999 11 1 \texaccent \'S
\setcharcode ? "B1 "B1 "91 1000 11 1 \texaccent \'s
\setcharcode ? "93 "B3 "93 999 11 1 \texaccent \c S
\setcharcode ? "B3 "B3 "93 1000 11 1 \texaccent \c s
\setcharcode ? "99 "B9 "99 999 11 1 \texaccent \'Z
\setcharcode ? "B9 "B9 "99 1000 11 1 \texaccent \'z
\setcharcode ? "9B "BB "9B 999 11 1 \texaccent \.Z
\setcharcode ? "BB "BB "9B 1000 11 1 \texaccent \.z
\setcharcode ? "C2 "E2 "C2 999 11 1 \texaccent \^A
\setcharcode ? "E2 "E2 "C2 1000 11 1 \texaccent \^a
\setcharcode ? "80 "A0 "80 999 11 1 \texaccent \u A
\setcharcode ? "A0 "A0 "80 1000 11 1 \texaccent \u a
\setcharcode ? "82 "A2 "82 999 11 1 \texaccent \'C
\setcharcode ? "A2 "A2 "82 1000 11 1 \texaccent \'c
\setcharcode ? "C7 "E7 "C7 999 11 1 \texaccent \c C
\setcharcode ? "E7 "E7 "C7 1000 11 1 \texaccent \c c
\setcharcode ? "86 "A6 "86 999 11 1 \texaccent \og E
\setcharcode ? "A6 "A6 "86 1000 11 1 \texaccent \og e
\setcharcode ? "CB "EB "CB 999 11 1 \texaccent \"E
\setcharcode ? "EB "EB "CB 1000 11 1 \texaccent \"e
\setcharcode ? "CE "EE "CE 999 11 1 \texaccent \^I
\setcharcode ? "EE "EE "CE 1000 11 1 \texaccent \^i \texaccent \^\i
\setcharcode ? "D0 "F0 "D0 999 11 1 \texmacro \Dslash
\setcharcode ? "F0 "F0 "D0 1000 11 1 \texmacro \dslash
\setcharcode ? "8B "AB "8B 999 11 1 \texaccent \'N
\setcharcode ? "AB "AB "8B 1000 11 1 \texaccent \'n
\setcharcode ? "8E "AE "8E 999 11 1 \texaccent \H O
\setcharcode ? "AE "AE "8E 1000 11 1 \texaccent \H o
\setcharcode ? "96 "B6 "96 999 11 1 \texaccent \H U
\setcharcode ? "B6 "B6 "96 1000 11 1 \texaccent \H u
\setcharcode ? "95 "B5 "95 999 11 1 \texaccent \c T
\setcharcode ? "B5 "B5 "95 1000 11 1 \texaccent \c t
\setcharcode ? "FF "FF "DF 1000 11 1 \texmacro \ss
\redefaccent \'
\redefaccent \v
\redefaccent \"
\redefaccent \^
\redefaccent \r
% finally, we can forbid the encTeX primitives in document
% (this is commented out here because it is only an example):
% \let\xordcode=\undefined \let\xchrcode=\undefined\let
% \let\xprncode=\undefined
% \let\mubytein=\undefined \let\mubyteout=\undefined
% \let\mubyte=\undefined \let\endmubyte=\undefined
\endinput