| 1 |
% \iffalse meta-comment |
| 2 |
% |
| 3 |
% Copyright (C) 1993-2025 |
| 4 |
% The LaTeX Project and any individual authors listed elsewhere |
| 5 |
% in this file. |
| 6 |
% |
| 7 |
% This file is part of the LaTeX base system. |
| 8 |
% ------------------------------------------- |
| 9 |
% |
| 10 |
% It may be distributed and/or modified under the |
| 11 |
% conditions of the LaTeX Project Public License, either version 1.3c |
| 12 |
% of this license or (at your option) any later version. |
| 13 |
% The latest version of this license is in |
| 14 |
% http://www.latex-project.org/lppl.txt |
| 15 |
% and version 1.3c or later is part of all distributions of LaTeX |
| 16 |
% version 2008 or later. |
| 17 |
% |
| 18 |
% This file has the LPPL maintenance status "maintained". |
| 19 |
% |
| 20 |
% The list of all files belonging to the LaTeX base distribution is |
| 21 |
% given in the file `manifest.txt'. See also `legal.txt' for additional |
| 22 |
% information. |
| 23 |
% |
| 24 |
% The list of derived (unpacked) files belonging to the distribution |
| 25 |
% and covered by LPPL is defined by the unpacking scripts (with |
| 26 |
% extension .ins) which are part of the distribution. |
| 27 |
% |
| 28 |
% \fi |
| 29 |
% |
| 30 |
|
| 31 |
|
| 32 |
\NeedsTeXFormat{LaTeX2e}[1995/12/01] |
| 33 |
|
| 34 |
\documentclass{ltxguide}[1994/11/20] |
| 35 |
|
| 36 |
\usepackage[T1]{fontenc} |
| 37 |
\IfFileExists{lmodern.sty}{\usepackage{lmodern}}{} |
| 38 |
\usepackage{textcomp} |
| 39 |
\usepackage{url} |
| 40 |
\usepackage{mflogo} |
| 41 |
|
| 42 |
\addtolength\textheight{6\baselineskip} |
| 43 |
\addtolength\topmargin{-2\baselineskip} |
| 44 |
|
| 45 |
|
| 46 |
\newcommand\ttverb[1]{\texttt{\string#1}} |
| 47 |
|
| 48 |
|
| 49 |
% for encodings |
| 50 |
\providecommand{\Enc}[1]{\texttt{#1}} |
| 51 |
|
| 52 |
% for packages |
| 53 |
\providecommand{\Pkg}[1]{% |
| 54 |
\textsf{#1}} |
| 55 |
|
| 56 |
% for files |
| 57 |
\providecommand{\File}[1]{% |
| 58 |
\texttt{#1}} |
| 59 |
|
| 60 |
% let's have meta values too |
| 61 |
\providecommand{\meta}[1]{% |
| 62 |
\ensuremath{\langle}\emph{#1}\ensuremath{\rangle}} |
| 63 |
|
| 64 |
\usepackage{tabularx} |
| 65 |
|
| 66 |
% eine Umgebung zur Darstellung von Kodierungen |
| 67 |
% |
| 68 |
% Argumente: |
| 69 |
% #1: Name in LaTeX (z.B. OT1) |
| 70 |
% #2: Name der Kodierung (z.B. TeX text) |
| 71 |
% #3: Name des Autors (z.B. Don Knuth) |
| 72 |
% #4: Bereich der benützten Glyphindizes |
| 73 |
% #5: variable Positionen |
| 74 |
% #6: Beispielzeichensatz |
| 75 |
% #7: Referenz |
| 76 |
% |
| 77 |
% XXX add code to handle more than a single font example (e.g., larm1000, |
| 78 |
% lbrm1000, and lcrm1000). |
| 79 |
% |
| 80 |
\newenvironment{encodinginfo}[7]% |
| 81 |
{\noindent |
| 82 |
\begin{tabularx}{\linewidth}{@{}l>{\raggedright\let\\\tabularnewline}X}% |
| 83 |
\LaTeX{} name: & \texttt{#1}\\% |
| 84 |
Public name: & #2\\% |
| 85 |
Author: & #3\\% |
| 86 |
Glyph slots used: & #4\\% |
| 87 |
Variable slots: & #5\\% |
| 88 |
Font example: & \def\@tempa{#6}\ifx\@tempa\@empty---% |
| 89 |
\else\texttt{#6}\referenceftable{#6}\fi\\% |
| 90 |
Further reference: & #7% |
| 91 |
\end{tabularx}% |
| 92 |
\par\nobreak |
| 93 |
\vspace*{3pt}% |
| 94 |
\quote |
| 95 |
}% |
| 96 |
{\endquote |
| 97 |
\vspace{6pt}} |
| 98 |
|
| 99 |
\makeatletter |
| 100 |
\def\referenceftable#1{ |
| 101 |
\@ifundefined{r@fonttable:#1}% |
| 102 |
\relax |
| 103 |
{;\space encoding table on page~\pageref{fonttable:#1}}% |
| 104 |
} |
| 105 |
|
| 106 |
% font table macros mainly lifted from manmac.tex |
| 107 |
\def\oct#1{\hbox{\rm\'{}\kern-.2em\it#1\/\kern.05em}} |
| 108 |
\def\hex#1{\hbox{\rm\H{}\tt#1}} |
| 109 |
|
| 110 |
\def\oddline#1{\cr\noalign{\nointerlineskip} |
| 111 |
\multispan{19}\hrulefill& |
| 112 |
\setbox0=\hbox{\lower 2.3pt\hbox{\hex{#1x}}}\smash{\box0}\cr |
| 113 |
\noalign{\nointerlineskip}} |
| 114 |
\def\evenline{\cr\noalign{\hrule}} |
| 115 |
\def\chartstrut{\lower4.5pt\vbox to14pt{}} |
| 116 |
\def\beginchart#1#2{$$\global\count@=0 #1 |
| 117 |
\halign to\hsize\bgroup |
| 118 |
\chartstrut##\tabskip0pt plus10pt& |
| 119 |
&\hfil##\hfil&\vrule##\cr |
| 120 |
\lower6.5pt\null |
| 121 |
&&\oct0&&\oct1&&\oct2&&\oct3&&\oct4&&\oct5&&\oct6&&\oct7&\evenline} |
| 122 |
\def\endchart{\raise11.5pt\null&&&\hex 8&&\hex 9&&\hex A&&\hex B& |
| 123 |
&\hex C&&\hex D&&\hex E&&\hex F&\cr\egroup$$} |
| 124 |
\def\:{\setbox0=\hbox{\noboundary\char\count@\noboundary}% |
| 125 |
\ifdim\ht0>7.5pt\reposition |
| 126 |
\else\ifdim\dp0>2.5pt\reposition\fi\fi |
| 127 |
\box0\global\advance\count@ by1 } |
| 128 |
\def\reposition{\setbox0=\hbox{$\vcenter{\kern2pt\box0\kern2pt}$}} |
| 129 |
\def\normalchart{% |
| 130 |
&\oct{00x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline0 |
| 131 |
&\oct{01x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 132 |
&\oct{02x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline1 |
| 133 |
&\oct{03x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 134 |
&\oct{04x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline2 |
| 135 |
&\oct{05x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 136 |
&\oct{06x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline3 |
| 137 |
&\oct{07x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 138 |
&\oct{10x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline4 |
| 139 |
&\oct{11x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 140 |
&\oct{12x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline5 |
| 141 |
&\oct{13x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 142 |
&\oct{14x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline6 |
| 143 |
&\oct{15x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 144 |
&\oct{16x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline7 |
| 145 |
&\oct{17x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 146 |
\top} |
| 147 |
|
| 148 |
\def\notophalf{} |
| 149 |
\def\tophalf{% |
| 150 |
%\noalign{\vskip 5pt\hrule} |
| 151 |
&\oct{20x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline8 |
| 152 |
&\oct{21x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 153 |
&\oct{22x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline9 |
| 154 |
&\oct{23x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 155 |
&\oct{24x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline A |
| 156 |
&\oct{25x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 157 |
&\oct{26x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline B |
| 158 |
&\oct{27x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 159 |
&\oct{30x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline C |
| 160 |
&\oct{31x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 161 |
&\oct{32x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline D |
| 162 |
&\oct{33x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 163 |
&\oct{34x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline E |
| 164 |
&\oct{35x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline |
| 165 |
&\oct{36x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\oddline F |
| 166 |
&\oct{37x}&&\:&&\:&&\:&&\:&&\:&&\:&&\:&&\:&\evenline} |
| 167 |
|
| 168 |
\def\ftable#1#2{% |
| 169 |
\batchmode |
| 170 |
\font\X=#1% |
| 171 |
\errorstopmode |
| 172 |
\ifx\X\nullfont |
| 173 |
\@warning{Font #1 not found, table omitted} |
| 174 |
\else |
| 175 |
\count@="80 |
| 176 |
\setbox0=\hbox{\X |
| 177 |
\loop\char\count@\advance\count@ by1 \ifnum\count@<"100 |
| 178 |
\repeat}% |
| 179 |
\ifdim\wd0>0pt \let\top\tophalf\else\let\top\notophalf\fi |
| 180 |
\beginchart\X{\hfill\llap{\textbf{#1, \large#2}\label{fonttable:#1}}}\normalchart |
| 181 |
\endchart\par\vfill |
| 182 |
\fi} |
| 183 |
\makeatother |
| 184 |
|
| 185 |
|
| 186 |
\setcounter{tocdepth}{3} |
| 187 |
|
| 188 |
\title{\LaTeX{} font encodings} |
| 189 |
|
| 190 |
\author{Frank Mittelbach \and Robin |
| 191 |
Fairbairns \and Werner Lemberg \and \LaTeX\ Project Team.} |
| 192 |
|
| 193 |
\date{\copyright~Copyright 1995--2016 \\[5pt] 18 February 2016} |
| 194 |
|
| 195 |
\begin{document} |
| 196 |
|
| 197 |
\maketitle |
| 198 |
|
| 199 |
\tableofcontents |
| 200 |
|
| 201 |
\section{Introduction} |
| 202 |
|
| 203 |
This document explains the ideas that underpin \LaTeX{} font |
| 204 |
encodings and the constraints that apply when defining a new encoding; it |
| 205 |
also lists the encodings that have already been defined. |
| 206 |
|
| 207 |
\subsection{Encodings in \TeX{}} |
| 208 |
|
| 209 |
\TeX{} (the program) implicitly recognises three sorts of encoding, |
| 210 |
and all are (in a sense) discussed in the \TeX{}book~\cite{A-W:DKn86}: |
| 211 |
\begin{itemize} |
| 212 |
\item[1.] The input encoding, which specifies the meanings of characters |
| 213 |
in files presented to \TeX{} for processing. The \TeX{}book |
| 214 |
suggests that `your version of \TeX{} will recognise the characters |
| 215 |
you type on your keyboard' (\TeX{} the program has provision for |
| 216 |
static translations of input characters). |
| 217 |
\end{itemize} |
| 218 |
Such direct use of \TeX{}'s facilities is not the way modern |
| 219 |
\LaTeX{} (or indeed any other \TeX{} macro package) is likely to deal |
| 220 |
with input encodings. This document does not address the topic of |
| 221 |
input encodings; the interested reader should examine the \LaTeX{} |
| 222 |
base package \Pkg{inputenc} \cite[sec.~7.5.2, p.~357]{A-W:MG2004}. |
| 223 |
\begin{itemize} |
| 224 |
\item[2.] The token stream that \TeX{} processes internally. This stream |
| 225 |
of \TeX{}'s consciousness is discussed in great detail in the |
| 226 |
\TeX{}book. |
| 227 |
\end{itemize} |
| 228 |
Again, this document does not address the topic. \LaTeX's internal |
| 229 |
character representation (\textsc{licr}) is well discussed in |
| 230 |
\cite[sec.~7.11.2, p.~442]{A-W:MG2004}. |
| 231 |
\begin{itemize} |
| 232 |
\item[3.] The font encoding---i.e., the mapping of character codes to |
| 233 |
glyphs in the fonts that are used to typeset \TeX{}'s output. |
| 234 |
Again, a set of font encodings is enumerated in the \TeX{}book, but |
| 235 |
that set has proved inadequate to the needs of modern multilingual |
| 236 |
use of \LaTeX. |
| 237 |
\end{itemize} |
| 238 |
This document explains \emph{why} Knuth's original set of encodings is |
| 239 |
inadequate to modern conditions, and discusses the issues that |
| 240 |
surround the design and definition of new font encodings. |
| 241 |
|
| 242 |
Font encodings are important for more than their r\^{o}le in mapping the |
| 243 |
glyphs of the fonts to be used for typesetting: their glyph tables are |
| 244 |
also the context in which \TeX{}'s hyphenation algorithm operates. |
| 245 |
There are constraints imposed by \TeX{} that affect the way in which |
| 246 |
new font encodings, for use in a multi-lingual environment, may be |
| 247 |
structured (see section~\ref{sec:restrictions} for details). |
| 248 |
|
| 249 |
\subsection{The history of \TeX{} font encodings} |
| 250 |
|
| 251 |
Little attention was paid to font encodings prior to the arrival of |
| 252 |
\TeX{}\,3. Up to that time, one used Donald Knuth's fonts (the |
| 253 |
Computer Modern family, using the encodings we now refer to as \Enc{OT1} and |
| 254 |
the \Enc{OM} series), or one was on one's own. |
| 255 |
|
| 256 |
The Computer Modern text encoding raises problems in unmodified |
| 257 |
\TeX{}, because hyphenation cannot break words containing |
| 258 |
\verb"\accent" commands. Even in those Western European languages for |
| 259 |
which the \Enc{OT1} encoding has symbols for the necessary |
| 260 |
\verb"\accent"-based diacritics, this shortcoming ruins typesetting of |
| 261 |
running text. |
| 262 |
|
| 263 |
With the advent of \TeX{}\,3, with its ability to switch between |
| 264 |
hyphenation pattern sets, it was clear that the situation could not |
| 265 |
continue. Thus a group at the TUG Annual General Meeting in Cork, |
| 266 |
Ireland, specified a uniform encoding for 256-glyph fonts, that |
| 267 |
contains accented letters and non-\textsc{ascii} letters necessary to |
| 268 |
express most Western European languages (and some Eastern European ones) |
| 269 |
without recourse to the \verb"\accent" command. |
| 270 |
|
| 271 |
This ``Cork'' encoding has since been realised in a series of fonts |
| 272 |
designed with Metafont, in at least one font series that is available |
| 273 |
both in Adobe Type 1 format and in OpenType format, % viz., Latin Modern |
| 274 |
and in a number of virtual-font mappings of other font series. |
| 275 |
|
| 276 |
Since the time of the Cork meeting, much effort has been devoted to |
| 277 |
the design of encodings for text fonts to use with \TeX{}, and the |
| 278 |
Cork encoding influenced the design of many such encodings. |
| 279 |
|
| 280 |
Encodings for mathematical fonts have, in contrast, changed little |
| 281 |
since Knuth's contributions. A TUG Technical Working Group was |
| 282 |
established at the Cork meeting, whose aim was to define a set of |
| 283 |
256-glyph encodings to regularise and extend Knuth's originals, using |
| 284 |
ideas from several other fonts that had appeared since, and from the |
| 285 |
known needs of researchers in mathematics and the mathematical sciences. |
| 286 |
|
| 287 |
Independently, a first proposal (the so-called \emph{Aston proposal}) was worked |
| 288 |
out by Justin Ziegler together with Frank Mittelbach and other members of the |
| 289 |
\LaTeX\ Project team~\cite{ziegler}. A first implementation of |
| 290 |
this propsal was realized by Matthias Clasen und Ulrik |
| 291 |
Vieth~\cite{clasen,clasen-vieth}. |
| 292 |
|
| 293 |
However, the slow progress of these Mathematical encodings has been |
| 294 |
overtaken by the addition (in the last decade or so) of a large number |
| 295 |
of mathematical symbols to Unicode~\cite{beeton}; one can expect |
| 296 |
further changes so that new public mathematical font encodings will |
| 297 |
most likely be delayed still further. |
| 298 |
|
| 299 |
|
| 300 |
|
| 301 |
\subsection{Further information} |
| 302 |
|
| 303 |
For a general introduction to \LaTeX, including the new features of |
| 304 |
\LaTeXe, you should read \emph{\LaTeXbook}, |
| 305 |
Leslie Lamport, Addison Wesley, 2nd~ed, 1994. |
| 306 |
|
| 307 |
A more detailed description of the new features of \LaTeX, including an |
| 308 |
overview of more than 200 packages and nearly 1000 ready to run examples, is |
| 309 |
to be found in \emph{\LaTeXcomp{} second edition} by Frank Mittelbach and |
| 310 |
Michel Goossens~\cite{A-W:MG2004}. |
| 311 |
|
| 312 |
The \LaTeX{} project sponsored a report on Mathematical % spelt out in full |
| 313 |
font encodings, which |
| 314 |
is worth reading for its insight into the problems of defining the way |
| 315 |
in which math is used: see~\cite{ziegler,clasen,clasen-vieth}. |
| 316 |
|
| 317 |
The \LaTeX{} font selection scheme is based on \TeX, which is described |
| 318 |
by its developer in \emph{The \TeX book}, Donald E.~Knuth, Addison |
| 319 |
Wesley, 1986, revised in 1991 to include the features of \TeX~3. |
| 320 |
|
| 321 |
For more information about \TeX{} and \LaTeX, please contact your local |
| 322 |
\TeX{} Users Group, or the international \TeX{} Users Group |
| 323 |
(\url{http://www.tug.org}). |
| 324 |
|
| 325 |
|
| 326 |
|
| 327 |
\section{Existing font encodings} |
| 328 |
|
| 329 |
This section lists the encodings currently assigned; for each |
| 330 |
encoding, we list the registered (\LaTeX{}) name, the assigned purpose |
| 331 |
of the encoding, and the author. Further details may list the code |
| 332 |
positions used in the encoding, the \emph{variable slots} (see below), |
| 333 |
an example font (for which a listing will be provided later in the |
| 334 |
document if the relevant fonts are present), and a source for further |
| 335 |
reference. |
| 336 |
|
| 337 |
While the characteristic feature of an encoding is that each font |
| 338 |
encoded according to the encoding should have the same glyph set, |
| 339 |
there are some encodings (notably \Enc{OT1} and its descendants) in |
| 340 |
which a few glyph code slots differ in their contents in different |
| 341 |
fonts. |
| 342 |
|
| 343 |
\subsection{Naming conventions} |
| 344 |
|
| 345 |
Names for encoding schemes are strings of up to three letters (all |
| 346 |
upper case) plus digits. |
| 347 |
|
| 348 |
The \LaTeX\ Project reserves the use of encoding names starting with the |
| 349 |
following letters: |T| (standard 256-long text encodings), |TS| |
| 350 |
(symbols that are designed to extend a corresponding |T| encoding), |
| 351 |
|X| (text encodings that do not conform to the strict requirements for |
| 352 |
|T| encodings), |M| (standard 256-long mathematical encodings), |S| (other |
| 353 |
symbol encodings), |A| (other special applications), |OT| (standard |
| 354 |
128-long text encodings), and |OM| (standard 128-long mathematical encodings). |
| 355 |
|
| 356 |
Please do not use the above starting letters for non-portable |
| 357 |
encodings. If new standard encodings emerge then we shall add them in |
| 358 |
a later release of \LaTeX. |
| 359 |
|
| 360 |
Encoding schemes which are local to a site or a system should start |
| 361 |
with |L|, experimental encodings intended for wide distribution will |
| 362 |
start with |E|, whilst |U| is for Unknown or Unclassified encodings. |
| 363 |
|
| 364 |
\begin{quote} |
| 365 |
\itshape We recommend that new encoding names should not be |
| 366 |
introduced unless careful consideration and discussion in the user |
| 367 |
community has confirmed the need for the encoding. If encodings have to |
| 368 |
change from font to font, a number of problems arise, so it is best to |
| 369 |
develop encodings that can be used with a large number of fonts in parallel. |
| 370 |
This allows documents to be typeset using different fonts without problems. |
| 371 |
|
| 372 |
The \Enc{TS1} encoding is a good example of a \emph{bad} encoding (even |
| 373 |
though it was developed with the best intentions) as a huge number of fonts |
| 374 |
can only implement parts of it. Similarly, the fact that the few sets of |
| 375 |
available mathematical fonts (beside Computer Modern Math) nearly |
| 376 |
all implement slightly different encodings is a huge source of |
| 377 |
problems. Don't add to this if possible! |
| 378 |
\end{quote} |
| 379 |
|
| 380 |
|
| 381 |
\subsection{128$^+$ glyph encodings (text)} |
| 382 |
|
| 383 |
The `OT' series of font encodings start with Donald Knuth's original |
| 384 |
text encoding, that used for the text fonts in the earliest releases |
| 385 |
of \TeX{} itself. The `O' of the encoding designator may be taken as |
| 386 |
signifying `original', or just `old'. |
| 387 |
|
| 388 |
\begin{encodinginfo}{OT1} |
| 389 |
{\TeX{} text} |
| 390 |
{Donald Ervin Knuth} |
| 391 |
{0x00--0x7F} |
| 392 |
{0x0B--0x0F, 0x24, 0x3C, 0x3E, 0x5C, 0x7B--0x7D} |
| 393 |
% {0X--'177} |
| 394 |
% {'13--'17, '44, '74, '76, '134, '173--'175} |
| 395 |
{cmr10} |
| 396 |
{\cite[p.427]{A-W:DKn86}} |
| 397 |
|
| 398 |
Donald Knuth designed his font encoding (and hence his fonts) in a |
| 399 |
very different environment from that which now pervades the \TeX{} |
| 400 |
world: his (mainframe) computer had very little memory, there was |
| 401 |
little experience in (or demand for) for multilingual technical |
| 402 |
typesetting, and as a result it was appropriate to sacrifice |
| 403 |
uniformity for efficiency. |
| 404 |
|
| 405 |
Thus Knuth's original fonts differ slightly in some encoded slots: |
| 406 |
for example, the glyphs \texttt{\string<}, \texttt{\string>}, |
| 407 |
\verb=\=, \verb={=, and \verb=}= are only available in the |
| 408 |
typewriter fonts and the \textdollar{} and \textsterling{} signs |
| 409 |
share the same position (in different font shapes). |
| 410 |
|
| 411 |
This means that direct selection of these slots can produce |
| 412 |
unpredictable results, e.g., typing \texttt{\string<} or |
| 413 |
\verb=\symbol{'74}= in a document can yield `\textquestiondown'. |
| 414 |
\end{encodinginfo} |
| 415 |
|
| 416 |
|
| 417 |
\begin{encodinginfo}{OT2} |
| 418 |
{UW cyrillic encoding} |
| 419 |
{University of Washington} |
| 420 |
{0x00--0x7F} |
| 421 |
{---} |
| 422 |
{wnr10} |
| 423 |
{\cite{Beeton:TB6-3-124}} |
| 424 |
Support for this encoding is available in the Cyrillic bundle although for |
| 425 |
all practical purposes it is better to use one of the \Enc{T2} encodings. |
| 426 |
\end{encodinginfo} |
| 427 |
|
| 428 |
|
| 429 |
\begin{encodinginfo}{OT3} |
| 430 |
{UW IPA encoding} |
| 431 |
{University of Washington} |
| 432 |
{0x00--0x7f} |
| 433 |
{---} |
| 434 |
{wsuipa10} |
| 435 |
{\cite[p.149]{CorkGW:91}} |
| 436 |
The \Enc{OT3} encoding was never really used with \LaTeXe{} |
| 437 |
following the introduction of the TIPA system which offers much |
| 438 |
better support for IPA. In particular, no \File{ot3enc.def} |
| 439 |
file was ever produced. |
| 440 |
\end{encodinginfo} |
| 441 |
|
| 442 |
|
| 443 |
\begin{encodinginfo}{OT4} |
| 444 |
{Polish text encoding} |
| 445 |
{B.~Jackowski and M.~Ry\'cko} %% ? Marcin Woli\'nski |
| 446 |
{0x00--0x7F, 0x81, 0x82, 0x86, 0x8A, 0x8B, 0x91, 0x99, 0x9B, 0xA1, |
| 447 |
0xA2, 0xA6, 0xAA, 0xAB, 0xAE, 0xAF, 0xB1, 0xB9, 0xBB, 0xD3, 0xF3, |
| 448 |
0xFF} |
| 449 |
{0x0B--0x0F, 0x24, 0x3C, 0x3E, 0x5C, 0x7B--0x7D} |
| 450 |
{plr10} |
| 451 |
{---} |
| 452 |
|
| 453 |
While Knuth included the means of typesetting the `lost L' (\L) in |
| 454 |
his \Enc{OT1} encoding, he omitted the ogonek (\,\,\k{}), a diacritic |
| 455 |
mark that is also needed in Polish text; hence the appearance, well |
| 456 |
before the \Enc{T1} encoding, of fonts using this encoding. |
| 457 |
\end{encodinginfo} |
| 458 |
|
| 459 |
\begin{encodinginfo}{OT5} |
| 460 |
{Not currently allocated} |
| 461 |
{---} |
| 462 |
{---} |
| 463 |
{---} |
| 464 |
{} |
| 465 |
{---} |
| 466 |
|
| 467 |
\end{encodinginfo} |
| 468 |
|
| 469 |
|
| 470 |
|
| 471 |
\begin{encodinginfo}{OT6} |
| 472 |
{Armenian text encoding} |
| 473 |
{Serguei Dachian} |
| 474 |
{0x03--0x0F, 0x13--0x7F} |
| 475 |
{---} |
| 476 |
{artmr10} |
| 477 |
{---} |
| 478 |
|
| 479 |
This encoding was allocated to permit use of Dachian's |
| 480 |
Armenian fonts in a standard \LaTeX{} environment. |
| 481 |
|
| 482 |
Because of license issues the \texttt{artmr} fonts are not necessarily |
| 483 |
included in distributed \TeX{} installations (and for this reason the |
| 484 |
corresponding encoding table is not shown below). However, the fonts |
| 485 |
and the support macros can be found on the CTAN archives (look for |
| 486 |
\texttt{armtex}). |
| 487 |
|
| 488 |
\end{encodinginfo} |
| 489 |
|
| 490 |
|
| 491 |
|
| 492 |
\subsection{256 glyph encodings (text)} |
| 493 |
|
| 494 |
\begin{encodinginfo}{T1} |
| 495 |
{Cork encoding} |
| 496 |
{Euro \TeX{} conference at Cork} |
| 497 |
{0x00--0xFF} |
| 498 |
{---} |
| 499 |
{ecrm1000} |
| 500 |
{\cite[p.514]{tub:MFe90}, \cite[p.99]{Knappen:TB17-2-96}} |
| 501 |
|
| 502 |
The Cork encoding was developed so that advantage could be taken of |
| 503 |
the (then) new facilities of \TeX{}\,3, allowing hyphenation of |
| 504 |
most Western European (and some Eastern European) languages in an |
| 505 |
unmodified version of \TeX{}. |
| 506 |
|
| 507 |
The encoding was developed in the absence of any extant effort at |
| 508 |
font design, but instances written in Metafont (the `EC' fonts), and |
| 509 |
more recently Adobe Type 1 instances of the same fonts have become |
| 510 |
available. |
| 511 |
|
| 512 |
Substantial (but incomplete) instances have also been developed, |
| 513 |
which use virtual fonts. These latter instances map either Knuth's |
| 514 |
original (OT1-encoded) fonts, or commercial fonts that contain the |
| 515 |
Adobe `standard' set of 224 glyphs. |
| 516 |
\end{encodinginfo} |
| 517 |
|
| 518 |
\begin{encodinginfo} |
| 519 |
{T2A, T2B, T2C} |
| 520 |
{Cyrillic encodings} |
| 521 |
{The CyrTUG font team} |
| 522 |
{0x00--0xFF} |
| 523 |
{--- (within each encoding)} |
| 524 |
{larm1000} |
| 525 |
{\cite{Berdnikov:eurotex-98}} |
| 526 |
|
| 527 |
There are too many glyphs in the full Cyrillic complement of |
| 528 |
languages for all of them to be covered by a single |
| 529 |
\LaTeX{}-compliant encoding (the lower half of each |
| 530 |
\Enc{T2}~encoding is identical to that of \Enc{T1}, in order that |
| 531 |
each should be a conforming \LaTeX{} encoding~--- see |
| 532 |
section~\ref{sec:restrictions}). The approach taken is |
| 533 |
therefore to develop a single encoding, \Enc{X2} (see \ref{sec:extendedenc}) |
| 534 |
which contains all the glyphs needed for the full set of |
| 535 |
languages, and then to derive the three \LaTeX{}-complaint |
| 536 |
\Enc{T2}-family encodings using the \Enc{X2} set together with that of |
| 537 |
\Enc{T1}. |
| 538 |
|
| 539 |
\end{encodinginfo} |
| 540 |
|
| 541 |
|
| 542 |
|
| 543 |
\begin{encodinginfo}{T3} |
| 544 |
{IPA encoding} |
| 545 |
{FUKUI Rei, University of Tokyo} |
| 546 |
{0x00--0xFF} |
| 547 |
{---} |
| 548 |
{tipa10} |
| 549 |
{\cite[p.102]{Rei:TB17-2-102}} |
| 550 |
|
| 551 |
|
| 552 |
The \Enc{T3} encoding (and associated macros) provides the glyphs required |
| 553 |
in phonetic description according to current International Phonetic |
| 554 |
Association recommendations \cite{ipa}. |
| 555 |
|
| 556 |
The \Enc{T3} encoding does \emph{not fulfil} the requirements for \Enc{T} |
| 557 |
encodings---the name is a historical accident. The correct name would be |
| 558 |
\Enc{X3}, but due to the fact that this font family has been used under its |
| 559 |
current encoding name for a long time, the name will not change for |
| 560 |
compatibility reasons. |
| 561 |
|
| 562 |
\end{encodinginfo} |
| 563 |
|
| 564 |
|
| 565 |
|
| 566 |
\begin{encodinginfo}{T4} |
| 567 |
{African Latin (fc)} % public name |
| 568 |
{J\"org Knappen} % author name |
| 569 |
{0x00--0xFF} % range(s) of slots used for glyphs |
| 570 |
{0x24} % range(s) of slots with variable glyphs if any |
| 571 |
{fcr10} % name of an example font |
| 572 |
{\cite{tub:JKn93}} |
| 573 |
|
| 574 |
The African Latin fonts contain in their lower half (0--127) the same |
| 575 |
characters as the European Latin (T1-encoded) Fonts, while in their |
| 576 |
upper half (128--255) they |
| 577 |
contain letters and symbols for African languages that use extended |
| 578 |
Latin alphabets. |
| 579 |
Due to lack of space, J\"org had to play the unfortunate trick of |
| 580 |
assigning \verb=\textdollar= and \verb=\textsterling= |
| 581 |
the same position; users should take these characters |
| 582 |
from the text companion font, if they are needed. Instead of defining |
| 583 |
a lot of new control sequences for the single letters, there are three |
| 584 |
accent-like control sequences with general purpose: |
| 585 |
\verb=\m= (Modified-1), |
| 586 |
\verb=\M= (Modified-2) and |
| 587 |
\verb=\B= (Barred). |
| 588 |
Most standard \LaTeX{} encoding-dependent commands |
| 589 |
work. However, the Icelandic special letters are not available and `best |
| 590 |
replacements' for \verb=\Th=, \verb=\th=, and \verb=\dh= |
| 591 |
are used (barred T and d resp.). |
| 592 |
\end{encodinginfo} |
| 593 |
|
| 594 |
|
| 595 |
\begin{encodinginfo}{T5} |
| 596 |
{Vietnamese encoding} |
| 597 |
{Werner Lemberg and |
| 598 |
Vladimir Volovich} |
| 599 |
{0x00--0xFF} |
| 600 |
{---} |
| 601 |
{vnr10} |
| 602 |
{\cite{vnr}} |
| 603 |
|
| 604 |
The \Enc{T5} encoding was developed for Vietnamese. Again, this encoding |
| 605 |
\emph{does not} conform to the requirements for a \Enc{T}-encoding |
| 606 |
because its large number of accented letters prevent the \verb=\lccode= and |
| 607 |
\verb=\uccode= mapping requirements for \Enc{T} encodings from being |
| 608 |
fulfilled. However, since the Vietnamese language does not |
| 609 |
use word division in typesetting so that this requirement is |
| 610 |
actually not important for this particular language. |
| 611 |
Since every glyph used in Vietnamese text is internally |
| 612 |
represented as \textsc{licr} macros, the commands \verb=\MakeUppercase= and |
| 613 |
\verb=\MakeLowercase= still work as expected (as they change the case of the |
| 614 |
\textsc{ascii} characters in \textsc{licr} definitions). |
| 615 |
|
| 616 |
\end{encodinginfo} |
| 617 |
|
| 618 |
\begin{encodinginfo} |
| 619 |
{T6} |
| 620 |
{Armenian} |
| 621 |
{---} |
| 622 |
{---} |
| 623 |
{---} |
| 624 |
{} |
| 625 |
{---} |
| 626 |
|
| 627 |
This encoding is reserved to permit future expansion of Armenian |
| 628 |
\TeX{} to use 256-character (hyphenatable) fonts. |
| 629 |
\end{encodinginfo} |
| 630 |
|
| 631 |
\begin{encodinginfo}{T7} |
| 632 |
{Greek encoding} |
| 633 |
{---} |
| 634 |
{---} |
| 635 |
{---} |
| 636 |
{} |
| 637 |
{---} |
| 638 |
|
| 639 |
The name is already reserved for a 256 glyph greek encoding. The encoding |
| 640 |
itself hasn't been defined so far. |
| 641 |
|
| 642 |
\end{encodinginfo} |
| 643 |
|
| 644 |
|
| 645 |
|
| 646 |
\subsection{256$^-$ glyph encodings (text symbols)} |
| 647 |
|
| 648 |
\begin{encodinginfo}{TS1} |
| 649 |
{Text Companion encoding (Cork)} |
| 650 |
{J\"org Knappen} |
| 651 |
{0x00--0x0D, 0x12, 0x15, 0x16, 0x18--0x1D, 0x20, 0x24, 0x27, 0x2A, |
| 652 |
0x2C--0x3A, 0x3C--0x3E, 0x4D, 0x4F, 0x57, 0x5B, 0x5D--0x60, |
| 653 |
0x62--0x64, 0x6C--0x6E, 0x7E--0xBF, 0xD6, 0xF6} |
| 654 |
{---} |
| 655 |
{tcrm1000} |
| 656 |
{\cite{Knappen:TB17-2-96}} |
| 657 |
|
| 658 |
The text symbol encoding offers access to symbolic glyphs that are |
| 659 |
commonly used in text (for a variety of reasons), and whose style |
| 660 |
should vary with the text that surrounds them. |
| 661 |
|
| 662 |
Unfortunately, the \Enc{TS1} encoding was developed without |
| 663 |
reference to the glyphs available in existing commercial fonts. |
| 664 |
As a result, only font families |
| 665 |
explicitly developed for \TeX{} (i.e., typically originating with |
| 666 |
\MF{}) actually contain all glyphs required by the \Enc{TS1} |
| 667 |
encoding. Most other font families (whether free or commercial) |
| 668 |
often only provide half of the set% |
| 669 |
%% |
| 670 |
%% don't show the comment if the tables are not generated |
| 671 |
%% |
| 672 |
\expandafter\ifx\csname r@fonttable:tcrm1000\endcsname\relax |
| 673 |
\else |
| 674 |
\expandafter\ifx\csname r@fonttable:ptmr8c\endcsname\relax |
| 675 |
\else |
| 676 |
\space (compare the two tables for \Enc{TS1} on |
| 677 |
pages~\pageref{fonttable:tcrm1000} |
| 678 |
and~\pageref{fonttable:ptmr8c})% |
| 679 |
\fi |
| 680 |
\fi. |
| 681 |
To improve this situation somewhat, NFSS provides a way to define encoding |
| 682 |
subsets on a per family basis in the \Pkg{textcomp} package (which |
| 683 |
package offers support for the \Enc{TS1} encoding). |
| 684 |
\end{encodinginfo} |
| 685 |
|
| 686 |
|
| 687 |
\begin{encodinginfo}{TS3} |
| 688 |
{IPA symbol encoding} |
| 689 |
{FUKUI Rei, University of Tokyo} |
| 690 |
{0x00--0x0A, 0x20--0x49, 0x50--0x56, 0x70--0x7B} |
| 691 |
{---} |
| 692 |
{tipx10} |
| 693 |
{\cite{Rei:TB17-2-102}} |
| 694 |
|
| 695 |
The \Enc{TS3} encoding (together with the \Enc{T3} encoding) provides the |
| 696 |
glyphs for typesetting phonetic transcriptions following the |
| 697 |
guidelines of the International Phonetic Association \cite{ipa}. Support |
| 698 |
is offered through the \Pkg{tipa} package. |
| 699 |
\end{encodinginfo} |
| 700 |
|
| 701 |
|
| 702 |
|
| 703 |
|
| 704 |
\subsection{256 glyph encodings (text extended)} |
| 705 |
\label{sec:extendedenc} |
| 706 |
|
| 707 |
\begin{encodinginfo} |
| 708 |
{X2} |
| 709 |
{Cyrillic glyph container} |
| 710 |
{The CyrTUG font team} |
| 711 |
{0x00--0xFF} |
| 712 |
{---} |
| 713 |
{rxrm1000} |
| 714 |
{\cite{Berdnikov:eurotex-98}} |
| 715 |
|
| 716 |
This encoding specifies the glyph container for Cyrillic characters, |
| 717 |
which is used in specifying the \Enc{T2A}, \Enc{T2B} and \Enc{T2C} encodings. |
| 718 |
\end{encodinginfo} |
| 719 |
|
| 720 |
|
| 721 |
|
| 722 |
|
| 723 |
\subsection{128$^+$ glyph encodings (mathematics)} |
| 724 |
|
| 725 |
|
| 726 |
\begin{encodinginfo}{OML} |
| 727 |
{\TeX{} math italic} |
| 728 |
{Donald Ervin Knuth} |
| 729 |
{0x00--0x7F} |
| 730 |
{---} |
| 731 |
{cmmi10} |
| 732 |
{\cite[p.430]{A-W:DKn86}} |
| 733 |
|
| 734 |
The \Enc{OML} encoding contains italic Latin and Greek letters for |
| 735 |
use in mathematical formulas (typically used for variables) together |
| 736 |
with some symbols. |
| 737 |
|
| 738 |
\end{encodinginfo} |
| 739 |
|
| 740 |
\begin{encodinginfo}{OMS} |
| 741 |
{\TeX{} math symbol} |
| 742 |
{Donald Ervin Knuth} |
| 743 |
{0x00--0x7F} |
| 744 |
{---} |
| 745 |
{cmsy10} |
| 746 |
{\cite[p.431]{A-W:DKn86}} |
| 747 |
|
| 748 |
The \Enc{OMS} encoding contains basic mathematical symbols, |
| 749 |
together with an uppercase ``calligraphic'' Latin alphabet. |
| 750 |
\end{encodinginfo} |
| 751 |
|
| 752 |
|
| 753 |
\begin{encodinginfo}{OMX} |
| 754 |
{\TeX{} math extension} |
| 755 |
{Donald Ervin Knuth} |
| 756 |
{0x00--0x7F} |
| 757 |
{---} |
| 758 |
{cmex10} |
| 759 |
{\cite[p.432]{A-W:DKn86}} |
| 760 |
|
| 761 |
\Enc{OMS} encodes mathematical symbols with variable sizes, such as |
| 762 |
the $\sum$ sign, which changes its size if used in displayed |
| 763 |
formulas, and the construction parts for |
| 764 |
brackets, braces and radicals, etc., which can stretch to accommodate |
| 765 |
the thing they're enclosing. |
| 766 |
|
| 767 |
\end{encodinginfo} |
| 768 |
|
| 769 |
|
| 770 |
|
| 771 |
|
| 772 |
\subsection{256 glyph encodings (mathematics)} |
| 773 |
|
| 774 |
So far there are no 256 glyph mathematical encodings. A proposal is |
| 775 |
given in \cite{ziegler}. |
| 776 |
|
| 777 |
|
| 778 |
\subsection{Other encodings} |
| 779 |
|
| 780 |
\begin{encodinginfo} |
| 781 |
{C..} |
| 782 |
{CJK encodings} |
| 783 |
{Werner Lemberg} |
| 784 |
{0x00--0xFF} |
| 785 |
{---} |
| 786 |
{} % no font, of course |
| 787 |
{\cite{CJK}} |
| 788 |
|
| 789 |
The \Pkg{CJK} package defines a number of encodings which access Chinese, |
| 790 |
Japanese and Korean fonts. |
| 791 |
|
| 792 |
\end{encodinginfo} |
| 793 |
|
| 794 |
\begin{encodinginfo} |
| 795 |
{E..} |
| 796 |
{Experimental encodings} |
| 797 |
{---} |
| 798 |
{0x00--0xFF} |
| 799 |
{all} |
| 800 |
{} |
| 801 |
{\cite[p.416]{A-W:MG2004}} |
| 802 |
|
| 803 |
As the name indicates, encodings starting with the letter \Enc{E} are |
| 804 |
intended for experimental encodings, that are still likely to change. |
| 805 |
\end{encodinginfo} |
| 806 |
|
| 807 |
\begin{encodinginfo}{L..} |
| 808 |
{Local encoding (site dependent)} |
| 809 |
{---} |
| 810 |
{0x00--0xFF} |
| 811 |
{all} |
| 812 |
{} |
| 813 |
{\cite[p.416]{A-W:MG2004}} |
| 814 |
|
| 815 |
`Local' encodings provide the means to develop representation |
| 816 |
techniques that are suited to a particular \TeX{} environment. While |
| 817 |
the developer has freedom to specify their encoding as he or she |
| 818 |
pleases, there is a strong incentive to obey the \LaTeX{} rules for |
| 819 |
encodings, since it will otherwise be difficult to compose text using |
| 820 |
the encoding. |
| 821 |
|
| 822 |
At least it was the intention that \Enc{L..} encodings are local and |
| 823 |
site dependent. However, a number of such encodings became generally |
| 824 |
used without ever getting a different name allocated. |
| 825 |
|
| 826 |
\end{encodinginfo} |
| 827 |
|
| 828 |
|
| 829 |
|
| 830 |
\begin{encodinginfo}{LY1} |
| 831 |
{Y\&Y 256 glyph encoding} |
| 832 |
{Berthold Horn} |
| 833 |
{0x00--0x08, 0x0C, 0x10, 0x12--0xFF} |
| 834 |
{\emph{believed none}} |
| 835 |
{ptmr8y} |
| 836 |
{\cite[p.416]{A-W:MG2004}} |
| 837 |
|
| 838 |
This is an alternative to the \Enc{T1} encoding developed by Y\&Y and |
| 839 |
used in their commercial \TeX{} implementation. |
| 840 |
|
| 841 |
\end{encodinginfo} |
| 842 |
|
| 843 |
|
| 844 |
\begin{encodinginfo}{LV1} |
| 845 |
{MicroPress encoding} |
| 846 |
{Michael Vulis} |
| 847 |
{\emph{unknown}} |
| 848 |
{\emph{unknown}} |
| 849 |
{} |
| 850 |
{\cite[p.416]{A-W:MG2004}} |
| 851 |
|
| 852 |
This is an encoding developed by MicroPress and used for some of their |
| 853 |
fonts. |
| 854 |
|
| 855 |
\end{encodinginfo} |
| 856 |
|
| 857 |
|
| 858 |
\begin{encodinginfo}{LGR} |
| 859 |
{Greek 256 glyph encoding} |
| 860 |
{\emph{unknown}} |
| 861 |
{0x00--0xFF} |
| 862 |
{\emph{believed none}} |
| 863 |
{grmn1000} |
| 864 |
{\cite[p.575]{A-W:MG2004}} |
| 865 |
|
| 866 |
Currently the main encoding in use for the Greek language. |
| 867 |
|
| 868 |
This encoding doesn't conform to the restrictions for |
| 869 |
\Enc{T}-encodings described in section~\ref{sec:restrictions} on |
| 870 |
page~\pageref{sec:restrictions} as it doesn't have \textsc{ascii} |
| 871 |
glyphs at all. |
| 872 |
|
| 873 |
\end{encodinginfo} |
| 874 |
|
| 875 |
|
| 876 |
\begin{encodinginfo} |
| 877 |
{PD1} |
| 878 |
{PDF DocEncoding} |
| 879 |
{Adobe} |
| 880 |
{0x08--0x0A, 0x0C, 0x0D, 0x18--0x7E, 0x80--0x9E, 0xA0--0xAE, 0xB0--0xFF} |
| 881 |
{---} |
| 882 |
{} |
| 883 |
{\cite{Adobe:PDF-1.6}, \cite{hyperref}} |
| 884 |
|
| 885 |
The \Enc{PD1} encoding is a virtual encoding with 256 glyphs needed to |
| 886 |
produce bookmarks and similar text in PDF document generated with pdf\LaTeX. |
| 887 |
The encoding is ``virtual'' because by design there are no \TeX{} |
| 888 |
fonts that cover \Enc{PD1}. Details can be found in appendix D.1 |
| 889 |
of~\cite{Adobe:PDF-1.6}. |
| 890 |
\end{encodinginfo} |
| 891 |
|
| 892 |
\begin{encodinginfo} |
| 893 |
{PU} |
| 894 |
{PDF Unicode Encoding} |
| 895 |
{Adobe} |
| 896 |
{---} |
| 897 |
{---} |
| 898 |
{} |
| 899 |
{\cite{Adobe:PDF-1.6}, \cite{hyperref}} |
| 900 |
|
| 901 |
Another virtual encoding (with more than 600 characters) for |
| 902 |
Unicode-encoded bookmarks in PDF documents. |
| 903 |
\end{encodinginfo} |
| 904 |
|
| 905 |
\begin{encodinginfo}{U} |
| 906 |
{Unknown encoding} |
| 907 |
{---} |
| 908 |
{potentially 0x00-0xFF} |
| 909 |
{all} |
| 910 |
{wasy10} |
| 911 |
{\cite[p.416]{A-W:MG2004}} |
| 912 |
|
| 913 |
This encoding should be used for fonts that resist classification, |
| 914 |
e.g., when it is clear that there will never be more than one font |
| 915 |
using the same encoding. |
| 916 |
|
| 917 |
\end{encodinginfo} |
| 918 |
|
| 919 |
|
| 920 |
|
| 921 |
\section{Restrictions} |
| 922 |
\label{sec:restrictions} |
| 923 |
|
| 924 |
|
| 925 |
\subsection{Required glyphs for general text encodings} |
| 926 |
|
| 927 |
Encodings that are supposed to be used with \LaTeX{} for `general |
| 928 |
purpose text fonts' need to have certain fixed glyphs in certain |
| 929 |
encoding slots. A `general purpose text font' is one intended for |
| 930 |
arbitrary natural language text and not just within special |
| 931 |
environments (such as the phonetic alphabet) or just for typesetting |
| 932 |
individual symbols (e.g., the text companion font with encoding |
| 933 |
\Enc{TS1}). |
| 934 |
|
| 935 |
This is the case for the following glyphs that have to be in their |
| 936 |
\textsc{ascii} positions for general purpose text encodings: |
| 937 |
\begin{center} |
| 938 |
\begin{tabular}[t]{cc} |
| 939 |
Glyph & Position \\ \hline |
| 940 |
! & \number`\! \\ |
| 941 |
' & \number`\' \\ |
| 942 |
( & \number`\( \\ |
| 943 |
) & \number`\) \\ |
| 944 |
\relax* & \number`\* \\ |
| 945 |
+ & \number`\+ \\ |
| 946 |
, & \number`\, \\ |
| 947 |
- & \number`\- \\ |
| 948 |
. & \number`\. \\ |
| 949 |
/ & \number`\/ \\ |
| 950 |
0 \ldots\ 9 & \number`\0\ to \number`\9 \\ |
| 951 |
\end{tabular} |
| 952 |
\quad |
| 953 |
\begin{tabular}[t]{cc} |
| 954 |
Glyph & Position \\ \hline |
| 955 |
: & \number`\: \\ |
| 956 |
; & \number`\; \\ |
| 957 |
= & \number`\= \\ |
| 958 |
? & \number`\? \\ |
| 959 |
@ & \number`\@ \\ |
| 960 |
A \ldots\ Z & \number`\A\ to \number`\Z \\ |
| 961 |
\relax[ & \number`\[ \\ |
| 962 |
] & \number`\] \\ |
| 963 |
` & \number`\` \\ |
| 964 |
a \ldots\ z & \number`\a\ to \number`\z \\ |
| 965 |
\end{tabular} |
| 966 |
\quad |
| 967 |
\begin{tabular}[t]{cc} |
| 968 |
Glyph\footnotemark & Position \\ \hline |
| 969 |
< & \number`\< \\ |
| 970 |
> & \number`\> \\ |
| 971 |
\string| & \number`\| \\ |
| 972 |
\end{tabular}\footnotetext{The requirement for these three glyphs is |
| 973 |
violated in the Latin alphabet \Enc{OT} encodings.} |
| 974 |
\end{center} |
| 975 |
In addition the following glyphs have to be present |
| 976 |
somewhere\footnote{The position in this case is not important as they |
| 977 |
are generated from ligature programs.} in the encoding together with |
| 978 |
corresponding ligature programs to generate them: |
| 979 |
\begin{center} |
| 980 |
\begin{tabular}[t]{cc} |
| 981 |
Glyph & Ligature program \\ \hline |
| 982 |
`` & \texttt{`\/`} \\ |
| 983 |
'' & \texttt{'\/'} \\ |
| 984 |
-- & \texttt{-\/-} \\ |
| 985 |
--- & \texttt{-\/-\/-} \\ |
| 986 |
\end{tabular} |
| 987 |
\end{center} |
| 988 |
|
| 989 |
This is $33 + 2 * 26 = 85$ positions ``required'', which leaves 171 |
| 990 |
positions free. |
| 991 |
|
| 992 |
If there are free slots available then adding all or some of the |
| 993 |
diacritics would be the best way to fill them. |
| 994 |
|
| 995 |
If there are insufficient slots for the characters needed, a possible |
| 996 |
technique is to create a subsidiary encoding, and to move non-letter |
| 997 |
characters to it. Since only ``letters'' take part in the hyphenation |
| 998 |
algorithm, this technique doesn't affect the appearance of the typeset |
| 999 |
result. |
| 1000 |
|
| 1001 |
\subsection{The constraints on upper/lower case tables} |
| 1002 |
|
| 1003 |
Due to some technical restrictions of \TeX{} related to hyphenation it |
| 1004 |
is not possible in \LaTeX{} to use more than one \verb=\lccode= or |
| 1005 |
\verb=\uccode= table. Therefore all encodings need to share these two |
| 1006 |
tables which are defined to be those of the \Enc{T1} encoding. |
| 1007 |
|
| 1008 |
The \Enc{T1} encoding has some nasty peculiarities which make certain slot |
| 1009 |
positions more or less unusable for other encodings if this |
| 1010 |
restriction is to be obeyed. This is unfortunate but since \Enc{T1} is well |
| 1011 |
established and the basis for a large number of languages it seemed |
| 1012 |
better to live with this situation instead of trying to replace \Enc{T1} with a |
| 1013 |
slightly better standard (with the result that for a long time |
| 1014 |
different \LaTeX{} installations would not be able to communicate with |
| 1015 |
each other because of incompatible font sets). |
| 1016 |
|
| 1017 |
The positions that are problematic are as follows. |
| 1018 |
\begin{center} |
| 1019 |
\begin{tabular}{lp{.8\linewidth}} |
| 1020 |
25 (\char 25) & uppercase maps strangely (same as for 105, \char 105)\\ |
| 1021 |
26 (\char 26) & uppercase maps strangely (same as for 106, \char 106)\\ |
| 1022 |
27 (\char 27) & lowercase maps to itself which makes this slot subject |
| 1023 |
to hyphenation (used to support \Enc{OT1} encoding) \\ |
| 1024 |
157 (\char 157) & lowercase maps strangely (same as for 73, \char 73) \\ |
| 1025 |
158 (\char 158) & uppercase maps strangely (same as for 240, \char 240) \\ |
| 1026 |
\end{tabular} |
| 1027 |
\end{center} |
| 1028 |
One way to use such slots is to fill them with ligature glyphs as |
| 1029 |
\TeX{} will not consult these tables for glyphs constructed through |
| 1030 |
ligatures programs but instead uses the entries for the individual |
| 1031 |
glyphs used to produce the ligature. |
| 1032 |
|
| 1033 |
A complete listing of the uppercase/lowercase mapping tables is to be |
| 1034 |
found in section~\ref{sec:uclc-tab} (page \pageref{sec:uclc-tab}). |
| 1035 |
|
| 1036 |
\newcount\temp \newcount\tempL \newcount\tempU |
| 1037 |
|
| 1038 |
\def\nextstep{\global\tempL=\lccode\temp |
| 1039 |
\global\tempU=\uccode\temp |
| 1040 |
\lctablenumbersize\the\temp & |
| 1041 |
\the\tempL& |
| 1042 |
\the\tempU&\printlowerupper{\the\temp}{\the\tempL}{\the\tempU}\\ |
| 1043 |
\global\advance\temp by 1 |
| 1044 |
\stepprint} |
| 1045 |
|
| 1046 |
\def\printlowerupper#1#2#3{\char#1\relax |
| 1047 |
(\ifnum#2=0\relax--\else\char#2\fi |
| 1048 |
/\ifnum#3=0\relax--\else\char#3\fi)} |
| 1049 |
|
| 1050 |
\def\stepprint{\relax\ifnum\temp<\endval |
| 1051 |
\let\next=\nextstep |
| 1052 |
\else |
| 1053 |
\let\next=\relax |
| 1054 |
\fi |
| 1055 |
\next} |
| 1056 |
|
| 1057 |
\def\dolctable#1#2{{\temp=#1\relax |
| 1058 |
\def\endval{#2}% |
| 1059 |
\setlength\tabcolsep{1.5pt}% |
| 1060 |
\begin{tabular}[t]{@{}cccc@{}} |
| 1061 |
pos&lc&uc&glyphs\\\hline |
| 1062 |
\stepprint |
| 1063 |
\end{tabular}}} |
| 1064 |
|
| 1065 |
\iffalse |
| 1066 |
\begin{center} |
| 1067 |
\tiny\let\lctablenumbersize\tiny |
| 1068 |
\mbox{\dolctable{0}{52}\vrule |
| 1069 |
\dolctable{52}{104}\vrule |
| 1070 |
\dolctable{104}{156}\vrule |
| 1071 |
\dolctable{156}{208}\vrule |
| 1072 |
\dolctable{208}{256}} |
| 1073 |
\end{center} |
| 1074 |
\fi |
| 1075 |
|
| 1076 |
\iffalse |
| 1077 |
\begin{center}\tiny |
| 1078 |
\mbox{\dolctable{0}{65}\vrule |
| 1079 |
\dolctable{65}{128}\vrule |
| 1080 |
\dolctable{128}{193}\vrule |
| 1081 |
\dolctable{193}{256}} |
| 1082 |
\end{center} |
| 1083 |
\fi |
| 1084 |
|
| 1085 |
|
| 1086 |
|
| 1087 |
\section{Encoding specific commands} |
| 1088 |
|
| 1089 |
An encoding specific command is one that generates a glyph (or |
| 1090 |
glyphs), to produce a graphic effect that may be implemented |
| 1091 |
differently in different encodings. The encoding specific command |
| 1092 |
automatically changes its implementation when the encoding changes in |
| 1093 |
the course of the document. Encoding specific commands figure in |
| 1094 |
\LaTeX's internal character representation (\textsc{licr}) and are also |
| 1095 |
discussed in \cite[sec.~7.11.2, p.~442]{A-W:MG2004}. |
| 1096 |
|
| 1097 |
The following table only covers the encoding specific commands from |
| 1098 |
the \Enc{OT1} and \Enc{T1} encodings. Other encodings may specify |
| 1099 |
additional encoding specific commands. In the table, the first 15 |
| 1100 |
commands are `accent-like' and need as an argument the character to be |
| 1101 |
accented. For example, |\v{c}| is the \textsc{licr} for `\v{c}'. |
| 1102 |
|
| 1103 |
\begin{tabbing} |
| 1104 |
\ttverb\textvisiblespace\quad\=bbbbbbbbbbbbbb\=b'b'\=ccccccccccc\kill |
| 1105 |
\ttverb\`{} \>OT1,T1\> \a`{}\> (grave) \\ |
| 1106 |
\ttverb\'{} \>OT1,T1\> \a'{}\> (acute) \\ |
| 1107 |
\ttverb\^{} \>OT1,T1\> \^{}\> (circumflex) \\ |
| 1108 |
\ttverb\~{} \>OT1,T1\> \~{}\> (tilde) \\ |
| 1109 |
\ttverb\"{} \>OT1,T1\> \"{}\> (umlaut) \\ |
| 1110 |
\ttverb\H{} \>OT1,T1\> \H{}\> (Hungarian umlaut) \\ |
| 1111 |
\ttverb\r{} \>OT1,T1\> \r{}\> (ring) \\ |
| 1112 |
\ttverb\v{} \>OT1,T1\> \v{}\> (ha\v{c}ek) \\ |
| 1113 |
\ttverb\u{} \>OT1,T1\> \u{}\> (breve) \\ |
| 1114 |
\ttverb\t{} \>OT1,T1\> \t{}\> (tie) \\ |
| 1115 |
\ttverb\={} \>OT1,T1\> \a={}\> (macron) \\ |
| 1116 |
\ttverb\.{} \>OT1,T1\> \.{}\> (dot) \\ |
| 1117 |
\ttverb\b{} \>OT1,T1\> \b{}\> (underbar) \\ |
| 1118 |
\ttverb\c{} \>OT1,T1\> \c{}\> (cedilla) \\ |
| 1119 |
\ttverb\d{} \>OT1,T1\> \d{}\> (dot under) \\ |
| 1120 |
\ttverb\k{} \>T1 \> \k{}\> (ogonek) \\ |
| 1121 |
% \ttverb\AA \>OT1,T1\> \AA \> \\ % no longer |
| 1122 |
\ttverb\AE \>OT1,T1\> \AE \> \\ |
| 1123 |
\ttverb\DH \>T1 \> \DH \> \\ |
| 1124 |
\ttverb\DJ \>T1 \> \DJ \> \\ |
| 1125 |
\ttverb\L \>OT1,T1\> \L \> \\ |
| 1126 |
\ttverb\NG \>T1 \> \NG \> \\ |
| 1127 |
\ttverb\OE \>OT1,T1\> \OE \> \\ |
| 1128 |
\ttverb\O \>OT1,T1\> \O \> \\ |
| 1129 |
\ttverb\SS \>OT1,T1\> \SS \> \\ |
| 1130 |
\ttverb\TH \>T1 \> \TH \> \\ |
| 1131 |
% \ttverb\aa \>OT1,T1\> \aa \> \\ no-longer |
| 1132 |
\ttverb\ae \>OT1,T1\> \ae \> \\ |
| 1133 |
\ttverb\dh \>T1 \> \dh \> \\ |
| 1134 |
\ttverb\dj \>T1 \> \dj \> \\ |
| 1135 |
\ttverb\guillemotleft \>T1 \> \guillemotleft \> (guillemet) \\ |
| 1136 |
\ttverb\guillemotright \>T1 \> \guillemotright \> (guillemet) \\ |
| 1137 |
\ttverb\guilsinglleft \>T1 \> \guilsinglleft \> (guillemet) \\ |
| 1138 |
\ttverb\guilsinglright \>T1 \> \guilsinglright \> (guillemet) \\ |
| 1139 |
\ttverb\i \>OT1,T1\> \i \> \\ |
| 1140 |
\ttverb\j \>OT1,T1\> \j \> \\ |
| 1141 |
\ttverb\l \>OT1,T1\> \l \> \\ |
| 1142 |
\ttverb\ng \>T1 \> \ng \> \\ |
| 1143 |
\ttverb\oe \>OT1,T1\> \oe \> \\ |
| 1144 |
\ttverb\o \>OT1,T1\> \o \> \\ |
| 1145 |
\ttverb\quotedblbase \>T1 \> \quotedblbase \> \\ |
| 1146 |
\ttverb\quotesinglbase \>T1 \> \quotesinglbase \> \\ |
| 1147 |
\ttverb\ss \>OT1,T1\> \ss \> \\ |
| 1148 |
\ttverb\textasciicircum \>OT1,T1\> \textasciicircum \> \\ |
| 1149 |
\ttverb\textasciitilde \>OT1,T1\> \textasciitilde \> \\ |
| 1150 |
\ttverb\textbackslash \>OT1,T1\> \textbackslash \> \\ |
| 1151 |
\ttverb\textbar \>OT1,T1\> \textbar \> \\ |
| 1152 |
\ttverb\textbraceleft \>OT1,T1\> \textbraceleft \> \\ |
| 1153 |
\ttverb\textbraceright \>OT1,T1\> \textbraceright \> \\ |
| 1154 |
\ttverb\textcompwordmark \>OT1,T1\> \textcompwordmark\> (invisible) \\ |
| 1155 |
\ttverb\textdollar \>OT1,T1\> \textdollar \> \\ |
| 1156 |
\ttverb\textemdash \>OT1,T1\> \textemdash \> \\ |
| 1157 |
\ttverb\textendash \>OT1,T1\> \textendash \> \\ |
| 1158 |
\ttverb\textexclamdown \>OT1,T1\> \textexclamdown \> \\ |
| 1159 |
\ttverb\textgreater \>OT1,T1\> \textgreater \> \\ |
| 1160 |
\ttverb\textless \>OT1,T1\> \textless \> \\ |
| 1161 |
\ttverb\textquestiondown \>OT1,T1\> \textquestiondown\> \\ |
| 1162 |
\ttverb\textquotedbl \>T1 \> \textquotedbl \> \\ |
| 1163 |
\ttverb\textquotedblleft \>OT1,T1\> \textquotedblleft\> \\ |
| 1164 |
\ttverb\textquotedblright \>OT1,T1\> \textquotedblright\> \\ |
| 1165 |
\ttverb\textquoteleft \>OT1,T1\> \textquoteleft \> \\ |
| 1166 |
\ttverb\textquoteright \>OT1,T1\> \textquoteright \> \\ |
| 1167 |
\ttverb\textregistered \>OT1,T1\> \textregistered \> \\ |
| 1168 |
\ttverb\textsection \>OT1,T1\> \textsection \> \\ |
| 1169 |
\ttverb\textsterling \>OT1,T1\> \textsterling \> \\ |
| 1170 |
\ttverb\texttrademark \>OT1,T1\> \texttrademark \> \\ |
| 1171 |
\ttverb\textunderscore \>OT1,T1\> \textunderscore \> \\ |
| 1172 |
\ttverb\textvisiblespace \>OT1,T1\> \textvisiblespace\> \\ |
| 1173 |
\ttverb\th \>T1 \> \th \> |
| 1174 |
\end{tabbing} |
| 1175 |
|
| 1176 |
\section{Encodings for Unicode based \TeX\ systems} |
| 1177 |
\label{sec:unicode} |
| 1178 |
|
| 1179 |
The preceding text has assumed a classic TeX system that is |
| 1180 |
restricted to the use of fonts with at most 256 characters. In order |
| 1181 |
to accommodate all the characters needed for different languages and |
| 1182 |
mathematics it is necessary to have multiple encodings as described |
| 1183 |
above, and \LaTeX\ needs to be aware of the encoding used for each |
| 1184 |
font. |
| 1185 |
|
| 1186 |
Unicode aims to provide a single encoding that removes most of the |
| 1187 |
need to switch encodings, apart from very specialist use for non-standard characters. Rather than assign codes in the range 0--256 (hex |
| 1188 |
FF) Unicode codes are in the range 0--1,114,111 (hex 10FFFF), although |
| 1189 |
not all slots are available for distinct characters for technical |
| 1190 |
reasons. Unicode offers the possibility to use a single input encoding |
| 1191 |
(usually UTF-8) for all documents and to use essentially the same |
| 1192 |
Unicode encoding for all fonts, so removing the need to switch |
| 1193 |
encodings in different contexts. |
| 1194 |
|
| 1195 |
Omega was perhaps the first widely used \TeX\ extension that |
| 1196 |
supported Unicode. Currently the two actively supported systems that are |
| 1197 |
present in most modern \TeX\ distributions are Xe\TeX\ and Lua\TeX. |
| 1198 |
|
| 1199 |
When used with these extended \TeX\ engines, \LaTeX's font system can |
| 1200 |
refer to Unicode fonts (typically OpenType fonts installed system-wide |
| 1201 |
on your operating system rather than fonts specifically encoded/installed for |
| 1202 |
\TeX). Currently the usual method of accessing these fonts is through |
| 1203 |
the contributed \Pkg{fontspec} package. This uses as encoding \Enc{TU}: |
| 1204 |
``\TeX{} Unicode'' (historically two experimental encodings \Enc{EU1} |
| 1205 |
and \Enc{EU2} |
| 1206 |
were used, depending on the engine, but these are deprecated). |
| 1207 |
The exact rules for \LaTeX\ encodings |
| 1208 |
for Unicode engines have not yet been finalised in terms of the (usual) |
| 1209 |
requirement that each slot should be defined. (This is not realistic for |
| 1210 |
a Unicode font, as almost all fonts address subsets of the full range.) |
| 1211 |
It is rare to need to specify the \Enc{TU} encoding a document as the |
| 1212 |
\Pkg{fontspec} package sets up the correct encoding when loaded. |
| 1213 |
|
| 1214 |
The restrictions described in section \ref{sec:restrictions} do not |
| 1215 |
apply, or need to be modified in a Unicode based engine. Clearly the |
| 1216 |
lowercase table (and hyphenation patterns) can not be restricted to |
| 1217 |
the values used for \Enc{T1} and do only refer to the first 256 |
| 1218 |
characters. |
| 1219 |
|
| 1220 |
When the \LaTeX\ format is made \LaTeX\ sets up the lowercase table |
| 1221 |
and classifies characters as letter- or non-letter-based on \Enc{T1} if |
| 1222 |
a classic \TeX\ or pdf\TeX\ is being used. If a Unicode based \TeX\ is |
| 1223 |
detected, the values are instead based on the classification and |
| 1224 |
lower-case mappings provided by the Unicode Character Database |
| 1225 |
\cite{ucd}. The \LaTeX{} team have written a generic loader bundle, |
| 1226 |
\Pkg{unicode-data}, which provides the mechanism to load this information |
| 1227 |
directly from the Unicode Character Database data files and which is read |
| 1228 |
when a Unicode-compliant engine is detected during format-building. |
| 1229 |
|
| 1230 |
Similarly in the default configuration files used by modern \TeX\ |
| 1231 |
distribution, the hyphenation files for each supported language are |
| 1232 |
written in UTF-8 encoding, using Unicode code points for all letters, |
| 1233 |
then if a classic \TeX\ system is detected, some additional macros are |
| 1234 |
loaded to convert these files to 256-character encodings where |
| 1235 |
possible, and assuming the \Enc{T1} lowercase table. For Unicode engines |
| 1236 |
no conversion takes place. (The hyphenation patterns for a small number of |
| 1237 |
languages require that some punctuation characters have non-zero |
| 1238 |
c values. This are set during pattern reading, and may at some |
| 1239 |
stage in the future use the e-\TeX{} \verb=\savinghyphcodes= mechanism to |
| 1240 |
avoid any need to manipulate \verb=\lccode= in the document.) |
| 1241 |
|
| 1242 |
|
| 1243 |
|
| 1244 |
|
| 1245 |
\begin{thebibliography}{99} |
| 1246 |
\addcontentsline{toc}{section}{\numberline{\relax}\refname} |
| 1247 |
|
| 1248 |
|
| 1249 |
\bibitem{Adobe:PDF-1.6} \emph{\textsc{PDF} reference}: |
| 1250 |
Adobe portable document format version~1.6. Adobe Systems |
| 1251 |
Incorporated, 2005. % why \textsuperscript{3}? |
| 1252 |
\url{http://partners.adobe.com/public/developer/en/pdf/PDFReference16.pdf}. |
| 1253 |
|
| 1254 |
\bibitem{Beeton:TB6-3-124} Barbara Beeton: |
| 1255 |
\emph{Mathematical symbols and cyrillic fonts ready for |
| 1256 |
distribution}. In: TUGBoat, 6\#3), 1985. |
| 1257 |
\url{http://tug.org/TUGboat/Articles/tb06-3/tb13beetcyr.pdf}. |
| 1258 |
|
| 1259 |
\bibitem{beeton} Barbara Beeton: \emph{Unicode |
| 1260 |
and math, a combination whose time has come -- Finally!}. In: |
| 1261 |
TUGBoat, 21\#3, 2000. |
| 1262 |
\url{http://www.tug.org/TUGboat/Articles/tb21-3/tb68beet.pdf}. |
| 1263 |
|
| 1264 |
|
| 1265 |
\bibitem{Berdnikov:eurotex-98} A.\@ Berdnikov, O.\@ |
| 1266 |
Lapko, M.\@ Kolodin, A.\@ Janishevsky and |
| 1267 |
A.\@ Burykin: \emph{The Encoding Paradigm in |
| 1268 |
\LaTeXe{} and the Projected X2 Encoding for Cyrillic Texts}. |
| 1269 |
Euro\TeX~98. |
| 1270 |
\url{http://www.gutenberg.eu.org/pub/GUTenberg/publicationsPDF/28-29-berdnikova.pdf}. |
| 1271 |
|
| 1272 |
\bibitem{CJK} \emph{The \Pkg{CJK} package}: |
| 1273 |
\url{http://cjk.ffii.org}. |
| 1274 |
|
| 1275 |
\bibitem{clasen} Matthias Clasen: \emph{A new |
| 1276 |
implementation of \LaTeX{} math}, 1997-98. |
| 1277 |
\url{http://www.tug.org/twg/mfg/papers/current/newmath.ps.gz}. |
| 1278 |
|
| 1279 |
\bibitem{clasen-vieth} Matthias Clasen and Ulrik |
| 1280 |
Vieth: \emph{Towards a new Math Font Encoding |
| 1281 |
for (La)\TeX}. March 1998, |
| 1282 |
\url{http://www.tug.org/twg/mfg/papers/current/mfg-euro-all.ps.gz}. |
| 1283 |
|
| 1284 |
\bibitem{CorkGW:91} |
| 1285 |
Dean Guenther and Janene Winter. |
| 1286 |
\newblock An international phonetic alphabet. |
| 1287 |
\newblock In Guenther \cite{proc:MGu91}, pages 149--156. |
| 1288 |
\newblock Published as {TUG}boat 12\#1. |
| 1289 |
|
| 1290 |
\bibitem{proc:MGu91} |
| 1291 |
Mary Guenther, editor. |
| 1292 |
\newblock {\em {\TeX} 90 Conference Proceedings}, March 1991. |
| 1293 |
\newblock Published as {TUG}boat 12\#1. |
| 1294 |
|
| 1295 |
\bibitem{tub:MFe90} |
| 1296 |
Michael~J. Ferguson. |
| 1297 |
\newblock Report on multilingual activities. |
| 1298 |
\newblock {\em {TUG}boat}, 11(4):514--516, 1990. |
| 1299 |
|
| 1300 |
\bibitem{fontinst} \emph{The \Pkg{fontinst} package}: |
| 1301 |
\textlangle CTAN\textrangle\url{/fonts/utilities/fontinst}. |
| 1302 |
|
| 1303 |
\bibitem{Rei:TB17-2-102} Fukui Rei: |
| 1304 |
\emph{\textsl{TIPA}: A system for processing phonetic |
| 1305 |
symbols in \LaTeX}. In: TUGBoat, 17\#, 1996. |
| 1306 |
\url{http://www.tug.org/TUGboat/Articles/tb17-2/tb51rei.pdf}. |
| 1307 |
|
| 1308 |
\bibitem{hyperref} \emph{The \Pkg{hyperref} package}: |
| 1309 |
\url{http://www.tug.org/applications/hyperref}. |
| 1310 |
|
| 1311 |
\bibitem{tub:JKn93} |
| 1312 |
J\"org Knappen. |
| 1313 |
\newblock Fonts for Africa: The fc Fonts. |
| 1314 |
\newblock {\em {TUG}boat}, 14(2):104, 1993. |
| 1315 |
|
| 1316 |
\bibitem{Knappen:TB17-2-96} J\"org Knappen: |
| 1317 |
\emph{The \Pkg{dc} fonts~1.3: Move towards stability |
| 1318 |
and completeness}. In: TUGBoat 17\#2, 1996. |
| 1319 |
\url{http://www.tug.org/TUGboat/Articles/tb17-2/tb51knap.pdf}. |
| 1320 |
|
| 1321 |
\bibitem{A-W:DKn86} |
| 1322 |
Donald~E. Knuth. |
| 1323 |
\newblock {\em The {\TeX}book}. |
| 1324 |
\newblock Volume~A of {\em Computers \& {T}ypesetting\/}, |
| 1325 |
May 1989. |
| 1326 |
\newblock Eight printing. |
| 1327 |
|
| 1328 |
\bibitem{vnr} \emph{The \Pkg{vnr} font family}, developed by |
| 1329 |
the author of pdf\TeX, {H\`an Th\^e\protect\llap{\raise 0.5ex\hbox{\'{\relax}}} Th\`anh}. |
| 1330 |
\url{http://vntex.org/download/vntex}. |
| 1331 |
|
| 1332 |
\bibitem{ipa} Home page of the International Phonetic Association. |
| 1333 |
\url{http://www.arts.gla.ac.uk/IPA/ipa.html} |
| 1334 |
|
| 1335 |
\bibitem{A-W:LLa94} |
| 1336 |
Leslie Lamport. |
| 1337 |
\newblock {\em {\LaTeX:} A Document Preparation System}. |
| 1338 |
\newblock Addison-Wesley, Reading, Massachusetts, second edition, 1994. |
| 1339 |
|
| 1340 |
\bibitem{LH-Fonts} \emph{The \Pkg{lh}-Fonts for Cyrillic}: |
| 1341 |
\textlangle CTAN\textrangle\url{/fonts/cyrillic/lh}. |
| 1342 |
|
| 1343 |
\bibitem{A-W:MG2004} |
| 1344 |
Frank Mittelbach and Michel Goossens. |
| 1345 |
\newblock {\em The {\LaTeX} Companion second edition}. |
| 1346 |
\newblock With Johannes Braams, David Carlisle, and Chris Rowley. |
| 1347 |
\newblock Addison-Wesley, Reading, Massachusetts, 2004. |
| 1348 |
|
| 1349 |
\bibitem{Unicode} \emph{The Unicode Standard}. |
| 1350 |
\url{http://unicode.org}. |
| 1351 |
|
| 1352 |
\bibitem{ucd} \emph{The Unicode Character Database}. |
| 1353 |
\url{http://unicode.org/ucd}. |
| 1354 |
|
| 1355 |
\bibitem{ziegler} Justin Ziegler, \emph{Technical |
| 1356 |
Report on Math Font Encodings}, June 1994, |
| 1357 |
\url{http://www.tug.org/twg/mfg/papers/ltx3pub/l3d007.ps.gz}. |
| 1358 |
|
| 1359 |
\end{thebibliography} |
| 1360 |
|
| 1361 |
\clearpage\appendix |
| 1362 |
\begin{center} |
| 1363 |
\Large\bfseries Appendices |
| 1364 |
\end{center} |
| 1365 |
|
| 1366 |
\section{Example code tables} |
| 1367 |
|
| 1368 |
This appendix contains a table of each font mentioned as an ``example'' |
| 1369 |
font above, providing that the font was available when the document |
| 1370 |
was processed with \LaTeX{}. (\LaTeX{} generates a warning message |
| 1371 |
for each font it fails to find.) |
| 1372 |
|
| 1373 |
\subsection{Text encodings} |
| 1374 |
|
| 1375 |
\ftable{cmr10}{OT1} |
| 1376 |
|
| 1377 |
\ftable{wnr10}{OT2} |
| 1378 |
|
| 1379 |
\ftable{wsuipa10}{OT3} |
| 1380 |
|
| 1381 |
\ftable{plr10}{OT4} |
| 1382 |
|
| 1383 |
%\ftable{artmr10}{OT6} |
| 1384 |
|
| 1385 |
\ftable{ecrm1000}{T1} |
| 1386 |
|
| 1387 |
\ftable{larm1000}{T2A} |
| 1388 |
|
| 1389 |
\ftable{lbrm1000}{T2B} |
| 1390 |
|
| 1391 |
\ftable{lcrm1000}{T2C} |
| 1392 |
|
| 1393 |
\ftable{tipa10}{T3} |
| 1394 |
|
| 1395 |
\ftable{fcr10}{T4} |
| 1396 |
|
| 1397 |
\ftable{vnr10}{T5} |
| 1398 |
|
| 1399 |
|
| 1400 |
\subsection{Text symbol encodings} |
| 1401 |
|
| 1402 |
The full table for \Enc{TS1} as provided by European Computer Modern family: |
| 1403 |
\ftable{tcrm1000}{TS1} |
| 1404 |
|
| 1405 |
\pagebreak |
| 1406 |
|
| 1407 |
In contrast typical PostScript fonts usually have incomplete implementations |
| 1408 |
of \Enc{TS1} sometimes missing more than half of the glyphs: |
| 1409 |
|
| 1410 |
\ftable{ptmr8c}{TS1} |
| 1411 |
|
| 1412 |
\ftable{tipx10}{TS3} |
| 1413 |
|
| 1414 |
|
| 1415 |
|
| 1416 |
\subsection{Extended text encodings} |
| 1417 |
|
| 1418 |
\ftable{rxrm1000}{X2} |
| 1419 |
|
| 1420 |
|
| 1421 |
\subsection{Mathematical encodings} |
| 1422 |
|
| 1423 |
\ftable{cmmi10}{OML} |
| 1424 |
|
| 1425 |
\ftable{cmsy10}{OMS} |
| 1426 |
|
| 1427 |
\ftable{cmex10}{OMX} |
| 1428 |
|
| 1429 |
|
| 1430 |
\subsection{Other encodings} |
| 1431 |
|
| 1432 |
\ftable{ptmr8y}{LY1} |
| 1433 |
|
| 1434 |
%%\ftable{????}{LV1} |
| 1435 |
|
| 1436 |
\ftable{grmn1000}{LGR} |
| 1437 |
|
| 1438 |
\ftable{wasy10}{U} |
| 1439 |
\ftable{logo10}{U} |
| 1440 |
|
| 1441 |
\clearpage |
| 1442 |
\section{Uppercase and lowercase tables} |
| 1443 |
\label{sec:uclc-tab} |
| 1444 |
|
| 1445 |
The following two sets of tables list the \verb"\uppercase" and |
| 1446 |
\verb"\lowercase" values for each position in the \LaTeX{} standard |
| 1447 |
256-character tables. |
| 1448 |
|
| 1449 |
Each row of each table lists: |
| 1450 |
\begin{quote} |
| 1451 |
\begin{tabular}{lp{0.7\textwidth}} |
| 1452 |
pos & The position in the table (0-255) \\ |
| 1453 |
lc & The value in the \verb"\lowercase" table at the position \\ |
| 1454 |
& (note that value 0 here means that \verb"\lowercase" is |
| 1455 |
ineffective for this character, and hyphenation does not apply |
| 1456 |
to it) \\ |
| 1457 |
uc & The value in the \verb"\uppercase" table at the position \\ |
| 1458 |
& (note that value 0 here means that \verb"\uppercase" is |
| 1459 |
ineffective for this character) \\ |
| 1460 |
glyphs & The glyphs specified for the T1 encoding for this |
| 1461 |
position, laid out as \meta{glyph}\textbf{(}\meta{lowercase |
| 1462 |
glyph}\textbf{/}\meta{uppercase glyph}\textbf{)} |
| 1463 |
\end{tabular} |
| 1464 |
\end{quote} |
| 1465 |
|
| 1466 |
\begin{center} |
| 1467 |
\let\lctablenumbersize\footnotesize |
| 1468 |
\makebox[\textwidth]{\hss |
| 1469 |
\dolctable{0}{32}\quad\dolctable{32}{64}\quad |
| 1470 |
\dolctable{64}{96}\quad\dolctable{96}{128}% |
| 1471 |
\hss} |
| 1472 |
|
| 1473 |
\makebox[\textwidth]{\hss |
| 1474 |
\dolctable{128}{160}\quad\dolctable{160}{192}\quad |
| 1475 |
\dolctable{192}{224}\quad\dolctable{224}{256}% |
| 1476 |
\hss} |
| 1477 |
\end{center} |
| 1478 |
\end{document} |
| 1479 |
|
| 1480 |
|
| 1481 |
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |