--- texttool-architecture/soft-cgi.tex	2004/01/06 21:34:05	1.4
+++ texttool-architecture/soft-cgi.tex	2004/06/01 13:07:27	1.18
@@ -2,11 +2,15 @@
 \label{sec:rec.cgi}
 
 \paragraph
-On the ECHO server, new texts are registered by means of reg.cgi (
-archimedes/web/cgi-bin/toc/admin/reg.cgi ). reg.cgi retrieves a
-metadata file from the entered uri (currently only local paths are
-supported ) and constructs from this file a toc.cgi object file (see
-below) , which it writes to toc.cgi's data section. [corpus???]
+On the ECHO server, the registration of new texts is implemented by
+means of a cgi script, reg.cgi
+(archimedes/web/cgi-bin/toc/admin/reg.cgi ). reg.cgi retrieves a
+metadata file  in MPIWG archive metadata format from the entered uri
+(currently only local paths are supported ) and constructs from this
+file a toc.cgi object file (see below) , which it writes to toc.cgi's
+data section. [corpus???] It should be stressed that this is a
+registration procedure developed for a particular implementation of
+toc.cgi and not a part of the core application. 
 
 \paragraph
 reg.cgi takes two parameters, path and show.  Path should give the
@@ -15,73 +19,143 @@ registered. If ``show'' is set to 1, reg
 inspection the toc.cgi object file that it has built out of the
 submitted metadata file. 
 
+\paragraph{input metadata file}
+
+The input metadata file must have the following form
+
+\begin{verbatim}
+<resource>
+    ...
+    <meta>
+      <meta>
+                <bib type=''Book''>
+
+<title>Mainzer Untergerichtsordnung (von 1534)</title>
+<author>anon</author>
+<year>1580</year>
+        <texttool><display>yes</display>
+        <image>pageimgtif</image>
+        <text>/mpiwg/online/experimental/echo_DRQEdit_test/anon_Mainz_1580/fulltextDW/mainzugo02_utf8.xml</text>
+        <pagebreak>pb</pagebreak><presentation>01-presentation/info.xml</presentation></texttool></meta>
+
+    </meta>
+\end{verbatim}
+
+\paragraph{archimedes object registration}
 
 \subsubsection{toc.cgi (display text)}
 \label{sec:toc.cgi}
 
 \paragraph{plan of this section }
 
-\begin{enumeration}
+\begin{enumerate}
+\item An overview of toc.cgi architecture
 \item A walk-through of typical cgi queries for toc.cgi
 \item An index of cgi parameters and values with short descriptions of function
-\end{enumeration}
+\item The TOC Perl modules
+\end{enumerate}
+
+\paragraph{Overview of toc.cgi architecture}
+
+\subparagraph{}
+toc.cgi is a perl script for displaying collections of xml texts and 
+linking them to related resources such as page-images, morphological
+analysis, commentaries, dictionaries, etc. It implements generic methods
+for resource-linking provided by a series of perl modules which are in
+turn based mainly on generic open-source tools for xml manipulation and networking
+written in C. 
+
+\subparagraph{toc.cgi collections--Network transparency}
+Each of the collections in toc.cgi is a ``virtual'' collection, that
+is, a collection of links or uri's to resources that reside somewhere on an accessible
+network, local or remote.  
+
+\subparagraph{toc.cgi collections--remote resources}
+
+What is at the other end of the link is of no concern to toc.cgi, as
+long as the resource referenced by the link meets minimal toc.cgi
+requirements--how the resource is actually implemented and exposed is
+a matter for the resource provider. The link may, for instance, point
+directly to an xml text or it may point to a container which exposes a
+particular xml view of an underlying resource that is perhaps not in
+xml format at all. 
+
+
+\subparagraph{resource registry}
+
+
+
 
 \paragraph{cgi parameters -- standard queries}
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=corpus }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=corpus }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=corpus }
 \newline
 \newline
 get a listing of corpora
 
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpusmanifest }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpusmanifest }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpusmanifest }
 \newline
 \newline
 get an xml listing of corpora 
 
-
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi }
 \newline
 \newline
 get a listing of works in default corpus
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?corpus=1 }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?corpus=1 }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?corpus=1 }
 \newline
 \newline
 get a listing of works in corpus 1 [default corpus = 0]
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpuslist }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpuslist }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpuslist }
 \newline
 \newline
 get an xml listing of works in default corpus 
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpuslist;corpus=1 }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpuslist;corpus=1 }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?step=xmlcorpuslist;corpus=1 }
 \newline
 \newline
 get an xml listing of works in corpus 1
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=baifl_renav_006_la_1537;step=thumb }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=baifl_renav_006_la_1537;step=thumb }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=baifl_renav_006_la_1537;step=thumb }
 \newline
 \newline
 get a work from default corpus with thumbnail navbar displayed left
 
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=jorda_ponde_050_la_1533;step=thumb;ftype=thumbright }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=jorda_ponde_050_la_1533;step=thumb;ftype=thumbright }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=jorda_ponde_050_la_1533;step=thumb;ftype=thumbright }
 \newline
 \newline
 get a work from default corpus with thumbnail navbar displayed right
 
-\htmladdnormallink{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=jorda_ponde_050_la_1533;step=textonly;corpus=;page=22 }{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=jorda_ponde_050_la_1533;step=textonly;corpus=;page=22 }
+\url{ http://archimedes.mpiwg-berlin.mpg.de/cgi-bin/toc/toc.cgi?dir=jorda_ponde_050_la_1533;step=textonly;corpus=;page=22 }
 \newline
 \newline
 get a page of text from a work from default corpus 
 
 
+\paragraph{TOC Perl Modules}
+\subparagraph{general}The documentation for the Toc Perl Modules is
+located in the modules themselves in POD format. The POD is the
+definitive documentation for the modules. 
+
+The modules are available to archimedes staff from cvs on the archimedes server at
+141.14.236.86:/perseus/cvsroot in the module
+/perseus/cvsroot/mpitexts/perl/perllib. To get them, log on to the
+archimedes server and use the commandline command: 
+\begin{verbatim}
+        cvs -d /perseus/cvsroot co /perseus/cvsroot/mpitexts/perl/perllib
+\end{verbatim}
+
+or from a remote location
+
+\begin{verbatim}
+      bash; export CVS_RSH=ssh; cvs -d :ext:myusername@141.14.236.86:/perseus/cvsroot co /perseus/cvsroot/mpitexts/perl/perllib
+\end{verbatim}
 
-
-\subsubsection{Indexing}
-\label{sec:indexing}
-
+\input{soft-search}
 
 \subsubsection{Morphology}
 \label{sec:morphology}
@@ -91,6 +165,56 @@ get a page of text from a work from defa
 \label{sec:dictionary-server}
 
 
+\subsubsection{helper programs}
+
+\paragraph{addarch.pl ARCHIMEDES} 
+
+Automatically registers new texts as toc.cgi objects when they appear in
+cvs. Automatically updates relevant morphological indices (slow!) each
+time a cvs update occurs. This program is called by a hook in the cvs
+``loginfo'' configuration file. 
+
+
+\paragraph{makelemma.pl ARCHIMEDES}
+
+Updates lemmatization indices. 
+Parameters: 
+No parameter--update all lemmatization indices
+[latin | ital | greek | en | nl | de]--  update this language
+
+\paragraph{makefast.pl ARCHIMEDES} 
+
+Updates the toc.cgi morphology indices
+Parameters
+No parameter--update all lemmatization indices
+[latin | ital | greek | en | nl | de]--  update this language
+
+\subsubsection{summary of differences btwn the archimedes toc.cgi
+  implementation and the echo toc.cgi impelementation (toc.x.cgi)}
+
+\paragraph{missing in archimedes}
+\begin{enumerate}
+
+\item html templates (coded but phased out of cvs branch)
+\end{enumerate}
+
+\paragraph{missing in echo}
+\begin{enumerate}
+
+\item word-coloring?
+\item remote text method may work differently
+
+
+
+\end{enumerate}
+\paragraph{differences}
+\begin{enumerate}
+\item structure of info.xml
+\item resource-discovery algorithm for info.xml
+\end{enumerate}
+
+
+
 %%% Local Variables: 
 %%% mode: latex
 %%% TeX-master: "texttools"