diff options
Diffstat (limited to 'Master/texmf-dist/doc/fontinst/base/encspecs/t1draft.etx')
-rw-r--r-- | Master/texmf-dist/doc/fontinst/base/encspecs/t1draft.etx | 1457 |
1 files changed, 1457 insertions, 0 deletions
diff --git a/Master/texmf-dist/doc/fontinst/base/encspecs/t1draft.etx b/Master/texmf-dist/doc/fontinst/base/encspecs/t1draft.etx new file mode 100644 index 00000000000..d160fab4e02 --- /dev/null +++ b/Master/texmf-dist/doc/fontinst/base/encspecs/t1draft.etx @@ -0,0 +1,1457 @@ +\relax +\documentclass[twocolumn]{article} +\usepackage[specification]{fontdoc}[2001/06/18] +\usepackage{shortvrb} + +\MakeShortVerb{\|} + +\begin{document} +\title{\texttt{T1} encoding draft specification} +\author{Lars Hellstr\"om} +\date{2002/07/05} +\maketitle + +\begin{abstract} + The \texttt{T1} encoding covers most\footnote{But not quite all.} + letters in the latin script that are used in European languages. + Code points 32--126 coincide with ASCII\footnote{As defined in + Appendix C of \emph{The \TeX book}~\cite{TeXbook}, not as defined + by the ANSI.} and code points 192--255 are mainly the same as in + the latin-1 encoding~\cite{ISO8859-1,latin-page}, but there are + exceptions. +\end{abstract} + +\encoding + +\needsfontinstversion{1.918} + +\begincomment +\section{Mandatory characters} +\endcomment + +\begincomment +\subsection{Letters} +More than two thirds of the characters in the encoding are letters. +This is a deliberate choice: \TeX's hyphenation algorithm requires +that all characters in a word are taken from the same font, hence it +is advantageous\footnote{Probably less so than what was thought when +the encoding was designed, but still advantageous.} to keep as many +letters as possible in the same font. Taking symbols from other fonts +is less of a disadvantage. + +\subsubsection{``Unaccented'' letters in slots 0--127} +\endcomment + +\nextslot{25} +\setslot{dotlessi} + \Unicode{0131}{LATIN SMALL LETTER DOTLESS I} + \comment{A dotless i `\i', used to produce accented letters such as + `\=\i'.} +\endsetslot + +\setslot{dotlessj} + \Unicode{F6BE}{LATIN SMALL LETTER DOTLESS J} + \comment{A dotless j `\j', used to produce accented letters such as + `\=\j'. The Unicode standard does not define this character, but + Adobe has assigned code point \texttt{U+F6BE} (which lies + in the private use subarea assigned by Adobe) to it.} +\endsetslot + + +\nextslot{65} +\setslot{A} + \Unicode{0041}{LATIN CAPITAL LETTER A} +\endsetslot + +\setslot{B} + \Unicode{0042}{LATIN CAPITAL LETTER B} +\endsetslot + +\setslot{C} + \Unicode{0043}{LATIN CAPITAL LETTER C} +\endsetslot + +\setslot{D} + \Unicode{0044}{LATIN CAPITAL LETTER D} +\endsetslot + +\setslot{E} + \Unicode{0045}{LATIN CAPITAL LETTER E} +\endsetslot + +\setslot{F} + \Unicode{0046}{LATIN CAPITAL LETTER F} +\endsetslot + +\setslot{G} + \Unicode{0047}{LATIN CAPITAL LETTER G} +\endsetslot + +\setslot{H} + \Unicode{0048}{LATIN CAPITAL LETTER H} +\endsetslot + +\setslot{I} + \Unicode{0049}{LATIN CAPITAL LETTER I} + \oddligature{This ligature only occurs in Dutch typography.} + {LIG}{J}{IJ} + \oddligature{This ligature only occurs in Dutch typography.} + {LIG}{j}{IJ} +\endsetslot + +\setslot{J} + \Unicode{004A}{LATIN CAPITAL LETTER J} +\endsetslot + +\setslot{K} + \Unicode{004B}{LATIN CAPITAL LETTER K} +\endsetslot + +\setslot{L} + \Unicode{004C}{LATIN CAPITAL LETTER L} +\endsetslot + +\setslot{M} + \Unicode{004D}{LATIN CAPITAL LETTER M} +\endsetslot + +\setslot{N} + \Unicode{004E}{LATIN CAPITAL LETTER N} +\endsetslot + +\setslot{O} + \Unicode{004F}{LATIN CAPITAL LETTER O} +\endsetslot + +\setslot{P} + \Unicode{0050}{LATIN CAPITAL LETTER P} +\endsetslot + +\setslot{Q} + \Unicode{0051}{LATIN CAPITAL LETTER Q} +\endsetslot + +\setslot{R} + \Unicode{0052}{LATIN CAPITAL LETTER R} +\endsetslot + +\setslot{S} + \Unicode{0053}{LATIN CAPITAL LETTER S} +\endsetslot + +\setslot{T} + \Unicode{0054}{LATIN CAPITAL LETTER T} +\endsetslot + +\setslot{U} + \Unicode{0055}{LATIN CAPITAL LETTER U} +\endsetslot + +\setslot{V} + \Unicode{0056}{LATIN CAPITAL LETTER V} +\endsetslot + +\setslot{W} + \Unicode{0057}{LATIN CAPITAL LETTER W} +\endsetslot + +\setslot{X} + \Unicode{0058}{LATIN CAPITAL LETTER X} +\endsetslot + +\setslot{Y} + \Unicode{0059}{LATIN CAPITAL LETTER Y} +\endsetslot + +\setslot{Z} + \Unicode{005A}{LATIN CAPITAL LETTER Z} +\endsetslot + + +\nextslot{97} +\setslot{a} + \Unicode{0061}{LATIN SMALL LETTER A} +\endsetslot + +\setslot{b} + \Unicode{0062}{LATIN SMALL LETTER B} +\endsetslot + +\setslot{c} + \Unicode{0063}{LATIN SMALL LETTER C} +\endsetslot + +\setslot{d} + \Unicode{0064}{LATIN SMALL LETTER D} +\endsetslot + +\setslot{e} + \Unicode{0065}{LATIN SMALL LETTER E} +\endsetslot + +\setslot{f} + \Unicode{0066}{LATIN SMALL LETTER F} + \ligature{LIG}{f}{ff} + \ligature{LIG}{i}{fi} + \ligature{LIG}{l}{fl} +\endsetslot + +\setslot{g} + \Unicode{0067}{LATIN SMALL LETTER G} +\endsetslot + +\setslot{h} + \Unicode{0068}{LATIN SMALL LETTER H} +\endsetslot + +\setslot{i} + \Unicode{0069}{LATIN SMALL LETTER I} + \oddligature{This ligature only occurs in Dutch typography.} + {LIG}{j}{ij} +\endsetslot + +\setslot{j} + \Unicode{006A}{LATIN SMALL LETTER J} +\endsetslot + +\setslot{k} + \Unicode{006B}{LATIN SMALL LETTER K} +\endsetslot + +\setslot{l} + \Unicode{006C}{LATIN SMALL LETTER L} +\endsetslot + +\setslot{m} + \Unicode{006D}{LATIN SMALL LETTER M} +\endsetslot + +\setslot{n} + \Unicode{006E}{LATIN SMALL LETTER N} +\endsetslot + +\setslot{o} + \Unicode{006F}{LATIN SMALL LETTER O} +\endsetslot + +\setslot{p} + \Unicode{0070}{LATIN SMALL LETTER P} +\endsetslot + +\setslot{q} + \Unicode{0071}{LATIN SMALL LETTER Q} +\endsetslot + +\setslot{r} + \Unicode{0072}{LATIN SMALL LETTER R} +\endsetslot + +\setslot{s} + \Unicode{0073}{LATIN SMALL LETTER S} +\endsetslot + +\setslot{t} + \Unicode{0074}{LATIN SMALL LETTER T} +\endsetslot + +\setslot{u} + \Unicode{0075}{LATIN SMALL LETTER U} +\endsetslot + +\setslot{v} + \Unicode{0076}{LATIN SMALL LETTER V} +\endsetslot + +\setslot{w} + \Unicode{0077}{LATIN SMALL LETTER W} +\endsetslot + +\setslot{x} + \Unicode{0078}{LATIN SMALL LETTER X} +\endsetslot + +\setslot{y} + \Unicode{0079}{LATIN SMALL LETTER Y} +\endsetslot + +\setslot{z} + \Unicode{007A}{LATIN SMALL LETTER Z} +\endsetslot + + +\begincomment +\subsubsection{Mainly East-European accented letters + in slots 128--191} +\endcomment + +\nextslot{128} +\setslot{Abreve} + \Unicode{0102}{LATIN CAPITAL LETTER A WITH BREVE} +\endsetslot + +\setslot{Aogonek} + \Unicode{0104}{LATIN CAPITAL LETTER A WITH OGONEK} +\endsetslot + +\setslot{Cacute} + \Unicode{0106}{LATIN CAPITAL LETTER C WITH ACUTE} +\endsetslot + +\setslot{Ccaron} + \Unicode{010C}{LATIN CAPITAL LETTER C WITH CARON} +\endsetslot + +\setslot{Dcaron} + \Unicode{010E}{LATIN CAPITAL LETTER D WITH CARON} +\endsetslot + +\setslot{Ecaron} + \Unicode{011A}{LATIN CAPITAL LETTER E WITH CARON} +\endsetslot + +\setslot{Eogonek} + \Unicode{0118}{LATIN CAPITAL LETTER E WITH OGONEK} +\endsetslot + +\setslot{Gbreve} + \Unicode{011E}{LATIN CAPITAL LETTER G WITH BREVE} +\endsetslot + +\setslot{Lacute} + \Unicode{0139}{LATIN CAPITAL LETTER L WITH ACUTE} +\endsetslot + +\setslot{Lcaron} + \Unicode{013D}{LATIN CAPITAL LETTER L WITH CARON} + \comment{The normal glyph for this character consists of a capital + L and a right single quote, but the underlying accent is a caron. + The glyph name \texttt{Lquoteright} is not uncommon, but + \cite{AGL} uses \texttt{Lcaron}.} +\endsetslot + +\setslot{Lslash} + \Unicode{0141}{LATIN CAPITAL LETTER L WITH STROKE} + \comment{The letter `\L'.} +\endsetslot + +\setslot{Nacute} + \Unicode{0143}{LATIN CAPITAL LETTER N WITH ACUTE} +\endsetslot + +\setslot{Ncaron} + \Unicode{0147}{LATIN CAPITAL LETTER N WITH CARON} +\endsetslot + +\setslot{Eng} + \Unicode{014A}{LATIN CAPITAL LETTER ENG} +\endsetslot + +\setslot{Ohungarumlaut} + \Unicode{0150}{LATIN CAPITAL LETTER O WITH DOUBLE ACUTE} + \comment{The letter `\H{O}'.} +\endsetslot + +\setslot{Racute} + \Unicode{0154}{LATIN CAPITAL LETTER R WITH ACUTE} +\endsetslot + +\setslot{Rcaron} + \Unicode{0158}{LATIN CAPITAL LETTER R WITH CARON} +\endsetslot + +\setslot{Sacute} + \Unicode{015A}{LATIN CAPITAL LETTER S WITH ACUTE} +\endsetslot + +\setslot{Scaron} + \Unicode{0160}{LATIN CAPITAL LETTER S WITH CARON} +\endsetslot + +\setslot{Scedilla} + \Unicode{015E}{LATIN CAPITAL LETTER S WITH CEDILLA} + \comment{In Romanian, character \textunicode{0218}{latin + capital letter s with comma below} is preferred, but that + wasn't known when this encoding was designed.} +\endsetslot + +\setslot{Tcaron} + \Unicode{0164}{LATIN CAPITAL LETTER T WITH CARON} +\endsetslot + +\setslot{Tcommaaccent} + \Unicode{021A}{LATIN CAPITAL LETTER T WITH COMMA BELOW} +\endsetslot + +\setslot{Uhungarumlaut} + \Unicode{0170}{LATIN CAPITAL LETTER U WITH DOUBLE ACUTE} + \comment{The letter `\H{U}'.} +\endsetslot + +\setslot{Uring} + \Unicode{016E}{LATIN CAPITAL LETTER U WITH RING ABOVE} +\endsetslot + +\setslot{Ydieresis} + \Unicode{0178}{LATIN CAPITAL LETTER Y WITH DIAERESIS} +\endsetslot + +\setslot{Zacute} + \Unicode{0179}{LATIN CAPITAL LETTER Z WITH ACUTE} +\endsetslot + +\setslot{Zcaron} + \Unicode{017D}{LATIN CAPITAL LETTER Z WITH CARON} +\endsetslot + +\setslot{Zdotaccent} + \Unicode{017B}{LATIN CAPITAL LETTER Z WITH DOT ABOVE} +\endsetslot + +\skipslots{1} +\setslot{Idotaccent} + \Unicode{0130}{LATIN CAPITAL LETTER I WITH DOT ABOVE} + \comment{This character's |\lccode| value points to slot 105 + (\texttt{i}), as does that of slot 73 (\texttt{I}).} +\endsetslot + +\setslot{dcroat} + \Unicode{0111}{LATIN SMALL LETTER D WITH STROKE} +\endsetslot + + +\nextslot{160} +\setslot{abreve} + \Unicode{0103}{LATIN SMALL LETTER A WITH BREVE} +\endsetslot + +\setslot{aogonek} + \Unicode{0105}{LATIN SMALL LETTER A WITH OGONEK} +\endsetslot + +\setslot{cacute} + \Unicode{0107}{LATIN SMALL LETTER C WITH ACUTE} +\endsetslot + +\setslot{ccaron} + \Unicode{010D}{LATIN SMALL LETTER C WITH CARON} +\endsetslot + +\setslot{dcaron} + \Unicode{010F}{LATIN SMALL LETTER D WITH CARON} + \comment{The normal glyph for this character consists of a + lower case d and a right single quote, but the underlying + accent is a caron.} +\endsetslot + +\setslot{ecaron} + \Unicode{011B}{LATIN SMALL LETTER E WITH CARON} +\endsetslot + +\setslot{eogonek} + \Unicode{0119}{LATIN SMALL LETTER E WITH OGONEK} +\endsetslot + +\setslot{gbreve} + \Unicode{011F}{LATIN SMALL LETTER G WITH BREVE} +\endsetslot + +\setslot{lacute} + \Unicode{013A}{LATIN SMALL LETTER L WITH ACUTE} +\endsetslot + +\setslot{lcaron} + \Unicode{013E}{LATIN SMALL LETTER L WITH CARON} + \comment{The normal glyph for this character consists of a + lower case l and a right single quote, but the underlying + accent is a caron. The glyph name \texttt{lquoteright} is + not uncommon, but \cite{AGL} uses \texttt{lcaron}.} +\endsetslot + +\setslot{lslash} + \Unicode{0142}{LATIN SMALL LETTER L WITH STROKE} +\endsetslot + +\setslot{nacute} + \Unicode{0144}{LATIN SMALL LETTER N WITH ACUTE} +\endsetslot + +\setslot{ncaron} + \Unicode{0148}{LATIN SMALL LETTER N WITH CARON} +\endsetslot + +\setslot{eng} + \Unicode{014B}{LATIN SMALL LETTER ENG} +\endsetslot + +\setslot{ohungarumlaut} + \Unicode{0151}{LATIN SMALL LETTER O WITH DOUBLE ACUTE} + \comment{The letter `\H{o}'.} +\endsetslot + +\setslot{racute} + \Unicode{0155}{LATIN SMALL LETTER R WITH ACUTE} +\endsetslot + +\setslot{rcaron} + \Unicode{0159}{LATIN SMALL LETTER R WITH CARON} +\endsetslot + +\setslot{sacute} + \Unicode{015B}{LATIN SMALL LETTER S WITH ACUTE} +\endsetslot + +\setslot{scaron} + \Unicode{0161}{LATIN SMALL LETTER S WITH CARON} +\endsetslot + +\setslot{scedilla} + \Unicode{015F}{LATIN SMALL LETTER S WITH CEDILLA} + \comment{In Romanian, character \textunicode{0219}{latin + small letter s with comma below} is preferred, but that + wasn't known when this encoding was designed.} +\endsetslot + +\setslot{tcaron} + \Unicode{0165}{LATIN SMALL LETTER T WITH CARON} + \comment{The normal glyph for this character consists of a + lower case t and a right single quote, but the underlying + accent is a caron.} +\endsetslot + +\setslot{tcommaaccent} + \Unicode{021B}{LATIN SMALL LETTER T WITH COMMA BELOW} +\endsetslot + +\setslot{uhungarumlaut} + \Unicode{0171}{LATIN SMALL LETTER U WITH DOUBLE ACUTE} +\endsetslot + +\setslot{uring} + \Unicode{016F}{LATIN SMALL LETTER U WITH RING ABOVE} +\endsetslot + +\setslot{ydieresis} + \Unicode{00FF}{LATIN SMALL LETTER Y WITH DIAERESIS} +\endsetslot + +\setslot{zacute} + \Unicode{017A}{LATIN SMALL LETTER Z WITH ACUTE} +\endsetslot + +\setslot{zcaron} + \Unicode{017E}{LATIN SMALL LETTER Z WITH CARON} +\endsetslot + +\setslot{zdotaccent} + \Unicode{017C}{LATIN SMALL LETTER Z WITH DOT ABOVE} +\endsetslot + + +\begincomment +\subsubsection{Mainly West-European accented letters in slots 192--255} +\endcomment + +\nextslot{192} +\setslot{Agrave} + \Unicode{00C0}{LATIN CAPITAL LETTER A WITH GRAVE} +\endsetslot + +\setslot{Aacute} + \Unicode{00C1}{LATIN CAPITAL LETTER A WITH ACUTE} +\endsetslot + +\setslot{Acircumflex} + \Unicode{00C2}{LATIN CAPITAL LETTER A WITH CIRCUMFLEX} +\endsetslot + +\setslot{Atilde} + \Unicode{00C3}{LATIN CAPITAL LETTER A WITH TILDE} +\endsetslot + +\setslot{Adieresis} + \Unicode{00C4}{LATIN CAPITAL LETTER A WITH DIAERESIS} +\endsetslot + +\setslot{Aring} + \Unicode{00C5}{LATIN CAPITAL LETTER A WITH RING ABOVE} +\endsetslot + +\setslot{AE} + \Unicode{00C6}{LATIN CAPITAL LETTER AE} +\endsetslot + +\setslot{Ccedilla} + \Unicode{00C7}{LATIN CAPITAL LETTER C WITH CEDILLA} +\endsetslot + +\setslot{Egrave} + \Unicode{00C8}{LATIN CAPITAL LETTER E WITH GRAVE} +\endsetslot + +\setslot{Eacute} + \Unicode{00C9}{LATIN CAPITAL LETTER E WITH ACUTE} +\endsetslot + +\setslot{Ecircumflex} + \Unicode{00CA}{LATIN CAPITAL LETTER E WITH CIRCUMFLEX} +\endsetslot + +\setslot{Edieresis} + \Unicode{00CB}{LATIN CAPITAL LETTER E WITH DIAERESIS} +\endsetslot + +\setslot{Igrave} + \Unicode{00CC}{LATIN CAPITAL LETTER I WITH GRAVE} +\endsetslot + +\setslot{Iacute} + \Unicode{00CD}{LATIN CAPITAL LETTER I WITH ACUTE} +\endsetslot + +\setslot{Icircumflex} + \Unicode{00CE}{LATIN CAPITAL LETTER I WITH CIRCUMFLEX} +\endsetslot + +\setslot{Idieresis} + \Unicode{00CF}{LATIN CAPITAL LETTER I WITH DIAERESIS} +\endsetslot + +\setslot{Eth} + \Unicode{00D0}{LATIN CAPITAL LETTER ETH} + \Unicode{0110}{LATIN CAPITAL LETTER D WITH STROKE} + \comment{This slot is being used to represent two different + letters whose capital forms are identical. The |\lccode| value + points to slot \ref{eth}.} +\endsetslot + +\setslot{Ntilde} + \Unicode{00D1}{LATIN CAPITAL LETTER N WITH TILDE} +\endsetslot + +\setslot{Ograve} + \Unicode{00D2}{LATIN CAPITAL LETTER O WITH GRAVE} +\endsetslot + +\setslot{Oacute} + \Unicode{00D3}{LATIN CAPITAL LETTER O WITH ACUTE} +\endsetslot + +\setslot{Ocircumflex} + \Unicode{00D4}{LATIN CAPITAL LETTER O WITH CIRCUMFLEX} +\endsetslot + +\setslot{Otilde} + \Unicode{00D5}{LATIN CAPITAL LETTER O WITH TILDE} +\endsetslot + +\setslot{Odieresis} + \Unicode{00D6}{LATIN CAPITAL LETTER O WITH DIAERESIS} +\endsetslot + +\setslot{OE} + \Unicode{0152}{LATIN CAPITAL LIGATURE OE} + \comment{This is a single letter, and should not be faked with `OE'.} +\endsetslot + +\setslot{Oslash} + \Unicode{00D8}{LATIN CAPITAL LETTER O WITH STROKE} +\endsetslot + +\setslot{Ugrave} + \Unicode{00D9}{LATIN CAPITAL LETTER U WITH GRAVE} +\endsetslot + +\setslot{Uacute} + \Unicode{00DA}{LATIN CAPITAL LETTER U WITH ACUTE} +\endsetslot + +\setslot{Ucircumflex} + \Unicode{00DB}{LATIN CAPITAL LETTER U WITH CIRCUMFLEX} +\endsetslot + +\setslot{Udieresis} + \Unicode{00DC}{LATIN CAPITAL LETTER U WITH DIAERESIS} +\endsetslot + +\setslot{Yacute} + \Unicode{00DD}{LATIN CAPITAL LETTER Y WITH ACUTE} +\endsetslot + +\setslot{Thorn} + \Unicode{00DE}{LATIN CAPITAL LETTER THORN} +\endsetslot + +\setslot{SS} + \comment{This is an ``uppercased'' sharp s (`\ss') which always + looks exactly like two S's next to each other. In a monowidth + font it should be two letters wide. There are other characters + which could have made better use of this slot; the only function + of this slot which could not have been handled using macros is + that |\SS| and |SS| can have different hyphenation.} +\endsetslot + +\setslot{agrave} + \Unicode{00E0}{LATIN SMALL LETTER A WITH GRAVE} +\endsetslot + +\setslot{aacute} + \Unicode{00E1}{LATIN SMALL LETTER A WITH ACUTE} +\endsetslot + +\setslot{acircumflex} + \Unicode{00E2}{LATIN SMALL LETTER A WITH CIRCUMFLEX} +\endsetslot + +\setslot{atilde} + \Unicode{00E3}{LATIN SMALL LETTER A WITH TILDE} +\endsetslot + +\setslot{adieresis} + \Unicode{00E4}{LATIN SMALL LETTER A WITH DIAERESIS} +\endsetslot + +\setslot{aring} + \Unicode{00E5}{LATIN SMALL LETTER A WITH RING ABOVE} +\endsetslot + +\setslot{ae} + \Unicode{00E6}{LATIN SMALL LETTER AE} +\endsetslot + +\setslot{ccedilla} + \Unicode{00E7}{LATIN SMALL LETTER C WITH CEDILLA} +\endsetslot + +\setslot{egrave} + \Unicode{00E8}{LATIN SMALL LETTER E WITH GRAVE} +\endsetslot + +\setslot{eacute} + \Unicode{00E9}{LATIN SMALL LETTER E WITH ACUTE} +\endsetslot + +\setslot{ecircumflex} + \Unicode{00EA}{LATIN SMALL LETTER E WITH CIRCUMFLEX} +\endsetslot + +\setslot{edieresis} + \Unicode{00EB}{LATIN SMALL LETTER E WITH DIAERESIS} +\endsetslot + +\setslot{igrave} + \Unicode{00EC}{LATIN SMALL LETTER I WITH GRAVE} +\endsetslot + +\setslot{iacute} + \Unicode{00ED}{LATIN SMALL LETTER I WITH ACUTE} +\endsetslot + +\setslot{icircumflex} + \Unicode{00EE}{LATIN SMALL LETTER I WITH CIRCUMFLEX} +\endsetslot + +\setslot{idieresis} + \Unicode{00EF}{LATIN SMALL LETTER I WITH DIAERESIS} +\endsetslot + +\setslot{eth} + \Unicode{00F0}{LATIN SMALL LETTER ETH} + \label{eth} +\endsetslot + +\setslot{ntilde} + \Unicode{00F1}{LATIN SMALL LETTER N WITH TILDE} +\endsetslot + +\setslot{ograve} + \Unicode{00F2}{LATIN SMALL LETTER O WITH GRAVE} +\endsetslot + +\setslot{oacute} + \Unicode{00F3}{LATIN SMALL LETTER O WITH ACUTE} +\endsetslot + +\setslot{ocircumflex} + \Unicode{00F4}{LATIN SMALL LETTER O WITH CIRCUMFLEX} +\endsetslot + +\setslot{otilde} + \Unicode{00F5}{LATIN SMALL LETTER O WITH TILDE} +\endsetslot + +\setslot{odieresis} + \Unicode{00F6}{LATIN SMALL LETTER O WITH DIAERESIS} +\endsetslot + +\setslot{oe} + \Unicode{0153}{LATIN SMALL LIGATURE OE} + \comment{This is a single letter, and should not be faked with `oe'.} +\endsetslot + +\setslot{oslash} + \Unicode{00F8}{LATIN SMALL LETTER O WITH STROKE} +\endsetslot + +\setslot{ugrave} + \Unicode{00F9}{LATIN SMALL LETTER U WITH GRAVE} +\endsetslot + +\setslot{uacute} + \Unicode{00FA}{LATIN SMALL LETTER U WITH ACUTE} +\endsetslot + +\setslot{ucircumflex} + \Unicode{00FB}{LATIN SMALL LETTER U WITH CIRCUMFLEX} +\endsetslot + +\setslot{udieresis} + \Unicode{00FC}{LATIN SMALL LETTER U WITH DIAERESIS} +\endsetslot + +\setslot{yacute} + \Unicode{00FD}{LATIN SMALL LETTER Y WITH ACUTE} +\endsetslot + +\setslot{thorn} + \Unicode{00FE}{LATIN SMALL LETTER THORN} +\endsetslot + +\setslot{germandbls} + \Unicode{00DF}{LATIN SMALL LETTER SHARP S} +\endsetslot + + +\begincomment +\subsection{Accents} +The Unicode equivalents of the accents are taken to be the combining +forms of the accents found in code point \texttt{U+0300} and upwards. +The reasons for this are (i) that they are primarily used with the +|\accent| primitive, i.e., as combining characters, (ii) that some +of them (e.g. \texttt{tilde}) have non-combining counterparts +elsewhere in the encoding, and (iii) that they are not primarily +phonetic marks. +\endcomment + +\nextslot{0} +\setslot{grave} + \Unicode{0300}{COMBINING GRAVE ACCENT} +\endsetslot + +\setslot{acute} + \Unicode{0301}{COMBINING ACUTE ACCENT} +\endsetslot + +\setslot{circumflex} + \Unicode{0302}{COMBINING CIRCUMFLEX ACCENT} +\endsetslot + +\setslot{tilde} + \Unicode{0303}{COMBINING TILDE} +\endsetslot + +\setslot{dieresis} + \Unicode{0308}{COMBINING DIAERESIS} +\endsetslot + +\setslot{hungarumlaut} + \Unicode{030B}{COMBINING DOUBLE ACUTE ACCENT} + \comment{The long Hungarian umlaut `\H{}'.} +\endsetslot + +\setslot{ring} + \Unicode{030A}{COMBINING RING ABOVE} +\endsetslot + +\setslot{caron} + \Unicode{030C}{COMBINING CARON} + \comment{The caron or h\'a\v cek accent `\v{}'.} +\endsetslot + +\setslot{breve} + \Unicode{0306}{COMBINING BREVE} +\endsetslot + +\setslot{macron} + \Unicode{0304}{COMBINING MACRON} +\endsetslot + +\setslot{dotaccent} + \Unicode{0307}{COMBINING DOT ABOVE} +\endsetslot + +\setslot{cedilla} + \Unicode{0327}{COMBINING CEDILLA} +\endsetslot + +\setslot{ogonek} + \Unicode{0328}{COMBINING OGONEK} +\endsetslot + + +\begincomment +\subsection{Digits} +\endcomment + +\nextslot{48} +\setslot{zero} + \Unicode{0030}{DIGIT ZERO} +\endsetslot + +\setslot{one} + \Unicode{0031}{DIGIT ONE} +\endsetslot + +\setslot{two} + \Unicode{0032}{DIGIT TWO} +\endsetslot + +\setslot{three} + \Unicode{0033}{DIGIT THREE} +\endsetslot + +\setslot{four} + \Unicode{0034}{DIGIT FOUR} +\endsetslot + +\setslot{five} + \Unicode{0035}{DIGIT FIVE} +\endsetslot + +\setslot{six} + \Unicode{0036}{DIGIT SIX} +\endsetslot + +\setslot{seven} + \Unicode{0037}{DIGIT SEVEN} +\endsetslot + +\setslot{eight} + \Unicode{0038}{DIGIT EIGHT} +\endsetslot + +\setslot{nine} + \Unicode{0039}{DIGIT NINE} +\endsetslot + + +\begincomment +\subsection{Symbols and punctuation} +\endcomment + +\nextslot{13} +\setslot{quotesinglbase} + \Unicode{201A}{SINGLE LOW-9 QUOTATION MARK} +\endsetslot + +\setslot{guilsinglleft} + \Unicode{2039}{SINGLE LEFT-POINTING ANGLE QUOTATION MARK} + \comment{In French typography this is an opening quotation mark, + but in German typography it is a closing quotation mark. The + character should kern well in both cases.} +\endsetslot + +\setslot{guilsinglright} + \Unicode{203A}{SINGLE RIGHT-POINTING ANGLE QUOTATION MARK} + \comment{In French typography this is a closing quotation mark, + but in German typography it is an opening quotation mark. The + character should kern well in both cases.} +\endsetslot + +\setslot{quotedblleft} + \Unicode{201C}{LEFT DOUBLE QUOTATION MARK} +\endsetslot + +\setslot{quotedblright} + \Unicode{201D}{RIGHT DOUBLE QUOTATION MARK} + \comment{In English typography this quotation mark is always + closing, but in Swedish typography it is also an opening + quotation mark. The character should kern well in both cases.} +\endsetslot + +\setslot{quotedblbase} + \Unicode{201E}{DOUBLE LOW-9 QUOTATION MARK} +\endsetslot + +\setslot{guillemotleft} + \Unicode{00AB}{LEFT-POINTING DOUBLE ANGLE QUOTATION MARK} + \comment{In French typography this is an opening quotation mark, + but in German typography it is a closing quotation mark. The + character should kern well in both cases. The glyph name is + misspelt (it should be \texttt{guillemetleft}), but this + incorrect name is \emph{de facto} the glyph name used.} +\endsetslot + +\setslot{guillemotright} + \Unicode{00BB}{RIGHT-POINTING DOUBLE ANGLE QUOTATION MARK} + \comment{In French typography this is a closing quotation mark, + but in German typography it is an opening quotation mark. The + character should kern well in both cases. The glyph name is + misspelt (it should be \texttt{guillemetright}), but this + incorrect name is \emph{de facto} the glyph name used.} +\endsetslot + +\setslot{endash} + \Unicode{2013}{EN DASH} + \label{endash} + \Ligature{LIG}{hyphen}{emdash} +\endsetslot + +\setslot{emdash} + \Unicode{2014}{EM DASH} + \comment{In a monowidth font this character is preferably given the + width of two normal characters.} +\endsetslot + +\nextslot{32} +\setslot{visiblespace} + \Unicode{2423}{OPEN BOX} + \comment{A visible space glyph `\textvisiblespace'.} +\endsetslot + +\setslot{exclam} + \Unicode{0021}{EXCLAMATION MARK} + \Ligature{LIG}{quoteleft}{exclamdown} +\endsetslot + +\setslot{quotedbl} + \Unicode{0022}{QUOTATION MARK} + \comment{The `neutral' double quotation mark, included for use in + monowidth fonts, or for setting computer programs.} +\endsetslot + +\setslot{numbersign} + \Unicode{0023}{NUMBER SIGN} +\endsetslot + +\setslot{dollar} + \Unicode{0024}{DOLLAR SIGN} +\endsetslot + +\setslot{percent} + \Unicode{0025}{PERCENT SIGN} +\endsetslot + +\setslot{ampersand} + \Unicode{0026}{AMPERSAND} +\endsetslot + +\setslot{quoteright} + \Unicode{2019}{RIGHT SINGLE QUOTATION MARK} + \Ligature{LIG}{quoteright}{quotedblright} +\endsetslot + +\setslot{parenleft} + \Unicode{0028}{LEFT PARENTHESIS} +\endsetslot + +\setslot{parenright} + \Unicode{0029}{RIGHT PARENTHESIS} +\endsetslot + +\setslot{asterisk} + \Unicode{002A}{ASTERISK} +\endsetslot + +\setslot{plus} + \Unicode{002B}{PLUS SIGN} +\endsetslot + +\setslot{comma} + \Unicode{002C}{COMMA} + \Ligature{LIG}{comma}{quotedblbase} +\endsetslot + +\setslot{hyphen} + \Unicode{002D}{HYPHEN-MINUS} + \Ligature{LIG}{hyphen}{endash} + \Ligature{LIG}{hyphenchar}{hyphenchar} + \comment{See also slot \ref{hyphenchar}.} + \label{hyphen} +\endsetslot + +\setslot{period} + \Unicode{002E}{FULL STOP} +\endsetslot + +\setslot{slash} + \Unicode{002F}{SOLIDUS} +\endsetslot + +\skipslots{10} +\setslot{colon} + \Unicode{003A}{COLON} +\endsetslot + +\setslot{semicolon} + \Unicode{003B}{SEMICOLON} +\endsetslot + +\setslot{less} + \Unicode{003C}{LESS-THAN SIGN} + \Ligature{LIG}{less}{guillemotleft} +\endsetslot + +\setslot{equal} + \Unicode{003D}{EQUALS SIGN} +\endsetslot + +\setslot{greater} + \Unicode{003E}{GREATER-THAN SIGN} + \Ligature{LIG}{greater}{guillemotright} +\endsetslot + +\setslot{question} + \Unicode{003F}{QUESTION MARK} + \Ligature{LIG}{quoteleft}{questiondown} +\endsetslot + +\setslot{at} + \Unicode{0040}{COMMERCIAL AT} +\endsetslot + +\nextslot{91} +\setslot{bracketleft} + \Unicode{005B}{LEFT SQUARE BRACKET} +\endsetslot + +\setslot{backslash} + \Unicode{005C}{REVERSE SOLIDUS} +\endsetslot + +\setslot{bracketright} + \Unicode{005D}{RIGHT SQUARE BRACKET} +\endsetslot + +\setslot{asciicircum} + \Unicode{005E}{CIRCUMFLEX ACCENT} + \comment{The ASCII upward-pointing arrow head `\textasciicircum'. + This is included for compatibility with typewriter fonts used + for computer listings.} +\endsetslot + +\setslot{underscore} + \Unicode{005F}{LOW LINE} + \comment{The ASCII underline character `\textunderscore', usually + set on the baseline. This is included for compatibility with + typewriter fonts used for computer listings.} +\endsetslot + +\setslot{quoteleft} + \Unicode{2018}{LEFT SINGLE QUOTATION MARK} + \Ligature{LIG}{quoteleft}{quotedblleft} +\endsetslot + +\nextslot{123} +\setslot{braceleft} + \Unicode{007B}{LEFT CURLY BRACKET} +\endsetslot + +\setslot{bar} + \Unicode{007C}{VERTICAL LINE} + \comment{The ASCII vertical bar `\textbar'. + This is included for compatibility with typewriter fonts used + for computer listings.} +\endsetslot + +\setslot{braceright} + \Unicode{007D}{RIGHT CURLY BRACKET} +\endsetslot + +\setslot{asciitilde} + \Unicode{007E}{TILDE} + \comment{The ASCII tilde `\textasciitilde'. + This is included for compatibility with typewriter fonts used + for computer listings.} +\endsetslot + +\nextslot{159} +\setslot{section} + \Unicode{00A7}{SECTION SIGN} +\endsetslot + +\nextslot{189} +\setslot{exclamdown} + \Unicode{00A1}{INVERTED EXCLAMATION MARK} +\endsetslot + +\setslot{questiondown} + \Unicode{00BF}{INVERTED QUESTION MARK} +\endsetslot + +\setslot{sterling} + \Unicode{00A3}{POUND SIGN} +\endsetslot + + + +\begincomment +\subsection{Miscellanea} +\endcomment + +\nextslot{23} +\setslot{compwordmark} + \Unicode{200C}{ZERO WIDTH NON-JOINER} + \comment{An invisible glyph, with zero width and depth, but the + height of lower case letters without ascenders. + It is used to stop ligaturing in words like `shelf{}ful'. + It is possible that this character should be considered a + letter (and that hyphenation patterns should be designed to + include it), but since its |\lccode| is 0, \TeX's hyphenation + mechanism considers it to be a nonletter which ends the + hyphenatable part of a word.} +\endsetslot + +\setslot{perthousandzero} + \comment{A glyph which is placed after `\%' to produce a + `per-thousand', or twice to produce `per-ten-thousand'. + Your guess is as good as mine as to what this glyph should look + like in a monowidth font. Since most fonts don't include this + glyph anyway, its use is discouraged.} +\endsetslot + +\nextslot{127} +\setslot{hyphenchar} + \label{hyphenchar} + \comment{This character is provided as a discretionary hyphen + symbol and may only appear at the end of a line, since it is often + hanging out of the character box, but apart from that it is almost + always the same as the \texttt{hyphen} character. Since \LaTeX\ + sets the |\hyphenchar| of \texttt{T1} fonts to slot \ref{hyphen} + rather than this slot, this feature is usually not used.} +\endsetslot + + + +\begincomment +\section{Usual characters} +The following characters are only accessed through ligatures and can +therefore be replaced by others or completely left out if the +ligature programs are modified accordingly. +\endcomment + +\nextslot{27} +\setslot{ff} + \Unicode{FB00}{LATIN SMALL LIGATURE FF} + \comment{This glyph should be two characters wide in a monowidth + font.} + \ligature{LIG}{i}{ffi} + \ligature{LIG}{l}{ffl} +\endsetslot + +\setslot{fi} + \Unicode{FB01}{LATIN SMALL LIGATURE FI} + \comment{This glyph should be two characters wide in a monowidth + font.} +\endsetslot + +\setslot{fl} + \Unicode{FB02}{LATIN SMALL LIGATURE FL} + \comment{This glyph should be two characters wide in a monowidth + font.} +\endsetslot + +\setslot{ffi} + \Unicode{FB03}{LATIN SMALL LIGATURE FFI} + \comment{This glyph should be three characters wide in a monowidth + font.} +\endsetslot + +\setslot{ffl} + \Unicode{FB04}{LATIN SMALL LIGATURE FFL} + \comment{This glyph should be three characters wide in a monowidth + font.} +\endsetslot + +\nextslot{156} +\setslot{IJ} + \Unicode{0132}{LATIN CAPITAL LIGATURE IJ} + \comment{This is a single letter, and in a monowidth font should + ideally be one letter wide.} +\endsetslot + +\nextslot{188} +\setslot{ij} + \Unicode{0133}{LATIN SMALL LIGATURE IJ} + \comment{This is a single letter, and in a monowidth font should + ideally be one letter wide.} +\endsetslot + + +\begincomment +\section{Fontdimens} +\endcomment + +\setfontdimen{1}{italicslant} % italic slant +\setfontdimen{2}{interword} % interword space +\setfontdimen{3}{stretchword} % interword stretch +\setfontdimen{4}{shrinkword} % interword shrink +\setfontdimen{5}{xheight} % x-height +\setfontdimen{6}{quad} % quad +\setfontdimen{7}{extraspace} % extra space after . +\setfontdimen{8}{capheight} % cap height +\setfontdimen{9}{ascender} % ascender +\setfontdimen{10}{acccapheight} % accented cap height +\setfontdimen{11}{descender} % descender's depth +\setfontdimen{12}{maxheight} % max height +\setfontdimen{13}{maxdepth} % max depth +\setfontdimen{14}{digitwidth} % digit width +\setfontdimen{15}{verticalstem} % dominant width of verical stems +\setfontdimen{16}{baselineskip} % baselineskip + + +\begincomment +\section{Coding scheme} +\endcomment + +\setstr{codingscheme}{EXTENDED TEX FONT ENCODING - LATIN} + + +\endencoding + + +\section{Discussion} + +As the \texttt{T1} encoding is an established standard, the discussion +of it has already been published elsewhere. [Unfortunately, I do not +know where as it all happened long before I started using \TeX. This +part of the document definitely needs to be improved. To begin with, I +would like to know if the TUGboat articles whose bibliography entries +appear in Figure~\ref{Bib-entries} are relevant for the matter. +\begin{figure*} +\small +\begin{verbatim} +@Article{Beebe:TB11-2-171, + author = "Nelson Beebe", + title = "{Character set encoding}", + journal = j-TUGboat, + volume = "11", + number = "2", + pages = "171--175", + month = jun, + year = "1990", + ISSN = "0896-3207", + bibdate = "Fri Jun 4 18:08:09 MDT 1999", + bibsource = "ftp://ftp.math.utah.edu/pub/tex/bib/tugboat.bib; + http://www.math.utah.edu/pub/tex/bib/index-table-t.html#tugboat", + acknowledgement = ack-bnb # " and " # ack-nhfb, +} +@Article{Bien:TB11-2-175, + author = "Janusz S. Bie{\'n}", + title = "{On standards for computer modern font extensions}", + journal = j-TUGboat, + volume = "11", + number = "2", + pages = "175--183", + month = jun, + year = "1990", + ISSN = "0896-3207", + bibdate = "Fri Jun 4 18:08:09 MDT 1999", + bibsource = "ftp://ftp.math.utah.edu/pub/tex/bib/tugboat.bib; + http://www.math.utah.edu/pub/tex/bib/index-table-t.html#tugboat", + acknowledgement = ack-bnb # " and " # ack-nhfb, +} +@Article{Ferguson:TB11-4-514, + author = "Michael Ferguson", + title = "{Report on multilingual activities}", + journal = j-TUGboat, + volume = "11", + number = "4", + pages = "514--516", + month = nov, + year = "1990", + ISSN = "0896-3207", + bibdate = "Fri Jun 4 18:08:09 MDT 1999", + bibsource = "ftp://ftp.math.utah.edu/pub/tex/bib/tugboat.bib; + http://www.math.utah.edu/pub/tex/bib/index-table-t.html#tugboat", + acknowledgement = ack-bnb # " and " # ack-nhfb, +} +\end{verbatim} +\normalsize + +\caption{Entries in \texttt{tugboat.bib} which may describe papers +that contain (at least part of) the discussion regarding the +\texttt{T1} encoding} +\label{Bib-entries} +\end{figure*} +Actually reading them would be nice too, as would of course getting +the references for whatever other papers there might be that +constituted the discussion of the \texttt{T1} encoding. The file +\texttt{cork.enc} in the \textit{Fontname} standard makes a cryptic +reference to ``TTN 1(4), December 1992'', whatever that might be.] + +I can however answer questions on the more immediate matter of how the +interpretation of the established standard that this file expresses was +constructed. It is mainly the result of a comparison between the +file \texttt{t1.etx}~\cite{t1.etx}, the Unicode +standard~\cite{Unicode}, and the Adobe glyph list~\cite{AGL}. + +(Some concerns have been expressed about the fact that the glyph name +listed for slot~0 is `\texttt{grave}', although that glyph name in +\cite{AGL} corresponds to \textunicode{0060}{GRAVE ACCENT}, whereas +\textunicode{0300}{COMBINING GRAVE ACCENT} is listed as corresponding +to `\texttt{gravecomb}'. This is however formally irrelevant, since +the glyph names are formally only internal labels in the encoding +specification. `\texttt{gravecomb}' would furthermore be a more +impractical label, since most font contains a `\texttt{grave}' glyph +that is used as a combining accent but no `\texttt{gravecomb}' +glyph.) + + +\section{Changes} + +The changes made to this specification since the original 2001/06/19 +version are as follows. + +2001/09/01: Corrected some typos (reported by Vladimir Volovich). /LH + +2001/09/16: Added \cite{latin-page} to the bibliography. /LH + +2001/09/21: Removed comment on \textunicode{2012}{FIGURE DASH} from +slot~\ref{endash}. \cite[Sec.~6.1]{Unicode} makes quite clear that +it's not to be used for ranges. /LH + +2002/07/05: Added the Ferguson:TB11-4-514 and ``TTN~1(4)'' references +to the discussion section. Also added remark on \texttt{grave} versus +\texttt{gravecomb}. /LH + + +\begin{thebibliography}{9} +\bibitem{AGL} + Adobe Systems Incorporated: \textit{Adobe Glyph List}, 1998; + \textsc{http}:/\slash \texttt{partners.adobe.com}\slash + \texttt{asn}\slash \texttt{developer}\slash \texttt{type}\slash + \texttt{glyphlist.txt} +\bibitem{latin-page} + Roman Czyborra: \textit{The ISO 8859 Alphabet Soup}, web page at + \textsc{http:}/\slash \texttt{czyborra.com}\slash + \texttt{charsets}\slash \texttt{iso8859.html}, 1998. +\bibitem{ISO8859-1} + International Organization for Standardization: + \textit{ISO/IEC standard 8859-1} (Information technology -- + 8-bit single-byte coded graphic character sets -- + Part 1: Latin alphabet No. 1). + See also~\cite{latin-page}. +\bibitem{t1.etx} + Alan Jeffrey, Sebastian Rahtz, and Ulrik Vieth: + \textit{The \TeX\ extended text encoding vector}, + version~1.801, 1998, + \textsc{ctan}:\discretionary{}{}{\thinspace}\texttt{fonts}\slash + \texttt{utilities}\slash \texttt{fontinst}\slash + \texttt{inputs}\slash \texttt{etx}\slash \texttt{t1.etx}. +\bibitem{TeXbook} + Donald E.\ Knuth, Duane Bibby (illustrations): + \textit{The \TeX book}, Ad\-di\-son--Wes\-ley, 1986; + ISBN~0-201-13447-0. +\bibitem{Unicode} + The Unicode Consortium (editor), \emph{et al.}: + \textit{The Unicode Standard, Version 3.0}, + Addison Wesley Longman Publisher, 2000; ISBN~0-201-61633-5. + Most of the information in this book is also available online at + the Unicode consortium website, at \textsc{http}:/\slash + \texttt{www.unicode.org}\slash \texttt{unicode}\slash + \texttt{uni2book}\slash \texttt{u2.html}. +\end{thebibliography} + + + +\end{document}
\ No newline at end of file |