diff options
Diffstat (limited to 'Master/texmf-dist/doc/fonts/itrans/icsx.itx')
| -rw-r--r-- | Master/texmf-dist/doc/fonts/itrans/icsx.itx | 395 |
1 files changed, 395 insertions, 0 deletions
diff --git a/Master/texmf-dist/doc/fonts/itrans/icsx.itx b/Master/texmf-dist/doc/fonts/itrans/icsx.itx new file mode 100644 index 00000000000..cd6ab99b1ca --- /dev/null +++ b/Master/texmf-dist/doc/fonts/itrans/icsx.itx @@ -0,0 +1,395 @@ +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% CS/CSX Encoding User Doc for ITRANS (Version 4.00 and above) +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +\documentclass[11pt]{article} +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +\usepackage[preprocess]{itrans} % Ross Moore's extensions to latex2html + +\usepackage{html} % from standard latex2html package + % if you do not have html.sty in your machine, change the html to + % htmlstub (htmlstub.sty is included in the ITRANS/lib directory) +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +#useshortmarkers % ITRANS command. Allows me to use ## + % instead of #indian and #endindian + % June '98: changed all ## to #indian, to allow + % the use of Ross Moore's latex2html ITRANS + % extensions. + +#usecsx % ITRANS command. Accept CS/CSX encoded text. +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +% -- devanagari +#hindiifm=dvng.ifm % ITRANS command +#hindifont=\fransdvng % ITRANS command: argument specifies use of + % Frans's font, fransdvng is a command defined + % in idevn.tex (itrans.sty loads this) + +%begin{latexonly} +\let\usedvng=\largedvng % override the default size (normaldvng) +%end{latexonly} + +% -- telugu +\newfont{\tlg}{tel18} +\hyphenchar\tlg=-1 % disable hyphenation using this font + +#teluguifm=tlgutx.ifm +#telugufont=\tlg +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +\portraitpage % from itrans.sty/idevn.tex (also: \landscapepage) +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +\def\diatop[#1|#2]{{\setbox1=\hbox{{#1{}}}\setbox2=\hbox{{#2{}}}% + \dimen0=\ifdim\wd1>\wd2\wd1\else\wd2\fi% + \dimen1=\ht2\advance\dimen1by-1ex% + \setbox1=\hbox to1\dimen0{\hss#1\hss}% + \rlap{\raise1\dimen1\box1}% + \hbox to1\dimen0{\hss#2\hss}}}% +%e.g. of use: \diatop[\'|{\=o}] gives u macron acute + +\begin{document} + +\footnotetext[0]{Last modification: \today} + +\centerline{\bf Transliteration Map} +\medskip +\centerline{\LARGE\bf CS/CSX Encoding} +\medskip +\centerline{\bf itrans} +\smallskip +\centerline{\bf \copyright 1994--1998 Avinash Chopde} + +\section{CS/CSX Encoding} + +During the 8th World Sanskrit Conference, Vienna 1990, a panel +was held to discuss the standardization of Sanskrit for +electronic data transfer. +Dominik Wujastyk presented a paper, titled ``Standardization of Sanskrit for +Electronic Data Transfer and Screen Representation,'' which outlines the +Classical Sanskrit and Classical Sanskrit Extended Encoding. +The original paper is available in a .zip archive, named ``iass.zip''. +Use archie to locate FTP sites that store iass.zip, if you need the original +paper, as of this writing, it was available at: +{\verb= ftp.bcc.ac.uk:/pub/users/ucgadkw/indology=}. + +{\sc itrans} now supports CS/CSX, in a limited form. + +To turn on recognition of CS/CSX encoded text, use this command before +the CS encoded text: + +{\tt \char35 usecsx} + +If necessary, you can turn off recognition of CS/CSX encoded text (and revert +to ITRANS only encoding), by using this command: + +{\tt \char35 ignorecsx} + +Both +{\tt \char35 usecsx} +and +{\tt \char35 ignorecsx} +apply to the text that follows in the file. + +\subsection{Avoid Capitals or Uppercase Characters} + +CS/CSX is a case-insensitive encoding, both uppercase and lowercase +characters have the same meaning, but ITRANS is case-sensitive. +Thus, an uppercase character in ITRANS is encoded to a different devanagari +character from its lowercase counterpart. + +This means that when you create input text in CSX, do not use uppercase +characters. ITRANS differentiates between lower case and uppercase characters. +For example, entering {\tt la} results in #hindi la#endhindi, but entering +{\tt La} results in a different character: #hindi La#endhindi. + +(If you already have input text that is in CS/CSX encoding and it also uses +uppercase characters, use some text editor or word processor to convert +all the uppercase characters to lowercase. This can be done easily using +the text editors such as emacs, or programs such as {\tt tr} (available +on UNIX machines, and also available for MS-DOS systems).) + +Table~\ref{ienc} provides the complete input encoding +accepted by ITRANS. +Note that technically, this uppercase character limitation +applies only to the ASCII character codes (those +less than 128). CS/CSX character codes over 128 are handled correctly +in ITRANS (by correct, I mean handling them with CS/CSX meanings). +But, it is simpler to just avoid using any uppercase characters at all. +The tables in this document should clarify all this. + +Table~\ref{csx} lists the non-ASCII character codes (128 to 255) +accepted by ITRANS. + +%------------------------------------------------------------------------ +\begin{htmlonly} +\subsection{CS/CSX Table of non-ASCII codes (128 to 255)} +\end{htmlonly} + +% Table 1 +\begin{table}[ht] +\begin{center} +\hspace*{-20pt}\begin{tabular}{cc} +\begin{makeimage} +\begin{tabular}{|c|c|c|} +\hline +devanagari & {\sc cs/csx} char & {\sc cs/csx} char code \\ \hline +{#hindi aa #endhindi} & {\a=a} & {\tt 224} \\ \hline +{#hindi aa #endhindi} & {\a=A} & {\tt 226} \\ \hline +{#hindi uu #endhindi} & {\a=u} & {\tt 229} \\ \hline +{#hindi uu #endhindi} & {\a=U} & {\tt 230} \\ \hline +{#hindi R^i #endhindi} & {\d r} & {\tt 231} \\ \hline +{#hindi R^i #endhindi} & {\d R} & {\tt 232} \\ \hline +{#hindi R^I #endhindi} & {\diatop[\a=|\d r]} & {\tt 233} \\ \hline +{#hindi R^I #endhindi} & {\diatop[\a=|\d R]} & {\tt 234} \\ \hline +{#hindi L^i #endhindi} & {\d l} & {\tt 235} \\ \hline +{#hindi L^i #endhindi} & {\d L} & {\tt 236} \\ \hline +{#hindi L^I #endhindi} & {\diatop[\a=|\d l]} & {\tt 237} \\ \hline +{#hindi L^I #endhindi} & {\diatop[\a=|\d L]} & {\tt 238} \\ \hline +{#hindi ~Na #endhindi} & {\.n} & {\tt 239} \\ \hline +{#hindi ~Na #endhindi} & {\.N} & {\tt 240} \\ \hline +{#hindi ~na #endhindi} & {\~ n} & {\tt 164} \\ \hline +{#hindi Ta #endhindi} & {\d t} & {\tt 241} \\ \hline +{#hindi Ta #endhindi} & {\d T} & {\tt 242} \\ \hline +{#hindi Tha #endhindi} & {\d th} & {\tt 241 + h} \\ \hline +{#hindi Tha #endhindi} & {\d Th} & {\tt 242 + h} \\ \hline +\multicolumn{3}{c}{ } +\end{tabular} +\end{makeimage} +& +\begin{makeimage} +\begin{tabular}{|c|c|c|} +\hline +devanagari & {\sc cs/csx} char & {\sc cs/csx} char code \\ \hline +{#hindi Da #endhindi} & {\d d} & {\tt 243} \\ \hline +{#hindi Da #endhindi} & {\d D} & {\tt 244} \\ \hline +{#hindi Dha #endhindi} & {\d dh} & {\tt 243 + h} \\ \hline +{#hindi Dha #endhindi} & {\d Dh} & {\tt 244 + h} \\ \hline +{#hindi Na #endhindi} & {\d n} & {\tt 245} \\ \hline +{#hindi Na #endhindi} & {\d N} & {\tt 246} \\ \hline +{#hindi sha #endhindi} & {\a's} & {\tt 247} \\ \hline +{#hindi sha #endhindi} & {\a'S} & {\tt 248} \\ \hline +{#hindi shha #endhindi} & {\d s} & {\tt 249} \\ \hline +{#hindi shha #endhindi} & {\d S} & {\tt 250} \\ \hline +{#hindi La #endhindi} & {\b l} & {\tt 215} \\ \hline +{#hindi .n #endhindi} & {\d m} & {\tt 252} \\ \hline +{#hindi .n #endhindi} & {\d M} & {\tt 253} \\ \hline +{#hindi .n #endhindi} & {\. m} & {\tt 167} \\ \hline +{#hindi H #endhindi} & {\d h} & {\tt 254} \\ \hline +{#hindi H #endhindi} & {\d H} & {\tt 255} \\ \hline +{#telugu Ra #endtelugu (telugu)} & {\b r} & {\tt 159} \\ \hline +\end{tabular} +\end{makeimage} +\end{tabular} +\end{center} +\caption {{\bf CS/CSX Mapping} (shows non-ASCII char codes only).} +\label{csx} +\end{table} + +\subsection{Incomplete CS/CSX Support} + +There are many characters in CS/CSX that are currently not mapped by ITRANS, +simply because I do not know what devanagari characters (if any) they +stand for. + +For example, \~ l is present in the CS table, but I don't know what +it represents, so, it is currently unrecognized by ITRANS. +If you find such gaps and know what devanagari or tamil or telugu character +it stands for, please send me e-mail, so that I can include it in the +next release of ITRANS. My e-mail address is available elsewhere in this +document. +Feel free to send me mail on any other issues regarding CS/CSX support +in ITRANS, too. + +\subsection{Breaking the lexical scan in ITRANS} + +ITRANS always matches the largest possible input sequence when scanning +the input. Thus, in devanagari, {\tt sha} will produce #hindi sha #endhindi even when +usecsx is in effect. +If instead you need ITRANS to recognize it as two different consonants, +you should use the lexical scan break character, the underscore. +Thus, typing {\tt s\_ha} will result in #hindi s_ha #endhindi. + +This is a thing to watch out for in all cases where some character has +a multiple letter mapping, and each letter by itself also represents some +other character. +In the above example, {\tt sh} is the two letter map, and both +{\tt s} and {\tt h} represent other characters. + +\section{ITRANS Encoding Accepted along with CS/CSX} + +Even when {\tt \char35usecsx} is in effect, the other ITRANS mappings +are still accepted. +Actually, even without the usecsx command, ITRANS will still accept all +the CS/CSX character codes. The only reason the usecsx command is needed +is to disambiguate the #hindi ca #endhindi and #hindi cha #endhindi characters. ITRANS by default +uses {\tt cha} and {\tt chha} to denote #hindi ca #endhindi and #hindi cha #endhindi, but CS/CSX +uses {\tt ca} and {\tt cha}. To handle this difference, the +{\tt \char35usecsx} command had to be introduced. + +Though this document shows only the Devanagari script, CS/CSX can be used +in ITRANS with every Indic Script that ITRANS supports. +For more details on those languages, consult the documentation for that +specific language. For Devanagari, consult dnvc.itx or dvng.itx, for Tamil, +tamil.itx, for Bengali, beng.itx, for Telugu tlgutx.itx, for Punjabi +pundoc.itx, for Romanized Sanskrit romancsx.itx. + +\subsection{Converting CSX Encoding to ITRANS Encoding} + +Sometimes, it is useful to convert input text from the 8-bit CS/CSX encoding +to the 7-bit ITRANS Encoding (ASCII text). +Many computers still do not have good 8-bit editing tools, and even if +such tools are present, the CS/CSX font may not be available, in which case +editing CSX texts becomes cumbersome. + +To convert input text from CS/CSX encoding to ITRANS encoding, the program +{\bf csx2i} has been provided. It is present in the {\tt src/} directory +of the ITRANS distribution. For x86 MS-DOS compatible machines, an executable +is also provided. Given a file called {\tt input.csx} which contains +text in CS/CSX encoding, to convert it to ITRANS encoding in a file called +{\tt output}, run it like this: + +{\tt csx2i < input.csx > output} + +C-source code to csx2i is provided, in file csx2i.c, and it should compile +easily on every platform. + +Once the file {\tt output} is checked over for manual corrections, you +can embed that text in between ITRANS commands, and process it like any +other ITRANS input file. + +\vfill + +\subsection{Author} + +\noindent +ITRANS has been developed by Avinash Chopde. \\ +E-mail: +\htmladdnormallink{\texttt{avinash@acm.org}}{mailto:avinash@acm.org}. \\ +Home page: +\htmladdnormallink{\texttt{http://www.aczone.com/}}{http://www.aczone.com/} + +\bigskip +\hrule +%------------------------------------------------------------------- +\begin{htmlonly} +\section{Devanagari Table} +\end{htmlonly} + +\begin{table}[hp] +\begin{center} +\begin{tabular}{c@{\hspace{1in}}c@{\hspace{1in}}c} +% --- first col is vowels inside a tabular +\begin{makeimage} +\begin{tabular}{|c|c|} +\multicolumn{2}{c}{Vowels} \\ +\hline +{#hindi a #endhindi} & {\tt a} \\ \hline +{#hindi aa #endhindi} & {\tt aa {\it or} A} \\ \hline +{#hindi i #endhindi} & {\tt i} \\ \hline +{#hindi ii #endhindi} & {\tt ii {\it or} I} \\ \hline +{#hindi u #endhindi} & {\tt u} \\ \hline +{#hindi uu #endhindi} & {\tt uu {\it or} U} \\ \hline +{#hindi R^i #endhindi} & {\tt RRi {\it or} R\char`^i} \\ \hline +{#hindi R^I #endhindi} & {\tt RRI {\it or} R\char`^I} \\ \hline +{#hindi L^i #endhindi} & {\tt LLi {\it or} L\char`^i} \\ \hline +{#hindi L^I #endhindi} & {\tt LLI {\it or} L\char`^I} \\ \hline +{#hindi e #endhindi} & {\tt e} \\ \hline +{#hindi ai #endhindi} & {\tt ai} \\ \hline +{#hindi o #endhindi} & {\tt o} \\ \hline +{#hindi au #endhindi} & {\tt au} \\ \hline +{#hindi aM #endhindi} & {\tt {\it a}M} \\ \hline +{#hindi aH #endhindi} & {\tt {\it a}H} \\ \hline +\multicolumn{2}{c}{} \\ +\multicolumn{2}{c}{} \\ +\multicolumn{2}{c}{Digits} \\ +\hline +{#hindi 0 #endhindi} & {\tt 0} \\ \hline +{#hindi 1 #endhindi} & {\tt 1} \\ \hline +{#hindi 2 #endhindi} & {\tt 2} \\ \hline +{#hindi 3 #endhindi} & {\tt 3} \\ \hline +{#hindi 4 #endhindi} & {\tt 4} \\ \hline +{#hindi 5 #endhindi} & {\tt 5} \\ \hline +{#hindi 6 #endhindi} & {\tt 6} \\ \hline +{#hindi 7 #endhindi} & {\tt 7} \\ \hline +{#hindi 8 #endhindi} & {\tt 8} \\ \hline +{#hindi 9 #endhindi} & {\tt 9} \\ \hline +\end{tabular} +\end{makeimage} +% --- end first col +& +% --- second col is consonants +\begin{makeimage} +\begin{tabular}{|c|c|} +\multicolumn{2}{c}{Consonants} \\ +\hline +{#hindi ka #endhindi} & {\tt k{\it a}} \\ \hline +{#hindi kha #endhindi} & {\tt kh{\it a}} \\ \hline +{#hindi ga #endhindi} & {\tt g{\it a}} \\ \hline +{#hindi gha #endhindi} & {\tt gh{\it a}} \\ \hline +{#hindi ~Na #endhindi} & {\tt \char`~N{\it a or} N\char`^{\it a}} \\ \hline +{#hindi ca #endhindi} & {\tt c{\it a}} \\ \hline +{#hindi cha #endhindi} & {\tt ch{\it a or} chh{\it a}} \\ \hline +{#hindi ja #endhindi} & {\tt j{\it a}} \\ \hline +{#hindi jha #endhindi} & {\tt jh{\it a}} \\ \hline +{#hindi ~na #endhindi} & {\tt \char`~n{\it a or} JN{\it a}} \\ \hline +{#hindi Ta #endhindi} & {\tt T{\it a}} \\ \hline +{#hindi Tha #endhindi} & {\tt Th{\it a}} \\ \hline +{#hindi Da #endhindi} & {\tt D{\it a}} \\ \hline +{#hindi Dha #endhindi} & {\tt Dh{\it a}} \\ \hline +{#hindi Na #endhindi} & {\tt N{\it a}} \\ \hline +{#hindi ta #endhindi} & {\tt t{\it a}} \\ \hline +{#hindi tha #endhindi} & {\tt th{\it a}} \\ \hline +{#hindi da #endhindi} & {\tt d{\it a}} \\ \hline +{#hindi dha #endhindi} & {\tt dh{\it a}} \\ \hline +{#hindi na #endhindi} & {\tt n{\it a}} \\ \hline +{#hindi pa #endhindi} & {\tt p{\it a}} \\ \hline +{#hindi pha #endhindi} & {\tt ph{\it a}} \\ \hline +{#hindi ba #endhindi} & {\tt b{\it a}} \\ \hline +{#hindi bha #endhindi} & {\tt bh{\it a}} \\ \hline +{#hindi ma #endhindi} & {\tt m{\it a}} \\ \hline +{#hindi ya #endhindi} & {\tt y{\it a}} \\ \hline +{#hindi ra #endhindi} & {\tt r{\it a}} \\ \hline +{#hindi la #endhindi} & {\tt l{\it a}} \\ \hline +{#hindi va #endhindi} & {\tt v{\it a or} w{\it a}} \\ \hline +{#hindi sha #endhindi} & {\tt sh{\it a}} \\ \hline +{#hindi Sha #endhindi} & {\tt Sh{\it a or} shh{\it a}} \\ \hline +{#hindi sa #endhindi} & {\tt s{\it a}} \\ \hline +{#hindi ha #endhindi} & {\tt h{\it a}} \\ \hline +{#hindi La #endhindi} & {\tt ld{\it a or} L{\it a}} \\ \hline +{#hindi kSha #endhindi} & {\tt kSh{\it a or} x{\it a}} \\ \hline +{#hindi j~na #endhindi} & {\tt j\char`~n{\it a or} GY{\it a}} \\ \hline +\end{tabular} +\end{makeimage} +% --- end second col +& +% --- third col of specials/accents inside a tabular +\begin{makeimage} +\begin{tabular}{|c|c|} +\multicolumn{2}{c}{Specials/Accents} \\ +\hline +{#hindi qa #endhindi} & {\tt q{\it a}} \\ \hline +{#hindi Ka #endhindi} & {\tt K{\it a}} \\ \hline +{#hindi Ga #endhindi} & {\tt G{\it a}} \\ \hline +{#hindi za #endhindi} & {\tt J{\it a or} z{\it a}} \\ \hline +{#hindi fa #endhindi} & {\tt f{\it a}} \\ \hline +{#hindi .Da #endhindi} & {\tt .D{\it a}} \\ \hline +{#hindi .Dha #endhindi} & {\tt .Dh{\it a}} \\ \hline +{#hindi AUM #endhindi} & {\tt AUM} or {\tt OM} \\ \hline +{#hindi Rga #endhindi} & {\tt R{\it ga}} \\ \hline +{#hindi rga #endhindi} & {\tt rga {\it or} {\it ga}\char`^r} \\ \hline +{#hindi ga.n #endhindi} & {\tt {\it ga}.n} \\ \hline +{#hindi aa.c #endhindi} & {\tt {\it aa}.c} \\ \hline +{#hindi Da.N #endhindi} & {\tt {\it Da}.N} \\ \hline +{#hindi D.h #endhindi} & {\tt {\it D}.h} \\ \hline +{#hindi duH #endhindi} & {\tt {\it du}H} \\ \hline +{#hindi .a #endhindi} & {\tt .a} \\ \hline +\end{tabular} +\end{makeimage} +\\ +\end{tabular} % end the larger tabular encompassing all four tables +\hfill +\\ +\end{center} +\caption {{\bf ITRANS: Devanagari to English with \char35usecsx} (in addition to Table 1).} +\label{ienc} +\end{table} + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% +\end{document} |