source: documented-example-collections/trunk/wiki-e/etc/collect.cfg@ 18807

creator     [email protected]
maintainer  [email protected]
public      true

buildtype   mgpp

#indexes    document:text document:Title document:Source
indexes     text Title Source
defaultindex    text

levels  document

plugin      GAPlug
plugin      PDFPlug
plugin      WordPlug
plugin      NULPlug
plugin      MetadataXMLPlug
plugin      MediaWikiPlug -searchbox_div_exp <div([^>]*)id=(\"|')p-search(\"|')(.|\n)*?</div> -show_toc -delete_toc -remove_title_suffix_exp " - (.*)" -toc_exp <table([^>]*)id=(\"|')toc(\"|')(.|\n)*?</table>\n -nav_div_exp <div([^>]*)id=(\"|')p-navigation(\"|')(.|\n)*?</div> -delete_searchbox -delete_nav
plugin      ArcPlug
plugin      RecPlug

classify    AZList -metadata Title
classify    AZList -metadata Source

format VList "<td valign=\"top\">[link][icon][/link]</td>
<td valign=\"top\">[ex.srclink]{Or}{[ex.thumbicon],[ex.srcicon]}[ex./srclink]</td>
<td valign=\"top\">[highlight]
{Or}{[dc.Title],[exp.Title],[ex.Title],Untitled}
[/highlight]{If}{[ex.Source],<br><i>([ex.Source])</i>}</td>"

format HList "[link][highlight][ex.Title][/highlight][/link]"

format DocumentHeading "{Or}{[parent(Top):Title],[Title],untitled}<br>"

format DocumentText "[Text]"

format DocumentButtons "Detach|Highlight"

format SearchTypes "plain,form"

collectionmeta  collectionname [l=en] "wiki"
collectionmeta  .document:text [l=en] "text"
collectionmeta  .document:Title [l=en] "titles"
collectionmeta  .document:Source [l=en] "filenames"
collectionmeta  .text [l=en] "text"
collectionmeta  .Title [l=en] "titles"
collectionmeta  .Source [l=en] "filenames"

# -- English text ----------------
collectionmeta  collectionextra [l=en] "This demonstration collection is made from the Greenstone Wiki website. It shows off the new feature of building a Greenstone collection from a MediaWiki website in Greestone.\n

<h3>How the collection works</h3>\n

<p>
The <a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>collection configuration file</a> contains nine plugins <i>MediaWikiPlug</i>, <i>ImagePlug</i>, <i>ZipPlug</i>, <i>PDFPlug</i>, <i>PPTPlug</i>, <i>WordPlug</i> (along with the standard three <i>GAPlug</i>, <i>ArcPlug</i> and <i>RecPlug</i>). The <i>MediaWikiPlug</i> handles the HTML pages downloaded from a MediaWiki website, while the <i>ImagePlug</i>, <i>ZipPlug</i>, <i>PDFPlug</i>, <i>PPTPlug</i>, <i>WordPlug</i> handles the image, zip, PDF, PPT and Word files associated with the Greenstone Wiki. \n

<p>
To build the collection from a MediaWiki website, first add the new <i>MediaWiki</i> download plug on the <i>Download</i> panel of GLI. This plug works in a similar way with the <i>Web</i> download plug, but is speically for crawling MediaWiki websites.\n

<p>
In the <i>Document Plugins</i> section of the <i>Design</i> panel, add <i>MediaWikiPlug</i>. <i>MediaWikiPlug</i> has 5 options, <i>show_toc</i>, <i>toc_exp</i>, <i>delete_toc</i>, <i>delete_nav</i>, <i>nav_exp</i>. Switch on <i>show_toc</i> will copy the table of contents on the website\'s main page to the collection\'s about page. This needs to specify a regex expression for the table of contents in the <i>toc_exp</i> option. Select the <i>delete_toc</i> option will surpress the table of content on each Wiki page. <i>delete_nav</i> and <i>nav_exp</i> options are for supressing the navigation toolbar, which is normally on the left side of a wiki page, and the <i>nav_exp</i> option is an regular expression of the position of the navigation toolbar. \n
"
collectionmeta  iconcollection [l=en] "_httpprefix_/collect/wiki/images/en/wiki.gif"
collectionmeta  iconcollectionsmall [l=en] "_httpprefix_/collect/wiki/images/en/wiki.gif"