From 9563104a250da3d3b1f5db8025c6a650669879a5 Mon Sep 17 00:00:00 2001 From: Benjamin Mako Hill Date: Thu, 23 Aug 2018 16:38:01 -0700 Subject: [PATCH] added wikipedia_namespaces.csv file This file was required to run the scripts but was accidently not included. --- README | 9 +++++++++ wikipedia_namespaces.csv | 39 +++++++++++++++++++++++++++++++++++++++ 2 files changed, 48 insertions(+) create mode 100644 wikipedia_namespaces.csv diff --git a/README b/README index 7995e40..342776d 100644 --- a/README +++ b/README @@ -75,6 +75,15 @@ Running the Software - GNU R - `data.table` R package available on CRAN +There is also a dependency on a file called `wikipedia_namespaces.csv` +which is included in this repository and which is drawn from data on +this page: https://en.wikipedia.org/wiki/Wikipedia:Namespace + +This file is taken from English Wikipedia in 2015. If you are working +with different wikis or with an updated dump, you will likely to need +to update this file. + + 1. Download Dumps ========================== diff --git a/wikipedia_namespaces.csv b/wikipedia_namespaces.csv new file mode 100644 index 0000000..7474d7f --- /dev/null +++ b/wikipedia_namespaces.csv @@ -0,0 +1,39 @@ +id,name,alias +0,,FALSE +1,Talk,FALSE +2,User,FALSE +3,User talk,FALSE +4,Wikipedia,FALSE +5,Wikipedia talk,FALSE +6,File,FALSE +7,File talk,FALSE +8,MediaWiki,FALSE +9,MediaWiki talk,FALSE +10,Template,FALSE +11,Template talk,FALSE +12,Help,FALSE +13,Help talk,FALSE +14,Category,FALSE +15,Category talk,FALSE +100,Portal,FALSE +101,Portal talk,FALSE +108,Book,FALSE +109,Book talk,FALSE +118,Draft,FALSE +119,Draft talk,FALSE +446,Education Program,FALSE +447,Education Program talk,FALSE +710,TimedText,FALSE +711,TimedText talk,FALSE +828,Module,FALSE +829,Module talk,FALSE +2600,Topic,FALSE +-1,Special,FALSE +-2,Media,FALSE +4,WP,TRUE +4,Project,TRUE +5,WT,TRUE +5,Project talk,TRUE +6,Image,TRUE +7,Image talk,TRUE + -- 2.39.5