Lexesis/tests/highlighter_7.exp

<mediawiki xmlns="http://www.mediawiki.org/xml/export-0.8/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.mediawiki.org/xml/export-0.8/ http://www.mediawiki.org/xml/export-0.8.xsd" version="0.8" xml:lang="en">

<!-- Optional global configuration info -->
<siteinfo>
<!-- Site name, as set in $wgSitename -->
<sitename>DemoWiki</sitename>

<!-- Forgot where you got this set? -->
<base>http://example.com/wiki/Main_Page</base>

<!-- Source software version -->
<generator>MediaWiki 1.20</generator>

<!-- Title case sensitivity options of the wiki this data came from -->
<!-- May be 'first-letter', 'case-sensitive', or 'case-insensitive' -->
<case>first-letter</case>

<!-- Defined namespace keys on the source wiki. -->
<namespaces>
<namespace key="-2" case="first-letter">Media</namespace>
<namespace key="-1" case="first-letter">Special</namespace>
<namespace key="0" case="first-letter" />
<namespace key="1" case="first-letter">Talk</namespace>
<namespace key="2" case="first-letter">User</namespace>
<namespace key="3" case="first-letter">User talk</namespace>
<namespace key="4" case="first-letter">DemoWiki</namespace>
<namespace key="5" case="first-letter">DemoWIki talk</namespace>
<namespace key="6" case="first-letter">File</namespace>
<namespace key="7" case="first-letter">File talk</namespace>
<namespace key="8" case="first-letter">MediaWiki</namespace>
<namespace key="9" case="first-letter">MediaWiki talk</namespace>
<namespace key="10" case="first-letter">Template</namespace>
<namespace key="11" case="first-letter">Template talk</namespace>
<namespace key="12" case="first-letter">Help</namespace>
<namespace key="13" case="first-letter">Help talk</namespace>
<namespace key="14" case="first-letter">Category</namespace>
<namespace key="15" case="first-letter">Category talk</namespace>
</namespaces>
</siteinfo>

<!-- The rest of the data will be a series of page records -->
<page>
<!-- Titles are listed here in text form, with namespace prefix -->
<!-- if any, and spaces rather than the underscores used in URLs. -->
<title>Page title</title>

<!-- Namespace in canonical form -->
<ns>0</ns>

<!-- The page's immutable page_id number in the source database. -->
<!-- Page ID numbers are kept across page moves, but may change -->
<!-- if a page is deleted and recreated. -->
<id>1</id>

<!-- Tag wether this article is a redirect and its target -->
<!-- This corresponds to the page_is_redirect in the page table -->
<redirect title="Target" />

<!-- If restricted, the ACL is listed here raw. -->
<restrictions>edit=sysop:move=sysop</restrictions>

<!-- With a series of revision records... -->

<!-- Remember this is XML; if you must use a regex-based extractor -->
<!-- in place of a standard XML parser, be very careful. -->
<!-- * Don't forget to decode character entities! -->
<!-- * If using a 'loose' XML parser, ensure that whitespace is -->
<!-- preserved in the <text> elements. -->
<revision>
<!-- Unique revision ID number (rev_id) in the source database. -->
<!-- This number uniquely identifies the revision on that wiki. -->
<id>100</id>
<!-- revision id of the parent revision -->
<parentid>99</parentid>
<timestamp>2001-01-15T13:15:00Z</timestamp>
<contributor>
<username>Foobar</username>
<id>42</id>
</contributor>
<minor />
<comment>I have just one thing to say!</comment>
<text xml:space="preserve" bytes="25">A bunch of [[text]] here.</text>
<sha1>5x0ux8iwjrbmfzgv6pkketxgkcnpr7h</sha1>
<model>wikitext</model>
<format>text/x-wiki</format>
</revision>

<revision>
<id>99</id>
<timestamp>2001-01-15T13:10:27Z</timestamp>
<contributor>
<ip>10.0.0.2</ip>
</contributor>
<comment>new!</comment>
<text xml:space="preserve" bytes="24">An earlier [[revision]].</text>
<sha1>etaxt3shcge6igz1biwy3d4um2pnle4</sha1>
<model>wikitext</model>
<format>text/x-wiki</format>
</revision>
</page>

<page>
<title>Talk:Page title</title>
<ns>1</ns>
<id>2</id>
<revision>
<id>101</id>
<timestamp>2001-01-15T14:03:00Z</timestamp>
<contributor><ip>10.0.0.2</ip></contributor>
<comment>hey</comment>
<text xml:space="preserve" bytes="47">WHYD YOU LOCK PAGE??!!! i was editing that jerk</text>
<sha1>ml80vmyjlixdstnywwihx003exfzq9j</sha1>
<model>wikitext</model>
<format>text/x-wiki</format>
</revision>
</page>

<page>
<title>File:Some image.jpg</title>
<ns>6</ns>
<id>3</id>
<revision>
<id>102</id>
<timestamp>2001-01-15T20:34:12Z</timestamp>
<contributor><username>Foobar</username><id>42</id></contributor>
<comment>My awesomeest image!</comment>
<text xml:space="preserve" bytes="52">This is an awesome little imgae. I lurves it. {{PD}}</text>
<sha1>mehom37npwkpzhaiwu3wyr0egalumki</sha1>
<model>wikitext</model>
<format>text/x-wiki</format>
</revision>
<upload>
<timestamp>2001-01-15T20:34:12Z</timestamp>
<contributor><username>Foobar</username><id>42</id></contributor>
<comment>My awesomeest image!</comment>
<filename>Some_image.jpg</filename>
<src>http://upload.wikimedia.org/commons/2/22/Some_image.jpg</src>
<size>12345</size>
</upload>
</page>

<!-- or a series of logitem records, but normaly page and logitem never exist both in one file -->
<logitem>
<id>15</id>
<timestamp>2008-10-23T03:20:32Z</timestamp>
<contributor>
<username>Wikimedian</username>
<id>12345</id>
</contributor>
<comment>content was: 'I think this was a silly edit'</comment>
<type>delete</type>
<action>delete</action>
<logtitle>Silly page name</logtitle>
<params xml:space="preserve" />
</logitem>

</mediawiki>