wikipedia-vandalism_detection 0.1.0-java

data/spec/resources/page_with_redirects.xml

@@ -0,0 +1,85 @@
+<mediawiki>
+  <siteinfo>
+    <sitename>Wikipedia</sitename>
+    <base>http://en.wikipedia.org/wiki/Main_Page</base>
+    <generator>MediaWiki 1.23wmf12</generator>
+    <case>first-letter</case>
+    <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">Wikipedia</namespace>
+      <namespace key="5" case="first-letter">Wikipedia 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>
+      <namespace key="100" case="first-letter">Portal</namespace>
+      <namespace key="101" case="first-letter">Portal talk</namespace>
+      <namespace key="108" case="first-letter">Book</namespace>
+      <namespace key="109" case="first-letter">Book talk</namespace>
+      <namespace key="118" case="first-letter">Draft</namespace>
+      <namespace key="119" case="first-letter">Draft talk</namespace>
+      <namespace key="446" case="first-letter">Education Program</namespace>
+      <namespace key="447" case="first-letter">Education Program talk</namespace>
+      <namespace key="710" case="first-letter">TimedText</namespace>
+      <namespace key="711" case="first-letter">TimedText talk</namespace>
+      <namespace key="828" case="first-letter">Module</namespace>
+      <namespace key="829" case="first-letter">Module talk</namespace>
+    </namespaces>
+  </siteinfo>
+<page>
+  <title>Vandalism on Wikipedia</title>
+  <ns>0</ns>
+  <id>100</id>
+  <revision>
+    <id>1</id>
+    <parentid>2</parentid>
+    <timestamp>time 1</timestamp>
+    <contributor>
+      <username>user</username>
+      <id>10</id>
+    </contributor>
+    <text xml:space="preserve" bytes="3177">text 3</text>
+    <sha1>hya1xftsfkq6wml6uigb6j480p4x2nt</sha1>
+    <model>wikitext</model>
+    <format>text/x-wiki</format>
+  </revision>
+  <revision>
+    <id>2</id>
+    <parentid>3</parentid>
+    <timestamp>time 4</timestamp>
+    <contributor>
+      <username>user</username>
+      <id>11</id>
+    </contributor>
+    <text xml:space="preserve" bytes="3261">text 4</text>
+    <sha1>ebb1e4tgy49mqdwtyk0rafzdcokp4lh</sha1>
+    <model>wikitext</model>
+    <format>text/x-wiki</format>
+  </revision>
+  <revision>
+    <id>3</id>
+    <parentid>4</parentid>
+    <timestamp>time 5</timestamp>
+    <contributor>
+      <ip>100.100.100.100</ip>
+    </contributor>
+    <comment>comment 3</comment>
+    <text xml:space="preserve" bytes="3541">#REDIRECT [[Liberty Stadium, Swansea]]
+    </text>
+    <sha1>t8s84rnkje13fkdkw0exui4hrs3fx8x</sha1>
+    <model>wikitext</model>
+    <format>text/x-wiki</format>
+  </revision>
+</page>
+</mediawiki>

data/spec/resources/redirect_page.xml

@@ -0,0 +1,59 @@
+<mediawiki>
+  <siteinfo>
+    <sitename>Wikipedia</sitename>
+    <base>http://en.wikipedia.org/wiki/Main_Page</base>
+    <generator>MediaWiki 1.23wmf12</generator>
+    <case>first-letter</case>
+    <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">Wikipedia</namespace>
+      <namespace key="5" case="first-letter">Wikipedia 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>
+      <namespace key="100" case="first-letter">Portal</namespace>
+      <namespace key="101" case="first-letter">Portal talk</namespace>
+      <namespace key="108" case="first-letter">Book</namespace>
+      <namespace key="109" case="first-letter">Book talk</namespace>
+      <namespace key="118" case="first-letter">Draft</namespace>
+      <namespace key="119" case="first-letter">Draft talk</namespace>
+      <namespace key="446" case="first-letter">Education Program</namespace>
+      <namespace key="447" case="first-letter">Education Program talk</namespace>
+      <namespace key="710" case="first-letter">TimedText</namespace>
+      <namespace key="711" case="first-letter">TimedText talk</namespace>
+      <namespace key="828" case="first-letter">Module</namespace>
+      <namespace key="829" case="first-letter">Module talk</namespace>
+    </namespaces>
+  </siteinfo>
+<page>
+  <title>Vandalism on Wikipedia</title>
+  <ns>0</ns>
+  <id>100</id>
+  <revision>
+    <id>3</id>
+    <parentid>4</parentid>
+    <timestamp>time 5</timestamp>
+    <contributor>
+      <ip>100.100.100.100</ip>
+    </contributor>
+    <comment>comment 3</comment>
+    <text xml:space="preserve" bytes="3541">#REDIRECT [[Vandalism]]
+    </text>
+    <sha1>t8s84rnkje13fkdkw0exui4hrs3fx8x</sha1>
+    <model>wikitext</model>
+    <format>text/x-wiki</format>
+  </revision>
+</page>
+</mediawiki>

data/spec/resources/revision_simplified.xml

@@ -0,0 +1,13 @@
+   <revision>
+      <id>id1</id>
+     <parentid>parentid1</parentid>
+      <timestamp>time1</timestamp>
+      <contributor>
+        <ip>ip1</ip>
+      </contributor>
+      <comment>comment 1</comment>
+      <text xml:space="preserve" bytes="1880">text 1</text>
+      <sha1>hash1</sha1>
+      <model>wikitext</model>
+      <format>text/x-wiki</format>
+   </revision>

data/spec/resources/sample_revision.txt

@@ -0,0 +1,137 @@
+{{Infobox Album | <!-- See Wikipedia:WikiProject_Albums -->
+| Name        = The Soundstage Sessions 
+| Type        = live
+| Longtype    = / <font style="background: {{Infobox Album/color|studio}}">[[Studio album]]</font>
+| Artist      = [[Stevie Nicks]]
+| Cover       = SS1.jpg
+| Released    = March 31, 2009
+| Recorded    = Oct. 2007–2008<br>Grainger Studio<br><small>([[Chicago, Illinois|Chicago]], [[Illinois]])</small> <br>[[Ocean Way Recording]]<br><small>([[Nashville, Tennessee|Nashville]], [[Tennessee]])</small> <br>[[Chicago Recording Company]]<br><small>([[Chicago, Illinois|Chicago]], [[Illinois]])</small>
+| Genre       = [[Rock music|Rock]]
+| Length      = 54:25
+| Label       = [[Reprise Records]]
+| Producer    = [[Joe Thomas (producer/director)|Joe Thomas]] <br> Stevie Nicks <br> [[Waddy Watchel]]
+|Reviews =
+* [[Allmusic]] {{Rating|3|5}} [http://www.allmusic.com/cg/amg.dll?p=amg&sql=10:3xftxzrkldhe link]
+| Last album  = ''[[Crystal Visions - The Very Best of Stevie Nicks]]'' <br /> (2007)
+| This album  = '''''The Soundstage Sessions''''' <br /> (2009)
+| Next album  =
+| Misc = {{Extra album cover 2
+| Upper caption = ''The Soundstage Sessions: Live in Chicago''
+| Type          =
+| Cover         = The_Soundstage_Sessions_-_Live_in_Chicago.jpg
+| Lower caption        = CD/DVD Deluxe Edition
+}}
+}}
+
+'''''The Soundstage Sessions''''' is the tenth album released by the American singer-songwriter and [[Fleetwood Mac]] vocalist [[Stevie Nicks]]. Although it is the first live album of Nicks' solo career, it was produced to sound like a studio album.
+
+
+==Album Information==
+''The Soundstage Sessions'' was recorded in October 2007 before an intimate audience at [[WTTW]]'s Grainger Studio in [[Chicago]], with the [[set list]] containing 18 songs. In early 2008, Nicks went to [[Nashville]] and entered the studio with director/producer [[Joe Thomas (producer/director)|Joe Thomas]]. In the studio, they added "Nashville strings" and additional vocals to the songs that were to go on the CD. Nicks wanted the CD to sound perfect, and when asked about the project has said "I am as proud of this as anything I’ve ever done in my entire career."  <ref>http://popculturezoo.com/archives/2255</ref>
+
+==Track listing==
+===Standard Edition===
+# "[[Stand Back (song)|Stand Back]]" <small>(Stevie Nicks)</small>&nbsp;– 4:40
+# "[[Crash Into Me#Stevie Nicks version|Crash Into Me]]" <small>([[Dave Matthews]])</small>&nbsp;– 5:33
+# "Sara" <small>(Nicks)</small>&nbsp;– 6:56
+# "If Anyone Falls in Love" <small>(Nicks, [[Sandy Stewart (musician)|Sandy Stewart]])</small>&nbsp;– 4:11
+# "[[Landslide (song)|Landslide]]" (Orchestra version) <small>(Nicks)</small>&nbsp;– 4:20
+# "How Still My Love" <small>(Nicks)</small>&nbsp;– 7:34
+# "Circle Dance" <small>(Duet with [[Vanessa Carlton]])</small> <small>([[Bonnie Raitt]])</small>&nbsp;– 4:14
+# "Fall From Grace" <small>(Nicks)</small>&nbsp;– 4:35
+# "Sorcerer" <small>(Nicks)</small>&nbsp;– 5:00
+# "[[Beauty and the Beast (Stevie Nicks song)|Beauty and the Beast]]" <small>(Nicks)</small>&nbsp;– 7:14
+
+===Amazon Mp3 Edition===
+#<li value=11>"Enchanted" <small>(Nicks)</small>&nbsp;– 3:14
+
+===[[iTunes]] Edition===
+#<li value=11>"Gold Dust Woman" <small>(Nicks)</small>&nbsp;– 10:07
+#<li value=12>"Edge of Seventeen" <small>(Nicks)</small>&nbsp;– 12:33
+
+==Deluxe Edition==
+Reprise Records released a Deluxe Edition exclusively through the Warner Bros. Records Store, which is called '''''The Soundstage Sessions: Live in Chicago'''''. The Deluxe Edition is a CD/DVD set, and includes new cover art, a [[lithograph]] of Nicks, and free [[mp3]] downloads of "Rhiannon" and "The One". <ref>http://www.jammfactory.net/wbr/stevienicks/pre-order.html</ref>
+
+==Standard and Blu-Ray DVD==
+The [[Blu-Ray]] DVD of this performance has been available exclusively at Sears since December 1st, 2008 and features a total of 16 tracks in high-definition. The standard edition DVD of this performance was released by Reprise Records as ''[[Live in Chicago (Stevie Nicks DVD)|Live In Chicago]]''. 
+
+==Personnel==
+'''Main Performers'''
+
+*Stevie Nicks - vocals, producer
+*[[Vanessa Carlton]] - guest performer 
+*Sharon Celani - backup vocals 
+*Lori Nicks - backup vocals 
+*Jana Anderson - backup vocals 
+
+'''Production'''
+
+*[[Joe Thomas (producer/director)|Joe Thomas]] - producer
+*Waddy Wachtel - producer
+*Frank Pappalardo - engineering 
+*Michael Czaszwicz - assistant engineering
+*Patrick DeWitte - assistant engineering 
+*Mixed at HD Ready, St. Charles 
+
+'''Musicians'''
+
+*Waddy Wachtel - musical director/guitar
+*Lenny Castro - percussion
+*Al Ortiz - bass
+*Jimmy Paxson - drums 
+*Ricky Peterson - keyboards
+*Carlos Rios - guitar 
+*Darrell Smith - keyboards  
+
+'''String Section'''
+
+*Eric Roth - conductor
+*Janice MacDonald - flute
+*Deb Stevenson - oboe
+*Greg Flint - horn
+*Christine Worthing - horn 
+*Guillaume Combet - violin 
+*Jennifer Cappelli - violin
+*Carmen Llop-Kassinger - violin
+*Christine Keiko Abe - violin
+*Carol Cook - viola 
+*Jocelyn Davis-Beck - cello
+*[[Eddie Bayers]] - drums 
+*Michael Rhodes - bass 
+*[[Joe Thomas (producer/director)|Joe Thomas]] - keyboards
+
+==Charts==
+{|class="wikitable"
+!Chart (2009)
+!Peak<br>position
+|-
+|U.S. [[Billboard 200|''Billboard'' 200]]
+|align="center"|47
+|-
+|U.S. ''Billboard'' Top Current Rock Albums
+|align="center"|15
+|-
+|U.S. ''Billboard'' Top Digital Albums
+|align="center"|55
+|-
+|U.S. ''Billboard'' Top Internet Albums
+|align="center"|5
+|-
+|}
+
+==References==
+{{reflist}}
+
+==External links==
+*http://www.amazon.com/dp/B001AW9DKU
+*http://www.pauseandplay.com/31march2009.htm
+*http://www.sears.com/shc/s/p_10153_12605_05801528000P?mv=rr
+*http://nickslive.blogspot.com/2009/04/live-in-chicago-first-week-sales.html
+
+
+{{DEFAULTSORT:Soundstage Sessions, The}}
+[[Category:2009 albums]]
+[[Category:Live albums]]
+[[Category:Reprise Records albums]]
+[[Category:Stevie Nicks albums]]
+[[Category:Albums produced by Waddy Wachtel]]

data/spec/resources/sample_revision_clean_text.txt

@@ -0,0 +1 @@
+The Soundstage Sessions is the tenth album released by the American singer-songwriter and Fleetwood Mac vocalist Stevie Nicks. Although it is the first live album of Nicks' solo career, it was produced to sound like a studio album. Album Information The Soundstage Sessions was recorded in October 2007 before an intimate audience at WTTW's Grainger Studio in Chicago, with the set list containing 18 songs. In early 2008, Nicks went to Nashville and entered the studio with director/producer Joe Thomas. In the studio, they added "Nashville strings" and additional vocals to the songs that were to go on the CD. Nicks wanted the CD to sound perfect, and when asked about the project has said "I am as proud of this as anything Ive ever done in my entire career." Track listing Standard Edition "Stand Back" (Stevie Nicks)Š 4:40 "Crash Into Me" (Dave Matthews)Š 5:33 "Sara" (Nicks)Š 6:56 "If Anyone Falls in Love" (Nicks, Sandy Stewart)Š 4:11 "Landslide" (Orchestra version) (Nicks)Š 4:20 "How Still My Love" (Nicks)Š 7:34 "Circle Dance" (Duet with Vanessa Carlton) (Bonnie Raitt)Š 4:14 "Fall From Grace" (Nicks)Š 4:35 "Sorcerer" (Nicks)Š 5:00 "Beauty and the Beast" (Nicks)Š 7:14 Amazon Mp3 Edition "Enchanted" (Nicks)Š 3:14 iTunes Edition "Gold Dust Woman" (Nicks)Š 10:07 "Edge of Seventeen" (Nicks)Š 12:33 Deluxe Edition Reprise Records released a Deluxe Edition exclusively through the Warner Bros. Records Store, which is called The Soundstage Sessions: Live in Chicago. The Deluxe Edition is a CD/DVD set, and includes new cover art, a lithograph of Nicks, and free mp3 downloads of "Rhiannon" and "The One". Standard and Blu-Ray DVD The Blu-Ray DVD of this performance has been available exclusively at Sears since December 1st, 2008 and features a total of 16 tracks in high-definition. The standard edition DVD of this performance was released by Reprise Records as Live In Chicago. Personnel Main Performers Stevie Nicks - vocals, producer Vanessa Carlton - guest performer Sharon Celani - backup vocals Lori Nicks - backup vocals Jana Anderson - backup vocals Production Joe Thomas - producer Waddy Wachtel - producer Frank Pappalardo - engineering Michael Czaszwicz - assistant engineering Patrick DeWitte - assistant engineering Mixed at HD Ready, St. Charles Musicians Waddy Wachtel - musical director/guitar Lenny Castro - percussion Al Ortiz - bass Jimmy Paxson - drums Ricky Peterson - keyboards Carlos Rios - guitar Darrell Smith - keyboards String Section Eric Roth - conductor Janice MacDonald - flute Deb Stevenson - oboe Greg Flint - horn Christine Worthing - horn Guillaume Combet - violin Jennifer Cappelli - violin Carmen Llop-Kassinger - violin Christine Keiko Abe - violin Carol Cook - viola Jocelyn Davis-Beck - cello Eddie Bayers - drums Michael Rhodes - bass Joe Thomas - keyboards Charts Chart (2009) Peak position U.S. Billboard 200 47 U.S. Billboard Top Current Rock Albums 15 U.S. Billboard Top Digital Albums 55 U.S. Billboard Top Internet Albums 5 References External links

data/spec/resources/sample_revision_plain_text.txt

@@ -0,0 +1,183 @@
+The Soundstage Sessions is the tenth album released by the American
+singer-songwriter and Fleetwood Mac vocalist Stevie Nicks. Although it is the
+first live album of Nicks' solo career, it was produced to sound like a studio
+album.
+
+1. Album Information
+
+
+The Soundstage Sessions was recorded in October 2007 before an intimate
+audience at WTTW's Grainger Studio in Chicago, with the set list containing 18
+songs. In early 2008, Nicks went to Nashville and entered the studio with
+director/producer Joe Thomas. In the studio, they added "Nashville strings" and
+additional vocals to the songs that were to go on the CD. Nicks wanted the CD
+to sound perfect, and when asked about the project has said "I am as proud of
+this as anything Ive ever done in my entire career."
+
+2. Track listing
+
+2.1. Standard Edition
+
+
+"Stand Back" (Stevie Nicks)Š 4:40
+
+"Crash Into Me" (Dave Matthews)Š 5:33
+
+"Sara" (Nicks)Š 6:56
+
+"If Anyone Falls in Love" (Nicks, Sandy Stewart)Š 4:11
+
+"Landslide" (Orchestra version) (Nicks)Š 4:20
+
+"How Still My Love" (Nicks)Š 7:34
+
+"Circle Dance" (Duet with Vanessa Carlton) (Bonnie Raitt)Š 4:14
+
+"Fall From Grace" (Nicks)Š 4:35
+
+"Sorcerer" (Nicks)Š 5:00
+
+"Beauty and the Beast" (Nicks)Š 7:14
+
+2.2. Amazon Mp3 Edition
+
+
+"Enchanted" (Nicks)Š 3:14
+
+2.3. iTunes Edition
+
+
+"Gold Dust Woman" (Nicks)Š 10:07
+
+"Edge of Seventeen" (Nicks)Š 12:33
+
+3. Deluxe Edition
+
+
+Reprise Records released a Deluxe Edition exclusively through the Warner Bros.
+Records Store, which is called The Soundstage Sessions: Live in Chicago. The
+Deluxe Edition is a CD/DVD set, and includes new cover art, a lithograph of
+Nicks, and free mp3 downloads of "Rhiannon" and "The One".
+
+4. Standard and Blu-Ray DVD
+
+
+The Blu-Ray DVD of this performance has been available exclusively at Sears
+since December 1st, 2008 and features a total of 16 tracks in high-definition.
+The standard edition DVD of this performance was released by Reprise Records as
+Live In Chicago.
+
+5. Personnel
+
+
+Main Performers
+
+Stevie Nicks - vocals, producer
+
+Vanessa Carlton - guest performer
+
+Sharon Celani - backup vocals
+
+Lori Nicks - backup vocals
+
+Jana Anderson - backup vocals
+
+Production
+
+Joe Thomas - producer
+
+Waddy Wachtel - producer
+
+Frank Pappalardo - engineering
+
+Michael Czaszwicz - assistant engineering
+
+Patrick DeWitte - assistant engineering
+
+Mixed at HD Ready, St. Charles
+
+Musicians
+
+Waddy Wachtel - musical director/guitar
+
+Lenny Castro - percussion
+
+Al Ortiz - bass
+
+Jimmy Paxson - drums
+
+Ricky Peterson - keyboards
+
+Carlos Rios - guitar
+
+Darrell Smith - keyboards
+
+String Section
+
+Eric Roth - conductor
+
+Janice MacDonald - flute
+
+Deb Stevenson - oboe
+
+Greg Flint - horn
+
+Christine Worthing - horn
+
+Guillaume Combet - violin
+
+Jennifer Cappelli - violin
+
+Carmen Llop-Kassinger - violin
+
+Christine Keiko Abe - violin
+
+Carol Cook - viola
+
+Jocelyn Davis-Beck - cello
+
+Eddie Bayers - drums
+
+Michael Rhodes - bass
+
+Joe Thomas - keyboards
+
+6. Charts
+
+
+Chart (2009)
+
+Peak
+position
+
+U.S. Billboard 200
+
+47
+
+
+U.S. Billboard Top Current Rock Albums
+
+15
+
+
+U.S. Billboard Top Digital Albums
+
+55
+
+
+U.S. Billboard Top Internet Albums
+
+5
+
+7. References
+
+8. External links
+
+
+http://www.amazon.com/dp/B001AW9DKU 
+
+http://www.pauseandplay.com/31march2009.htm 
+
+http://www.sears.com/shc/s/p_10153_12605_05801528000P?mv=rr 
+
+http://nickslive.blogspot.com/2009/04/live-in-chicago-first-week-sales.html