Revision a91ede24c84df04fcfb986fbc928ac28bb6dfe37 authored by Joseph Wright on 21 July 2020, 09:02:33 UTC, committed by Joseph Wright on 21 July 2020, 09:02:33 UTC
1 parent 2df6a50
utf8ienc.dtx
% \iffalse meta-comment
%
% Copyright (C) 1993-2020
% The LaTeX3 Project and any individual authors listed elsewhere
% in this file.
%
% This file is part of the LaTeX base system.
% -------------------------------------------
%
% It may be distributed and/or modified under the
% conditions of the LaTeX Project Public License, either version 1.3c
% of this license or (at your option) any later version.
% The latest version of this license is in
% https://www.latex-project.org/lppl.txt
% and version 1.3c or later is part of all distributions of LaTeX
% version 2008 or later.
%
% This file has the LPPL maintenance status "maintained".
%
% The list of all files belonging to the LaTeX base distribution is
% given in the file `manifest.txt'. See also `legal.txt' for additional
% information.
%
% The list of derived (unpacked) files belonging to the distribution
% and covered by LPPL is defined by the unpacking scripts (with
% extension .ins) which are part of the distribution.
%
% \fi
%
% \iffalse
%<*driver>
\documentclass{ltxdoc}
\usepackage[latin1,utf8]{inputenc}% force utf8 to be re-loaded, to get version info
\GetFileInfo{utf8.def}
\title{Providing some UTF-8 support via \texttt{inputenc}}
\date{\fileversion\space\filedate{} printed \today}
\author{%
David Carlisle \and Frank Mittelbach \and
Chris Rowley\thanks{Borrowing heavily from tables by Sebastian Rahtz; some table
and code cleanup by Javier Bezos}}
\begin{document}
\MaintainedByLaTeXTeam{latex}
\maketitle
\tableofcontents
\DocInput{utf8ienc.dtx}
\end{document}
%</driver>
% \fi
%
% \newpage
%
% \section{Introduction}
%
%
% \subsection{Background and general stuff}
%
% For many reasons what this package provides is a long way from any
% type of `Unicode compliance'.
%
% In stark contrast to 8-bit character sets, with 16 or more bits it can
% easily be very inefficient to support the full range.\footnote{In
% fact, \LaTeX's current 8-bit support does not go so far as to make
% all 8-bit characters into valid input.} Moreover, useful support of
% character input by a typesetting system overwhelmingly means finding
% an acceptable visual representation of a sequence of characters and
% this, for \LaTeX{}, means having available a suitably encoded 8-bit
% font.
%
% Unfortunately it is not possible to predict exactly what valid UTF-8
% octet sequences will appear in a particular file so it is best to
% make all the unsupported but valid sequences produce a reasonably
% clear and noticeable error message.
%
% There are two directions from which to approach the question of what
% to load. One is to specify the ranges of Unicode characters that will
% result in some sensible typesetting; this requires the provider to
% ensure that suitable fonts are loaded and that these input characters
% generate the correct typesetting via the encodings of those fonts. The
% other is to inspect the font encodings to be used and use these to
% define which input Unicode characters should be supported.
%
% For Western European languages, at least, going in either direction
% leads to many straightforward decisions and a few that are more
% subjective. In both cases some of the specifications are \TeX{}
% specific whilst most are independent of the particular typesetting
% software in use.
%
% As we have argued elsewhere, \LaTeX{} needs to refer to characters via
% `seven-bit-text' names and, so far, these have been chosen by
% reference to historical sources such as Plain \TeX{} or Adobe encoding
% descriptions. It is unclear whether this ad hoc naming structure should
% simply be extended or whether it would be useful to
% supplement it with standardised internal Unicode character names such as
% one or more of the following:\footnote{Burkhard und Holger Mittelbach
% spielen mit mir! Sie haben etwas hier geschrieben.}
%
% \begin{verbatim}
% \ltxutwochar <4 hex digits>
%
% \ltxuchar {<hex digits>}
% B H U R R R
%
% \ltxueightchartwo <2 utf8 octets as 8-bit char tokens>
% \ltxueightcharthree <3 utf8 octets ...>
% \ltxueightcharfour <4 utf8 octets ...>
% \end{verbatim}
%
%
% \subsection{More specific stuff}
%
% In addition to setting up the mechanism for reading UTF-8 characters
% and specifying the \LaTeX-level support available, this package
% contains support for some default historically expected \TeX-related
% characters and some example `Unicode definition files' for standard
% font encodings.
%
%
% \subsection{Notes}
%
% This package does not support Unicode combining characters as \TeX{}
% is not really equipped to make this possible.
%
% No attempt is made to be useful beyond Latin, and maybe Cyrillic,
% for European languages (as of now).
%
%
% \subsection{Basic operation of the code}
%
% The \texttt{inputenc} package makes the upper 8-bit characters active and
% assigns to all of them an error message. It then waits for the
% input encoding files to change this set-up. Similarly, whenever
% |\inputencoding| is encountered in a document, first the upper
% 8-bit characters are set back to produce an error and then the
% definitions for the new input encoding are loaded, changing some of the
% previous settings.
%
% The 8-bit input encodings currently supported by \texttt{inputenc}
% all use declarations such as |\DeclareInputText| and the like to map an
% 8-bit number to some \LaTeX{} internal form, e.g.~to |\"a|.
%
% The situation when supporting UTF-8 as the input encoding is
% different, however. Here we only have to set up the actions of
% those 8-bit numbers that can be the first octet in a UTF-8
% representation of a Unicode character. But we cannot simply set
% this to some internal \LaTeX{} form since the Unicode character
% consists of more than one octet; instead we have to define this
% starting octet to parse the right number of further octets that
% together form the UTF-8 representation of some Unicode character.
%
% Therefore when switching to \texttt{utf8} within the
% \texttt{inputenc} framework the characters with numbers (hex)
% from \texttt{"C2} to \texttt{"DF} are defined to parse for a
% second octet following, the characters from \texttt{"E0} to
% \texttt{"EF} are defined to parse for two more octets and finally
% the characters from \texttt{"F0} to \texttt{"F3} are defined to
% parse for three additional octets. These additional octets are
% always in the range \texttt{"80} to \texttt{"B9}.
%
% Thus, when such a character is encountered in the document (so
% long as expansion is not prohibited) a defined number of
% additional octets (8-bit characters) are read and from them a
% unique control sequence name is immediately constructed.
%
% This control sequence is either defined (good) or undefined
% (likely); in the latter case the user gets an error message
% saying that this UTF-8 sequence (or, better, Unicode character)
% is not supported.
%
% If the control sequence is set up to do something useful then it will
% expand to a \LaTeX{} internal form: e.g.~for the utf8 sequence of
% two octets \texttt{"C3 "A4} we get |\"a| as the
% internal form which then, depending on the font encoding,
% eventually resolves to the single glyph `latin-a-umlaut' or to
% the composite glyph `latin-a with an umlaut accent'.
%
% These mappings from (UTF-8 encoded) Unicode characters to \LaTeX{}
% internal forms are made indirectly. The code below provides a
% declaration |\DeclareUnicodeCharacter| which maps Unicode numbers
% (as hexadecimal) to \LaTeX{} internal forms.
%
% This mapping needs to be set up only once so it is done at
% |\begin{document}| by looking at the list of font encodings that
% are loaded by the document and providing mappings related to
% those font encodings whenever these are available. Thus at most
% only those Unicode characters that can be represented by the glyphs
% available in these encodings will be defined.
%
% Technically this is done by loading one file per encoding,
% if available, that is supposed to provide the necessary mapping
% information.
%
%
% \StopEventually{}
%
%
%
%
% \section{Coding}
%
% \subsection{Housekeeping}
%
% The usual introductory bits and pieces:
%
% \begin{macrocode}
%<utf8>\ProvidesFile{utf8.def}
%<test>\ProvidesFile{utf8-test.tex}
%<+lcy> \ProvidesFile{lcyenc.dfu}
%<+ly1> \ProvidesFile{ly1enc.dfu}
%<+oms> \ProvidesFile{omsenc.dfu}
%<+ot1> \ProvidesFile{ot1enc.dfu}
%<+ot2> \ProvidesFile{ot2enc.dfu}
%<+t1> \ProvidesFile{t1enc.dfu}
%<+t2a> \ProvidesFile{t2aenc.dfu}
%<+t2b> \ProvidesFile{t2benc.dfu}
%<+t2c> \ProvidesFile{t2cenc.dfu}
%<+ts1> \ProvidesFile{ts1enc.dfu}
%<+x2> \ProvidesFile{x2enc.dfu}
%<+all> \ProvidesFile{utf8enc.dfu}
%<-utf8-2018> [2019/11/14 v1.2k UTF-8 support for inputenc]
% \end{macrocode}
%
% \begin{macrocode}
%<*utf8>
% \end{macrocode}
% This is a temporary fix for the e-p\TeX{} / e-up\TeX{} engines that do not yet
% have a |\ifincsname| primitive. Once this is available the extra file will
% be dropped.
% \changes{v1.2h}{2019/07/09}{Temp rollback fix for e-pTeX}
% \begin{macrocode}
\ifx\ifincsname\@undefined % old e-pTeX or e-upTeX engines
\input utf8-2018.def
\expandafter\@firstofone
\else
\expandafter\@gobble
\fi
\endinput
% \end{macrocode}
%
% \begin{macrocode}
\makeatletter
% \end{macrocode}
% We restore the |\catcode| of space (which is set to ignore in
% \texttt{inputenc}) while reading \texttt{.def} files. Otherwise
% we would need to explicitly use |\space| all over the place in
% error and log messages.
% \changes{v1.1d}{2004/05/08}{Explicitly set catcode of space}
% \begin{macrocode}
\catcode`\ \saved@space@catcode
% \end{macrocode}
%
%
%
% \subsection{Parsing UTF-8 input}
%
% A UTF-8 char (that is not actually a 7-bit char, i.e.~a single
% octet) is parsed as follows: each starting octet is an active
% \TeX{} character token; each of these is defined below to be a
% macro with one to three arguments nominally (depending on the
% starting octet). It calls one of |\UTFviii@two@octets|,
% |\UTFviii@three@octets|, or |\UTFviii@four@octets| which then
% actually picks up the remaining octets as the argument(s).
%
% \begin{itemize}
% \item When typesetting we pick up the necessary number of additional
% octets, check if they form a command that \LaTeX{} knows about
% (via \cs{csname} \texttt{u8:}\cs{string}
% \verb=#1=\cs{string} \verb=#2...=\cs{endcsname}) and if so use that
% for typesetting. \cs{string} is needed as the octets may (all?) be
% active and we want the literal values in the name.
%
% \item If the UTF-8 character is going to be part of a label, then it is
% essentially becoming part of some csname and with the
% test \cs{ifincsname} we can find this out. If so, we render the whole
% sequence off octets harmless by using \cs{string} too when the
% starting octet executes (\cs{UTF@...@octets@string}).
%
% \item Another possible case is that \cs{protect} has \emph{not} the meaning
% of \cs{typeset@protect}. In that case we may do a \cs{write} or we may do
% a \cs{protected@edef} or \ldots{} In all such cases we want to keep the
% sequence of octets unchanged, but we can't use \cs{string} this time, since at
% least in the case of \cs{protect@edef} the result may later be
% typeset after all (in fact that is quite likely) and so at that
% point the starting octet needs to be an active character again
% (the others could be stringified). So for this case we use \cs{noexpand}
% ((\cs{UTF@...s@octets@noexpand}).
% \end{itemize}
%
% \begin{macro}{\UTFviii@two@octets}
% \changes{v1.2a}{2018/03/24}{Macros made `\cs{long} for improved error messages}%
% Putting that all together the code for a start octet of a two
% byte sequence would then look like this:
% \begin{macrocode}
\long\def\UTFviii@two@octets{%
\ifincsname
\expandafter \UTF@two@octets@string
\else
\ifx \protect\@typeset@protect \else
\expandafter\expandafter\expandafter \UTF@two@octets@noexpand
\fi
\fi
\UTFviii@two@octets@combine
}
% \end{macrocode}
% \cs{ifcsname} is tested first because that can be true even if we
% are otherwise doing typesetting. If this is the case we use
% \cs{string} on the whole octet
% sequence. \cs{UTF@two@octets@string} not only does this but also
% gets rid of the command \cs{UTFviii@two@octets@combine} in the input
% stream by picking it up as a first argument and dropping it.
%
% If this is not the case and we are doing typesetting (i.e.,
% \cs{protect} is \cs{typeset@protect}), then we execute
% \cs{UTFviii@two@octets@combine} which picks up all octets and typesets
% the character (or generates an error if it doesn't know how to
% typeset it).
%
% However, if we are not doing typesetting, then we execute the
% command \cs{UTFviii@two@octets@noexpand} which works like
% \cs{UTF@two@octets@string} but uses \cs{noexpand} instead of
% \cs{string}. This way the sequence is temporay rendered harmless,
% e.g., would display as is or stays put inside a
% \cs{protected@edef}. But if the result is later reused the
% starting octet is still active and so will be able to construct
% the UTF-8 character again.
% \end{macro}
%
%
% \begin{macro}{\UTFviii@three@octets}
% \changes{v1.2a}{2018/03/24}{Macros made `\cs{long} for improved error messages}%
% \begin{macro}{\UTFviii@four@octets}
% \changes{v1.2a}{2018/03/24}{Macros made `\cs{long} for improved
% error messages}
% The definitions for the other starting octets
% are the same except that they pick up more octets after them.
% \begin{macrocode}
\long\def\UTFviii@three@octets{%
\ifincsname
\expandafter \UTF@three@octets@string
\else
\ifx \protect\@typeset@protect \else
\expandafter\expandafter\expandafter \UTF@three@octets@noexpand
\fi
\fi
\UTFviii@three@octets@combine
}
% \end{macrocode}
% \begin{macrocode}
\long\def\UTFviii@four@octets{%
\ifincsname
\expandafter \UTF@four@octets@string
\else
\ifx \protect\@typeset@protect \else
\expandafter\expandafter\expandafter \UTF@four@octets@noexpand
\fi
\fi
\UTFviii@four@octets@combine
}
% \end{macrocode}
% \end{macro}
% \end{macro}
%
% \begin{macro}{\UTFviii@two@octets@noexpand}
% \begin{macro}{\UTFviii@three@octets@noexpand}
% \begin{macro}{\UTFviii@four@octets@noexpand}
% These tempoarily prevent the active chars from expanding.
% \begin{macrocode}
\long\def\UTF@two@octets@noexpand#1#2{\noexpand#2\noexpand}
\long\def\UTF@three@octets@noexpand#1#2#3{\noexpand#2\noexpand#3\noexpand}
\long\def\UTF@four@octets@noexpand#1#2#3#4{\noexpand#2\noexpand#3\noexpand#4\noexpand}
% \end{macrocode}
% \end{macro}
% \end{macro}
% \end{macro}
% \begin{macro}{\UTFviii@two@octets@string}
% \begin{macro}{\UTFviii@three@octets@string}
% \begin{macro}{\UTFviii@four@octets@string}
% And the same with \cs{string} for use in \cs{csname} constructions.
% \begin{macrocode}
\long\def\UTF@two@octets@string#1#2{\string#2\string}
\long\def\UTF@three@octets@string#1#2#3{\string#2\string#3\string}
\long\def\UTF@four@octets@string#1#2#3#4{\string#2\string#3\string#4\string}
% \end{macrocode}
% \end{macro}
% \end{macro}
% \end{macro}
% \begin{macro}{\UTFviii@two@octets@combine}
% \begin{macro}{\UTFviii@three@octets@combine}
% \begin{macro}{\UTFviii@four@octets@combine}
% From the arguments a control sequence with a name of the form
% \verb=u8:#1#2...= is constructed where the |#i| ($i>1$) are the
% arguments and |#1| is the starting octet (as a \TeX{} active character
% token). Since some or even all of these characters are active
% we need to use |\string| when building
% the \cs{csname}.
%
% The \cs{csname} thus constructed can of course be undefined but to
% avoid producing an unhelpful low-level undefined command error we
% pass it to |\UTFviii@defined| which is responsible for producing
% a more sensible error message (not yet done!!). If, however, it is
% defined we simply execute the thing (which should then expand to
% an encoding specific internal \LaTeX{} form).
% \begin{macrocode}
\long\def\UTFviii@two@octets@combine#1#2{\expandafter
\UTFviii@defined\csname u8:\string#1\string#2\endcsname}
% \end{macrocode}
%
% \begin{macrocode}
\long\def\UTFviii@three@octets@combine#1#2#3{\expandafter
\UTFviii@defined\csname u8:\string#1\string#2\string#3\endcsname}
% \end{macrocode}
%
% \begin{macrocode}
\long\def\UTFviii@four@octets@combine#1#2#3#4{\expandafter
\UTFviii@defined\csname u8:\string#1\string#2\string#3\string#4\endcsname}
% \end{macrocode}
% \end{macro}
% \end{macro}
% \end{macro}
%
%
% \begin{macro}{\UTFviii@defined}
% This tests whether its argument is different from |\relax|: it
% either calls for a sensible error message (not done), or it gets
% the |\fi| out of the way (in case the command has arguments) and
% executes it.
% \begin{macrocode}
\def\UTFviii@defined#1{%
\ifx#1\relax
% \end{macrocode}
% Test if the sequence is invalid UTF-8 or valid UTF-8 but without
% a \LaTeX\ definition.
% \begin{macrocode}
\if\relax\expandafter\UTFviii@checkseq\string#1\relax\relax
% \end{macrocode}
% The endline character has a special definition within the
% inputenc package (it is gobbling spaces). For this reason we
% can't produce multiline strings without some precaution.
% \changes{v1.1b}{2004/02/09}{No newlines allowed in error messages}
% \changes{v1.1g}{2005/09/27}{Real spaces do not show up so use \cs{space}}
% \changes{v1.1o}{2015/08/28}{Show Unicode number of character in hex}
% \changes{v1.2a}{2018/03/24}{Error message improved for non-UTF-8 sequences}%
% \begin{macrocode}
\UTFviii@undefined@err{#1}%
% \end{macrocode}
%
% \begin{macrocode}
\else
\PackageError{inputenc}{Invalid UTF-8 byte sequence}%
\UTFviii@invalid@help
\fi
% \end{macrocode}
%
% \begin{macrocode}
\else\expandafter
#1%
\fi
}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\UTFviii@invalid@err}
% \begin{macro}{\UTFviii@invalid@help}
% \changes{v1.2a}{2018/03/24}{Macro added}%
% \changes{v1.2f}{2018/10/05}{Show invalid byte in hex}%
% \begin{macrocode}
\def\UTFviii@invalid@err#1{%
\PackageError{inputenc}{Invalid UTF-8 byte "\UTFviii@hexnumber{`#1}}%
\UTFviii@invalid@help}
% \end{macrocode}
%
% \begin{macrocode}
\def\UTFviii@invalid@help{%
The document does not appear to be in UTF-8 encoding.\MessageBreak
Try adding \noexpand\UseRawInputEncoding as the first line of the file\MessageBreak
or specify an encoding such as \noexpand\usepackage[latin1]{inputenc}\MessageBreak
in the document preamble.\MessageBreak
Alternatively, save the file in UTF-8 using your editor or another tool}
% \end{macrocode}
% \end{macro}
% \end{macro}
%
% \begin{macro}{\UTFviii@undefined@err}
% \changes{v1.2a}{2018/03/24}{Macro added}%
% \begin{macrocode}
\def\UTFviii@undefined@err#1{%
\PackageError{inputenc}{Unicode character \expandafter
\UTFviii@splitcsname\string#1\relax
\MessageBreak
not set up for use with LaTeX}%
{You may provide a definition with\MessageBreak
\noexpand\DeclareUnicodeCharacter}%
}
% \end{macrocode}
% \end{macro}
%
%
% \begin{macro}{\UTFviii@checkseq}
% \begin{macro}{\UTFviii@check@continue}
% \changes{v1.2a}{2018/03/24}{Macro added}%
% Check that the csname consists of a valid UTF-8 sequence.
% \begin{macrocode}
\def\UTFviii@checkseq#1:#2#3{%
\ifnum`#2<"80 %
\ifx\relax#3\else1\fi
\else
\ifnum`#2<"C0 %
1 %
\else
\expandafter\expandafter\expandafter\UTFviii@check@continue
\expandafter\expandafter\expandafter#3%
\fi
\fi}
% \end{macrocode}
%
% \begin{macrocode}
\def\UTFviii@check@continue#1{%
\ifx\relax#1%
\else
\ifnum`#1<"80 1\else\ifnum`#1>"BF 1\fi\fi
\expandafter\UTFviii@check@continue
\fi
}
% \end{macrocode}
% \end{macro}
% \end{macro}
%
%
% \begin{macro}{\UTFviii@loop}
% This bit of code derived from \texttt{xmltex} defines the active character
% correspnding to starting octets to call |\UTFviii@two@octets| etc as appropriate.
% The starting octet itself is passed directly as the first argument, the others
% are picked up later en route.
%
% The |\UTFviii@loop| loops through the numbers starting at
% |\count@| and ending at |\@tempcnta|${} - 1$, each time executing
% the code in |\UTFviii@tmp|.
%
% All this is done in a group so that temporary catcode changes
% etc.~vanish after everything is set up.
%
% \begin{macrocode}
\begingroup
\catcode`\~13
\catcode`\"12
% \end{macrocode}
%
% \begin{macrocode}
\def\UTFviii@loop{%
\uccode`\~\count@
\uppercase\expandafter{\UTFviii@tmp}%
\advance\count@\@ne
\ifnum\count@<\@tempcnta
\expandafter\UTFviii@loop
\fi}
% \end{macrocode}
%
% Handle the single byte control characters.
% \changes{v1.2a}{2018/03/24}{Loop over C0 controls added}%
% C0 controls are valid UTF-8 but defined to give the ``Character not defined error''
% They may be defined with |\DeclareUnicodeCharacter|.
% \begin{macrocode}
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@undefined@err{:\string~}}}
% 0 ^^@ null
\count@"1
\@tempcnta9
% 9 ^^I tab
% 10 ^^J nl
\UTFviii@loop
\count@11
\@tempcnta12
\UTFviii@loop
% 12 ^^L
% 13 ^^M
\count@14
\@tempcnta32
\UTFviii@loop
% \end{macrocode}
%
%
% Bytes with leading bits |10| are not valid UTF-8 starting bytes
% \begin{macrocode}
\count@"80
\@tempcnta"C2
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@invalid@err\string~}}
\UTFviii@loop
% \end{macrocode}
%
% Setting up 2-byte UTF-8: The starting bytes is passed as an
% active character so that it can be reprocessed later!
% \begin{macrocode}
\count@"C2
\@tempcnta"E0
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@two@octets\noexpand~}}
\UTFviii@loop
% \end{macrocode}
%
% Setting up 3-byte UTF-8:
% \begin{macrocode}
\count@"E0
\@tempcnta"F0
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@three@octets\noexpand~}}
\UTFviii@loop
% \end{macrocode}
%
% Setting up 4-byte UTF-8:
% \changes{v1.2e}{2018/09/28}{Fix "F4 lead byte}%
% \begin{macrocode}
\count@"F0
\@tempcnta"F5
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@four@octets\noexpand~}}
\UTFviii@loop
% \end{macrocode}
%
% Bytes above F4 are not valid UTF-8 starting bytes as they would encode numbers beyond
% the Unicode range
% \begin{macrocode}
\count@"F5
\@tempcnta"100
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@invalid@err\string~}}
\UTFviii@loop
% \end{macrocode}
%
% \begin{macrocode}
\endgroup
% \end{macrocode}
%
% \end{macro}
%
% For this case we must disable the warning generated by
% \texttt{inputenc} if it doesn't see any new |\DeclareInputText|
% commands.
% \begin{macrocode}
\@inpenc@test
% \end{macrocode}
%
%
% If this file (\texttt{utf8.def}) is not being read while setting
% up \texttt{inputenc}, i.e.~in the preamble, but when
% |\inputencoding| is called somewhere within the document, we do not
% need to input the specific Unicode mappings again. We therefore
% stop reading the file at this point.
% \begin{macrocode}
\ifx\@begindocumenthook\@undefined
\makeatother
% \end{macrocode}
% The |\fi| must be on the same line as |\endinput| or else it will
% never be seen!
% \begin{macrocode}
\endinput \fi
% \end{macrocode}
%
%
% \subsection{Mapping Unicode codes to \LaTeX{} internal forms}
%
%
% \begin{macro}{\DeclareUnicodeCharacter}
% The |\DeclareUnicodeCharacter| declaration defines a mapping from
% a Unicode character code point to a \LaTeX{} internal form. The first
% argument is the Unicode number as hexadecimal digits and the second is
% the actual \LaTeX{} internal form.
%
% We start by making sure that some characters have the right
% |\catcode| when they are used in the definitions below.
% \begin{macrocode}
\begingroup
\catcode`\"=12
\catcode`\<=12
\catcode`\.=12
\catcode`\,=12
\catcode`\;=12
\catcode`\!=12
\catcode`\~=13
% \end{macrocode}
%
% \begin{macrocode}
\gdef\DeclareUnicodeCharacter#1#2{%
\count@"#1\relax
\wlog{ \space\space defining Unicode char U+#1 (decimal \the\count@)}%
\begingroup
% \end{macrocode}
% Next we do the parsing of the number stored in |\count@| and assign the
% result to |\UTFviii@tmp|. Actually all this could be done in-line,
% the macro |\parse@XML@charref| is only there to extend this code
% to parsing Unicode numbers in other contexts one day (perhaps).
% \begin{macrocode}
\parse@XML@charref
% \end{macrocode}
%
% Here is an example of what is happening, for the pair \texttt{"C2 "A3}
% (which is the utf8 represenation for the character \textsterling{}).
% After |\parse@XML@charref| we have, stored in |\UTFviii@tmp|, a
% single command with two character tokens as arguments:
% \begin{quote}
% [$t_{C2}$ and $t_{A3}$ are the characters corresponding to these
% two octets]\\
% |\UTFviii@two@octets| $t_{\rm C2}t_{\rm A3}$
% \end{quote}
% what we actually need to produce is a definition of the form
% \begin{quote}
% |\def\u8:|$t_{\rm C2}$$t_{\rm A3}$ |{|\textit{\LaTeX{} internal form}|}|\,.
% \end{quote}
% So here we temporarily redefine the prefix commands
% |\UTFviii@two@octets|, etc.~to
% generate the csname that we wish to define> the |\string|s are
% added in case these tokens are still active.
% \begin{macrocode}
\def\UTFviii@two@octets##1##2{\csname u8:##1\string##2\endcsname}%
\def\UTFviii@three@octets##1##2##3{\csname u8:##1%
\string##2\string##3\endcsname}%
\def\UTFviii@four@octets##1##2##3##4{\csname u8:##1%
\string##2\string##3\string##4\endcsname}%
% \end{macrocode}
% Now we simply:-) need to use the right number of |\expandafter|s to
% finally construct the definition: expanding |\UTFviii@tmp| once to get
% its contents, a second time to replace the prefix command by its
% |\csname| expansion, and a third time to turn the expansion into
% a csname after which the |\gdef| finally gets applied.
% We add an irrelevant |\IeC| and braces around the definition, in
% order to avoid any space after the command being gobbled up
% when the text is written out to an auxiliary file (see
% \texttt{inputenc} for further details
% \begin{macrocode}
\expandafter\expandafter\expandafter
\expandafter\expandafter\expandafter
\expandafter
\gdef\UTFviii@tmp{\IeC{#2}}%
\endgroup
}
% \end{macrocode}
% \end{macro}
%
%
% \begin{macro}{\parse@XML@charref}
% This macro parses a Unicode number (decimal) and returns its
% UTF-8 representation as a sequence of non-active \TeX{} character
% tokens. In the
% original code it had two arguments delimited by \texttt{;} here,
% however, we supply the Unicode number implicitly.
% \begin{macrocode}
\gdef\parse@XML@charref{%
% \end{macrocode}
% We need to keep a few things local, mainly the |\uccode|'s that
% are set up below. However, the group originally used here is
% actually unnecessary since we call this macro only within another
% group; but it will be important to restore the group if this
% macro gets used for other purposes.
% \begin{macrocode}
% \begingroup
% \end{macrocode}
% The original code from \texttt{xmltex} supported the convention that a
% Unicode slot number could be given either as a decimal or as a
% hexadecimal (by starting with \texttt{x}). We do not do this so
% this code is also removed. This could be reactivated if one
% wants to support document commands that accept Unicode numbers
% (but then the first case needs to be changed from an error
% message back to something more useful again).
% \begin{macrocode}
% \uppercase{\count@\if x\noexpand#1"\else#1\fi#2}\relax
% \end{macrocode}
% As |\count@| already contains the right value we make
% |\parse@XML@charref| work without arguments.
% \changes{v1.1g}{2005/09/27}{Real spaces do not show up so use \cs{space}}
% \changes{v1.2a}{2018/03/24}{Allow control characters if active}
% In the case single byte UTF-8 sequences, only allow definition if
% the character os already active. The definition of |\UTFviii@tmp|
% looks slightly strange but is designed for the sequence of |\expandafter|
% in |\DeclareUnicodeCharacter|.
%
% \begin{macrocode}
\ifnum\count@<"A0\relax
\ifnum\catcode\count@=13
\uccode`\~=\count@\uppercase{\def\UTFviii@tmp{\@empty\@empty~}}%
\else
\PackageError{inputenc}%
{Cannot define non-active Unicode char value < 00A0}%
\@eha
\def\UTFviii@tmp{\UTFviii@tmp}%
\fi
% \end{macrocode}
% The code below is derived from \texttt{xmltex} and generates the UTF-8 byte sequence
% for the number in |\count@|.
%
% The reverse operation (just used in error messages)
% has now been added as \cs{decode@UTFviii}.
% \begin{macrocode}
\else\ifnum\count@<"800\relax
\parse@UTFviii@a,%
\parse@UTFviii@b C\UTFviii@two@octets.,%
\else\ifnum\count@<"10000\relax
\parse@UTFviii@a;%
\parse@UTFviii@a,%
\parse@UTFviii@b E\UTFviii@three@octets.{,;}%
\else
% \end{macrocode}
%
% Test added here for out of range values, the 4-octet definitions are still set up
% so that |\DeclareUnicodeCharacter| does something sensible if the user scrolls
% past this error.
% \begin{macrocode}
\ifnum\count@>"10FFFF\relax
\PackageError{inputenc}%
{\UTFviii@hexnumber\count@\space too large for Unicode}%
{Values between 0 and 10FFFF are permitted}%
\fi
% \end{macrocode}
%
% \begin{macrocode}
\parse@UTFviii@a;%
\parse@UTFviii@a,%
\parse@UTFviii@a!%
\parse@UTFviii@b F\UTFviii@four@octets.{!,;}%
\fi
\fi
\fi
% \endgroup
}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\parse@UTFviii@a}
% \ldots so somebody else can document this part :-)
% \changes{v1.1b}{2004/02/09}{Space in the wrong place \cs{count @64}}
% \begin{macrocode}
\gdef\parse@UTFviii@a#1{%
\@tempcnta\count@
\divide\count@ 64
\@tempcntb\count@
\multiply\count@ 64
\advance\@tempcnta-\count@
\advance\@tempcnta 128
\uccode`#1\@tempcnta
\count@\@tempcntb}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\parse@UTFviii@b}
% \ldots same here
% \begin{macrocode}
\gdef\parse@UTFviii@b#1#2#3#4{%
\advance\count@ "#10\relax
\uccode`#3\count@
\uppercase{\gdef\UTFviii@tmp{#2#3#4}}}
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\decode@UTFviii}
% \changes{v1.1o}{2015/08/28}{Macro added}
% In the reverse direction, take a sequence of octects(bytes)
% representing a character in UTF-8 and construct the Unicode number.
% The sequence is terminated by |\relax|.
%
% In this version, if the sequence is not valid UTF-8 you probably
% get a low level arithmetic error from |\numexpr| or stray characters
% at the end. Getting a better error message would be somewhat expensive.
% As the main use is for reporting characters in messages, this is done
% just using expansion, so |\numexpr| is used, A stub returning 0 is defined
% if |\numexpr| is not available.
% \begin{macrocode}
\ifx\numexpr\@undefined
% \end{macrocode}
%
% \begin{macrocode}
\gdef\decode@UTFviii#1{0}
% \end{macrocode}
%
% \begin{macrocode}
\else
% \end{macrocode}
%
% If the input is malformed UTF-8 there may not be enough closing ) so
% add 5 so there are always some remaining then cleanup and remove
% any remaining ones at the end. This avoids |\numexpr| parse errors
% while outputting a package error.
% \begin{macrocode}
\gdef\decode@UTFviii#1\relax{%
\expandafter\UTFviii@cleanup
\the\numexpr\dec@de@UTFviii#1\relax)))))\@empty}
% \end{macrocode}
%
% \begin{macrocode}
\gdef\UTFviii@cleanup#1)#2\@empty{#1}
% \end{macrocode}
%
% \begin{macrocode}
\gdef\dec@de@UTFviii#1{%
\ifx\relax#1%
\else
\ifnum`#1>"EF
((((`#1-"F0)%
\else
\ifnum`#1>"DF
(((`#1-"E0)%
\else
\ifnum`#1>"BF
((`#1-"C0)%
\else
\ifnum`#1>"7F
)*64+(`#1-"80)%
\else
+`#1 %
\fi
\fi
\fi
\fi
\expandafter\dec@de@UTFviii
\fi}
% \end{macrocode}
%
% \begin{macrocode}
\fi
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\UTFviii@hexnumber}
% \changes{v1.1o}{2015/08/28}{Macro added}
% Convert a number to a sequence of uppercase hex digits.
% If |\numexpr| is not available, it returns its argument unchanged.
% \begin{macrocode}
\ifx\numexpr\@undefined
% \end{macrocode}
% \begin{macrocode}
\global\let\UTFviii@hexnumber\@firstofone
\global\UTFviii@hexdigit\hexnumber@
% \end{macrocode}
% \begin{macrocode}
\else
% \end{macrocode}
% \begin{macrocode}
\gdef\UTFviii@hexnumber#1{%
\ifnum#1>15 %
\expandafter\UTFviii@hexnumber\expandafter{\the\numexpr(#1-8)/16\relax}%
\fi
\UTFviii@hexdigit{\numexpr#1\ifnum#1>0-((#1-8)/16)*16\fi\relax}%
}
% \end{macrocode}
%
% Almost but not quite |\hexnumber@|.
% \begin{macrocode}
\gdef\UTFviii@hexdigit#1{\ifcase\numexpr#1\relax
0\or1\or2\or3\or4\or5\or6\or7\or8\or9\or
A\or B\or C\or D\or E\or F\fi}
% \end{macrocode}
%
% \begin{macrocode}
\fi
% \end{macrocode}
% \end{macro}
%
% \begin{macro}{\UTFviii@splitcsname}
% \changes{v1.1o}{2015/08/28}{Macro added}
% \begin{macro}{\UTFviii@hexcodepoint}
% \changes{v1.2e}{2018/09/28}{Macro added: Format codepoint properly}
% Split a csname representing a unicode character and return
% the character and the unicode number in hex.
% \begin{macrocode}
\gdef\UTFviii@hexcodepoint#1{U+%
\ifnum#1<16 0\fi
\ifnum#1<256 0\fi
\ifnum#1<4096 0\fi
\UTFviii@hexnumber{#1}%
}%
\gdef\UTFviii@splitcsname#1:#2\relax{%
% \end{macrocode}
% \changes{v1.2b}{2018/03/26}{add percent as \cs{endlinechar} not -1 in the format}%
% Need to pre-expand the argument to ensure cleanup in case of mal-formed UTF-8.
% \begin{macrocode}
#2 (\expandafter\UTFviii@hexcodepoint\expandafter{%
\the\numexpr\decode@UTFviii#2\relax})%
}
% \end{macrocode}
% \end{macro}
% \end{macro}
%
% \begin{macrocode}
\endgroup
% \end{macrocode}
%
% \begin{macrocode}
\@onlypreamble\DeclareUnicodeCharacter
% \end{macrocode}
% These are preamble only as long as we don't support Unicode
% charrefs in documents.
% \begin{macrocode}
\@onlypreamble\parse@XML@charref
\@onlypreamble\parse@UTFviii@a
\@onlypreamble\parse@UTFviii@b
% \end{macrocode}
%
%
% \subsection{Loading Unicode mappings at begin document}
%
% The original plan was to set up the UTF-8 support at
% |\begin{document}|; but then any text characters used in the preamble
% (as people do even though advised against it) would fail in one way or
% the other.
% So the implementation was changed and the Unicode definition files
% for already defined encodings are loaded here.
%
% We loop through all defined font encodings
% (stored in |\cdp@list|) and for each load a file
% \textit{name}\texttt{enc.dfu} if it exist. That file is then
% supposed to contain |\DeclareUnicodeCharacter| declarations.
% \begin{macrocode}
\begingroup
\def\cdp@elt#1#2#3#4{%
\wlog{Now handling font encoding #1 ...}%
\lowercase{%
\InputIfFileExists{#1enc.dfu}}%
{\wlog{... processing UTF-8 mapping file for font %
encoding #1}%
% \end{macrocode}
% \changes{v1.1m}{2008/04/05}{Ensure we don't lose spaces in the log}
% The previous line is written to the log with the newline char being
% ignored (thus not producing a space). Therefore either everything has to
% be on a single input line or some special care must be taken. From this
% point on we ignore spaces again, i.e., while we are reading the
% \texttt{.dfu} file. The |\endgroup| below will restore it again.
% \changes{v1.1d}{2004/05/08}{Explicitly set catcode of space}
% \changes{v1.1g}{2005/09/27}{We lost the ``false'' case}
% \begin{macrocode}
\catcode`\ 9\relax}%
{\wlog{... no UTF-8 mapping file for font encoding #1}}%
}
\cdp@list
\endgroup
% \end{macrocode}
% However, we don't know if there are font encodings still to be
% loaded (either with \texttt{fontenc} or directly with |\input| by
% some package). Font encoding files are loaded only if the
% corresponding encoding has not been loaded yet, and they always
% begin with |\DeclareFontEncoding|. We now redefine the internal
% kernel version of the latter to load the Unicode file if available.
%
% \begin{macrocode}
\def\DeclareFontEncoding@#1#2#3{%
\expandafter
\ifx\csname T@#1\endcsname\relax
\def\cdp@elt{\noexpand\cdp@elt}%
\xdef\cdp@list{\cdp@list\cdp@elt{#1}%
{\default@family}{\default@series}%
{\default@shape}}%
\expandafter\let\csname#1-cmd\endcsname\@changed@cmd
\begingroup
\wlog{Now handling font encoding #1 ...}%
\lowercase{%
\InputIfFileExists{#1enc.dfu}}%
{\wlog{... processing UTF-8 mapping file for font %
encoding #1}}%
{\wlog{... no UTF-8 mapping file for font encoding #1}}%
\endgroup
\else
\@font@info{Redeclaring font encoding #1}%
\fi
\global\@namedef{T@#1}{#2}%
\global\@namedef{M@#1}{\default@M#3}%
\xdef\LastDeclaredEncoding{#1}%
}
%</utf8>
% \end{macrocode}
%
%
%
% \section{Mapping characters ---\newline based on font (glyph) encodings}
%
% This section is a first attempt to provide Unicode definitions for
% characters whose standard glyphs are currently provided by the
% standard \LaTeX{} font-encodings |T1|, |OT1|, etc. They are by
% no means completed and need checking.
%
% For example, one should check the already existing input encodings
% for glyphs that may in fact be available and required,
% e.g.~\texttt{latin4} has a number of glyphs with the |\=|
% accent. Since the |T1| encoding does not provide such glyphs,
% these characters are not listed below (yet).
%
% The list below was generated by looking at the current \LaTeX{} font
% encoding files, e.g., \texttt{t1enc.def} and using the work by
% Sebastian Rahtz (in \texttt{ucharacters.sty}) with a few
% modifications. In combinations such as |\^\i| the preferred form
% is that and not |\^i|.
%
% This list has been built from several sources, obviously including
% the Unicode Standard itself. These sources include Passive \TeX{} by
% Sebastian Rahtz, the \texttt{unicode}
% package by Dominique P. G. Unruh (mainly for Latin encodings) and
% \texttt{text4ht} by Eitan Gurari (for Cyrillic ones).
%
% Note that it strictly follows the Mittelbach principles for
% input character encodings: thus it offers no support for using utf8
% representations of math symbols such as $\times$ or $\div$ (in math mode).
%
%
% \subsection{About the table itself}
%
% In addition to generating individual files, the table below is, at present,
% a one-one (we think) partial relationship between the (ill-defined) set
% of LICRs and the Unicode slots "0080 to "FFFF. At present these entries
% are used only to define a collection of partial mappings from Unicode
% slots to LICRs; each of these mappings becomes full if we add an exception
% value (`not defined') to the set of LICRs.
%
% It is probably not essential for the relationship in the full table to be
% one-one; this raises questions such as: the exact role of LICRs;
% the formal relationships on the set of LICRs; the (non-mathematical)
% relationship between
% LICRs and Unicode (which has its own somewhat fuzzy equivalences);
% and ultimately what a character is and what a character representation
% and/or name is.
%
% It is unclear the extent to which entries in this table should
% resemble the closely related ones in the 8-bit \texttt{inputenc} files.
% The Unicode standard claims that the first 256 slots `are' ASCII and
% Latin-1.
%
% Of course, \TeX{} itself typically does not treat even many perfectly
% `normal text' 7-bit slots as text characters, so it is unclear
% whether \LaTeX{} should even attempt to deal in any consistent way with
% those Unicode slots that are not definitive text characters.
%
%
% \subsection{The mapping table}
%
% \begingroup
% \hfuzz=12pt ^^A just because
%
% Note that the first argument must be a hex-digit number greater
% than \texttt{00BF} and at most \texttt{10FFFF}.
%
% There are few notes about inconsistencies etc at the end of the table.
%
% \changes{v1.1o}{2015/08/28}{Add U+00A0 and U+00AD}
% \changes{v1.1q}{2015/12/02}{Add remaining latin uses of accents in T1}
% \changes{v1.1r}{2015/12/03}{Add some more ogoneck cases}
% \changes{v1.1s}{2016/01/11}{Add some more caron and acute}
% \changes{v1.1t}{2017/01/28}{Add caron cominations for GgYy}
% \begin{macrocode}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00A0}{\nobreakspace}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00A1}{\textexclamdown}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00A2}{\textcent}
%<all,ts1,t1,ot1,ly1>\DeclareUnicodeCharacter{00A3}{\textsterling}
%<all,x2,ts1,t2c,t2b,t2a,ly1,lcy>\DeclareUnicodeCharacter{00A4}{\textcurrency}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00A5}{\textyen}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00A6}{\textbrokenbar}
%<all,x2,ts1,t2c,t2b,t2a,oms,ly1>\DeclareUnicodeCharacter{00A7}{\textsection}
%<all,ts1>\DeclareUnicodeCharacter{00A8}{\textasciidieresis}
%<all,ts1,utf8>\DeclareUnicodeCharacter{00A9}{\textcopyright}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00AA}{\textordfeminine}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
\DeclareUnicodeCharacter{00AB}{\guillemotleft}
%</all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
%<all,ts1>\DeclareUnicodeCharacter{00AC}{\textlnot}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00AD}{\-}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00AE}{\textregistered}
%<all,ts1>\DeclareUnicodeCharacter{00AF}{\textasciimacron}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00B0}{\textdegree}
%<all,ts1>\DeclareUnicodeCharacter{00B1}{\textpm}
%<all,ts1>\DeclareUnicodeCharacter{00B2}{\texttwosuperior}
%<all,ts1>\DeclareUnicodeCharacter{00B3}{\textthreesuperior}
%<all,ts1>\DeclareUnicodeCharacter{00B4}{\textasciiacute}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00B5}{\textmu} % micro sign
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{00B6}{\textparagraph}
%<all,oms,ts1,ly1>\DeclareUnicodeCharacter{00B7}{\textperiodcentered}
%<all,ot1>\DeclareUnicodeCharacter{00B8}{\c\ }
%<all,ts1>\DeclareUnicodeCharacter{00B9}{\textonesuperior}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{00BA}{\textordmasculine}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
\DeclareUnicodeCharacter{00BB}{\guillemotright}
%</all,x2,t2c,t2b,t2a,t1,ot2,ly1,lcy>
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BC}{\textonequarter}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BD}{\textonehalf}
%<all,ts1,ly1>\DeclareUnicodeCharacter{00BE}{\textthreequarters}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00BF}{\textquestiondown}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C0}{\@tabacckludge`A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C1}{\@tabacckludge'A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C2}{\^A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C3}{\~A}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C4}{\"A}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00C5}{\r A}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00C6}{\AE}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C7}{\c C}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C8}{\@tabacckludge`E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00C9}{\@tabacckludge'E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CA}{\^E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CB}{\"E}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CC}{\@tabacckludge`I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CD}{\@tabacckludge'I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CE}{\^I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00CF}{\"I}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D0}{\DH}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D1}{\~N}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D2}{\@tabacckludge`O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D3}{\@tabacckludge'O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D4}{\^O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D5}{\~O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D6}{\"O}
%<all,ts1>\DeclareUnicodeCharacter{00D7}{\texttimes}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00D8}{\O}
%<all,t1,ly1>\DeclareUnicodeCharacter{00D9}{\@tabacckludge`U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DA}{\@tabacckludge'U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DB}{\^U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DC}{\"U}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DD}{\@tabacckludge'Y}
%<all,t1,ly1>\DeclareUnicodeCharacter{00DE}{\TH}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00DF}{\ss}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E0}{\@tabacckludge`a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E1}{\@tabacckludge'a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E2}{\^a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E3}{\~a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E4}{\"a}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E5}{\r a}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00E6}{\ae}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E7}{\c c}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E8}{\@tabacckludge`e}
%<all,t1,ly1>\DeclareUnicodeCharacter{00E9}{\@tabacckludge'e}
%<all,t1,ly1>\DeclareUnicodeCharacter{00EA}{\^e}
%<all,t1,ly1>\DeclareUnicodeCharacter{00EB}{\"e}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00EC}{\@tabacckludge`\i}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00ED}{\@tabacckludge'\i}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00EE}{\^\i}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{00EF}{\"\i}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F0}{\dh}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F1}{\~n}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F2}{\@tabacckludge`o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F3}{\@tabacckludge'o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F4}{\^o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F5}{\~o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F6}{\"o}
%<all,ts1>\DeclareUnicodeCharacter{00F7}{\textdiv}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{00F8}{\o}
%<all,t1,ly1>\DeclareUnicodeCharacter{00F9}{\@tabacckludge`u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FA}{\@tabacckludge'u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FB}{\^u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FC}{\"u}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FD}{\@tabacckludge'y}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FE}{\th}
%<all,t1,ly1>\DeclareUnicodeCharacter{00FF}{\"y}
%<all,t1>\DeclareUnicodeCharacter{0100}{\@tabacckludge=A}
%<all,t1>\DeclareUnicodeCharacter{0101}{\@tabacckludge=a}
%<all,t1>\DeclareUnicodeCharacter{0102}{\u A}
%<all,t1>\DeclareUnicodeCharacter{0103}{\u a}
%<all,t1>\DeclareUnicodeCharacter{0104}{\k A}
%<all,t1>\DeclareUnicodeCharacter{0105}{\k a}
%<all,t1>\DeclareUnicodeCharacter{0106}{\@tabacckludge'C}
%<all,t1>\DeclareUnicodeCharacter{0107}{\@tabacckludge'c}
%<all,t1>\DeclareUnicodeCharacter{0108}{\^C}
%<all,t1>\DeclareUnicodeCharacter{0109}{\^c}
%<all,t1>\DeclareUnicodeCharacter{010A}{\.C}
%<all,t1>\DeclareUnicodeCharacter{010B}{\.c}
%<all,t1>\DeclareUnicodeCharacter{010C}{\v C}
%<all,t1>\DeclareUnicodeCharacter{010D}{\v c}
%<all,t1>\DeclareUnicodeCharacter{010E}{\v D}
%<all,t1>\DeclareUnicodeCharacter{010F}{\v d}
%<all,t1>\DeclareUnicodeCharacter{0110}{\DJ}
%<all,t1>\DeclareUnicodeCharacter{0111}{\dj}
%<all,t1>\DeclareUnicodeCharacter{0112}{\@tabacckludge=E}
%<all,t1>\DeclareUnicodeCharacter{0113}{\@tabacckludge=e}
%<all,t1>\DeclareUnicodeCharacter{0114}{\u E}
%<all,t1>\DeclareUnicodeCharacter{0115}{\u e}
%<all,t1>\DeclareUnicodeCharacter{0116}{\.E}
%<all,t1>\DeclareUnicodeCharacter{0117}{\.e}
%<all,t1>\DeclareUnicodeCharacter{0118}{\k E}
%<all,t1>\DeclareUnicodeCharacter{0119}{\k e}
%<all,t1>\DeclareUnicodeCharacter{011A}{\v E}
%<all,t1>\DeclareUnicodeCharacter{011B}{\v e}
%<all,t1>\DeclareUnicodeCharacter{011C}{\^G}
%<all,t1>\DeclareUnicodeCharacter{011D}{\^g}
%<all,t1>\DeclareUnicodeCharacter{011E}{\u G}
%<all,t1>\DeclareUnicodeCharacter{011F}{\u g}
%<all,t1>\DeclareUnicodeCharacter{0120}{\.G}
%<all,t1>\DeclareUnicodeCharacter{0121}{\.g}
%<all,t1>\DeclareUnicodeCharacter{0122}{\c G}
%<all,t1>\DeclareUnicodeCharacter{0123}{\c g}
%<all,t1>\DeclareUnicodeCharacter{0124}{\^H}
%<all,t1>\DeclareUnicodeCharacter{0125}{\^h}
%<all,t1>\DeclareUnicodeCharacter{0128}{\~I}
%<all,t1>\DeclareUnicodeCharacter{0129}{\~\i}
%<all,t1>\DeclareUnicodeCharacter{012A}{\@tabacckludge=I}
%<all,t1>\DeclareUnicodeCharacter{012B}{\@tabacckludge=\i}
%<all,t1>\DeclareUnicodeCharacter{012C}{\u I}
%<all,t1>\DeclareUnicodeCharacter{012D}{\u\i}
%<all,t1>\DeclareUnicodeCharacter{012E}{\k I}
% \end{macrocode}
% \changes{v1.2g}{2019/02/06}{Corrected 012F (github/122)}
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{012F}{\k i}
%<all,t1>\DeclareUnicodeCharacter{0130}{\.I}
%<all,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{0131}{\i}
%<all,t1>\DeclareUnicodeCharacter{0132}{\IJ}
%<all,t1>\DeclareUnicodeCharacter{0133}{\ij}
%<all,t1>\DeclareUnicodeCharacter{0134}{\^J}
%<all,t1>\DeclareUnicodeCharacter{0135}{\^\j}
%<all,t1>\DeclareUnicodeCharacter{0136}{\c K}
%<all,t1>\DeclareUnicodeCharacter{0137}{\c k}
%<all,t1>\DeclareUnicodeCharacter{0139}{\@tabacckludge'L}
%<all,t1>\DeclareUnicodeCharacter{013A}{\@tabacckludge'l}
%<all,t1>\DeclareUnicodeCharacter{013B}{\c L}
%<all,t1>\DeclareUnicodeCharacter{013C}{\c l}
%<all,t1>\DeclareUnicodeCharacter{013D}{\v L}
%<all,t1>\DeclareUnicodeCharacter{013E}{\v l}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0141}{\L}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0142}{\l}
%<all,t1>\DeclareUnicodeCharacter{0143}{\@tabacckludge'N}
%<all,t1>\DeclareUnicodeCharacter{0144}{\@tabacckludge'n}
%<all,t1>\DeclareUnicodeCharacter{0145}{\c N}
%<all,t1>\DeclareUnicodeCharacter{0146}{\c n}
%<all,t1>\DeclareUnicodeCharacter{0147}{\v N}
%<all,t1>\DeclareUnicodeCharacter{0148}{\v n}
%<all,t1>\DeclareUnicodeCharacter{014A}{\NG}
%<all,t1>\DeclareUnicodeCharacter{014B}{\ng}
%<all,t1>\DeclareUnicodeCharacter{014C}{\@tabacckludge=O}
%<all,t1>\DeclareUnicodeCharacter{014D}{\@tabacckludge=o}
%<all,t1>\DeclareUnicodeCharacter{014E}{\u O}
%<all,t1>\DeclareUnicodeCharacter{014F}{\u o}
%<all,t1>\DeclareUnicodeCharacter{0150}{\H O}
%<all,t1>\DeclareUnicodeCharacter{0151}{\H o}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{0152}{\OE}
%<all,t1,ot1,ly1,lcy>\DeclareUnicodeCharacter{0153}{\oe}
%<all,t1>\DeclareUnicodeCharacter{0154}{\@tabacckludge'R}
%<all,t1>\DeclareUnicodeCharacter{0155}{\@tabacckludge'r}
%<all,t1>\DeclareUnicodeCharacter{0156}{\c R}
%<all,t1>\DeclareUnicodeCharacter{0157}{\c r}
%<all,t1>\DeclareUnicodeCharacter{0158}{\v R}
%<all,t1>\DeclareUnicodeCharacter{0159}{\v r}
%<all,t1>\DeclareUnicodeCharacter{015A}{\@tabacckludge'S}
%<all,t1>\DeclareUnicodeCharacter{015B}{\@tabacckludge's}
%<all,t1>\DeclareUnicodeCharacter{015C}{\^S}
%<all,t1>\DeclareUnicodeCharacter{015D}{\^s}
%<all,t1>\DeclareUnicodeCharacter{015E}{\c S}
%<all,t1>\DeclareUnicodeCharacter{015F}{\c s}
%<all,t1,ly1>\DeclareUnicodeCharacter{0160}{\v S}
%<all,t1,ly1>\DeclareUnicodeCharacter{0161}{\v s}
%<all,t1>\DeclareUnicodeCharacter{0162}{\c T}
%<all,t1>\DeclareUnicodeCharacter{0163}{\c t}
%<all,t1>\DeclareUnicodeCharacter{0164}{\v T}
%<all,t1>\DeclareUnicodeCharacter{0165}{\v t}
%<all,t1>\DeclareUnicodeCharacter{0168}{\~U}
%<all,t1>\DeclareUnicodeCharacter{0169}{\~u}
%<all,t1>\DeclareUnicodeCharacter{016A}{\@tabacckludge=U}
%<all,t1>\DeclareUnicodeCharacter{016B}{\@tabacckludge=u}
%<all,t1>\DeclareUnicodeCharacter{016C}{\u U}
%<all,t1>\DeclareUnicodeCharacter{016D}{\u u}
%<all,t1>\DeclareUnicodeCharacter{016E}{\r U}
%<all,t1>\DeclareUnicodeCharacter{016F}{\r u}
%<all,t1>\DeclareUnicodeCharacter{0170}{\H U}
%<all,t1>\DeclareUnicodeCharacter{0171}{\H u}
%<all,t1>\DeclareUnicodeCharacter{0172}{\k U}
%<all,t1>\DeclareUnicodeCharacter{0173}{\k u}
% \end{macrocode}
%
% \changes{v1.1p}{2015/09/07}{Welsh circumflex combinations}
% \begin{macrocode}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0174}{\^W}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0175}{\^w}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0176}{\^Y}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0177}{\^y}
%<all,t1,ly1>\DeclareUnicodeCharacter{0178}{\"Y}
%<all,t1>\DeclareUnicodeCharacter{0179}{\@tabacckludge'Z}
%<all,t1>\DeclareUnicodeCharacter{017A}{\@tabacckludge'z}
%<all,t1>\DeclareUnicodeCharacter{017B}{\.Z}
%<all,t1>\DeclareUnicodeCharacter{017C}{\.z}
%<all,t1,ly1>\DeclareUnicodeCharacter{017D}{\v Z}
%<all,t1,ly1>\DeclareUnicodeCharacter{017E}{\v z}
%<all,ts1,ly1>\DeclareUnicodeCharacter{0192}{\textflorin}
% \end{macrocode}
% \changes{v1.1s}{2016/01/11}{add 01CD-01F4}
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{01CD}{\v A}
%<all,t1>\DeclareUnicodeCharacter{01CE}{\v a}
%<all,t1>\DeclareUnicodeCharacter{01CF}{\v I}
%<all,t1>\DeclareUnicodeCharacter{01D0}{\v \i}
%<all,t1>\DeclareUnicodeCharacter{01D1}{\v O}
%<all,t1>\DeclareUnicodeCharacter{01D2}{\v o}
%<all,t1>\DeclareUnicodeCharacter{01D3}{\v U}
%<all,t1>\DeclareUnicodeCharacter{01D4}{\v u}
%<all,t1>\DeclareUnicodeCharacter{01E2}{\@tabacckludge=\AE}
%<all,t1>\DeclareUnicodeCharacter{01E3}{\@tabacckludge=\ae}
%<all,t1>\DeclareUnicodeCharacter{01E6}{\v G}
%<all,t1>\DeclareUnicodeCharacter{01E7}{\v g}
%<all,t1>\DeclareUnicodeCharacter{01E8}{\v K}
%<all,t1>\DeclareUnicodeCharacter{01E9}{\v k}
%<all,t1>\DeclareUnicodeCharacter{01EA}{\k O}
%<all,t1>\DeclareUnicodeCharacter{01EB}{\k o}
%<all,t1>\DeclareUnicodeCharacter{01F0}{\v\j}
%<all,t1>\DeclareUnicodeCharacter{01F4}{\@tabacckludge'G}
%<all,t1>\DeclareUnicodeCharacter{01F5}{\@tabacckludge'g}
% \end{macrocode}
% \changes{v1.1o}{2015/08/28}{comma accent latex/4414}
% \begin{macrocode}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0218}{\textcommabelow S}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{0219}{\textcommabelow s}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{021A}{\textcommabelow T}
%<all,t1,ot1,ly1>\DeclareUnicodeCharacter{021B}{\textcommabelow t}
% \end{macrocode}
%
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{0232}{\@tabacckludge=Y}
%<all,t1>\DeclareUnicodeCharacter{0233}{\@tabacckludge=y}
%<all,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{0237}{\j}
%<all,ly1,utf8>\DeclareUnicodeCharacter{02C6}{\textasciicircum}
%<all,ts1>\DeclareUnicodeCharacter{02C7}{\textasciicaron}
%<all,ly1,utf8>\DeclareUnicodeCharacter{02DC}{\textasciitilde}
%<all,ts1>\DeclareUnicodeCharacter{02D8}{\textasciibreve}
%<all,t1>\DeclareUnicodeCharacter{02D9}{\.{}}
%<all,t1>\DeclareUnicodeCharacter{02DB}{\k{}}
%<all,ts1>\DeclareUnicodeCharacter{02DD}{\textacutedbl}
% \end{macrocode}
% The Cyrillic code points have been recently checked (2007) and extended
% and corrected by Matthias Noe (\verb=a9931078@unet.univie.ac.at=) --- thanks.
% \changes{v1.1j}{2007/11/09}{Added a few new unicode decls in cyrillic (pr/3988)}
% \changes{v1.1k}{2007/11/11}{Added and further unicode decls in cyrillic}
% \changes{v1.1n}{2015/06/27}{correct accent https://tex.stackexchange.com/q/252521}
% \begin{macrocode}
%<*all,x2,t2c,t2b,t2a,ot2,lcy>
\DeclareUnicodeCharacter{0400}{\@tabacckludge`\CYRE}
%</all,x2,t2c,t2b,t2a,ot2,lcy>
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0401}{\CYRYO}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{0402}{\CYRDJE}
%<*all,x2,t2c,t2b,t2a,ot2,lcy>
\DeclareUnicodeCharacter{0403}{\@tabacckludge'\CYRG}
%</all,x2,t2c,t2b,t2a,ot2,lcy>
%<all,x2,t2a,ot2,lcy>\DeclareUnicodeCharacter{0404}{\CYRIE}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0405}{\CYRDZE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0406}{\CYRII}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0407}{\CYRYI}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0408}{\CYRJE}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{0409}{\CYRLJE}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{040A}{\CYRNJE}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{040B}{\CYRTSHE}
%<*all,x2,t2c,t2b,t2a,ot2,lcy>
\DeclareUnicodeCharacter{040C}{\@tabacckludge'\CYRK}
\DeclareUnicodeCharacter{040D}{\@tabacckludge`\CYRI}
%</all,x2,t2c,t2b,t2a,ot2,lcy>
%<all,x2,t2b,t2a,lcy>\DeclareUnicodeCharacter{040E}{\CYRUSHRT}
%<all,x2,t2c,t2a,ot2>\DeclareUnicodeCharacter{040F}{\CYRDZHE}
%<*all,x2,t2c,t2b,t2a,ot2,lcy>
\DeclareUnicodeCharacter{0410}{\CYRA}
\DeclareUnicodeCharacter{0411}{\CYRB}
\DeclareUnicodeCharacter{0412}{\CYRV}
\DeclareUnicodeCharacter{0413}{\CYRG}
\DeclareUnicodeCharacter{0414}{\CYRD}
\DeclareUnicodeCharacter{0415}{\CYRE}
\DeclareUnicodeCharacter{0416}{\CYRZH}
\DeclareUnicodeCharacter{0417}{\CYRZ}
\DeclareUnicodeCharacter{0418}{\CYRI}
\DeclareUnicodeCharacter{0419}{\CYRISHRT}
\DeclareUnicodeCharacter{041A}{\CYRK}
\DeclareUnicodeCharacter{041B}{\CYRL}
\DeclareUnicodeCharacter{041C}{\CYRM}
\DeclareUnicodeCharacter{041D}{\CYRN}
\DeclareUnicodeCharacter{041E}{\CYRO}
\DeclareUnicodeCharacter{041F}{\CYRP}
\DeclareUnicodeCharacter{0420}{\CYRR}
\DeclareUnicodeCharacter{0421}{\CYRS}
\DeclareUnicodeCharacter{0422}{\CYRT}
\DeclareUnicodeCharacter{0423}{\CYRU}
\DeclareUnicodeCharacter{0424}{\CYRF}
\DeclareUnicodeCharacter{0425}{\CYRH}
\DeclareUnicodeCharacter{0426}{\CYRC}
\DeclareUnicodeCharacter{0427}{\CYRCH}
\DeclareUnicodeCharacter{0428}{\CYRSH}
\DeclareUnicodeCharacter{0429}{\CYRSHCH}
\DeclareUnicodeCharacter{042A}{\CYRHRDSN}
\DeclareUnicodeCharacter{042B}{\CYRERY}
\DeclareUnicodeCharacter{042C}{\CYRSFTSN}
\DeclareUnicodeCharacter{042D}{\CYREREV}
\DeclareUnicodeCharacter{042E}{\CYRYU}
\DeclareUnicodeCharacter{042F}{\CYRYA}
\DeclareUnicodeCharacter{0430}{\cyra}
\DeclareUnicodeCharacter{0431}{\cyrb}
\DeclareUnicodeCharacter{0432}{\cyrv}
\DeclareUnicodeCharacter{0433}{\cyrg}
\DeclareUnicodeCharacter{0434}{\cyrd}
\DeclareUnicodeCharacter{0435}{\cyre}
\DeclareUnicodeCharacter{0436}{\cyrzh}
\DeclareUnicodeCharacter{0437}{\cyrz}
\DeclareUnicodeCharacter{0438}{\cyri}
\DeclareUnicodeCharacter{0439}{\cyrishrt}
\DeclareUnicodeCharacter{043A}{\cyrk}
\DeclareUnicodeCharacter{043B}{\cyrl}
\DeclareUnicodeCharacter{043C}{\cyrm}
\DeclareUnicodeCharacter{043D}{\cyrn}
\DeclareUnicodeCharacter{043E}{\cyro}
\DeclareUnicodeCharacter{043F}{\cyrp}
\DeclareUnicodeCharacter{0440}{\cyrr}
\DeclareUnicodeCharacter{0441}{\cyrs}
\DeclareUnicodeCharacter{0442}{\cyrt}
\DeclareUnicodeCharacter{0443}{\cyru}
\DeclareUnicodeCharacter{0444}{\cyrf}
\DeclareUnicodeCharacter{0445}{\cyrh}
\DeclareUnicodeCharacter{0446}{\cyrc}
\DeclareUnicodeCharacter{0447}{\cyrch}
\DeclareUnicodeCharacter{0448}{\cyrsh}
\DeclareUnicodeCharacter{0449}{\cyrshch}
\DeclareUnicodeCharacter{044A}{\cyrhrdsn}
\DeclareUnicodeCharacter{044B}{\cyrery}
\DeclareUnicodeCharacter{044C}{\cyrsftsn}
\DeclareUnicodeCharacter{044D}{\cyrerev}
\DeclareUnicodeCharacter{044E}{\cyryu}
\DeclareUnicodeCharacter{044F}{\cyrya}
\DeclareUnicodeCharacter{0450}{\@tabacckludge`\cyre}
\DeclareUnicodeCharacter{0451}{\cyryo}
%</all,x2,t2c,t2b,t2a,ot2,lcy>
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{0452}{\cyrdje}
%<*all,x2,t2c,t2b,t2a,ot2,lcy>
\DeclareUnicodeCharacter{0453}{\@tabacckludge'\cyrg}
%</all,x2,t2c,t2b,t2a,ot2,lcy>
%<all,x2,t2a,ot2,lcy>\DeclareUnicodeCharacter{0454}{\cyrie}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0455}{\cyrdze}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0456}{\cyrii}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0457}{\cyryi}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0458}{\cyrje}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{0459}{\cyrlje}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{045A}{\cyrnje}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{045B}{\cyrtshe}
%<*all,x2,t2c,t2b,t2a,ot2,lcy>
\DeclareUnicodeCharacter{045C}{\@tabacckludge'\cyrk}
\DeclareUnicodeCharacter{045D}{\@tabacckludge`\cyri}
%</all,x2,t2c,t2b,t2a,ot2,lcy>
%<all,x2,t2b,t2a,lcy>\DeclareUnicodeCharacter{045E}{\cyrushrt}
%<all,x2,t2c,t2a,ot2>\DeclareUnicodeCharacter{045F}{\cyrdzhe}
%<all,x2,ot2>\DeclareUnicodeCharacter{0462}{\CYRYAT}
%<all,x2,ot2>\DeclareUnicodeCharacter{0463}{\cyryat}
%<all,x2>\DeclareUnicodeCharacter{046A}{\CYRBYUS}
%<all,x2>\DeclareUnicodeCharacter{046B}{\cyrbyus}
% \end{macrocode}
% The next two declarations are questionable, the encoding definition
% should probably contain |\CYROTLD| and |\cyrotld|. Or alternatively, if
% the characters in the X2 encodings are really meant to represent the
% historical characters in Ux0472 and Ux0473 (they look like them) then
% they would need to change instead.
%
% However, their looks are probably a font designers decision and the next
% two mappings are wrong or rather the names in OT2 should change for
% consistency.
%
% On the other hand the names |\CYROTLD| are somewhat questionabled as the
% Unicode standard only describes ``Cyrillic barred O'' while |TLD| refers
% to a tilde (which is more less what the ``Cyrillic FITA looks according
% to the Unicode book).
% \begin{macrocode}
%<all,ot2>\DeclareUnicodeCharacter{0472}{\CYRFITA}
%<all,ot2>\DeclareUnicodeCharacter{0473}{\cyrfita}
% \end{macrocode}
%
% \begin{macrocode}
%<all,x2,ot2>\DeclareUnicodeCharacter{0474}{\CYRIZH}
%<all,x2,ot2>\DeclareUnicodeCharacter{0475}{\cyrizh}
% \end{macrocode}
% While the double grave accent seems to exist in X2, T2A, T2B and T2C
% encoding, the letter izhitsa exists only in X2 and OT2. Therefore,
% izhitsa with double grave seems to be possible only using X2.
% \begin{macrocode}
%<all,x2>\DeclareUnicodeCharacter{0476}{\C\CYRIZH}
%<all,x2>\DeclareUnicodeCharacter{0477}{\C\cyrizh}
% \end{macrocode}
%
% \begin{macrocode}
%<all,t2c>\DeclareUnicodeCharacter{048C}{\CYRSEMISFTSN}
%<all,t2c>\DeclareUnicodeCharacter{048D}{\cyrsemisftsn}
%<all,t2c>\DeclareUnicodeCharacter{048E}{\CYRRTICK}
%<all,t2c>\DeclareUnicodeCharacter{048F}{\cyrrtick}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0490}{\CYRGUP}
%<all,x2,t2a,lcy>\DeclareUnicodeCharacter{0491}{\cyrgup}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0492}{\CYRGHCRS}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0493}{\cyrghcrs}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{0494}{\CYRGHK}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{0495}{\cyrghk}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0496}{\CYRZHDSC}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{0497}{\cyrzhdsc}
%<all,x2,t2a>\DeclareUnicodeCharacter{0498}{\CYRZDSC}
%<all,x2,t2a>\DeclareUnicodeCharacter{0499}{\cyrzdsc}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{049A}{\CYRKDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{049B}{\cyrkdsc}
%<all,x2,t2a>\DeclareUnicodeCharacter{049C}{\CYRKVCRS}
%<all,x2,t2a>\DeclareUnicodeCharacter{049D}{\cyrkvcrs}
%<all,x2,t2c>\DeclareUnicodeCharacter{049E}{\CYRKHCRS}
%<all,x2,t2c>\DeclareUnicodeCharacter{049F}{\cyrkhcrs}
%<all,x2,t2a>\DeclareUnicodeCharacter{04A0}{\CYRKBEAK}
%<all,x2,t2a>\DeclareUnicodeCharacter{04A1}{\cyrkbeak}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04A2}{\CYRNDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04A3}{\cyrndsc}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04A4}{\CYRNG}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04A5}{\cyrng}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A6}{\CYRPHK}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A7}{\cyrphk}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A8}{\CYRABHHA}
%<all,x2,t2c>\DeclareUnicodeCharacter{04A9}{\cyrabhha}
%<all,x2,t2a>\DeclareUnicodeCharacter{04AA}{\CYRSDSC}
%<all,x2,t2a>\DeclareUnicodeCharacter{04AB}{\cyrsdsc}
%<all,x2,t2c>\DeclareUnicodeCharacter{04AC}{\CYRTDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04AD}{\cyrtdsc}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04AE}{\CYRY}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04AF}{\cyry}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B0}{\CYRYHCRS}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B1}{\cyryhcrs}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B2}{\CYRHDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B3}{\cyrhdsc}
%<all,x2,t2c>\DeclareUnicodeCharacter{04B4}{\CYRTETSE}
%<all,x2,t2c>\DeclareUnicodeCharacter{04B5}{\cyrtetse}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B6}{\CYRCHRDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04B7}{\cyrchrdsc}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B8}{\CYRCHVCRS}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B9}{\cyrchvcrs}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04BA}{\CYRSHHA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04BB}{\cyrshha}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BC}{\CYRABHCH}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BD}{\cyrabhch}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BE}{\CYRABHCHDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BF}{\cyrabhchdsc}
% \end{macrocode}
% The character |\CYRpalochka| is not defined by OT2 and LCY. However it is
% looking identical to |\CYRII| and the Unicode standard explicitly refers
% to that (and to Latin I). So perhaps those encodings could get an alias?
% On the other hand, why are there two distinct slots in the T2 encodings
% even though they are so pressed for space? Perhaps they don't always look
% alike.
% \begin{macrocode}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04C0}{\CYRpalochka}
% \end{macrocode}
%
% \begin{macrocode}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04C1}{\U\CYRZH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04C2}{\U\cyrzh}
%<all,x2,t2b>\DeclareUnicodeCharacter{04C3}{\CYRKHK}
%<all,x2,t2b>\DeclareUnicodeCharacter{04C4}{\cyrkhk}
% \end{macrocode}
% According to the Unicode standard Ux04C5 should be an L with ``tail'' not
% with descender (which also exists as Ux04A2) but it looks as if the char
% names do not make this distinction). Should they?
% \begin{macrocode}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C5}{\CYRLDSC}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C6}{\cyrldsc}
% \end{macrocode}
%
% \begin{macrocode}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C7}{\CYRNHK}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C8}{\cyrnhk}
%<all,x2,t2b>\DeclareUnicodeCharacter{04CB}{\CYRCHLDSC}
%<all,x2,t2b>\DeclareUnicodeCharacter{04CC}{\cyrchldsc}
% \end{macrocode}
% According to the Unicode standard Ux04CD should be an M with ``tail'' not
% with descender. However this time there is no M with descender in the
% Unicode standard.
% \begin{macrocode}
%<all,x2,t2c>\DeclareUnicodeCharacter{04CD}{\CYRMDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04CE}{\cyrmdsc}
% \end{macrocode}
%
% \begin{macrocode}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D0}{\U\CYRA}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D1}{\U\cyra}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D2}{\"\CYRA}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D3}{\"\cyra}
%<all,x2,t2a>\DeclareUnicodeCharacter{04D4}{\CYRAE}
%<all,x2,t2a>\DeclareUnicodeCharacter{04D5}{\cyrae}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D6}{\U\CYRE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D7}{\U\cyre}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04D8}{\CYRSCHWA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04D9}{\cyrschwa}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04DA}{\"\CYRSCHWA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04DB}{\"\cyrschwa}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DC}{\"\CYRZH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DD}{\"\cyrzh}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DE}{\"\CYRZ}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DF}{\"\cyrz}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04E0}{\CYRABHDZE}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04E1}{\cyrabhdze}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E2}{\@tabacckludge=\CYRI}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E3}{\@tabacckludge=\cyri}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E4}{\"\CYRI}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E5}{\"\cyri}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E6}{\"\CYRO}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E7}{\"\cyro}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04E8}{\CYROTLD}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04E9}{\cyrotld}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EC}{\"\CYREREV}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04ED}{\"\cyrerev}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EE}{\@tabacckludge=\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EF}{\@tabacckludge=\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F0}{\"\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F1}{\"\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F2}{\H\CYRU}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F3}{\H\cyru}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F4}{\"\CYRCH}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F5}{\"\cyrch}
%<all,x2,t2b>\DeclareUnicodeCharacter{04F6}{\CYRGDSC}
%<all,x2,t2b>\DeclareUnicodeCharacter{04F7}{\cyrgdsc}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F8}{\"\CYRERY}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F9}{\"\cyrery}
%<all,t2b>\DeclareUnicodeCharacter{04FA}{\CYRGDSCHCRS}
%<all,t2b>\DeclareUnicodeCharacter{04FB}{\cyrgdschcrs}
%<all,x2,t2b>\DeclareUnicodeCharacter{04FC}{\CYRHHK}
%<all,x2,t2b>\DeclareUnicodeCharacter{04FD}{\cyrhhk}
%<all,t2b>\DeclareUnicodeCharacter{04FE}{\CYRHHCRS}
%<all,t2b>\DeclareUnicodeCharacter{04FF}{\cyrhhcrs}
%<all,ts1>\DeclareUnicodeCharacter{0E3F}{\textbaht}
%<all,t1>\DeclareUnicodeCharacter{1E02}{\.B}
%<all,t1>\DeclareUnicodeCharacter{1E03}{\.b}
%<all,t1>\DeclareUnicodeCharacter{1E9E}{\SS}
%<all,x2,t2c,t2b,t2a,t1,utf8>\DeclareUnicodeCharacter{200C}{\textcompwordmark}
% \end{macrocode}
% \changes{v1.1s}{2016/02/28}{Add more hyphens and dashes}
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{2010}{-}
%<all,t1>\DeclareUnicodeCharacter{2011}{\mbox{-}}
% \end{macrocode}
% U+2012 should be the width of a digit, endash is OK in many fonts including cm.
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{2012}{\textendash}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>
\DeclareUnicodeCharacter{2013}{\textendash}
\DeclareUnicodeCharacter{2014}{\textemdash}
% \end{macrocode}
% U+2015 is Horizontal bar
% \begin{macrocode}
%<all,t1>\DeclareUnicodeCharacter{2015}{\textemdash}
%</all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>
%<all,ts1>\DeclareUnicodeCharacter{2016}{\textbardbl}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ot1,lcy>
\DeclareUnicodeCharacter{2018}{\textquoteleft}
\DeclareUnicodeCharacter{2019}{\textquoteright}
%</all,x2,t2c,t2b,t2a,t1,ot2,ot1,lcy>
%<all,t1>\DeclareUnicodeCharacter{201A}{\quotesinglbase}
%<*all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>
\DeclareUnicodeCharacter{201C}{\textquotedblleft}
\DeclareUnicodeCharacter{201D}{\textquotedblright}
%</all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>
%<all,x2,t2c,t2b,t2a,t1,lcy>\DeclareUnicodeCharacter{201E}{\quotedblbase}
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2020}{\textdagger}
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2021}{\textdaggerdbl}
%<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2022}{\textbullet}
%<all,ly1,utf8>\DeclareUnicodeCharacter{2026}{\textellipsis}
%<*all,x2,ts1,t2c,t2b,t2a,t1,ly1>
\DeclareUnicodeCharacter{2030}{\textperthousand}
%</all,x2,ts1,t2c,t2b,t2a,t1,ly1>
%<*all,x2,ts1,t2c,t2b,t2a,t1>
\DeclareUnicodeCharacter{2031}{\textpertenthousand}
%</all,x2,ts1,t2c,t2b,t2a,t1>
%<all,t1,ly1>\DeclareUnicodeCharacter{2039}{\guilsinglleft}
%<all,t1,ly1>\DeclareUnicodeCharacter{203A}{\guilsinglright}
%<all,ts1>\DeclareUnicodeCharacter{203B}{\textreferencemark}
%<all,ts1>\DeclareUnicodeCharacter{203D}{\textinterrobang}
%<all,ts1>\DeclareUnicodeCharacter{2044}{\textfractionsolidus}
%<all,ts1>\DeclareUnicodeCharacter{204E}{\textasteriskcentered}
%<all,ts1>\DeclareUnicodeCharacter{2052}{\textdiscount}
%<all,ts1>\DeclareUnicodeCharacter{20A1}{\textcolonmonetary}
%<all,ts1>\DeclareUnicodeCharacter{20A4}{\textlira}
%<all,ts1>\DeclareUnicodeCharacter{20A6}{\textnaira}
%<all,ts1>\DeclareUnicodeCharacter{20A9}{\textwon}
%<all,ts1>\DeclareUnicodeCharacter{20AB}{\textdong}
%<all,ts1>\DeclareUnicodeCharacter{20AC}{\texteuro}
%<all,ts1>\DeclareUnicodeCharacter{20B1}{\textpeso}
%<all,ts1>\DeclareUnicodeCharacter{2103}{\textcelsius}
%<all,x2,ts1,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{2116}{\textnumero}
%<all,ts1>\DeclareUnicodeCharacter{2117}{\textcircledP}
%<all,ts1>\DeclareUnicodeCharacter{211E}{\textrecipe}
%<all,ts1>\DeclareUnicodeCharacter{2120}{\textservicemark}
%<all,ts1,ly1,utf8>\DeclareUnicodeCharacter{2122}{\texttrademark}
%<all,ts1>\DeclareUnicodeCharacter{2126}{\textohm}
%<all,ts1>\DeclareUnicodeCharacter{2127}{\textmho}
%<all,ts1>\DeclareUnicodeCharacter{212E}{\textestimated}
%<all,ts1>\DeclareUnicodeCharacter{2190}{\textleftarrow}
%<all,ts1>\DeclareUnicodeCharacter{2191}{\textuparrow}
%<all,ts1>\DeclareUnicodeCharacter{2192}{\textrightarrow}
%<all,ts1>\DeclareUnicodeCharacter{2193}{\textdownarrow}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{2329}{\textlangle}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{232A}{\textrangle}
%<all,ts1>\DeclareUnicodeCharacter{2422}{\textblank}
%<all,x2,t2c,t2b,t2a,t1,utf8>\DeclareUnicodeCharacter{2423}{\textvisiblespace}
%<all,ts1>\DeclareUnicodeCharacter{25E6}{\textopenbullet}
%<all,ts1>\DeclareUnicodeCharacter{25EF}{\textbigcircle}
%<all,ts1>\DeclareUnicodeCharacter{266A}{\textmusicalnote}
% \end{macrocode}
% \changes{v1.2h}{2019/02/07}{Added 27E8 and 27E9 (github/110)}
% \begin{macrocode}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{27E8}{\textlangle}
%<all,x2,ts1,t2c,t2b,t2a>\DeclareUnicodeCharacter{27E9}{\textrangle}
%<all,t1>\DeclareUnicodeCharacter{1E20}{\@tabacckludge=G}
%<all,t1>\DeclareUnicodeCharacter{1E21}{\@tabacckludge=g}
% \end{macrocode}
%
% When doing cut-and-paste from other documents f-ligatures might show
% up as Unicode characters. We translate them back to individual
% characters so that they get accepted. If supported by the font
% (which is normally the case) they are then reconstructed as
% ligatures so they come out as desired. Otherwise they will come
% out as individual characters which is fine too.
% \changes{v1.2j}{2019/07/11}{Add typical f-ligatures and s-ligatures and st (github/154)}
% \changes{v1.kj}{2019/11/14}{Fixed setting for FB05 = long-s t lig (github/154)}
% \begin{macrocode}
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB00}{ff} % ff
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB01}{fi} % fi
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB02}{fl} % fl
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB03}{ffi} % ffi
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB04}{ffl} % ffl
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB05}{st} % ſt -- this is the long s (not f)
%<all,t1,ot1,ly1,t2a,t2b,t2c>\DeclareUnicodeCharacter{FB06}{st} % st
% \end{macrocode}
%
%
% \changes{v1.2c}{2018/04/05}{Add BOM}
% \begin{macrocode}
%<all,ts1,utf8>\DeclareUnicodeCharacter{FEFF}{\ifhmode\nobreak\fi}
% \end{macrocode}
%
%
% \endgroup
% \subsection{Notes}
%
% \changes{v1.1e}{2004/05/22}{Added notes on inconsistency with `8-bit files'.}
% The following inputs are inconsistent with the 8-bit inputenc files
% since they will always only produce the `text character'. This is an
% area where inputenc is notoriously confused.
% \begin{verbatim}
% %<all,ts1,t1,ot1,ly1>\DeclareUnicodeCharacter{00A3}{\textsterling}
% %<*all,x2,ts1,t2c,t2b,t2a,oms,ly1>
% \DeclareUnicodeCharacter{00A7}{\textsection}
% %</all,x2,ts1,t2c,t2b,t2a,oms,ly1>
% %<all,ts1,utf8>\DeclareUnicodeCharacter{00A9}{\textcopyright}
% %<all,ts1>\DeclareUnicodeCharacter{00B1}{\textpm}
% %<all,ts1,oms,ly1>\DeclareUnicodeCharacter{00B6}{\textparagraph}
% %<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2020}{\textdagger}
% %<all,ts1,oms,ly1>\DeclareUnicodeCharacter{2021}{\textdaggerdbl}
% %<all,ly1,utf8>\DeclareUnicodeCharacter{2026}{\textellipsis}
% \end{verbatim}
%
% The following definitions are in an encoding file but have no
% direct equivalent in Unicode, or they simply do not make sense in that
% context (or we have not yet found anything or \ldots :-). For
% example, the non-combining accent characters are certainly
% available somewhere but these are not equivalent to a \TeX{}
% accent command.
%\begin{verbatim}
%\DeclareTextSymbol{\j}{OT1}{17}
%\DeclareTextSymbol{\SS}{T1}{223}
%\DeclareTextSymbol{\textcompwordmark}{T1}{23}
%
%\DeclareTextAccent{\"}{OT1}{127}
%\DeclareTextAccent{\'}{OT1}{19}
%\DeclareTextAccent{\.}{OT1}{95}
%\DeclareTextAccent{\=}{OT1}{22}
%\DeclareTextAccent{\H}{OT1}{125}
%\DeclareTextAccent{\^}{OT1}{94}
%\DeclareTextAccent{\`}{OT1}{18}
%\DeclareTextAccent{\r}{OT1}{23}
%\DeclareTextAccent{\u}{OT1}{21}
%\DeclareTextAccent{\v}{OT1}{20}
%\DeclareTextAccent{\~}{OT1}{126}
%\DeclareTextCommand{\b}{OT1}[1]
%\DeclareTextCommand{\c}{OT1}[1]
%\DeclareTextCommand{\d}{OT1}[1]
%\DeclareTextCommand{\k}{T1}[1]
%\end{verbatim}
%
%
%
% \subsection{Mappings for OT1 glyphs}
%
% This is even more incomplete as again it covers only the single
% glyphs from |OT1| plus some that have been explicitly defined for
% this encoding. Everything that is provided in |T1|, and that
% could be provided as composite glyphs via |OT1|, could and
% probably should be set up as well. Which leaves the many things
% that are not provided in |T1| but can be provided in |OT1| (and
% in |T1|) by composite glyphs.
%
% Stuff not mapped (note that |\j| ($\jmath$) is not equivalent to any
% Unicode character):
%\begin{verbatim}
%\DeclareTextSymbol{\j}{OT1}{17}
%\DeclareTextAccent{\"}{OT1}{127}
%\DeclareTextAccent{\'}{OT1}{19}
%\DeclareTextAccent{\.}{OT1}{95}
%\DeclareTextAccent{\=}{OT1}{22}
%\DeclareTextAccent{\^}{OT1}{94}
%\DeclareTextAccent{\`}{OT1}{18}
%\DeclareTextAccent{\~}{OT1}{126}
%\DeclareTextAccent{\H}{OT1}{125}
%\DeclareTextAccent{\u}{OT1}{21}
%\DeclareTextAccent{\v}{OT1}{20}
%\DeclareTextAccent{\r}{OT1}{23}
%\DeclareTextCommand{\b}{OT1}[1]
%\DeclareTextCommand{\c}{OT1}[1]
%\DeclareTextCommand{\d}{OT1}[1]
%\end{verbatim}
%
%
%
% \subsection{Mappings for OMS glyphs}
%
% Characters like |\textbackslash| are not mapped as they are
% (primarily) only in the lower 127 and the code here only sets up
% mappings for UTF-8 characters that are at least 2 octets long.
%\begin{verbatim}
%\DeclareTextSymbol{\textbackslash}{OMS}{110} % "6E
%\DeclareTextSymbol{\textbar}{OMS}{106} % "6A
%\DeclareTextSymbol{\textbraceleft}{OMS}{102} % "66
%\DeclareTextSymbol{\textbraceright}{OMS}{103} % "67
%\end{verbatim}
%
% But the following (and some others) might actually lurk in Unicode
% somewhere\ldots
%\begin{verbatim}
%\DeclareTextSymbol{\textasteriskcentered}{OMS}{3} % "03
%\DeclareTextCommand{\textcircled}{OMS}
%\end{verbatim}
%
%
%
%
% \subsection{Mappings for TS1 glyphs}
%
% Exercise for somebody else.
%
%
% \subsection{Mappings for \texttt{latex.ltx} glyphs}
%
% There is also a collection of characters already set up in the kernel,
% one way or the other. Since these do not clearly relate to any
% particular font encoding they are mapped when the
% \texttt{utf8} support is first set up.
%
% Also there are a number of |\providecommand|s in the various input
% encoding files which may or may not go into this part.
% \changes{v1.1b}{2004/02/09}{Added commands already defined in the kernel}
% \begin{macrocode}
%<*utf8>
% This space is intentionally empty ...
%</utf8>
% \end{macrocode}
%
% \subsection{Old \texttt{utf8.def} file as a temp fix for p\TeX{} and friends}
%
%
% \changes{v1.2h}{2019/07/09}{Temp rollback fix for e-pTeX}
% \begin{macrocode}
%<*utf8-2018>
\ProvidesFile{utf8.def}
[2018/10/05 v1.2f UTF-8 support for inputenc]
\makeatletter
\catcode`\ \saved@space@catcode
\long\def\UTFviii@two@octets#1#2{\expandafter
\UTFviii@defined\csname u8:#1\string#2\endcsname}
\long\def\UTFviii@three@octets#1#2#3{\expandafter
\UTFviii@defined\csname u8:#1\string#2\string#3\endcsname}
\long\def\UTFviii@four@octets#1#2#3#4{\expandafter
\UTFviii@defined\csname u8:#1\string#2\string#3\string#4\endcsname}
\def\UTFviii@defined#1{%
\ifx#1\relax
\if\relax\expandafter\UTFviii@checkseq\string#1\relax\relax
\UTFviii@undefined@err{#1}%
\else
\PackageError{inputenc}{Invalid UTF-8 byte sequence}%
\UTFviii@invalid@help
\fi
\else\expandafter
#1%
\fi
}
\def\UTFviii@invalid@err#1{%
\PackageError{inputenc}{Invalid UTF-8 byte "\UTFviii@hexnumber{`#1}}%
\UTFviii@invalid@help}
\def\UTFviii@invalid@help{%
The document does not appear to be in UTF-8 encoding.\MessageBreak
Try adding \noexpand\UseRawInputEncoding as the first line of the file\MessageBreak
or specify an encoding such as \noexpand\usepackage[latin1]{inputenc}\MessageBreak
in the document preamble.\MessageBreak
Alternatively, save the file in UTF-8 using your editor or another tool}
\def\UTFviii@undefined@err#1{%
\PackageError{inputenc}{Unicode character \expandafter
\UTFviii@splitcsname\string#1\relax
\MessageBreak
not set up for use with LaTeX}%
{You may provide a definition with\MessageBreak
\noexpand\DeclareUnicodeCharacter}%
}
\def\UTFviii@checkseq#1:#2#3{%
\ifnum`#2<"80 %
\ifx\relax#3\else1\fi
\else
\ifnum`#2<"C0 %
1 %
\else
\expandafter\expandafter\expandafter\UTFviii@check@continue
\expandafter\expandafter\expandafter#3%
\fi
\fi}
\def\UTFviii@check@continue#1{%
\ifx\relax#1%
\else
\ifnum`#1<"80 1\else\ifnum`#1>"BF 1\fi\fi
\expandafter\UTFviii@check@continue
\fi
}
\begingroup
\catcode`\~13
\catcode`\"12
\def\UTFviii@loop{%
\uccode`\~\count@
\uppercase\expandafter{\UTFviii@tmp}%
\advance\count@\@ne
\ifnum\count@<\@tempcnta
\expandafter\UTFviii@loop
\fi}
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@undefined@err{:\string~}}}
\count@"1
\@tempcnta9
\UTFviii@loop
\count@11
\@tempcnta12
\UTFviii@loop
\count@14
\@tempcnta32
\UTFviii@loop
\count@"80
\@tempcnta"C2
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@invalid@err\string~}}
\UTFviii@loop
\count@"C2
\@tempcnta"E0
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@two@octets\string~}}
\UTFviii@loop
\count@"E0
\@tempcnta"F0
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@three@octets\string~}}
\UTFviii@loop
\count@"F0
\@tempcnta"F5
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@four@octets\string~}}
\UTFviii@loop
\count@"F5
\@tempcnta"100
\def\UTFviii@tmp{\xdef~{\noexpand\UTFviii@invalid@err\string~}}
\UTFviii@loop
\endgroup
\@inpenc@test
\ifx\@begindocumenthook\@undefined
\makeatother
\endinput \fi
\begingroup
\catcode`\"=12
\catcode`\<=12
\catcode`\.=12
\catcode`\,=12
\catcode`\;=12
\catcode`\!=12
\catcode`\~=13
\gdef\DeclareUnicodeCharacter#1#2{%
\count@"#1\relax
\wlog{ \space\space defining Unicode char U+#1 (decimal \the\count@)}%
\begingroup
\parse@XML@charref
\def\UTFviii@two@octets##1##2{\csname u8:##1\string##2\endcsname}%
\def\UTFviii@three@octets##1##2##3{\csname u8:##1%
\string##2\string##3\endcsname}%
\def\UTFviii@four@octets##1##2##3##4{\csname u8:##1%
\string##2\string##3\string##4\endcsname}%
\expandafter\expandafter\expandafter
\expandafter\expandafter\expandafter
\expandafter
\gdef\UTFviii@tmp{\IeC{#2}}%
\endgroup
}
\gdef\parse@XML@charref{%
\ifnum\count@<"A0\relax
\ifnum\catcode\count@=13
\uccode`\~=\count@\uppercase{\def\UTFviii@tmp{\@empty\@empty~}}%
\else
\PackageError{inputenc}%
{Cannot define non-active Unicode char value < 00A0}%
\@eha
\def\UTFviii@tmp{\UTFviii@tmp}%
\fi
\else\ifnum\count@<"800\relax
\parse@UTFviii@a,%
\parse@UTFviii@b C\UTFviii@two@octets.,%
\else\ifnum\count@<"10000\relax
\parse@UTFviii@a;%
\parse@UTFviii@a,%
\parse@UTFviii@b E\UTFviii@three@octets.{,;}%
\else
\ifnum\count@>"10FFFF\relax
\PackageError{inputenc}%
{\UTFviii@hexnumber\count@\space too large for Unicode}%
{Values between 0 and 10FFFF are permitted}%
\fi
\parse@UTFviii@a;%
\parse@UTFviii@a,%
\parse@UTFviii@a!%
\parse@UTFviii@b F\UTFviii@four@octets.{!,;}%
\fi
\fi
\fi
}
\gdef\parse@UTFviii@a#1{%
\@tempcnta\count@
\divide\count@ 64
\@tempcntb\count@
\multiply\count@ 64
\advance\@tempcnta-\count@
\advance\@tempcnta 128
\uccode`#1\@tempcnta
\count@\@tempcntb}
\gdef\parse@UTFviii@b#1#2#3#4{%
\advance\count@ "#10\relax
\uccode`#3\count@
\uppercase{\gdef\UTFviii@tmp{#2#3#4}}}
\ifx\numexpr\@undefined
\gdef\decode@UTFviii#1{0}
\else
\gdef\decode@UTFviii#1\relax{%
\expandafter\UTFviii@cleanup
\the\numexpr\dec@de@UTFviii#1\relax)))))\@empty}
\gdef\UTFviii@cleanup#1)#2\@empty{#1}
\gdef\dec@de@UTFviii#1{%
\ifx\relax#1%
\else
\ifnum`#1>"EF
((((`#1-"F0)%
\else
\ifnum`#1>"DF
(((`#1-"E0)%
\else
\ifnum`#1>"BF
((`#1-"C0)%
\else
\ifnum`#1>"7F
)*64+(`#1-"80)%
\else
+`#1 %
\fi
\fi
\fi
\fi
\expandafter\dec@de@UTFviii
\fi}
\fi
\ifx\numexpr\@undefined
\global\let\UTFviii@hexnumber\@firstofone
\global\UTFviii@hexdigit\hexnumber@
\else
\gdef\UTFviii@hexnumber#1{%
\ifnum#1>15 %
\expandafter\UTFviii@hexnumber\expandafter{\the\numexpr(#1-8)/16\relax}%
\fi
\UTFviii@hexdigit{\numexpr#1\ifnum#1>0-((#1-8)/16)*16\fi\relax}%
}
\gdef\UTFviii@hexdigit#1{\ifcase\numexpr#1\relax
0\or1\or2\or3\or4\or5\or6\or7\or8\or9\or
A\or B\or C\or D\or E\or F\fi}
\fi
\gdef\UTFviii@hexcodepoint#1{U+%
\ifnum#1<16 0\fi
\ifnum#1<256 0\fi
\ifnum#1<4096 0\fi
\UTFviii@hexnumber{#1}%
}%
\gdef\UTFviii@splitcsname#1:#2\relax{%
#2 (\expandafter\UTFviii@hexcodepoint\expandafter{%
\the\numexpr\decode@UTFviii#2\relax})%
}
\endgroup
\@onlypreamble\DeclareUnicodeCharacter
\@onlypreamble\parse@XML@charref
\@onlypreamble\parse@UTFviii@a
\@onlypreamble\parse@UTFviii@b
\begingroup
\def\cdp@elt#1#2#3#4{%
\wlog{Now handling font encoding #1 ...}%
\lowercase{%
\InputIfFileExists{#1enc.dfu}}%
{\wlog{... processing UTF-8 mapping file for font %
encoding #1}%
\catcode`\ 9\relax}%
{\wlog{... no UTF-8 mapping file for font encoding #1}}%
}
\cdp@list
\endgroup
\def\DeclareFontEncoding@#1#2#3{%
\expandafter
\ifx\csname T@#1\endcsname\relax
\def\cdp@elt{\noexpand\cdp@elt}%
\xdef\cdp@list{\cdp@list\cdp@elt{#1}%
{\default@family}{\default@series}%
{\default@shape}}%
\expandafter\let\csname#1-cmd\endcsname\@changed@cmd
\begingroup
\wlog{Now handling font encoding #1 ...}%
\lowercase{%
\InputIfFileExists{#1enc.dfu}}%
{\wlog{... processing UTF-8 mapping file for font %
encoding #1}}%
{\wlog{... no UTF-8 mapping file for font encoding #1}}%
\endgroup
\else
\@font@info{Redeclaring font encoding #1}%
\fi
\global\@namedef{T@#1}{#2}%
\global\@namedef{M@#1}{\default@M#3}%
\xdef\LastDeclaredEncoding{#1}%
}
\DeclareUnicodeCharacter{00A9}{\textcopyright}
\DeclareUnicodeCharacter{00AA}{\textordfeminine}
\DeclareUnicodeCharacter{00AE}{\textregistered}
\DeclareUnicodeCharacter{00BA}{\textordmasculine}
\DeclareUnicodeCharacter{02C6}{\textasciicircum}
\DeclareUnicodeCharacter{02DC}{\textasciitilde}
\DeclareUnicodeCharacter{200C}{\textcompwordmark}
\DeclareUnicodeCharacter{2026}{\textellipsis}
\DeclareUnicodeCharacter{2122}{\texttrademark}
\DeclareUnicodeCharacter{2423}{\textvisiblespace}
\DeclareUnicodeCharacter{FEFF}{\ifhmode\nobreak\fi}
\endinput
</utf8-2018>
% \end{macrocode}
%
%
% \section{A test document}
%
% Here is a very small test document which may or may not survive
% if the current document is transferred from one place to the
% other.
% \begin{macrocode}
%<*test>
\documentclass{article}
\usepackage[latin1,utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{trace}
\scrollmode % to run past the error below
\begin{document}
German umlauts in UTF-8: ^^c3^^a4^^c3^^b6^^c3^^bc %%% äöü
\inputencoding{latin1} % switch to latin1
German umlauts in UTF-8 but read by latin1 (and will produce one
error since \verb=\textcurrency= is not provided):
^^c3^^a4^^c3^^b6^^c3^^bc
\inputencoding{utf8} % switch back to utf8
German umlauts in UTF-8: ^^c3^^a4^^c3^^b6^^c3^^bc
Some codes that should produce errors as nothing is set up
for them: ^^c3F ^^e1^^a4^^b6
And some that are not legal utf8 sequences: ^^c3X ^^e1XY
\showoutput
\tracingstats=2
\stop
%</test>
% \end{macrocode}
%
% \Finale
%
\endinput
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...