1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
|
%%% The re-encoding table for Czech/Slovak alphabet using encTeX,
%%% v.Sep.2005 (C) Petr Ol\v s\'ak
%%% input: UTF8, internal TeX: T1Encoding
%%% Oct.2012 added plainTeX csnames mapping and \setucode definition.
% This is very simple setting of Czech and Slovak alphabet 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
extension of TeX binary. See ftp://math.feld.cvut.cz/pub/olsak/enctex.}
\errmessage{The encTeX Feb2003 or later is not detected -- re-encoding is impossible}
\endinput \fi
%% TeX input
\mubyte ^^c1 ^^c3^^81\endmubyte % \'A
\mubyte ^^e1 ^^c3^^a1\endmubyte % \'a
\mubyte ^^c9 ^^c3^^89\endmubyte % \'E
\mubyte ^^e9 ^^c3^^a9\endmubyte % \'e
\mubyte ^^cd ^^c3^^8d\endmubyte % \'I
\mubyte ^^ed ^^c3^^ad\endmubyte % \'i
\mubyte ^^d3 ^^c3^^93\endmubyte % \'O
\mubyte ^^f3 ^^c3^^b3\endmubyte % \'o
\mubyte ^^da ^^c3^^9a\endmubyte % \'U
\mubyte ^^fa ^^c3^^ba\endmubyte % \'u
\mubyte ^^dd ^^c3^^9d\endmubyte % \'Y
\mubyte ^^fd ^^c3^^bd\endmubyte % \'y
\mubyte ^^d4 ^^c3^^94\endmubyte % \^O
\mubyte ^^f4 ^^c3^^b4\endmubyte % \^o
\mubyte ^^c4 ^^c3^^84\endmubyte % \"A
\mubyte ^^e4 ^^c3^^a4\endmubyte % \"a
\mubyte ^^d6 ^^c3^^96\endmubyte % \"O
\mubyte ^^f6 ^^c3^^b6\endmubyte % \"o
\mubyte ^^dc ^^c3^^9c\endmubyte % \"U
\mubyte ^^fc ^^c3^^bc\endmubyte % \"u
\mubyte ^^83 ^^c4^^8c\endmubyte % \v C
\mubyte ^^a3 ^^c4^^8d\endmubyte % \v c
\mubyte ^^84 ^^c4^^8e\endmubyte % \v D
\mubyte ^^a4 ^^c4^^8f\endmubyte % \v d
\mubyte ^^85 ^^c4^^9a\endmubyte % \v E
\mubyte ^^a5 ^^c4^^9b\endmubyte % \v e
\mubyte ^^88 ^^c4^^b9\endmubyte % \' L
\mubyte ^^a8 ^^c4^^ba\endmubyte % \' l
\mubyte ^^89 ^^c4^^bd\endmubyte % \v L
\mubyte ^^a9 ^^c4^^be\endmubyte % \v l
\mubyte ^^8c ^^c5^^87\endmubyte % \v N
\mubyte ^^ac ^^c5^^88\endmubyte % \v n
\mubyte ^^90 ^^c5^^98\endmubyte % \v R
\mubyte ^^b0 ^^c5^^99\endmubyte % \v r
\mubyte ^^92 ^^c5^^a0\endmubyte % \v S
\mubyte ^^b2 ^^c5^^a1\endmubyte % \v s
\mubyte ^^94 ^^c5^^a4\endmubyte % \v T
\mubyte ^^b4 ^^c5^^a5\endmubyte % \v t
\mubyte ^^97 ^^c5^^ae\endmubyte % \r U
\mubyte ^^b7 ^^c5^^af\endmubyte % \r u
\mubyte ^^9a ^^c5^^bd\endmubyte % \v Z
\mubyte ^^ba ^^c5^^be\endmubyte % \v z
\mubyte ^^8f ^^c5^^94\endmubyte % \' R
\mubyte ^^af ^^c5^^95\endmubyte % \' r
\def\setcsucode #1 #2 #3 #4 #5{} % to skip the data from utf8lat1.tex
% and utf8lata.tex
% \setucode re-definition in order to map all T1 slots rawly during \input
% utf8lat1.tex or utf8lata.tex. This is usable if the text occurres in
% \upercase and \lowercase arguments.
\def\setucode #1 #2 #3 #4 #5{%
\ifx*#4% The character is not provided by T1 encoding, we need to use csname:
\expandafter \mubyte \csname#1\endcsname #3\endmubyte
\expandafter \ifx \csname#1\endcsname \relax
\expandafter \def\csname#1\endcsname{#5}%
\fi
\else % raw UTF-8 to T1 mapping is possible:
\mubyte #4 #3\endmubyte
\fi
}
% 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 ^^ff ^^c3^^9f\endmubyte % german sharp s
\mubyte ^^aa ^^c5^^82\endmubyte % l slashed
\mubyte ^^8a ^^c5^^81\endmubyte % L slashed
\mubyte ^^e6 ^^c3^^a6\endmubyte % ae ligature
\mubyte ^^f7 ^^c5^^93\endmubyte % oe ligature
\mubyte ^^f8 ^^c3^^b8\endmubyte % o slash
\mubyte ^^c6 ^^c3^^86\endmubyte % AE ligature
\mubyte ^^d7 ^^c5^^92\endmubyte % OE ligature
\mubyte ^^d8 ^^c3^^98\endmubyte % O slash
\mubyte \i ^^c4^^b1\endmubyte % dotless i
\mubyte \j ^^c8^^b7\endmubyte % dotless j
\mubyte ^^e5 ^^c3^^a5\endmubyte % a with ring
\mubyte ^^c5 ^^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
\mubyte \erqq ^^e2^^80^^9d\endmubyte % English right double quote
\mubyte \elq ^^e2^^80^^98\endmubyte % English left single quote
\mubyte \erq ^^e2^^80^^99\endmubyte % English right single quote
% user can write \input utf8lat1 to access all T1 codes
\ifx\baseutfencoding\undefined \else \expandafter\endinput\fi
% if the csplain is used, we cannot process this part of the file. May be
% somebody used it from iniTeX...
\let\baseutfencoding\relax
\global\everyjob=\expandafter{\the\everyjob
\message{The utf8->T1 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=3 \mubytelog=1
\endinput
|
