From c41c28e8b22ec1f316aa705939e021f6ec59cdaa Mon Sep 17 00:00:00 2001 From: Robert Alessi Date: Mon, 4 Jul 2016 21:07:54 +0200 Subject: done documenting the Buckwalter input scheme; getting close to v1.4 --- arabluatex.dtx | 151 ++++++++++++++++++++++++++++++++++++++++++++++++++++- arabluatex_voc.lua | 5 ++ 2 files changed, 154 insertions(+), 2 deletions(-) diff --git a/arabluatex.dtx b/arabluatex.dtx index 736c44d..7f5246c 100644 --- a/arabluatex.dtx +++ b/arabluatex.dtx @@ -1932,6 +1932,153 @@ muhaddamaTaN mi'_danatu-hu}: \arb[trans]{ra'aytu % \end{arab} % \SetTranslitConvention{dmg} % +% \section{Buckwalter input scheme} +% \label{sec:buckwalter-scheme} +% \NEWfeature{v1.4} Even though \package{arabluatex} is primarily +% designed to process the Arab\TeX\ notation, it can also process the +% Buckwalter input scheme to a large extent.\footnote{See +% \url{http://www.qamus.org/transliteration.htm}} The Buckwalter +% scheme is actually processed in two steps, as it is first converted +% into Arab\TeX. Then, once this is accomplished, the Arab\TeX\ scheme +% is processed through the above described functions. In this way, the +% Buckwalter input scheme can make the most of the +% \package{arabluatex} special features that are presented in +% \vref{sec:options}. +% +% \DescribeMacro{\SetInputScheme} The input scheme, which is set to +% |arabtex| by default, may be changed at any point of the document by +% the command \cs{SetInputScheme}\marg{scheme}, where \meta{scheme} +% may be either |arabtex| or |buckwalter|. This command is also +% accepted in the preamble should one wish to set the input scheme +% globally, like so:--- +% \iffalse +%<*example> +% \fi +\begin{arabluaverbatim} +\usepackage{arabluatex} +\SetInputScheme{buckwalter} +\end{arabluaverbatim} +% \iffalse +% +% \fi +% +% \paragraph{Limitations} +% To date, the following two limitations apply: +% \begin{compactenum}[(a)] +% \item The braces |{| and |}|, which are used in Buckwalter scheme to +% encode \arb[novoc]{"a} and \arb[novoc]{y"'}, must be replaced with +% square brackets viz. |[| and |]| respectively. +% \item The underscore character |_|, which is used in Buckwalter +% scheme to encode the Arabic \arb[trans]{ta.twIl} must be replaced +% with a double hyphen |--| (see above \vref{sec:tatwil}). +% \end{compactenum} +% +% \Cref{tab:buckwalter-scheme} gives the Buckwalter equivalents that +% are currently used by \package{arabluatex}. The additional +% characters that are defined in \vref{tab:additional-arabic-codings} +% are also available. +% \begin{longtable}{llll} +% \captionlistentry{Buckwalter scheme}\\[-1em] +% \toprule +% Letter & \multicolumn{2}{l}{Transliteration\footnotemark} +% & Buckwalter notation \\ +% & \texttt{dmg} & \texttt{loc} & \\ \midrule +% \endfirsthead +% \toprule +% Letter & \multicolumn{2}{l}{Transliteration} +% & Buckwalter notation \\ +% & \texttt{dmg} & \texttt{loc} & \\ \midrule +% \endhead \footnotetext{See \vref{sec:transliteration}.} +% \label{tab:buckwalter-scheme} +% \arb[novoc]{a} & \dmg{a} & \loc{a} & \verb|A| \\ +% \arb[novoc]{b} & \dmg{b} & \loc{b} & |b| \\ +% \arb[novoc]{t} & \dmg{t} & \loc{t} & |t| \\ +% \arb[novoc]{_t} & \dmg{_t} & \loc{_t} & |v|\\ +% \arb[novoc]{j} & \dmg{j} & \loc{j} & |j| \\ +% \arb[novoc]{.h} & \dmg{.h} & \loc{.h} & |H| \\ +% \arb[novoc]{x} & \dmg{x} & \loc{x} & |x|\\ +% \arb[novoc]{d} & \dmg{d} & \loc{d} & |d| \\ +% \arb[novoc]{_d} & \dmg{_d} & \loc{_d} & |*| \\ +% \arb[novoc]{r} & \dmg{r} & \loc{r} & |r| \\ +% \arb[novoc]{z} & \dmg{z} & \loc{z} & |z| \\ +% \arb[novoc]{s} & \dmg{s} & \loc{s} & |s| \\ +% \arb[novoc]{^s} & \dmg{^s} & \loc{^s} & |$| \\ +% \arb[novoc]{.s} & \dmg{.s} & \loc{.s} & |S| \\ +% \arb[novoc]{.d} & \dmg{.d} & \loc{.d} & |D| \\ +% \arb[novoc]{.t} & \dmg{.t} & \loc{.t} & |T| \\ +% \arb[novoc]{.z} & \dmg{.z} & \loc{.z} & |Z| \\ +% \arb[novoc]{`} & \dmg{`} & \loc{`} & |E| \\ +% \arb[novoc]{.g} & \dmg{.g} & \loc{.g} & |g| \\ +% \arb[novoc]{f} & \dmg{f} & \loc{f} & |f| \\ +% \arb[novoc]{q} & \dmg{q} & \loc{q} & |q| \\ +% \arb[novoc]{k} & \dmg{k} & \loc{k} & |k| \\ +% \arb[novoc]{l} & \dmg{l} & \loc{l} & |l| \\ +% \arb[novoc]{m} & \dmg{m} & \loc{m} & |m| \\ +% \arb[novoc]{n} & \dmg{n} & \loc{n} & |n| \\ +% \arb[novoc]{h} & \dmg{h} & \loc{h} & |h| \\ +% \arb[novoc]{w} & \dmg{w} & \loc{w} & |w| \\ +% \arb[novoc]{y} & \dmg{y} & \loc{y} & |y| \\ +% \arb[novoc]{T} & \dmg{aT} & \loc{aT} & |p| \\ +% \midrule +% \arb[novoc]{|"'} & \dmg{|"'} & \loc{|"'} & \verb|'| \\ +% \arb[novoc]{A"'} & \dmg{A"'} & \loc{A"'} & \verb+|+ \\ +% \arb[novoc]{a"'} & \dmg{a"'} & \loc{a"'} & \verb|>| \\ +% \arb[novoc]{w"'} & \dmg{w"'} & \loc{w"'} & \verb|&| \\ +% \arb[novoc]{i"'} & \dmg{i"'} & \loc{i"'} & \verb|<| \\ +% \arb[novoc]{y"'} & \dmg{y"'} & \loc{y"'} & \verb|]| \\ +% \midrule +% \arb[novoc]{BB} & --- & --- & \verb|~| \\ +% \arb[novoc]{"a} & ' & ' & |[| \\ +% \midrule +% \arb[voc]{Ba} & \dmg{Ba} & \loc{Ba} & \verb|a| \\ +% \arb[voc]{Bu} & \dmg{Bu} & \loc{Bu} & \verb|u| \\ +% \arb[voc]{Bi} & \dmg{Bi} & \loc{Bi} & \verb|i| \\ +% \arb[voc]{BaN} & \dmg{BaN} & \loc{BaN} & \verb|F| \\ +% \arb[voc]{BuN} & \dmg{BuN} & \loc{BuN} & \verb|N| \\ +% \arb[voc]{BiN} & \dmg{BiN} & \loc{BiN} & \verb|K| \\ +% \arb[voc]{B"} & --- & --- & \verb|o| \\ +% \midrule +% \arb[novoc]{B_a} & \dmg{B_a} & \loc{B_a} & |`| \\ +% \midrule +% \arb[novoc]{--} & --- & --- & |--| (\arb[trans]{ta.twIl})\\ +% \bottomrule +% \caption*{\Cref*{tab:buckwalter-scheme}: Buckwalter scheme} +% \end{longtable} +% +% \paragraph{Transliteration} +% The Buckwalter notation can also be transliterated into any accepted +% romanization standard of Arabic. See above +% \vref{sec:transliteration} for more information. However, it should +% be pointed out again that only accurate coding produces accurate +% transliteration. It is therefore at the very least highly advisable +% to use the hyphen for tying the definite article and the inseparable +% particles (viz. prepositions, adverbs and conjunctions) to words, +% like so:--- \SetInputScheme{buckwalter} +% \begin{quote} +% |Al-EaAlamu| \arb{Al-EaAlam-u} \arb[trans]{Al-EaAlam-u}, +% |Al-$~amsu| \arb{Al-$~ams-u} \arb[trans]{Al-$~ams-u}, +% |bi-SinaAEapi| |Al-T~ib~i|, \arb{bi-SinaAEap-i Al-T~ib~-i} +% \arb[trans]{bi-SinaAEap-i Al-T~ib~-i}. +% +% |wa-Al-l~`hi| \arb{wa-Al-l~`h-i} \arb[trans]{wa-Al-l~`h-i}, +% |Al-Hamdu| |li-l~`hi| \arb{Al-Hamd-u li-l~`h-i} +% \arb[trans]{Al-Hamd-u li-l~`h-i}. +% \end{quote} +% \SetInputScheme{arabtex} +% +% Similary, it is not advisable to use \verb+|+ and |[| to encode the +% \arb[trans]{'alif-u 'l-mamdUdaT-i} and the \arb[trans]{'alif-u +% 'l-wa.sl-i} for such signs can be generated by \package{arabluatex}. +% Besides, as they do not \emph{per se} convey any morphological +% information on what they are derived from, they cannot be +% transliterated accurately. To take one example, % +% \SetInputScheme{buckwalter}% +% |ilY Al-[ntiqaADi} as expected, but +% only |