source: collections/documented-examples/trunk/wiki-e/etc/collect.cfg@ 19148

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      GreenstoneXMLPlugin
plugin      PDFPlugin
plugin      WordPlugin
plugin      NulPlugin
plugin      MediaWikiPlugin -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      MetadataXMLPlugin
plugin      ArchivesInfPlugin
plugin      DirectoryPlugin

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"

collectionmeta  .text  "_labeltext_"
collectionmeta  .Title  "_labeltitle_"
collectionmeta  .Source "_labelSource_"

# -- English text ----------------
collectionmeta  collectionname [l=en] "MediaWiki collection"
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.

<h3>How the collection works</h3>

<p>
The <a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>collection
 configuration file</a> contains the plugins <i>MediaWikiPlugin</i>, 
<i>ImagePlugin</i>, <i>ZipPlugin</i>, <i>PDFPlugin</i>, 
<i>PowerPointPlugin</i>, <i>WordPlugin</i> (along with the standard 
plugins <i>GreenstoneXMLPlugin</i>, <i>ArchivesInfPlugin</i> and 
<i>DirectoryPlugin</i>). The <i>MediaWikiPlugin</i> handles the HTML pages 
downloaded from a MediaWiki website, while <i>ImagePlugin</i>, 
<i>ZipPlugin</i>, <i>PDFPlugin</i>, <i>PowerPointPlugin</i> and 
<i>WordPlugin</i> handle the image, zip, PDF, PowerPoint and Word 
files associated with the Greenstone Wiki. 

<p>
To build a collection from a MediaWiki website, first download the wiki 
files using the <i>MediaWiki</i> option on the <i>Download</i> panel of GLI. 
This download type works in a similar way to a the <i>Web</i> download, but 
is specially designed for crawling MediaWiki websites.\n

<p>Once the files are downloaded, copy them into a collection using the <i>Gather</i>, dragging them from the <i>Downloaded Files</i> folder in the Workspace tree on the left-hand side.
 
<p>
In the <i>Document Plugins</i> section of the <i>Design</i> panel, 
add <i>MediaWikiPlugin</i>. <i>MediaWikiPlugin</i> has several specific 
options which control aspects of page presentation, such as whether or not 
the table of contents, navigation toolbars and search box are shown on each 
page. Configure these options based on how you want the pages to appear. You can see the options used by this collection in its 
<a href=\"_httpcollection_/etc/collect.cfg\" target=collect.cfg>collection
 configuration file</a>.
"