summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/tex/generic/enctex/utf8-csf.tex
blob: b1291cb48c8d72626725e1889a106a7594e3b20a (plain)
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
% utf8-csf.tex
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% This file implements the conversion from UTF8 to ISO-8859-2
% encoding (used by CSfonts in csplain and cslatex).
% 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. 2003.}
   \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 ^^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 ^^c8  ^^c4^^8c\endmubyte % \v C
\mubyte ^^e8  ^^c4^^8d\endmubyte % \v c
\mubyte ^^cf  ^^c4^^8e\endmubyte % \v D
\mubyte ^^ef  ^^c4^^8f\endmubyte % \v d
\mubyte ^^cc  ^^c4^^9a\endmubyte % \v E
\mubyte ^^ec  ^^c4^^9b\endmubyte % \v e
\mubyte ^^c5  ^^c4^^b9\endmubyte % \' L
\mubyte ^^e5  ^^c4^^ba\endmubyte % \' l
\mubyte ^^a5  ^^c4^^bd\endmubyte % \v L
\mubyte ^^b5  ^^c4^^be\endmubyte % \v l

\mubyte ^^d2  ^^c5^^87\endmubyte % \v N
\mubyte ^^f2  ^^c5^^88\endmubyte % \v n
\mubyte ^^d8  ^^c5^^98\endmubyte % \v R
\mubyte ^^f8  ^^c5^^99\endmubyte % \v r
\mubyte ^^a9  ^^c5^^a0\endmubyte % \v S
\mubyte ^^b9  ^^c5^^a1\endmubyte % \v s
\mubyte ^^ab  ^^c5^^a4\endmubyte % \v T
\mubyte ^^bb  ^^c5^^a5\endmubyte % \v t
\mubyte ^^d9  ^^c5^^ae\endmubyte % \r U
\mubyte ^^f9  ^^c5^^af\endmubyte % \r u
\mubyte ^^ae  ^^c5^^bd\endmubyte % \v Z
\mubyte ^^be  ^^c5^^be\endmubyte % \v z
\mubyte ^^c0  ^^c5^^94\endmubyte % \' R
\mubyte ^^e0  ^^c5^^95\endmubyte % \' r

% Non-characters
\chardef\erqq="22
\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, \elq, they are the same Unicode character as \crqq, \crq
\chardef\endash="7B
\chardef\emdash="7C
\mubyte \endash ^^e2^^80^^93\endmubyte % en dash
\mubyte \emdash ^^e2^^80^^94\endmubyte % em dash
\chardef\utfinvexclamation="3C
\chardef\utfinvquestion="3E
\mubyte \utfinvexclamation ^^c2^^a1\endmubyte % inverted exclamation mark
\mubyte \utfinvquestion ^^c2^^bf\endmubyte % inverted question mark
\chardef\utfligatureff="0B
\chardef\utfligaturefi="0C
\chardef\utfligaturefl="0D
\chardef\utfligatureffi="0E
\chardef\utfligatureffl="0F
\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 csfmacro \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  ?  "C8  "E8  "C8   999  11  1  \texaccent \v C
\setcharcode  ?  "E8  "E8  "C8  1000  11  1  \texaccent \v c
\setcharcode  ?  "CF  "EF  "CF   999  11  1  \texaccent \v D
\setcharcode  ?  "EF  "EF  "CF  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  ?  "CC  "EC  "CC   999  11  1  \texaccent \v E
\setcharcode  ?  "EC  "EC  "CC  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  ?  "C5  "E5  "C5   999  11  1  \texaccent \'L
\setcharcode  ?  "E5  "E5  "C5  1000  11  1  \texaccent \'l
\setcharcode  ?  "A5  "B5  "A5   999  11  1  \texaccent \v L
\setcharcode  ?  "B5  "B5  "A5  1000  11  1  \texaccent \v l
\setcharcode  ?  "D2  "F2  "D2   999  11  1  \texaccent \v N
\setcharcode  ?  "F2  "F2  "D2  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  ?  "C0  "E0  "C0   999  11  1  \texaccent \'R
\setcharcode  ?  "E0  "E0  "C0  1000  11  1  \texaccent \'r
\setcharcode  ?  "D8  "F8  "D8   999  11  1  \texaccent \v R
\setcharcode  ?  "F8  "F8  "D8  1000  11  1  \texaccent \v r
\setcharcode  ?  "A9  "B9  "A9   999  11  1  \texaccent \v S
\setcharcode  ?  "B9  "B9  "A9  1000  11  1  \texaccent \v s
\setcharcode  ?  "AB  "BB  "AB   999  11  1  \texaccent \v T
\setcharcode  ?  "BB  "BB  "AB  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  ?  "D9  "F9  "D9   999  11  1  \texaccent \r U
\setcharcode  ?  "F9  "F9  "D9  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  ?  "AE  "BE  "AE   999  11  1  \texaccent \v Z
\setcharcode  ?  "BE  "BE  "AE  1000  11  1  \texaccent \v z

\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